CN120152009A

CN120152009A - A communication method and a communication device

Info

Publication number: CN120152009A
Application number: CN202311710770.0A
Authority: CN
Inventors: 田洋; 孙琰
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2023-12-12
Filing date: 2023-12-12
Publication date: 2025-06-13
Also published as: WO2025124280A1

Abstract

A communication method and a communication device are applied to positioning scenarios. The method includes: receiving configuration information from a core network element, using a first model to process a channel measurement result to obtain a probability distribution of a measurement result of a measurement quantity used for positioning a terminal device, and the first model is determined based on the configuration parameters of the generation model. The configuration information is used to indicate the configuration parameters of the generation model, and the measurement quantity corresponds to the channel measurement result. In the present application, the core network element and the first device align the configuration information of the generation model to obtain a first model for fitting/training the terminal device positioning, in order to support the improvement of the measurement accuracy of the terminal device.

Description

Communication method and communication device

Technical Field

The present application relates to the field of communication technology, and more particularly, to a communication method and a communication apparatus.

Background

In positioning technologies based on artificial intelligence (ARTIFICIAL INTELLIGENT, AI), AI-positioning models can be deployed in different devices or nodes, e.g., typically on the positioning device side, such as the location management function (location management function, LMF), or on the base station (gnob, gNB) side, with channel measurement results reported by channel measurement network elements as input and the location of a terminal device (e.g., user Equipment (UE)) as output. Thus, the channel measurement network element typically needs to report the channel measurement report to the location management function network element.

In downlink positioning, the gNB sends a Positioning Reference Signal (PRS) to the UE, and the UE measures the PRS sent by the gNB to obtain a gaussian mixture model distributed by downlink-received reference signal time difference (DL-RSTD) and sends relevant parameters of the gaussian mixture model to a core network element (e.g., LMF) for the core network element to position the UE. Research finds that the current UE positioning accuracy is poor. Therefore, how to improve the positioning accuracy of the UE is a problem to be solved.

Disclosure of Invention

The application provides a communication method and a communication device, which aim to support improvement of positioning precision of terminal equipment.

In a first aspect, a communication method is provided, which may be performed by a first device, or may also be performed by a chip or a circuit of the first device, which is not limited by the present application. For convenience of description, an example will be described below as being executed by the first device.

The method comprises the steps of receiving configuration information from a core network element, wherein the configuration information is used for indicating configuration parameters of a generation model, and processing channel measurement results by using a first model to obtain probability distribution of measurement results of measurement quantities for positioning of terminal equipment, wherein the first model determines that the measurement quantities correspond to the channel measurement results based on the configuration parameters of the generation model.

According to the scheme provided by the application, the terminal equipment receives the configuration information from the core network element, so that the core network element and the first equipment generate the configuration information of the model through alignment, the first model used for fitting/training of the positioning of the terminal equipment can be obtained to be the same, further, the analysis and the application of the probability distribution of the measurement result of the measurement quantity based on the first model are more accurate, and the positioning precision of the terminal equipment can be improved.

The channel measurement is illustratively based on a measurement of the reference signal, which may be, for example, the first device or another device measuring the reference signal.

The first device may be an end device or an access network device, and the first device may also be referred to as a network element performing channel measurement, or a channel measurement network element, or a reference signal measurement node, etc., which is not limited by the name of the present application. The core network element may be a positioning node or a positioning device for managing the position of the terminal device, e.g. a location management function network element LMF.

In the embodiment of the application, the first model is determined based on the configuration parameters of the generation model, and the first device can be fit or trained to obtain the first model according to the obtained configuration parameters of the generation model, if the generation model is a Gaussian mixture model, the first device can be trained or fit to obtain a certain or a certain kind of specific Gaussian mixture model according to the configuration parameters, namely, the first model is a trained Gaussian mixture model at the moment and can be used for positioning of terminal equipment.

In the embodiment of the application, the measurement quantity corresponds to the measurement result, and the first equipment can be understood that the first equipment measures one or more measurement quantities corresponding to the reference signal to obtain the measurement result, wherein the measurement result is the measurement result of the one or more measurement quantities. For example, taking a downlink positioning scenario as an example, assuming that the measurement quantity is a time difference of arrival (TDoA), the first device is a terminal device, the network device #1 may send a reference signal, such as prs#1, to the terminal device, the network device #2 may send prs#2 to the terminal device, and correspondingly, the terminal device may measure TDoA of prs#1 and prs#2, such as t2-t1, as a measurement result #1, where t1 represents a transmission time when the network device #1 and the terminal device transmit signals, and t2 represents a transmission time when the network device #2 and the terminal device transmit signals. Alternatively, network device #1 and network device #2 may send PRS multiple times, or network device #3 may also send PRS #3 to the terminal device, and the terminal device may measure TDoA of PRS #2 and PRS #3, e.g., t3-t2, as measurement result #2, where t3 represents a transmission time when network device #3 transmits signals with the terminal device, and so on.

With reference to the first aspect, in certain implementation manners of the first aspect, the method further includes sending first information to a core network element, where the first information is used to indicate a probability distribution.

Based on the scheme, the terminal equipment can enable the core network element to acquire the probability distribution of the measurement result of the measurement quantity for positioning the terminal equipment by sending the first information, so that the measurement quantity can be accurately analyzed according to the probability distribution and the configuration information of the generation model, and the high-precision positioning of the terminal equipment is facilitated.

With reference to the first aspect, in certain implementation manners of the first aspect, the method further includes acquiring a type of the generative model and/or a function of the generative model.

Alternatively, the type of the generative model and/or the function of the generative model may be dynamically configured (dynamic configured) by signaling or messaging by the core network element to the first device, or may be preconfigured (pre-configured), for example, may be implemented by pre-storing a corresponding code, table, or other manner in the first device that may be used to indicate the type of the generative model and/or the function of the generative model, and the implementation of the present application is not limited. For example, the first device may determine that the generated model to be trained or fitted is a GMM by the type of generated model and/or the function of the generated model, and locate the terminal device by the trained or fitted GMM (i.e., the first model).

With reference to the first aspect, in some implementations of the first aspect, the generation model is any one of a gaussian mixture model, a variational self-encoder, and a generation countermeasure network.

With reference to the first aspect, in some implementations of the first aspect, the generating model is a gaussian mixture model, and the configuration parameters of the generating model include one or more of a generating method of the gaussian mixture model, a convergence threshold of the gaussian mixture model, a maximum value of iteration times of the gaussian mixture model, model parameters of the gaussian mixture model, a maximum value M of the number of single gaussian models included in the gaussian mixture model, M being a positive integer, a maximum value N of expected values of the single gaussian models included in the gaussian mixture model, N being a positive number, and a maximum value A of variance or covariance of the single gaussian models included in the gaussian mixture model, A being a positive number, and a duty ratio of one or more single gaussian models included in the gaussian mixture model.

With reference to the first aspect, in some implementations of the first aspect, generating the model as a variational self-encoder, generating configuration parameters of the model includes one or more of a structural parameter of the variational self-encoder, a type of neural network used by the variational self-encoder, an input and/or output dimension of the variational self-encoder, and a value of the model parameter of the variational self-encoder.

The structural parameters of the variable self-encoder comprise one or more of the following layers of the neural network used by the variable self-encoder, the number of neurons contained in the neural network used by the variable self-encoder, parameters related to an input layer of the variable self-encoder, parameters related to a hidden layer or parameters related to an output layer.

With reference to the first aspect, in certain implementations of the first aspect, the measurement includes one or more of a reference signal time difference (REFERENCE SIGNAL TIME DIFFERENCE, RSTD), a time difference of arrival (TIME DIFFERENCE of arrival, TDoA), a time of arrival (ToA), an angle of arrival (AoA), a line of sight (LOS) probability.

It should be appreciated that RSTD, TDoA, toA, aoA and LoS probabilities described above may be considered as measures of one channel measurement, and that a channel may include one or more paths (e.g., a set of paths). For example, the LoS probability may be an average LoS probability of line-of-sight recognition results for all paths in one channel. The ToA estimate may be an average of the arrival times for all paths in a channel. The AoA estimation result may be an average value of arrival angles corresponding to all paths in one channel, or the like.

It should be noted that, in the embodiment of the present application, the measurement quantity may be one or more of the above parameters, and correspondingly, the measurement result of the measurement quantity may also be one or more, and meanwhile, the probability distribution of the measurement result of the measurement quantity for positioning the terminal device may also be one or more.

With reference to the first aspect, in some implementations of the first aspect, the generating model is a gaussian mixture model, the gaussian mixture model includes k single gaussian models, k is an integer greater than or equal to 1, and the first information includes one or more of k expected values, k variance or covariance values, and k single gaussian models in the gaussian mixture model, where the k expected values, the k variance or covariance values are in one-to-one correspondence with the k single gaussian models.

Illustratively, the probability distribution of the gaussian mixture model satisfies:

Wherein, I.e., the expectation, variance (or covariance), probability (or duty cycle) of occurrence in the gaussian mixture model, of each single gaussian model.

With reference to the first aspect, in some implementations of the first aspect, the generating the model is a variation self-encoder, and the first information includes one or more of a value of a model parameter of the variation self-encoder and a value of a probability distribution output by the variation self-encoder.

With reference to the first aspect, in some implementations of the first aspect, the channel measurement result is based on measurement of a reference signal, including any one of the first device being an access network device, the channel measurement result being based on a first channel measurement, the first channel measurement including measurement of a sounding reference signal from a terminal device, or the first device being a terminal device, the channel measurement result being based on a second channel measurement, the second channel measurement including measurement of a positioning reference signal or a channel state information reference signal from the access network device, or the first device being a first terminal device, the channel measurement result being based on a third channel measurement, the third channel measurement including measurement of a side-by-side positioning reference signal from a second terminal device.

With reference to the first aspect, in some implementations of the first aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, where the configuration information is used to indicate the first configuration parameter and the second configuration parameter, or the configuration information is used to indicate the first configuration parameter, where the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate a corresponding relationship between the first configuration parameter and the second configuration parameter.

With reference to the first aspect, in some implementations of the first aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, and receiving configuration information from the core network element includes receiving the configuration information from the core network element through a first signaling, where the configuration information of the first configuration parameter is carried in a first portion of the first signaling, and the configuration information of the second configuration parameter is carried in a second portion of the first signaling.

With reference to the first aspect, in some implementations of the first aspect, receiving configuration information from a core network element through a first signaling includes receiving, at a first time, a first configuration parameter from the core network element through a first portion of the first signaling, and receiving, at a second time, a second configuration parameter from the core network element through a second portion of the first signaling, where the first time and the second time are the same or different.

In a second aspect, a communication method is provided, which may be performed by a core network element, or may also be performed by a chip or a circuit of the core network element, which is not limited by the present application. For ease of description, the following description will be given by taking an example of execution by a core network element.

The method comprises the steps of sending configuration information to the first device, wherein the configuration information is used for indicating configuration parameters of a generated model, and receiving first information from the first device, wherein the first information indicates probability distribution of measurement results of measurement quantities used for positioning of the terminal device, and the probability distribution is related to the configuration parameters of the generated model.

It should be appreciated that the measurement quantity corresponds to a channel measurement result, which is based on a measurement of the reference signal, and may be, for example, the measurement of the reference signal by the first device or another device.

According to the scheme provided by the application, the core network element sends the configuration information to the terminal equipment, so that the core network element and the first equipment generate the configuration information of the model through alignment, the first model used for fitting/training of the positioning of the terminal equipment can be known to be the same, and further, the analysis and the application of the probability distribution of the measurement result of the measurement quantity based on the first model are more accurate, so that the positioning precision of the terminal equipment can be improved.

With reference to the second aspect, in certain implementations of the second aspect, the method further includes determining a location of the terminal device according to a probability distribution of measurement results of the measurement quantities and configuration parameters of the generated model.

With reference to the second aspect, in some implementations of the second aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, where the configuration information is used to indicate the first configuration parameter and the second configuration parameter, or the configuration information is used to indicate the first configuration parameter, where the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate a correspondence relationship between the first configuration parameter and the second configuration parameter.

With reference to the second aspect, in some implementations of the second aspect, the generation model is any one of a gaussian mixture model, a variational self-encoder, and a generation countermeasure network.

With reference to the second aspect, in some implementations of the second aspect, the generating model is a gaussian mixture model, and the configuration parameters of the generating model include one or more of a generating method of the gaussian mixture model, a convergence threshold of the gaussian mixture model, a maximum value of iteration times of the gaussian mixture model, model parameters of the gaussian mixture model, a maximum value M of the number of single gaussian models included in the gaussian mixture model, M being a positive integer, a maximum value N of expected values of the single gaussian models included in the gaussian mixture model, N being a positive number, and a maximum value A of variance or covariance of the single gaussian models included in the gaussian mixture model, A being a positive number, and a duty ratio of one or more single gaussian models included in the gaussian mixture model.

With reference to the second aspect, in some implementations of the second aspect, generating the model as a variational self-encoder, generating configuration parameters of the model includes one or more of a structural parameter of the variational self-encoder, a type of neural network used by the variational self-encoder, an input and/or output dimension of the variational self-encoder, and a value of the model parameter of the variational self-encoder.

With reference to the second aspect, in certain implementations of the second aspect, the measurement includes one or more of a reference signal time difference RSTD, a time difference of arrival TDoA, a time of arrival ToA, an angle of arrival AoA, and a line of sight LoS probability.

With reference to the second aspect, in some implementations of the second aspect, the generating model is a gaussian mixture model, the gaussian mixture model includes k single gaussian models, k is an integer greater than or equal to 1, and the first information includes one or more of a value of k expected values, a value of k variances or covariances, a value of a duty ratio of the k single gaussian models in the gaussian mixture model, and the k expected values, the k variances or covariances are in one-to-one correspondence with the k single gaussian models.

With reference to the second aspect, in some implementations of the second aspect, the generating the model is a variation self-encoder, and the first information includes one or more of a value of a model parameter of the variation self-encoder and a value of a probability distribution output by the variation self-encoder.

With reference to the second aspect, in some implementations of the second aspect, the channel measurement result is based on measurement of a reference signal, including any one of the first device being an access network device, the channel measurement result being based on a first channel measurement, the first channel measurement including measurement of a sounding reference signal from a terminal device, or the first device being a terminal device, the channel measurement result being based on a second channel measurement, the second channel measurement including measurement of a positioning reference signal or a channel state information reference signal from the access network device, or the first device being a first terminal device, the channel measurement result being based on a third channel measurement, the third channel measurement including measurement of a sidelink positioning reference signal from a second terminal device.

With reference to the second aspect, in some implementations of the second aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, and receiving configuration information from the core network element includes receiving the configuration information from the core network element through a first signaling, where the configuration information of the first configuration parameter is carried in a first portion of the first signaling, and the configuration information of the second configuration parameter is carried in a second portion of the first signaling.

With reference to the second aspect, in some implementations of the second aspect, receiving configuration information from the core network element through the first signaling includes receiving, at a first time, a first configuration parameter from the core network element through a first portion of the first signaling, and receiving, at a second time, a second configuration parameter from the core network element through a second portion of the first signaling, where the first time and the second time are the same or the first time and the second time are different.

The foregoing second aspect and advantageous effects of certain implementations of the second aspect may correspond to the descriptions related to the first aspect, which are not repeated herein.

In a third aspect, a communication method is provided, which may be performed by the first device, or may also be performed by a chip or a circuit of the first device, which is not limited by the present application. For convenience of description, an example will be described below as being executed by the first device.

The method comprises the steps of obtaining configuration information, wherein the configuration information is used for indicating configuration parameters of a generation model, processing channel measurement results by using a first model to obtain probability distribution of measurement results of measurement quantities for positioning terminal equipment, and determining the measurement quantities corresponding to the channel measurement results by the first model based on the configuration parameters of the generation model.

According to the scheme provided by the application, the terminal equipment sends the configuration information to the core network element, so that the core network element and the first equipment generate the configuration information of the model through alignment, the first model used for fitting/training of the positioning of the terminal equipment can be known to be the same, and further, the analysis and the application of the probability distribution of the measurement result of the measurement quantity based on the first model are more accurate, so that the positioning precision of the terminal equipment can be improved.

With reference to the third aspect, in some implementations of the third aspect, the method further includes sending all or part of first information and configuration information to the core network element, the first information being used to indicate the probability distribution, and the configuration information being used to indicate configuration parameters of the generation model.

With reference to the third aspect, in some implementations of the third aspect, the method further includes obtaining a type of the generative model and/or a function of the generative model.

With reference to the third aspect, in some implementations of the third aspect, the generation model is any one of a gaussian mixture model, a variational self-encoder, and a generation countermeasure network.

With reference to the third aspect, in some implementations of the third aspect, the generating model is a gaussian mixture model, and the configuration parameters of the generating model include one or more of a generating method of the gaussian mixture model, a convergence threshold of the gaussian mixture model, a maximum value of iteration times of the gaussian mixture model, model parameters of the gaussian mixture model, a maximum value M of the number of single gaussian models included in the gaussian mixture model, M being a positive integer, a maximum value N of expected values of the single gaussian models included in the gaussian mixture model, N being a positive number, and a maximum value A of variance or covariance of the single gaussian models included in the gaussian mixture model, A being a positive number, and a duty ratio of one or more single gaussian models included in the gaussian mixture model.

With reference to the third aspect, in some implementations of the third aspect, the generating the model is a variable self-encoder, and the generating the configuration parameters of the model includes one or more of a structural parameter of the variable self-encoder, a type of neural network used by the variable self-encoder, an input and/or output dimension of the variable self-encoder, and a value of the model parameter of the variable self-encoder.

With reference to the third aspect, in certain implementations of the third aspect, the measurement includes one or more of a reference signal time difference RSTD, a time difference of arrival TDoA, a time of arrival ToA, an angle of arrival AoA, and a line of sight LoS probability.

With reference to the third aspect, in some implementations of the third aspect, the generating model is a gaussian mixture model, the gaussian mixture model includes k single gaussian models, k is an integer greater than or equal to 1, and the first information includes one or more of k expected values, k variance or covariance values, and k single gaussian models in the gaussian mixture model, where the k expected values, the k variance or covariance values are in one-to-one correspondence with the k single gaussian models.

With reference to the third aspect, in some implementations of the third aspect, the generating the model is a variation self-encoder, and the first information includes one or more of a value of a model parameter of the variation self-encoder and a value of a probability distribution output by the variation self-encoder.

With reference to the third aspect, in some implementations of the third aspect, the channel measurement result is based on measurement of a reference signal, including any one of the first device being an access network device, the channel measurement result being based on a first channel measurement, the first channel measurement including measurement of a sounding reference signal from a terminal device, or the first device being a terminal device, the channel measurement result being based on a second channel measurement, the second channel measurement including measurement of a positioning reference signal or a channel state information reference signal from the access network device, or the first device being a first terminal device, the channel measurement result being based on a third channel measurement, the third channel measurement including measurement of a sidelink positioning reference signal from a second terminal device.

With reference to the third aspect, in some implementations of the third aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, where the configuration information is used to indicate the first configuration parameter and the second configuration parameter, or the configuration information is used to indicate the first configuration parameter, where the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate a corresponding relationship between the first configuration parameter and the second configuration parameter.

With reference to the third aspect, in some implementations of the third aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, and receiving configuration information from the core network element includes receiving the configuration information from the core network element through a first signaling, where the configuration information of the first configuration parameter is carried in a first portion of the first signaling, and the configuration information of the second configuration parameter is carried in a second portion of the first signaling.

With reference to the third aspect, in some implementations of the third aspect, receiving configuration information from a core network element through a first signaling includes receiving, at a first time, a first configuration parameter from the core network element through a first portion of the first signaling, and receiving, at a second time, a second configuration parameter from the core network element through a second portion of the first signaling, where the first time and the second time are the same, or the first time and the second time are different.

The foregoing third aspect and advantageous effects of certain implementations of the third aspect may correspond to the descriptions related to the first aspect, which are not repeated herein.

In a fourth aspect, a communication method is provided, which may be performed by a core network element, or may also be performed by a chip or a circuit of the core network element, which is not limited by the present application. For ease of description, the following description will be given by taking an example of execution by a core network element.

The method comprises receiving all or part of first information from a first device, the first information indicating a probability distribution of measurement results of measurement quantities for terminal device positioning, and configuration information indicating configuration parameters of a generation model, the probability distribution being related to the configuration parameters of the generation model.

According to the scheme provided by the application, the core network element receives the configuration information from the terminal equipment, so that the core network element and the first equipment generate the configuration information of the model through alignment, the first model used for fitting/training of the positioning of the terminal equipment can be known to be the same, further, the analysis and the application of the probability distribution of the measurement result of the measurement quantity based on the first model are more accurate, and the positioning precision of the terminal equipment can be improved.

With reference to the fourth aspect, in some implementations of the fourth aspect, the method further includes determining a location of the terminal device according to a probability distribution of measurement results of the measurement quantities and configuration parameters of the generated model.

With reference to the fourth aspect, in some implementations of the fourth aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, where the configuration information is used to indicate the first configuration parameter and the second configuration parameter, or the configuration information is used to indicate the first configuration parameter, where the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate a correspondence relationship between the first configuration parameter and the second configuration parameter.

With reference to the fourth aspect, in some implementations of the fourth aspect, the generation model is any one of a gaussian mixture model, a variational self-encoder, and a generation countermeasure network.

With reference to the fourth aspect, in some implementations of the fourth aspect, the generating model is a gaussian mixture model, and the configuration parameters of the generating model include one or more of a generating method of the gaussian mixture model, a convergence threshold of the gaussian mixture model, a maximum value of iteration times of the gaussian mixture model, model parameters of the gaussian mixture model, a maximum value M of the number of single gaussian models included in the gaussian mixture model, M being a positive integer, a maximum value N of expected values of the single gaussian models included in the gaussian mixture model, N being a positive number, and a maximum value A of variance or covariance of the single gaussian models included in the gaussian mixture model, A being a positive number, and a duty ratio of one or more single gaussian models included in the gaussian mixture model.

With reference to the fourth aspect, in some implementations of the fourth aspect, generating the model as a variational self-encoder, generating configuration parameters of the model includes one or more of a structural parameter of the variational self-encoder, a type of neural network used by the variational self-encoder, an input and/or output dimension of the variational self-encoder, and a value of the model parameter of the variational self-encoder.

With reference to the fourth aspect, in certain implementations of the fourth aspect, the measurement includes one or more of a reference signal time difference RSTD, a time difference of arrival TDoA, a time of arrival ToA, an angle of arrival AoA, and a line of sight LoS probability.

With reference to the fourth aspect, in some implementations of the fourth aspect, the generating model is a gaussian mixture model, the gaussian mixture model includes k single gaussian models, k is an integer greater than or equal to 1, and the first information includes one or more of a value of k expected values, a value of k variances or covariances, a value of a duty ratio of the k single gaussian models in the gaussian mixture model, and the k expected values, the k variances or covariances are in one-to-one correspondence with the k single gaussian models.

With reference to the fourth aspect, in some implementations of the fourth aspect, the generating the model is a variation self-encoder, and the first information includes one or more of a value of a model parameter of the variation self-encoder and a value of a probability distribution output by the variation self-encoder.

With reference to the fourth aspect, in some implementations of the fourth aspect, the channel measurement result is based on measurement of a reference signal, including any one of the first device being an access network device, the channel measurement result being based on a first channel measurement, the first channel measurement including measurement of a sounding reference signal from a terminal device, or the first device being a terminal device, the channel measurement result being based on a second channel measurement, the second channel measurement including measurement of a positioning reference signal or a channel state information reference signal from the access network device, or the first device being a first terminal device, the channel measurement result being based on a third channel measurement, the third channel measurement including measurement of a sidelink positioning reference signal from a second terminal device.

With reference to the fourth aspect, in some implementations of the fourth aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, and receiving configuration information from the core network element includes receiving the configuration information from the core network element through a first signaling, where the configuration information of the first configuration parameter is carried in a first portion of the first signaling, and the configuration information of the second configuration parameter is carried in a second portion of the first signaling.

With reference to the fourth aspect, in some implementations of the fourth aspect, receiving configuration information from the core network element through the first signaling includes receiving, at a first time, a first configuration parameter from the core network element through a first portion of the first signaling, and receiving, at a second time, a second configuration parameter from the core network element through a second portion of the first signaling, where the first time and the second time are the same or the first time and the second time are different.

Advantageous effects of the fourth aspect and certain implementations of the fourth aspect may correspond to those described in relation to the second aspect, and are not described here again.

In a fifth aspect, a communication device is provided, the device comprising a transceiver unit configured to receive configuration information from a core network element, the configuration information being configured to indicate configuration parameters of a generation model, and a processing unit configured to process channel measurement results with a first model, to obtain a probability distribution of measurement results of measurement quantities for positioning a terminal device, the first model being determined based on the configuration parameters of the generation model, the measurement quantities corresponding to the channel measurement results.

The transceiver unit may perform the processing of the reception and transmission in the foregoing first aspect, and the processing unit of the communication apparatus may perform other processing than the reception and transmission in the foregoing first aspect.

In a sixth aspect, a communication apparatus is provided, the apparatus comprising a transceiver unit configured to send configuration information to a first device, the configuration information being configured to indicate configuration parameters of a generated model, and a processing unit configured to receive first information from the first device, the first information being indicative of a probability distribution of measurement results of measurement quantities for positioning of the terminal device, the probability distribution being related to the configuration parameters of the generated model.

The transceiver unit may perform the processing of the reception and transmission in the foregoing second aspect, and the processing unit of the communication apparatus may perform other processing than the reception and transmission in the foregoing second aspect.

In a seventh aspect, a communication apparatus is provided, the apparatus including a processing unit configured to configure information, where the configuration information is configured to indicate configuration parameters of a generation model, and a transceiver unit configured to process a channel measurement result by using a first model, to obtain a probability distribution of a measurement result of a measurement quantity for positioning a terminal device, where the first model is determined based on the configuration parameters of the generation model, and the measurement quantity corresponds to the channel measurement result.

Alternatively, the channel measurement result is based on measurement of the reference signal, which may be, for example, the first device or another device performing measurement on the reference signal to obtain the channel measurement result.

The transceiving unit may perform the processing of reception and transmission in the aforementioned third aspect, and the processing unit of the communication apparatus may perform other processing than reception and transmission in the aforementioned third aspect.

In an eighth aspect, a communication apparatus is provided, the apparatus comprising a transceiver unit configured to receive all or part of first information and configuration information from a first device, the first information indicating a probability distribution of measurement results of measurement quantities for positioning of a terminal device, the configuration information indicating configuration parameters of a generated model, the probability distribution being related to the configuration parameters of the generated model, and a processing unit configured to determine a location of the terminal device based on the probability distribution of measurement results of the measurement quantities and the configuration parameters of the generated model.

The transceiving unit may perform the processing of reception and transmission in the aforementioned fourth aspect, and the processing unit of the communication apparatus may perform other processing than reception and transmission in the aforementioned fourth aspect.

In a ninth aspect, a communication apparatus is provided comprising processing circuitry for executing a computer program to cause the apparatus to perform the method of any one of the above first to fourth aspects and any one of its possible implementations.

Optionally, the processing circuitry is one or more processors, or circuitry for processing functionality in whole or in part of one or more processors.

Optionally, the communication device further comprises a memory for storing said computer program, said memory being one or more.

Alternatively, the memory may be integrated with the processor, or the memory may be separate from the processor, or the memory may be located within the processor.

Optionally, the communication device further comprises a transceiver circuit, such as a transceiver or an input-output circuit.

A tenth aspect provides a communication system comprising a first device for performing the method of the first or third aspect and any of its possible implementation forms, and a core network element for performing the method of the second or fourth aspect and any of its possible implementation forms.

In an eleventh aspect, there is provided a computer readable storage medium storing a computer program or code which, when run on a computer, causes the computer to perform the method of the first or second aspect and any one of its possible implementations.

In a twelfth aspect, a chip is provided, comprising processing circuitry for running a computer program to cause an apparatus on which the chip is mounted to perform the method of any one of the above first to fourth aspects and any one of its possible implementations.

The chip may include, among other things, an output circuit or interface for transmitting information or data, and an input circuit or interface for receiving information or data.

In a thirteenth aspect, there is provided a computer program product comprising computer program code for performing the method of the first to fourth aspects and any possible implementation thereof, when the computer program code is run on the computer.

Drawings

Fig. 1 is a schematic diagram of a wireless communication system 100 suitable for use in embodiments of the present application;

fig. 2 is a schematic diagram of a wireless communication system 200 suitable for use in embodiments of the present application;

Fig. 3 is a schematic diagram of a wireless communication system 300 suitable for use in embodiments of the present application;

fig. 4 is a schematic diagram of a network element according to an embodiment of the present application;

FIG. 5 is a schematic diagram of an AI/ML network element or module;

FIG. 6 is a schematic diagram of an AI positioning model framework;

fig. 7 is a schematic diagram of TDoA location;

FIG. 8 is a schematic diagram of LOS and NLOS;

FIG. 9 shows a schematic diagram of probability distributions for Gaussian mixture models corresponding to different model fitting configurations;

FIG. 10 is a schematic flow chart diagram of a communication method 1000 provided by an embodiment of the present application;

FIG. 11 is a schematic flow chart diagram of a communication method 1100 provided by an embodiment of the application;

FIG. 12 is a schematic flow chart diagram of a communication method 1200 provided by an embodiment of the present application;

fig. 13 is a schematic flow chart of a communication method 1300 provided by an embodiment of the present application;

FIG. 14 is a schematic flow chart diagram of a communication method 1400 provided by an embodiment of the present application;

FIG. 15 is a schematic flow chart diagram of a communication method 1500 provided by an embodiment of the present application;

FIG. 16 is a schematic flow chart diagram of a communication method 1600 provided by an embodiment of the present application;

FIG. 17 is a schematic flow chart of a communication method 1700 provided by an embodiment of the present application;

FIG. 18 is a schematic block diagram of a communication device 1800 provided by an embodiment of the application;

Fig. 19 is a schematic block diagram of a communication apparatus 1900 provided by an embodiment of the present application.

Detailed Description

The technical scheme of the application will be described below with reference to the accompanying drawings.

The technical scheme provided by the application can be applied to various communication systems, such as a fifth generation (5th generation,5G) or New Radio (NR) system, a long term evolution (long term evolution, LTE) system, an LTE frequency division duplex (frequency division duplex, FDD) system, an LTE time division duplex (time division duplex, TDD) system, a wireless local area network (wireless local area network, WLAN) system, a satellite communication system, a future communication system, such as a sixth generation mobile communication system, or a fusion system of a plurality of systems, and the like. The technical solution provided by the present application may also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (machine to machine, M2M) communication, machine type communication (MACHINE TYPE communication, MTC), and internet of things (internet of things, ioT) communication systems or other communication systems.

One device in a communication system may send signals to or receive signals from another device. Wherein the signal may comprise information, signaling, data, or the like. Wherein the device may also be replaced by an entity, a network entity, a communication device, a communication module, a node, a communication node, etc., which device is described in the present application as an example. For example, the communication system may comprise at least one terminal device and at least one network device. The network device may send a downstream signal to the terminal device and/or the terminal device may send an upstream signal to the network device. It will be appreciated that the terminal device/network device of the present application may be replaced by a first device, and perform the corresponding communication method of the present application with a core network element (e.g. a location device, which may be a location management function network element LMF).

The terminal device in the embodiment of the application comprises various devices with wireless communication functions, and can be used for connecting people, objects, machines and the like. The terminal device can be widely applied to various scenes, such as scenes of cellular communication, D2D, V2X, peer-to-peer (P2P), M2M, MTC, ioT, virtual Reality (VR), augmented reality (augmented reality, AR), industrial control, autopilot, telemedicine, smart grid, smart furniture, smart office, smart wear, smart transportation, smart city unmanned aerial vehicle, robot, remote sensing, passive sensing, positioning, navigation and tracking, autonomous delivery and the like. The terminal device may be a terminal in any of the above scenarios, such as an MTC terminal, an IoT terminal, etc. The terminal device may be a User Equipment (UE) standard of the third generation partnership project (3rd generation partnership project,3GPP), a terminal (terminal), a fixed device, a mobile station (mobile station) device or a mobile device, a subscriber unit (subscriber unit), a handheld device, a vehicle-mounted device, a wearable device, a cellular phone (cellular phone), a smart phone (smart phone), a session initiation protocol (session initialization protocol, SIP) phone, a wireless data card, a personal digital assistant (personal DIGITAL ASSISTANT, PDA), a computer, a tablet computer, a notebook computer, a wireless modem, a handheld device (handset), a laptop computer (laptop computer), a computer with wireless transceiver function, a smart book, a vehicle, a satellite, a global positioning system (global positioning system, GPS) device, a target tracking device, an aircraft (e.g., a drone, a helicopter, a multi-helicopter, a quad-helicopter, or an airplane, etc.), a ship, a remote control device smart home device, an industrial device, or a device built into the above device (e.g., a modem, a communication module or a wireless modem of the above device), a wireless modem, a communication module or other processing device, or a wireless modem. For convenience of description, the terminal device will be described below by taking a terminal or UE as an example.

It should be appreciated that in some scenarios, the UE may also be used to act as a base station. For example, the UEs may act as scheduling entities that provide sidelink signals between UEs in a V2X, D2D or P2P or the like scenario.

In the embodiment of the present application, the device for implementing the function of the terminal device may be the terminal device, or may be a device capable of supporting the terminal device to implement the function, for example, a chip system or a chip, and the device may be installed in the terminal device. In the embodiment of the application, the chip system can be formed by a chip, and can also comprise the chip and other discrete devices.

The network device in the embodiment of the present application may be a device for communicating with a terminal device, and the network device may also be referred to as an access network device or a radio access network device, for example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (radio access network, RAN) node (or device) that accesses the terminal device to the wireless network. A base station may broadly cover or be replaced with various names such as a node B (NodeB), an evolved NodeB (eNB), a next generation NodeB (gNB), a relay station, an access point, a transmission point (TRANSMITTING AND RECEIVING point, TRP), a transmission point (TRANSMITTING POINT, TP), a master station, a secondary station, a multi-mode radio (motor SLIDE RETAINER, MSR) node, a home base station, a network controller, an access node, a radio node, an Access Point (AP), a transmission node, a transceiver node, a baseband unit (BBU), a remote radio unit (remote radio unit, RRU), an active antenna unit (ACTIVE ANTENNA unit, AAU), a radio head (remote radio head, RRH), a Central Unit (CU), a distributed unit (RU), a positioning node, a RAN intelligent controller (RAN INTELLIGENT controller, RIC), and the like. The base station may be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. A base station may also refer to a communication module, modem, or chip for placement within the aforementioned device or apparatus. The base station may also be a mobile switching center, a device that performs a base station function in D2D, V2X, M M communication, a network side device in a 6G network, a device that performs a base station function in a future communication system, or the like. The base stations may support networks of the same or different access technologies. The embodiment of the application does not limit the specific technology and the specific equipment form adopted by the network equipment.

The base station may be fixed or mobile. For example, a helicopter or drone may be configured to act as a mobile base station, and one or more cells may move according to the location of the mobile base station. In other examples, a helicopter or drone may be configured to function as a device to communicate with another base station.

In some deployments, the network device mentioned in the embodiments of the present application may be a device including a CU, or a DU, or a device including a CU and a DU, or a device of a control plane CU node (central unit-control plane, CU-CP) and a user plane CU node (central unit-user plane, CU-UP) and a DU node. For example, the network devices may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

In some deployments, a plurality of RAN nodes cooperate to assist a terminal in implementing radio access, and different RAN nodes implement part of the functions of the base station, respectively. For example, the RAN node may be a CU, DU, CU-CP, CU-UP, or RU, etc. The CU and the DU may be provided separately or may be comprised in the same network element, e.g. the BBU. The RU may be included in a radio frequency device or a radio frequency unit, e.g., in an RRU, AAU, or RRH.

The RAN node may support one or more types of forwarding interfaces, different forwarding interfaces corresponding to DUs and RUs with different functions, respectively. If the forwarding interface between the DU and the RU is a common public radio interface (common public radio interface, CPRI), the DU is configured to implement one or more of the baseband functions and the RU is configured to implement one or more of the radio frequency functions. If the forward interface between the DU and RU is another interface, it moves one or more of downlink and/or uplink baseband functions, such as, for example, for downlink, precoding (precoding), digital Beamforming (BF), or inverse fast fourier transform (INVERSE FAST Fourier transform, IFFT)/adding Cyclic Prefix (CP), from the DU to the RU, and for uplink, digital Beamforming (BF), or fast fourier transform (fast Fourier transform, FFT)/removing Cyclic Prefix (CP), from the DU to the RU. In one possible implementation, the interface may be an enhanced universal public radio interface (enhanced common public radio interface, eCPRI). Under eCPRI architecture, the splitting manner between DU and RU is different, corresponding to eCPRI of different types (category, cat), such as ECPRI CAT A, B, C, D, E, F.

Taking ECPRI CAT A as an example, for downlink transmission, taking layer mapping as a cut, a DU is configured to implement layer mapping and one or more functions before (i.e., one or more of coding, rate matching, scrambling, modulation, layer mapping), while other functions after layer mapping (e.g., one or more of Resource Element (RE) mapping, digital Beamforming (BF), or inverse fast fourier transform (INVERSE FAST Fourier transform, IFFT)/adding Cyclic Prefix (CP)) are moved to RU for implementation. For uplink transmission, with de-RE mapping as a cut, the DUs are configured to implement de-mapping and one or more functions before (i.e., one or more of decoding, de-rate matching, descrambling, demodulation, inverse discrete fourier transform (INVERSE DISCRETE Fourier transform, IDFT), channel equalization, de-RE mapping), while other functions after de-mapping (e.g., one or more of digital BF or fast fourier transform (fast Fourier transform, FFT)/decp) are moved to the RU for implementation. It is to be understood that, for the description of the functions of the DUs and RUs corresponding to the various types eCPRI, reference may be made to the eCPRI protocol, which is not described herein.

In one possible design, a processing unit in the BBU for implementing the baseband function is called a baseband high layer (BBH) unit, and a processing unit in the RRU/AAU/RRH for implementing the baseband function is called a baseband low layer (BBL) unit.

In different systems, CUs (or CU-CP and CU-UP), DUs or RUs may also have different names, but the meaning will be understood by those skilled in the art. For example, the radio access network may also be an open radio access network (open radio access network, O-RAN) architecture, and in ORAN systems, a CU may also be referred to as an O-CU (open CU), a DU may also be referred to as an O-DU, a CU-CP may also be referred to as an O-CU-CP, a CU-UP may also be referred to as an O-CU-UP, and an RU may also be referred to as an O-RU. Any unit of CU (or CU-CP, CU-UP), DU and RU in the present application may be implemented by a software module, a hardware module, or a combination of software and hardware modules.

In the embodiment of the present application, the means for implementing the function of the network device may be the network device, or may be a means capable of supporting the network device to implement the function, for example, a chip system or a chip, and the means may be installed in the network device. In the embodiment of the application, the chip system can be formed by a chip, and can also comprise the chip and other discrete devices.

The network equipment and the terminal equipment can be deployed on land, including indoor or outdoor, handheld or vehicle-mounted, on water surface, and on aerial planes, balloons and satellites. In the embodiment of the application, the scene where the network equipment and the terminal equipment are located is not limited. In addition, the terminal device and the network device may be hardware devices, or may be software functions running on dedicated hardware, or software functions running on general-purpose hardware, for example, be virtualized functions instantiated on a platform (for example, a cloud platform), or be entities including dedicated or general-purpose hardware devices and software functions.

In the embodiment of the application, the location management function network element may be a location node or a location device, such as an LMF, for performing location management on the location of the terminal device. The means for locating or managing the position of the terminal device may be, for example, a location management function network element, or may be a chip system, chip or circuit of the location management function network element, which may be installed in the location management function network element. The chip system may be composed of a chip or may include a chip and other discrete devices.

Alternatively, the location management function network element may be a core network device, where the core network device refers to a device in a Core Network (CN) that provides service support for the terminal device. The core network device may comprise one or more core network elements. Taking a 5G core network as an example, the 5G core network includes an access and mobility management function (ACCESS AND mobility management function, AMF) network element responsible for mobility management, access management, and other services, a session management function (session management function, SMF) network element responsible for session management, a user plane function (user plane function, UPF) network element responsible for packet routing forwarding and quality of service (quality of service, qoS) control of a user plane, a policy control function (policy control function, PCF) network element, and the like. The core network elements can work independently or can be combined together to realize certain control functions, for example, AMF, SMF and PCF can be combined together to be used as a core network device. All or part of the core network elements may be independent in form, or may be integrated in the same device, which is not limited herein.

In the embodiment of the present application, the first device may be a terminal device or a network device, or a component (such as a chip or a circuit) of the terminal device or the network device. Alternatively, the network device may be a network device provided with one or more AI modules. For example, the network device may be one or more of a core network device, an access network node (RAN node), or an OAM device. For example, the AI module may be a RAN Intelligent Controller (RIC), such as a near real-time RIC or a non-real-time RIC, or the like. For example, near real-time RIC is provided in a RAN node (e.g., in a CU or DU), non-real-time RIC is provided in OAM, in a cloud server, in a core network device, or in other network devices. The location management function network element is a storage network element of a training of AI positioning models and/or of an AI positioning model library, or is also a selection/reasoning network element of AI positioning models at the same time, for example, the AI positioning model for positioning is configured in the location management function network element.

For example, the first device and the location management function element may be disposed logically separately, and as a different implementation, the first device and the location management function element may be disposed physically on the same network element or different network elements, without limitation. For example, the first device is a terminal device, the location management function network element is a server (also referred to as a host) or a cloud device in an Over The Top (OTT) system, and the terminal device and the server or the cloud device of the OTT system can communicate through the internet. For another example, the first device is one module in the terminal device (e.g., a module of a physical layer), and the location management function network element is another module of the device (e.g., an LMF) (e.g., a module of an application layer, such as an application module connected to an OTT server). It should be understood that, in the embodiment of the present application, the modules may be implemented by hardware, or may be implemented by software, or implemented by a combination of hardware and software, which is not limited.

A communication system suitable for use in embodiments of the present application will first be briefly described as follows.

Fig. 1 is a schematic diagram of a wireless communication system 100 suitable for use in embodiments of the present application. As shown in fig. 1, the wireless communication system includes a radio access network 100. The radio access network 100 may be a next generation (e.g., 6G or higher version) radio access network, or a legacy (e.g., 5G, 4G, 3G, or 2G) radio access network. One or more terminal devices (120 a-120j, collectively 120) may be interconnected or connected to one or more network devices (110 a, 110b, collectively 110) in the radio access network 100. Fig. 1 is only a schematic diagram, and other devices may be further included in the wireless communication system, for example, a core network device, a wireless relay device, and/or a wireless backhaul device, which are not shown in fig. 1.

In practical applications, the wireless communication system may include a plurality of network devices at the same time, or may include a plurality of terminal devices at the same time, without limitation. One network device may serve one or more terminal devices simultaneously. One terminal device may also access one or more network devices simultaneously. The embodiment of the application does not limit the number of terminal equipment and network equipment included in the wireless communication system.

Fig. 2 is a schematic diagram of a wireless communication system 200 suitable for use in embodiments of the present application. As shown in fig. 2, the wireless communication system 200 may include at least one network device, such as the network device 210 shown in fig. 2, the wireless communication system 200 may further include at least one terminal device, such as the terminal device 220 and the terminal device 230 shown in fig. 2, and the wireless communication system 200 may further include a positioning device, such as the positioning device 240 shown in fig. 2. Illustratively, the positioning device 240 is a location management function LMF network element, abbreviated as LMF.

Wherein the positioning device and the network device can communicate via interface messages. For example, using network device 210 as the gNB and locating device 240 as the LMF, information may be exchanged between the gNB and the LMF through NRPPa messages. For another example, using the network device 210 as an eNB and the positioning device 240 as an LMF, information may be exchanged between the eNB and the LMF through LTE positioning protocol (LTE positioning protocol, LPP) messages.

The terminal device and the positioning device may communicate directly or may also communicate through other devices, for example, the network device and/or the core network element. As an example, as shown in fig. 2, a terminal device 220 and a positioning device 240 may communicate through a network device 210.

Alternatively, the positioning device may be a different module of the same device as the network device, or may be a separate and different device.

Fig. 3 is a schematic diagram of a wireless location system suitable for use in embodiments of the present application. As shown in fig. 3, the wireless positioning system mainly includes an access network device, a terminal device, and a positioning device. The positioning device is mainly responsible for receiving a positioning service request, collecting measurement results related to positioning, calculating positioning results, providing corresponding wireless positioning services and the like. Alternatively, the location device may receive a location service request from the access network device, or an upper layer application. As one example, the positioning device may be a location management function network element, such as an LMF. See the description above for access network devices and terminal devices.

Fig. 4 is a schematic diagram of an apparatus according to an embodiment of the present application. As shown in fig. 4, includes a UE, a location management function network element, and an access network device. Optionally, an access mobility management function (ACCESS MANAGEMENT function, AMF) network element is also included. As an example, the access network device may be a ng-eNB or a gNB, where ng-eNB represents a 4G base station that may access a 5G core network and gNB represents a 5G base station, both being network elements of the NR-RAN. The radio access network device or the base station mentioned in the embodiment of the present application may be a ng-eNB or a gNB, which is not limited. The UE and the radio access network device communicate through corresponding interfaces, for example, the UE and the gNB communicate through an NR-Uu interface, and the UE and the ng-eNB communicate through an LTE-Uu interface. In the embodiment of the application, the NR-Uu interface and the LTE-Uu interface are used for transmitting signaling and/or data related to positioning. In addition, communication between the gNB and the AMF, and between the NG-eNB and the AMF is performed through an NG-C interface, such as signaling related to transmission positioning. Communication between the AMF and the LMF is performed through the NL1 interface, such as transmitting positioning related signaling. Optionally, the interaction between the UE and the LMF is based on the LTE positioning protocol (LTE positioning protocol, LPP) protocol, and the interaction between the NG-RAN and the LMF is based on the NRPPa protocol, the NRPPa protocol being transparent transmission across the AMF. It should be understood that NG-RAN is only an example, and that when the technical solution of the present application is applied to future wireless communication systems, such as 6G systems, NG-RAN is correspondingly an access network device in the 6G system. Also, names of network elements, interface names between network elements, message names, and the like are merely examples, and network elements, interfaces, and interface messages having the same or similar functions may be employed in future wireless communication systems to implement the technical solution of the present application.

In addition, in order to support the machine learning function in the wireless communication system, an AI node may be introduced in the wireless communication system.

Optionally, the communication system further comprises at least one AI node.

Alternatively, the AI node may be deployed at one or more of a network device, a terminal device, a core network, or a positioning device, or the AI node may be deployed separately, such as at a location other than any of the above. The AI node may communicate with other devices in the communication system, which may be, for example, one or more of a network device, a terminal device, a core network element, or a positioning device.

Optionally, the AI node is configured to perform an AI-related operation. By way of example, the AI-related operations may include, for example, one or more of a model failure test, a model performance test, a model training test, or a data acquisition, among others.

For example, the network device may forward data related to the AI-positioning model reported by the terminal device to the AI node, which performs AI-related operations. For another example, the access network device or terminal device may forward data related to the AI-positioning model to an AI node, which performs AI-related operations. As another example, the AI node may transmit an output of an AI-related operation, such as one or more of a trained neural network model, a model evaluation, or a test result, to a network device and/or a terminal device. For example, the AI node may send the output of the AI-related operation directly to the network device and the terminal device. For another example, the AI node may send the output of the AI-related operation to a terminal device via a network device. For another example, the AI node may send the output of the AI-related operation to a network device via a terminal device.

It will be appreciated that the present application is not limited to the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes may be partitioned based on functionality, such as with different AI nodes being responsible for different functionality.

It is further understood that the AI node may be a separate device, or may be integrated into the same device to implement different functions, or may be a network element in a hardware device, or may be a software function running on dedicated hardware, or may be a virtualized function instantiated on a platform (e.g., a cloud platform), and the specific form of the AI node is not limited by the present application.

The AI node may be, for example, an AI network element or AI module.

Fig. 5 is a schematic diagram of an AI/ML network element or module. If the AI is introduced, it means that the AI corresponds to an independent network element, and if the AI is introduced, the AI may be located inside a certain network element. As described above, the network elements involved in the embodiments of the present application include UE, radio access network device, and LMF, and optionally, may further include AMF. The AI module may be provided inside one or more of these UE, radio access network device, AMF (if the network element is involved) and LMF, or one or more of the UE, radio access network device, AMF and LMF may incorporate a corresponding AI network element, or a combination of both, which the present application is not limited to.

The AI module is used for realizing the corresponding AI function. AI modules deployed in different network elements may be the same or different. The model of the AI module is configured according to different parameters, and the AI module can realize different functions. The model of the AI module may be configured based on one or more parameters of a structural parameter (e.g., at least one of a number of layers of the neural network, a width of the neural network, a connection relationship between layers, a weight of the neuron, an activation function of the neuron, or a bias in the activation function), an input parameter (e.g., a type of input parameter and/or a dimension of the input parameter), a hidden layer parameter (e.g., a type of hidden layer parameter and/or a dimension of the hidden layer parameter), or an output parameter (e.g., a type of output parameter and/or a dimension of the output parameter).

An AI module may have one or more models. A model can infer an output that includes a parameter or parameters. The learning process, training process, or reasoning process of the different models may be deployed in different nodes or devices, or may be deployed in the same node or device.

It should be appreciated that if one or more of the UE, the radio access network device, the AMF, and the LMF introduces a corresponding AI network element and the AI operations are performed by the corresponding AI network element, the UE, the radio access network device, the AMF, or the LMF needs to send AI operation-related information to the corresponding AI network element. For example, the LMF introduces a corresponding AI network element, and the AI network element performs an inference operation of the AI model, and after receiving a channel measurement report from a first device (for example, an access network device or UE), the LMF sends a channel measurement result carried in the channel measurement report to the corresponding AI network element. For another example, in uplink positioning, if the access network device introduces a corresponding AI network element, it is assumed that the input of the AI model takes as input a channel feature extracted from a channel measurement result obtained by the access network device measuring a Sounding REFERENCE SIGNAL (SRS) of the UE. After obtaining the channel measurement result, the access network device sends the channel measurement result to the corresponding AI network element, the AI network element extracts the channel characteristics from the channel measurement result through the AI model, and then the extracted channel characteristics are returned to the access network device, and the access network device sends the channel characteristics to the LMF.

It will be further appreciated that fig. 1-5 are simplified schematic diagrams illustrated for ease of understanding, and that other network devices, or other terminal devices, or other AI nodes, may be included in the wireless communication system, not shown in fig. 1-5.

In order to facilitate understanding of the embodiments of the present application, the following description will be given for the terms involved in the embodiments of the present application.

(1) An artificial intelligence AI;

The learning machine has learning ability, can accumulate experience, and solves the problems of natural language understanding, image recognition, chess playing and the like which can be solved by human through experience. Artificial intelligence may be understood as the intelligence exhibited by a machine made by a person. Artificial intelligence generally refers to the technology of presenting human intelligence by a computer program. The goal of artificial intelligence includes understanding intelligence by constructing computer programs with symbolically meaningful reasoning or reasoning.

(2) Machine learning (MACHINE LEARNING, ML);

ML is one implementation of artificial intelligence. Machine learning is a method that enables machine learning to be performed, thereby enabling the machine to perform functions that cannot be performed by direct programming. In a practical sense, machine learning is a method of training out models by using data and then using model predictions. Machine learning methods are numerous, such as Neural Networks (NN), decision trees, support vector machines, etc. Machine learning theory is mainly to design and analyze algorithms that allow computers to learn automatically. The machine learning algorithm is an algorithm for automatically analyzing and obtaining rules from data and predicting unknown data by utilizing the rules.

(3) An AI model;

The AI model is an algorithm or a computer program capable of realizing the AI function, the AI model characterizes the mapping relation between the input and the output of the model, or the AI model is a function model mapping the input with a certain dimension to the output with a certain dimension, and the parameters of the function model can be obtained through machine learning training. For example, f (x) =mx ² +n is a quadratic function model, which can be regarded as an AI model, m and n are parameters of the AI model, and m and n can be obtained by machine learning training. Illustratively, the AI model referred to in the following embodiments of the present application is not limited to being a neural network, a linear regression model, a decision tree model, a support vector machine (support vector machine, SVM), a bayesian network, a Q learning model, or other machine learning (MACHINE LEARNING, ML) model.

AI model design mainly includes a data collection link (e.g., collecting training data and/or reasoning data), a model training link, and a model reasoning link. Further, an inference result application link can be included. In the foregoing data collection procedure, a data source (data source) is used to provide training data sets and reasoning data. In the model training link, an AI model is obtained by analyzing or training data (TRAINING DATA) provided by a data source. The AI model is obtained through model training node learning, which is equivalent to obtaining the mapping relation between the input and the output of the AI model through training data learning. In the model reasoning link, an AI model trained by the model training link is used for reasoning based on the reasoning data provided by the data source, so as to obtain a reasoning result. The link can also be understood as inputting the reasoning data into the AI model, and obtaining an output through the AI model, wherein the output is the reasoning result. The inference results may indicate configuration parameters used (performed) by the execution object, and/or operations performed by the execution object. The issuing of the inference results is performed in the inference result application link, for example, the inference results may be uniformly planned by the execution (actor) entity, for example, the execution entity may send the inference results to one or more execution objects (for example, a core network device, an access network device, or a terminal device, etc.) for execution. For another example, the executing entity can also feed back the performance of the AI model to the data source, so that the updating training of the AI model can be conveniently carried out subsequently.

It is understood that the implementation of the AI model may be, without limitation, a hardware circuit, or may be software, or may be a combination of software and hardware. Non-limiting examples of software include program code, programs, subroutines, instructions, instruction sets, code segments, software modules, applications, or software applications, among others.

(4) Neural Networks (NN);

Neural networks are one specific implementation of AI or machine learning. According to the general approximation theorem, the neural network can theoretically approximate any continuous function, so that the neural network has the capability of learning any mapping.

The neural network may be composed of neural units, which may refer to arithmetic units with xs and intercept 1 as inputs. A neural network is a network formed by joining together a number of the above-described single neural units, i.e., the output of one neural unit may be the input of another. The input of each neural unit may be connected to a local receptive field of a previous layer to extract features of the local receptive field, which may be an area composed of several neural units.

Taking the type of AI model as a neural network as an example, the AI model related to the present application may be a deep neural network (deep neural network, DNN). The DNNs may include feed forward neural networks (feedforward neural network, FNN), convolutional neural networks (convolutional neural networks, CNN), recurrent neural networks (recurrent neural network, RNN), and the like, depending on the manner in which the network is constructed.

(5) Training data sets and reasoning data;

In the machine learning field, a true value (ground truth) generally refers to data that is considered accurate or true.

The training data set is used for training of the AI model, and the training data set may include an input of the AI model, or include an input of the AI model and a target output. The training data set includes one or more training data, which may include training samples input to the AI model, or may include a target output of the AI model. Wherein the target output may also be referred to as a label, a sample label, or a label sample. The label is true.

In the field of communications, the training data set may include simulation data collected through a simulation platform, experimental data collected in an experimental scenario, or measured data collected in an actual communications network. The collected data may be classified when the data is acquired due to differences in the geographical environment and channel conditions in which the data is generated, e.g., indoor, outdoor, moving speed, frequency band, or antenna configuration. For example, data of the same channel propagation environment and antenna configuration are classified into one type.

Model training essentially learns some of its features from training data, and in training an AI model (e.g., a neural network model), because the output of the AI model is expected to be as close as possible to the value actually desired, the weight vector for each layer of AI model can be updated by comparing the predicted value of the current network with the actually desired target value, and then based on the difference between the two (of course, there is typically an initialization process before the first update, i.e., pre-configuring parameters for each layer in the AI model), e.g., if the predicted value of the network is higher, the weight vector is adjusted to make it predict lower, and continuously adjusted until the AI model can predict the actually desired target value or a value very close to the actually desired target value. Thus, it is necessary to define in advance "how to compare the difference between the predicted value and the target value", which is a loss function (loss function) or an objective function (objective function), which are important equations for measuring the difference between the predicted value and the target value. Taking the loss function as an example, the higher the output value (loss) of the loss function is, the larger the difference is, and then training of the AI model becomes a process of reducing the loss as much as possible, so that the value of the loss function is smaller than the threshold, or the value of the loss function is enabled to meet the target requirement. For example, the AI model is a neural network and adjusting model parameters of the neural network includes adjusting at least one of a number of layers of the neural network, a width of the neural network, a weight of a neuron, or a parameter in an activation function of the neuron.

The inference data can be used as input to the AI model for which training has been completed. In the model reasoning process, the reasoning data is input into an AI model, and the corresponding output can be obtained, namely the reasoning result.

Fig. 6 is an AI application framework.

In the foregoing data collection procedure, a data source (data source) is used to provide training data sets and reasoning data. In the model training link, an AI model is obtained by analyzing or training data (TRAINING DATA) provided by a data source. Wherein the AI model characterizes a mapping between the input and the output of the model. The AI model is obtained through model training node learning, which is equivalent to obtaining the mapping relation between the input and the output of the model through training data learning. In the model reasoning link, an AI model trained by the model training link is used for reasoning based on the reasoning data provided by the data source, so as to obtain a reasoning result. The link can also be understood as inputting the reasoning data into the AI model, and obtaining an output through the AI model, wherein the output is the reasoning result. The inference results may indicate configuration parameters used (performed) by the execution object, and/or operations performed by the execution object. The issuing of the inference results is performed in the inference result application link, for example, the inference results may be uniformly planned by the execution (actor) entity, for example, the execution entity may send the inference results to one or more execution objects (for example, access network devices or terminal devices, etc.) for execution. For another example, the executing entity can also feed back the performance of the model to the data source, so that the model can be updated and trained later.

It will be appreciated that network elements with artificial intelligence functionality may be included in the communication system. The links related to the AI model design may be performed by one or more network elements with artificial intelligence functionality. In one possible design, AI functionality (e.g., AI modules or AI entities) may be configured within an existing network element in a communication system to enable AI-related operations, such as training and/or reasoning about AI models. For example, the existing network element may be an access network device or a terminal device, etc. Or in another possible design, a separate network element may be introduced into the communication system to perform AI-related operations, such as training an AI model. The independent network element may be referred to as an AI network element or an AI node, etc., and embodiments of the present application are not limited in this regard. The AI network element may be, for example, directly connected to a network device in the communication system, or may be indirectly connected to the network device through a third party network element. The third party network element may be a core network element such as an authentication management function (authentication management function, AMF) network element, a user plane function (user plane function, UPF) network element, an operation and maintenance management (operation administration AND MAINTENANCE, OAM), a cloud server, or other network elements, without limitation. The separate network element may be deployed, for example, at one or more of the network device side, the terminal device side, or the core network side. Alternatively, it may be deployed on a cloud server.

The training processes of different models can be deployed in different devices or nodes, or can be deployed in the same device or node. The reasoning processes of the different models can be deployed in different devices or nodes, or in the same device or node. By way of example, the model parameters of the AI model may include one or more of the model's structural parameters (e.g., number of layers, and/or weights, etc. of the model), model's input parameters (e.g., input dimensions, number of input ports), or model's output parameters (e.g., output dimensions, number of output ports). It will be appreciated that the input dimension may refer to the size of an input data, for example when the input data is a sequence, the corresponding input dimension of the sequence may indicate the length of the sequence. The number of input ports may refer to the amount of input data. Similarly, the output dimension may refer to a size of output data, e.g., when the output data is a sequence, the corresponding output dimension of the sequence may indicate a length of the sequence. The number of output ports may refer to the amount of output data.

(6) Generating a model (GENERATIVE MODEL);

Generating a model refers to a model that is capable of randomly generating observation data, particularly given certain implicit parameters. In machine learning ML, a generative model may be used to model data directly (e.g., data sampling from a probability density function of a certain variable) or to build a conditional probability distribution between variables. Wherein the conditional probability distribution may be formed by a generative model according to Bayes' theorem.

For example, the data generation method for generating the model includes the steps of:

a) Obtaining a probability distribution model of the training sample according to the training sample data and a specific generation learning method;

b) Sampling the data of the obtained probability distribution model to obtain a newly generated data sample;

the generation model represents the distribution condition of the data from the statistical angle, and can reflect the similarity of the similar data.

For example, generative models include, but are not limited to, naive Bayesian, markov models, gaussian mixture models (Gaussian Mixture Model, GMM), typically based on statistics and Bayesian theory.

As another example, a deep learning idea-based generation model includes, but is not limited to, a variational self-encoder (Variational AutoEncoder, VAE) and a generation of a countermeasure network (GENERATIVE ADVERSARIAL Networks, GAN). For easy understanding and description, the technical scheme of the application is exemplified by GMM and VAE as generative models.

(7) Gaussian mixture model (Gaussian Mixture Model, GMM);

GMM is a generative model that can be considered as a model that is composed of K single gaussian models (also called sub-steps), K being an integer greater than or equal to 1. The K single Gaussian models are hidden variables of the hybrid model. In general, a hybrid model may use any probability distribution. The gaussian mixture model GMM is used here because of the better mathematical properties and the good computational performance of the gaussian distribution.

For example, a single Gaussian model may be defined in that when the sample data X is one-dimensional data, the probability density function satisfied by the Gaussian distribution is as follows:

wherein μ is the mean value of the data, σ is the standard deviation of the data;

When the sample data X is multidimensional data, the probability density function satisfied by the gaussian distribution is as follows:

where μ is the mean of the data, Σ is the covariance of the data, and D is the dimension of the data.

For example, the probability distribution of the gaussian mixture model GMM satisfies:

where the complete mixture gaussian model typically includes a covariance matrix, a parameter mean vector, and a mixture weight, it may be expressed as θ, i.e., θ= (r _k,σ_k,p_k),r_k、σ_k、p_k represents the expectation (or mean), variance (or covariance), probability of occurrence in the mixture model, which may be referred to as weight, respectively) of the kth single gaussian model.

(8) -A variation self-encoder (Variational AutoEncoder, VAE);

VAE is a generative model, a structure made up of an encoder and a decoder, trained to minimize reconstruction errors between the output data after the encoder and decoder and the original input data. Alternatively, to introduce some regularization of the hidden space, the VAE may modify the encoding-decoding process, i.e. the input data encodes a probability distribution in the hidden space instead of a single point in the hidden space, a specific implementation comprising the steps of:

a) Encoding the input as a distribution over a hidden space;

b) Sampling a point in hidden space from the distribution;

c) Decoding the sampling points and calculating a reconstruction error;

d) The reconstruction error counter propagates through the network.

It should be noted that, through the encoding of the variational self-encoder, the feature of each measurement result is not a single value in the variational self-encoder but a probability distribution, and the VAE can build two probability density distribution models by using two neural networks, namely, one variational inference for the original input data, namely, generating the variational probability distribution of the hidden variable, which is called an inference network, and the other is used for generating the approximate probability distribution of the original data according to the generated variational probability distribution reduction, which is called a generation network.

(9) Generating an antagonism network (GENERATIVE ADVERSARIAL Networks, GAN);

GAN is a typical unsupervised learning method, which can automatically extract features to complete data generation. The GAN is composed of two important parts, namely a generator (generating data through a neural network) for generating data as similar as possible to the original data, spoofing a arbiter, and a arbiter (judging whether the data is real or machine-generated through the neural network) for finding out "dummy data" generated by the generator.

The essence of GAN is in fact to exploit the strong nonlinear fitting capability of neural networks to learn the nonlinear mapping from an arbitrary a priori noise distribution to a true data distribution, thus giving the generator the ability to produce realistic samples. The GAN is input in any noise distribution, and the generation of final data is completed through supervision of the original training data.

(10) The expectation is a very large (Expectation Maximization, EM) algorithm;

The EM algorithm is an iterative optimization strategy, and can solve the parameter estimation problem under the condition of data missing, and the basic idea is that firstly, the value of a model parameter is estimated according to the given observation data, then the value of the missing data is estimated according to the value of the model parameter, and then the value of the model parameter is estimated again according to the value of the missing data plus the given observation data, and the iteration is repeated until the final convergence is achieved, and the iteration is finished.

(11) Time difference of arrival (TIME DIFFERENCE of arrival, TDoA), a method of positioning using time difference.

Fig. 7 is a schematic diagram of TDoA location. As shown in fig. 7, it is assumed that a distance between the network device #1 and the terminal device is d1, a transmission time when the network device #1 and the terminal device transmit signals is t1, a distance between the network device #2 and the terminal device is d2, a transmission time when the network device #2 and the terminal device transmit signals is t2, a distance between the network device #3 and the terminal device is d3, and a transmission time when the network device #3 and the terminal device transmit signals is t3.

In TDoA, as an example, a plurality of network devices may send reference signals, such as Positioning Reference Signals (PRS), to a terminal device, which determines the location of the terminal device by measuring the TDoA of the reference signals, which may also be referred to as reference signal time difference (REFERENCE SIGNAL TIME DIFFERENCE, RSTD). Taking fig. 7 as an example, assume that a reference signal transmitted from the network device #1 to the terminal device is P1, a reference signal transmitted from the network device #2 to the terminal device is P2, and a reference signal transmitted from the network device #3 to the terminal device is P3. The terminal device measures TDoA of P2 and P1, i.e. t2-t1, and using t2-t1 can infer the distance difference d2-d1 between network device #2 and network device #1, and obtain a curve, each point on the curve satisfying the distance difference d2-d1 between network device #2 and network device # 1. Similarly, the terminal device measures TDoA of P3 and P1, i.e., t3-t1, and using t3-t1, can infer the distance difference d3-d1 between network device #3 and network device #1, and obtain another curve, each point on the curve satisfying the distance difference d3-d1 between network device #3 and network device # 1. By using the intersection point of the two curves, the position of the terminal equipment can be determined, and the mathematical model can be used for representing the formula (4):

Where (a _i,b_i) represents the location coordinates of network device #i. (a, b) represents the position coordinates of the terminal device to be solved, for example, a represents the position coordinates of the terminal device to be solved in the X-axis, b represents the position coordinates of the terminal device to be solved in the Y-axis, and c represents the speed of light.

Because of a certain synchronization error between different network devices, a certain uncertainty exists in the corresponding measured value.

The method for positioning according to the network device sending the reference signal to the terminal device is described in connection with fig. 7 above, which may also be referred to as downlink TDoA (DL-TDoA) or observed time difference of arrival OTDoA. Similarly, the positioning may also be performed according to the terminal device sending a reference signal, such as SRS, to the network device, and the positioning method may be called uplink TDoA (UL-TDoA).

It will be appreciated that in addition to measuring the time difference, positioning can also be performed by measuring the angle. The angle may be an angle of arrival (AoA) or an angle of departure (angle of departure, aoD). The arrival angle is used for indicating the included angle between the direction of the signal received by the receiving end and the reference direction. The separation angle is used for indicating an included angle between a direction of a signal transmitted by the transmitting end and a reference direction, wherein the reference direction can be a direction determined according to the position and/or the shape of the antenna.

Under the actual communication scene, due to the influence of noise and interference, certain measurement errors exist in the time or angle measurement values, and certain errors also exist in the corresponding positioning results.

Fig. 8 is a schematic diagram of line of sight LoS and non-line of sight (NLoS). As shown in fig. 8, the LoS (shown as a dotted line in fig. 8) between the network device and the terminal device is blocked by the blocking object, and the reference signal transmitted between the network device and the terminal device is actually a reflected NLoS (shown as a solid line in fig. 8), and it can be seen from the figure that the distance of the NLoS (i.e., d2+d3) is greater than the distance of the LoS (i.e., d 1). If NLoS is considered LoS when making a position estimate, a large measurement error may occur. Therefore, loS and NLoS classification are also important for positioning accuracy.

In the positioning technology based on AI, an AI positioning model is usually deployed in an LMF, where the AI positioning model takes a channel measurement result reported by a channel measurement network element as input and a position of a terminal device as output. Thus, the channel measurement network element typically needs to report the channel measurement report to the location management function network element. For example, in downlink positioning, gNB sends PRS to UE, UE measures PRS sent by gNB to obtain GMM distributed by DL-RSTD, and sends related parameters of GMM to LMF for LMF to position UE.

Fig. 9 shows a schematic diagram of probability distributions (which may be referred to as gaussian mixture distributions) of gaussian mixture models corresponding to different model fitting configurations.

Where (a) of fig. 9 represents the true value of the gaussian mixture distribution of the data, the gaussian mixture model including 3 single gaussian models. Specifically, (b) of fig. 9 shows a gaussian mixture distribution obtained by converging the number of single gaussian models with the maximum number of iterations being 10, and (c) of fig. 9 shows a gaussian mixture distribution obtained by converging the number of single gaussian models with the maximum number of iterations being 50, and (d) of fig. 9 shows a gaussian mixture distribution obtained by converging the number of single gaussian models with the maximum number of iterations being 3 and the maximum number of iterations being 50, whereby it is seen that the larger the number of single gaussian models and the maximum number of iterations, the closer to the true value of the gaussian mixture distribution. For the same Gaussian mixture distribution, the convergence result obtained by adopting different model fitting configurations may be different, that is, the GMM obtained by fitting the UE through different model fitting configurations has large difference, which may result in poor positioning accuracy of the UE. Therefore, how to improve the positioning accuracy of the UE is a problem to be solved.

Based on this, the embodiment of the application provides a communication method and a communication device, and configuration information of a model is generated by alignment between a core network element and first equipment, so that the first model used for fitting/training of positioning of terminal equipment can be known to be the same, further, the probability distribution of a measurement result of a measurement quantity is analyzed and applied more accurately based on the first model, and the positioning precision of the terminal equipment can be improved.

The communication method provided by the embodiment of the application will be described in detail below with reference to the accompanying drawings. The embodiments provided by the present application may be applied to the communication system shown in fig. 1 or fig. 2, and are not limited thereto.

Fig. 10 is a schematic flow chart of a communication method 1000 provided by an embodiment of the present application. As shown in fig. 10, method 1000 may include the following steps. It should be understood that the method may be performed by the first device and the core network element, or may be performed by a chip, a system-on-chip or a circuit of the first device and the core network element, which is not limited by the present application. For convenience of description, the following description will be given by taking the first device and the core network element as execution bodies. It should be noted that, in this implementation, training/fitting of the model occurs at the first device side, model reasoning/use occurs at the core network element side, or training/fitting of the model occurs at the OTT or third party device or cloud device side, and model reasoning/use occurs at the OTT or third party device or cloud device side, which is not limited in this application.

S1010, the core network element sends configuration information to the first device, and the first device receives the configuration information from the core network element.

The configuration information is used for indicating configuration parameters of the generation model.

In one example, the first device may be a terminal device or an access network device, and the core network element may be a positioning node or a positioning device for managing the location of the terminal device, e.g. a location management function network element (such as LMF). The first device may also be called a network element performing channel measurement, or a channel measurement network element, or a reference signal measurement node, etc., and the name of the first device is not limited by the present application.

Illustratively, the generative model is any one of the following:

(1) For specific definitions, the gaussian mixture model GMM may be referred to the above description.

(2) The variations are derived from the encoder VAE and reference is made to the relevant description above for specific explanation.

(3) For specific explanation, reference is made to the above description of generating the antagonism network GAN.

In a first implementation, when the generative model is a GMM, the configuration parameters include one or more of:

(1) The maximum value M of the number of the single Gaussian models contained in the GMM is a positive integer;

for example, if the upper limit of the number of the single gaussian models included in the GMM is 5, it is indicated that the number of the single gaussian models included in the GMM is less than or equal to 5, that is, M is less than or equal to 5, for example, the number of the single gaussian models included in the GMM may be 2 or 3.

(2) A method for generating a GMM;

The method of generating the GMM may be, for example, an EM algorithm, which is an iterative algorithm for maximum likelihood estimation or maximum a posteriori probability estimation of a probabilistic parametric model containing Hidden variables (Hidden Variable). For example, the first device first estimates the value of the model parameter according to the given observation data, then estimates the value of the missing data according to the value of the model parameter, then re-estimates the value of the model parameter according to the value of the missing data plus the given observation data, and iterates until the final convergence and the iteration ends.

(3) A convergence threshold of the GMM;

illustratively, assuming that the convergence threshold is p, it may be understood that the convergence value of the GMM trained or fitted by the first device is less than or equal to p, e.g., p=0.01. For example, the convergence value of the GMM obtained by the first device training is q, q is less than or equal to p, where p and q are both positive numbers.

(4) Maximum number of iterations of GMM;

For example, the upper limit of the iteration number is 50, which indicates that the number of iterations in the first device training or GMM fitting process may be less than or equal to 50, for example, the iteration number may be 10, 20, or 50. It will be appreciated that to some extent, the greater the number of iterations, the better the convergence effect.

(5) Model parameters of the GMM;

The model parameters of the GMM include, by way of example, one or more of the expected r _k of the k single gaussian models contained by the GMM, the variance or covariance σ _k of the k single gaussian models, and the duty cycle p _k of the k single gaussian models in the GMM, for specific definitions reference being made to the relevant description of equation (3) above.

(6) The GMM comprises a maximum value N of a single Gaussian model expected value, wherein N is a positive number;

Illustratively, assuming that the GMM contains 3 single gaussian models, the expected values for each of the 3 single gaussian models are less than or equal to N.

(7) The GMM comprises a variance or maximum value A of covariance of a single Gaussian model, wherein A is a positive number;

Illustratively, assuming that the GMM contains 3 single gaussian models, the variance or covariance of these 3 single gaussian models is less than or equal to a.

(8) The GMM includes a duty cycle X of one or more single gaussian models in the GMM.

Illustratively, assuming that the GMM contains 3 single gaussian models, the 3 single gaussian models have a duty cycle of less than or equal to X throughout the GMM.

In a second implementation, when the generative model is a VAE, the configuration parameters include one or more of the following:

(1) The value of the model parameters of the VAE;

The model parameters of the VAE include one or more of weights of neurons, activation functions of neurons, or offsets in activation functions of neurons, wherein the offsets in activation functions may also be referred to as offsets of a neural network. It should be understood that the model parameters of the VAE refer to already trained model parameters, i.e. the first device may determine an already trained VAE based on the model parameters of the VAE.

Illustratively, let the neuron input be x= [ x ₀,x₁,…,x_n ], the corresponding weights be w= [ w, w ₁,…,w_n ], respectively, and the weighted sum bias be b. Where b may be an integer, a decimal, or a complex number, etc. The form of the activation function may vary, for example, assuming that the activation function of a neuron is y=f (z) =max (0, z), the output of the neuron is: For another example, assuming that the activation function of a neuron is y=f (z) =z, the output of the neuron is: the activation functions of different neurons in a neural network may be the same or different.

(2) Structural parameters of the VAE;

By way of example, the structural parameters of the VAE include one or more of the number of layers of the neural network used by the VAE, the number of neurons comprised by the neural network used by the VAE, parameters related to the input layer of the VAE, i.e., input parameters, parameters related to the hidden layer of the VAE, or parameters related to the output layer of the VAE, i.e., output parameters, for specific definitions reference is made to the description related to the AI model described above.

It should be appreciated that neural networks used by VAEs may include a multi-layer structure, each layer may include one or more logical judgment units, which may be referred to as neurons. For example, a neural network includes an input layer and an output layer. The input layer of the neural network transmits the result to the output layer after the received input is processed by the neurons, and the output layer obtains the output result of the neural network. As another example, a neural network includes an input layer, a hidden layer, and an output layer. The input layer of the neural network transmits the received input to the middle hidden layer after the received input is processed by the neurons, the hidden layer transmits the calculation result to the output layer or the adjacent hidden layer, and finally the output layer obtains the output result of the neural network. A neural network may include, without limitation, one or more hidden layers connected in sequence.

Illustratively, the number of layers of the neural network used by the VAE may be referred to as the depth of the neural network. The expression capacity of the neural network can be improved by increasing the depth of the neural network, and more powerful information extraction and abstract modeling capacity is provided for a complex system.

Illustratively, the neural network used by the VAE includes a multi-layer structure, and the number of neurons included in each layer may be referred to as the width of the layer. The expression capacity of the neural network can be improved by increasing the width of the neural network, and more powerful information extraction and abstract modeling capacity is provided for a complex system.

Illustratively, the input dimension of the VAE may refer to the size of an input data, e.g., when the input data is a sequence, the corresponding input dimension of the sequence may indicate the length of the sequence. The VAE output dimension may refer to a size of output data, e.g., when the output data is a sequence, the corresponding output dimension of the sequence may indicate a length of the sequence. Alternatively, the VAE may characterize a mapping between the input and the output of the model, or the VAE is a functional model that maps a dimensional input to a dimensional output.

(3) The type of neural network used by the VAE;

By way of example, the type of neural network used by the VAE may be a deep neural network DNN or other neural network, where the DNN may include one or more of a feed forward neural network FNN, a convolutional neural network CNN, or a recurrent neural network RNN.

The number of configuration parameters, transmission method, or transmission timing is not particularly limited in the present application. Further, it will be appreciated that the configuration parameters not indicated may be predefined for the protocol or otherwise obtained, without limitation.

Optionally, the configuration parameters include a first configuration parameter and a second configuration parameter, where the configuration information is used to indicate the first configuration parameter and the second configuration parameter, or the configuration information is used to indicate a part of the indications (e.g., the first configuration parameter or the second configuration parameter), and another part of the configuration parameters may be determined according to a mapping relationship, where the mapping relationship is a corresponding relationship between the first configuration parameter and the second configuration parameter, and this implementation may save signaling overhead. That is, the configuration information in the embodiment of the present application may indicate all the configuration parameters of the generated model, or may indicate some of the configuration parameters of the generated model, which is not limited in the present application.

In the present application, the mapping relationship between the first configuration parameter and the second configuration parameter may be predefined, which may include predefined, such as protocol definition, or the mapping relationship may be configured through signaling or preconfigured, where the preconfiguration may be implemented by pre-storing a corresponding code, table, or other manner that may be used to indicate relevant information in the device, and the present application is not limited to a specific implementation manner thereof.

Alternatively, the mapping relationship may exist in the form of a table, a function, text, or a string, such as a storage or transmission.

In the following, a mapping relationship between the first configuration parameter and the second configuration parameter is illustrated in a table form, as shown in table 1, taking GMM as an example, assuming that the configuration information is used to indicate the first configuration parameter, that is, the maximum value m=5 of the number of single gaussian models included in the GMM, and the generating method of the GMM is an EM algorithm, according to the mapping relationship shown in table 1, the convergence threshold p=0.01 of the GMM may be further determined, the maximum value of the iteration number of the GMM is 100, and a specific GMM, that is, the first model may be obtained by fitting based on these configuration parameters. Taking the VAE as an example, assuming that the configuration information is used to indicate the second configuration parameter, that is, the number of layers of the neural network used by the VAE is 5, and the number of neurons included in the neural network used by the VAE is 1, the neural network used by the VAE may be further determined to be DNN according to the mapping relationship shown in table 1, and a specific VAE, that is, the first model, may be obtained by fitting based on the configuration parameters.

Optionally, the number of the first configuration parameters and the second configuration parameters corresponding to each generation model in table 1 is not limited.

TABLE 1

It should be understood that the mapping relationship between the first configuration parameter and the second configuration parameter of the GMM and the mapping relationship between the first configuration parameter and the second configuration parameter of the VAE shown in table 1 may be implemented independently or may be implemented in combination. For example, the row corresponding to GMM and the row corresponding to VAE in table 1 may be respectively embodied in two tables, which is not limited in the present application.

It should be understood that table 1 above is only an example given for ease of understanding and should not constitute any limitation on the technical solutions of the present application.

Optionally, the configuration parameters comprise a first configuration parameter and a second configuration parameter, the first device receives configuration information from the core network element, and the first device receives the configuration information from the core network element through a first signaling, wherein the configuration information of the first configuration parameter is carried in a first part of the first signaling, and the configuration information of the second configuration parameter is carried in a second part of the first signaling.

Optionally, the first device receives configuration information from the core network element through the first signaling, and the configuration information comprises that the first device receives a first configuration parameter from the core network element through a first part of the first signaling at a first time, and the first device receives a second configuration parameter from the core network element through a second part of the first signaling at a second time, wherein the first time and the second time are the same or different.

Optionally, the method further comprises the first device obtaining the type of the generative model and/or the function of the generative model.

In one implementation, before performing step S1010 described above, the first device obtains the type of the generative model and/or the function of the generative model. The type of the generative model and/or the function of the generative model may be dynamically configured (dynamic configured) by the core network element through signaling or a message to the first device, or may also be preconfigured (pre-configured), for example, may be implemented by pre-storing a corresponding code, a table or other manners that may be used to indicate the type of the generative model and/or the function of the generative model in the first device, and the implementation manner of the present application is not limited.

Alternatively, the type of generative model may be any of GMM, VAE, GAN, for which reference is made to the relevant description above for a specific explanation.

Alternatively, the function of generating the model may be for terminal device positioning, or for identifying images, etc. For example, in positioning the terminal device, the function of the generated model may be to output a probability distribution of position coordinate information of the terminal device, or may be to output a probability distribution of measurement results of measurement amounts for positioning the terminal device, or the like.

For example, the first device may determine the GMM for terminal device location based on the type of the generated model and/or the function of the generated model, that is, the first device may determine that the generated model to be trained or fitted is the GMM through the type of the generated model and/or the function of the generated model, and locate the terminal device through the trained or fitted GMM.

S1020, the first device processes the channel measurement result by using the first model to obtain a probability distribution of the measurement result of the measurement quantity for positioning the terminal device.

The first model is determined based on configuration parameters of the generated model, and it can be understood that the first device can be fitted or trained to obtain the first model according to the obtained configuration parameters of the generated model, if the generated model is a GMM, it is stated that the first device can be trained or fitted to obtain a specific GMM or a specific GMM according to the configuration parameters, that is, the first model is a trained GMM model at the moment and can be used for positioning of the terminal device. For example, the first model is a GMM that is iterated 50 times using the EM algorithm, and the trained GMM may contain 3 single gaussian models.

By way of example, the measurement quantities may include one or more of the following:

(1)RSTD;

For example, RSTD may also be referred to as TDoA, and specific definitions and implementations may be referred to above in connection with fig. 7.

(2)TDoA;

TDoA is an exemplary method for positioning using time differences, and a specific implementation may be referred to in the description of fig. 7.

(3)ToA;

For example, toA is a method of calculating a physical distance using a propagation delay of a wireless signal between two nodes, i.e., determining a position by measuring a time interval from a transmitted signal to a received signal, typically requiring synchronization timing at a receiving node.

(4)AoA;

By way of example, a low power consumption (LE) device may make its direction available to peer devices by transmitting data packets with direction finding functionality using a single antenna. The peer device includes a radio frequency switch and an antenna array that switches antennas and acquires In-phase quadrature (In-phase Quardrature, IQ) signal samples when receiving a portion of a data packet. The IQ signal samples may be used to calculate the phase differences of the radio signals received by the different elements of the antenna array, which may then be used to estimate the angle of arrival AoA.

(5) LoS probability;

The LoS probability is used to determine, for example, the NLoS level of the channel environment, the difference in the NLoS level (i.e., the difference in the channel conditions), and the difference in the degree of influence of the channel measurement result on the inference accuracy of the generated model. The first device can thus learn the NLOS level of the channel, and thus the current channel conditions, based on the channel measurements. For example, LOS (1) or NLOS (0) may be used to indicate that LOS between a network device and a terminal device is not occluded by an obstruction, and reference signals transmitted between the network device and the terminal device are not affected.

The LOS means that the transmitting antenna and the receiving antenna transmit signals between distances where they can see each other. It is understood that there is no obstacle between the two antennas that affects the propagation of the signal, and the signal can be transmitted completely. Non-line-of-sight NLoS refers to transmitting and receiving antennas transmitting signals between distances that are "not visible to each other". It is understood that there are obstacles between the two antennas that affect the propagation of the signal, and the signal may not be completely transmitted.

It should be noted that, in the embodiment of the present application, the measurement quantity may be one or more of the above parameters (1) - (5), and the corresponding channel measurement result may also be one or more, and the probability distribution of the measurement result of the measurement quantity for positioning the terminal device may also be one or more, which is not limited in this application.

In one possible implementation of the embodiment of the application, the channel measurement result is based on a measurement of the reference signal.

In a first example, the channel measurement may be a measurement of the reference signal by the first device.

For example, in an uplink positioning scenario, when the first device is a network device, the channel measurement result is based on a first channel measurement, where the first channel measurement includes the network device measuring a sounding reference signal (e.g., SRS) from the terminal device.

For another example, in a downlink positioning scenario, when the first device is a terminal device, the channel measurement result is obtained based on a second channel measurement, where the second channel measurement includes the terminal device measuring a positioning reference signal (e.g., PRS, or preamble) or a channel state information reference signal (CHANNEL STATE information REFERENCE SIGNAL, CSI-RS) from the access network device;

For another example, in a sidelink positioning scenario, when the first device is a first terminal device, the channel measurement is based on a third channel measurement, the third channel measurement comprising the first terminal device measuring a sidelink positioning reference signal (SL-PRS) from the second terminal device.

In the second example, the channel measurement result may also be obtained by measuring the reference signal by other devices (for example, a network element performing channel measurement, or a channel measurement network element, or other devices such as a reference signal measurement node, etc.), which is not limited in the present application.

It should be noted that, the embodiment of the present application is mainly described by taking the example of performing channel measurement based on the reference signal and further obtaining the channel measurement result, which is not limited. For example, the channel measurements may also include results of pedestrian dead reckoning (PEDESTRIAN DEAD-reckoning, PDR) measurements of the terminal, or the channel measurements may also include camera environmental monitoring recognition results, such as monitoring camera environmental monitoring recognition results of an indoor plant.

In the embodiment of the application, the measurement quantity corresponds to the channel measurement result, which can be understood that the first device measures one or more measurement quantities corresponding to the reference signal to obtain the channel measurement result, and the measurement result is the measurement result of the one or more measurement quantities. For example, taking a downlink positioning scenario as an example, assuming that the measurement quantity is TDoA, the first device is a terminal device, the network device #1 may send a reference signal, such as prs#1, to the terminal device, the network device #2 may send prs#2 to the terminal device, and correspondingly, the terminal device may measure TDoA of prs#1 and prs#2, such as t2-t1, as a channel measurement result #1, where t1 represents a transmission time when the network device #1 and the terminal device transmit signals, and t2 represents a transmission time when the network device #2 and the terminal device transmit signals. Alternatively, network device #1 and network device #2 may send PRS multiple times, or network device #3 may also send PRS #3 to the terminal device, and the terminal device may measure TDoA of PRS #2 and PRS #3, e.g., t3-t2, as channel measurement result #2, where t3 represents a transmission time when network device #3 transmits signals with the terminal device, and so on.

In the following, a probability distribution of the measurement results of the measurement quantities for terminal device positioning is illustrated for the first device processing the channel measurement results using the first model.

In one example, the first device may take the channel measurements (or channel characteristics extracted from the channel measurements, the application being illustrated by way of example) as input to a first model, the output of which is used to determine the location of the terminal device directly or indirectly, e.g. the output of the first model may be a probability distribution of the measurements of the measurement quantities for terminal device positioning.

For example, when the generated model is a GMM, the first model may be a GMM obtained by fitting or training according to a configuration parameter of the GMM, and the first device may use the obtained channel measurement result #1 and the obtained channel measurement result #2 as inputs of the GMM, respectively, and may obtain a probability distribution of the GMM of the TDoA for terminal device positioning.

For another example, when the generation model is a VAE, the first model may be a VAE obtained by fitting or training according to configuration parameters of the VAE, and the first device may respectively use the obtained channel measurement result #1 and the obtained channel measurement result #2 as input of the VAE, so as to obtain the variation probability distribution of the TDoA for positioning the terminal device correspondingly.

It should be noted that, in the embodiment of the present application, the number of channel measurement results corresponding to a certain measurement quantity is not specifically limited to the input of the first model. Alternatively, it can be generally understood that the more the number of channel measurement results is, the more accurate the probability distribution of the measurement results of the corresponding measurement quantities is, and thus the higher the positioning accuracy of the terminal device is.

Illustratively, taking an estimated value of the distance between two nodes (i.e., the product of the propagation delay ToA between the two nodes and the propagation speed of the electromagnetic wave), where the propagation speed of the electromagnetic wave in free space is equal to the speed of light, the speed is c= 299792458m/s≡3×10 ⁸ m/s. The probability distribution of the distance estimate is described using GMM (i.e. the first model).

For example, a common estimation algorithm is maximum likelihood (maximum likelihood, ML) estimation, and a set of distance estimation value vector sequences for training may be set to x= { X ₁,x₂,…,x_N }, where the distance estimation values in LOS and NLOS environments are included, and N is an integer greater than 1. The probability density function of the distance estimation value under the sight distance condition meets the following conditions: x=x ₁,x₂,…,x_N, where r _LOS represents the true distance in the line-of-sight environment, When the indoor environment is stable, the value is set to be 0 when there is no large deviation,Representing the variance in the line-of-sight environment, i.e., the distance estimate x follows a gaussian distribution, at which point,Representing the mean value of the gaussian distribution,Representing the variance of the gaussian distribution. The probability density function of the distance estimate x in a non-line-of-sight environment satisfies: Wherein, I.e., the distance estimate x follows a gaussian distribution, where r _NLOS represents the mean of the gaussian distribution,Representing the variance of the gaussian distribution. From this, a probability density function of a K-order mixture gaussian model can be obtained, expressed as:

Wherein, θ= (r _k,σ_k,p_k), Represents the N-dimensional joint Gaussian probability distribution of the kth single Gaussian model, sigma _k is the variance or covariance matrix of the kth single Gaussian model, r _k is the expected value of the kth single Gaussian model, represents the distance estimated value between two nodes, p _k is the weight of the kth single Gaussian model in the mixed Gaussian model,

It should be understood that the probability distribution function and the probability density function are functions describing the probability of a random variable in a certain interval, and assuming that F (X) is the probability distribution function of the random variable X and F (X) is the probability density function of X, there is F (X) = c F (X) dx. The probability distribution function represents the probability of the value of the random variable in a certain interval, and the probability density function represents the probability density of the value of the random variable at a certain point.

For example, iterating the weight, the expectation, the variance, or the covariance estimate of the kth single gaussian model in the GMM using the EM algorithm may result in:

the iterative formula of the estimated value of the weight is:

the iterative formula of the estimated value of the expected value is:

The iterative formula for the variance or covariance estimate is:

wherein p (kN) in the above three formulas is a posterior probability, which can be expressed as:

It should be appreciated that the EM algorithm can better address the problem of estimating gaussian mixture model parameters of training samples using a maximum likelihood algorithm. After a large number of distance measurement values are acquired, distance estimation values are obtained through an EM algorithm, so that positioning estimation of the terminal equipment is realized.

Optionally, after performing step S1020, the method 1000 further includes step S1030.

S1030, the first device sends first information to the core network element, and the core network element receives the first information from the first device.

Wherein the first information is used to indicate a probability distribution of measurement results of the measurement quantity for terminal equipment positioning.

In a first example, when the generative model is a GMM, the first information may indicate a GMM for a measured quantity of terminal device positioning. For example, assuming that the GMM includes k single gaussian models, k is an integer greater than or equal to 1, the first information may include one or more of:

(1) k expected values Is a value of (2);

(2) k variances or covariances Is a value of (2);

(3) Duty ratio of k single Gaussian models in Gaussian mixture model Is a value of (2);

wherein k expected values, k variances or covariances are in one-to-one correspondence with k single Gaussian models, and specific definitions can be referred to the related description of the formula (3).

It is to be understood that the above parameters (1) - (3) may be specific values, wherein,AndAll are positive numbers. The core network element can determine a first model, namely the GMM, obtained by fitting or training the first equipment based on the parameters (1) - (3) contained in the first information, and further, the analysis and the application of the probability distribution of the measurement result of the measurement quantity based on the first model can be more accurate, so that the positioning precision of the terminal equipment is improved.

In a second example, when the generation model is a VAE, the first information may indicate a variance probability distribution of the measurement quantity for terminal device positioning, where the first information may include one or more of:

(1) The value of the model parameters of the VAE;

Illustratively, the model parameters of the VAE may be valued for one or more of the weights w= [ w, w ₁,…,w_n ] of the neurons, or the bias in the activation function of the neurons (or the bias of the neural network) b.

(2) The probability distribution of the VAE output takes on values.

For example, the value of the probability distribution output by the VAE may be the value of the probability distribution of the measurement result of a certain measurement quantity, for example, when the measurement quantity is TDoA, the value of the probability distribution output by the VAE may include the values x, y, z of the probability distribution corresponding to t2-t1, t3-t2, t3-t1, where t2-t1 may represent the channel measurement result #1 obtained by the terminal device measuring the TDoA of prs#1 and prs#2, t3-t2 may represent the channel measurement result #2 obtained by the terminal device measuring the TDoA of prs#3 and prs#2, and t3-t1 may represent the channel measurement result #3 obtained by the terminal device measuring the TDoA of prs#3 and prs#1, and prs#2 and prs#3 may be the reference signals transmitted to the terminal device #1, the network device #2 and the network device #3, respectively.

It is to be understood that the above parameters (1) - (2) may be specific values, wherein w, w ₁,…,w_n, b, x, y and z are positive numbers. The core network element can determine a first model obtained by fitting or training the first device, namely the VAE, based on the parameters (1) - (2) contained in the first information, and further, the analysis and the application of the probability distribution of the measurement result of the measurement quantity based on the first model can be more accurate, so that the positioning precision of the terminal device is improved.

Optionally, after performing step S1030, the method 1000 further includes step S1040.

S1040, the core network element determines the position of the terminal device according to the probability distribution of the measurement result of the measurement quantity and the configuration parameters of the generation model.

In a first example, assuming that the generation model is GMM, the core network element may determine the location of the terminal device based on the GMM distribution of the measurement quantities and the configuration information of the generation model.

Illustratively, taking an uplink positioning scenario as an example, P first devices (e.g. network devices) may respectively send GMM probability distributions of P measurement quantities for terminal device positioning to a core network element. Alternatively, for the same measurement (e.g., TDoA), the number of single gaussian models included in the first model (i.e., GMM) corresponding to each of the P GMM probability distributions may be different, and the expected value, variance, or covariance value, and the duty cycle value in the entire GMM may be different for each single gaussian model.

For example, assuming that the number k=3 of single gaussian models included in the GMM corresponding to each GMM distribution is the same, and the first information reported by each network device includes the expected values and the variance values of 3 single gaussian models, the core network element may average the expected values and the variance values of 3 single gaussian models in P first information, thereby obtaining an average value of the expected average value and the variance of the 3 single gaussian models, further obtaining a more accurate estimated value of TDoA according to the average value of the expected average value and the variance, or the core network element may also calculate the first information reported by each network device to obtain a corresponding estimated value of TDoA, average all the estimated values of TDoA to obtain a final estimated value of TDoA, and perform more accurate positioning on the terminal device according to the estimated value of TDoA.

For another example, assuming that p=2, the number of single gaussian models corresponding to the GMM probability distribution sent by the network device #1 to the core network element is 3, the first information reported by the network device #1 includes the expected values and the variance values of the 3 single gaussian models, the number of single gaussian models corresponding to the GMM probability distribution sent by the network device #2 to the core network element is 2, the first information reported by the network device #2 includes the expected values and the variance values of the 2 single gaussian models, then the core network element may obtain the estimated value of TDoA #1 based on the expected values and the variance values of the 3 single gaussian models reported by the network device #1, obtain the estimated value of TDoA #2 based on the expected values and the variance values of the 2 single gaussian models reported by the network device #2, further average the estimated values of TDoA #1 and TDoA #2 to obtain the final estimated value of TDoA, and perform more accurate positioning on the terminal device according to the estimated value of TDoA.

For example, assuming that p=2, the number of single gaussian models corresponding to the GMM probability distribution sent by the network device #1 to the core network element is 3, the first information reported by the network device #1 includes the expected values and the values of the duty ratios (or weights) of the 3 single gaussian models, the number of single gaussian models corresponding to the GMM probability distribution sent by the network device #2 to the core network element is 3, and the first information reported by the network device #2 includes the expected values and the values of the duty ratios (or weights) of the 3 single gaussian models, the core network element may average the products of the expected values and the values of the duty ratios (or weights) of the 3 single gaussian models in the two first information, so as to obtain a weighted average value of the expected values of the 3 single gaussian models corresponding to the GMM probability distribution, and obtain a more accurate estimated TDoA value according to the weighted average value.

In a second example, assuming that the generation model is a VAE, the core network element may determine the location of the terminal device based on the variance probability distribution of the measurement quantities and the configuration information of the generation model.

For example, taking an uplink positioning scenario as an example, Q first devices (e.g. network devices) may each send a variable probability distribution of measurement quantities for terminal device positioning to a core network element. Alternatively, the probability distribution corresponding to the Q variation probability distributions may be different for the same measurement (e.g., TDoA), e.g., the probability distribution x, y, z corresponding to the measurement result t2-t1, t3-t2, t3-t1 may be different in each variation probability distribution. Optionally, the core network element may select a value of a higher probability distribution from the Q variation probability distributions, and further obtain a more accurate estimated value of the TDoA according to the value of the higher probability distribution, and perform more accurate positioning on the terminal device according to the estimated value of the TDoA.

In the embodiment of the present application, the transmission of information and/or data between devices is not limited to direct transmission, indirect transmission (including transparent transmission) or the like, so that device a sends information to device B, that is, includes that device a directly sends the information to device B through an interface between device a and device B, or that device a sends the message to device C, that device C sends the message to device B, and that the forwarding of how many relays have passed between device a and device B is also not limited. For example, the UE sending the first information to the LMF may include, but is not limited to, the UE sending the first information directly to the LMF through an LPP message, or the UE sending the first information to the LMF through a gNB, an AMF, and the UE sending the first information to the LMF through an AMF. Interactions between other devices are similar, and those skilled in the art will appreciate that they are not described in detail. The interface messages between the devices are specifically described with reference to fig. 4.

According to the scheme, the core network element sends the configuration information to the first equipment, so that the core network element and the first equipment generate the configuration information of the model through alignment, the first model used for fitting/training of terminal equipment positioning can be known to be the same, and further the analysis and the application of the core network element on the probability distribution of the measurement result of the measurement quantity based on the first model can be more accurate, and the positioning precision of the terminal equipment can be further improved.

It should be understood that in the scheme shown in fig. 10, the core network element sends configuration information to the first device, so that the first device determines a first model for fitting/training of positioning of the terminal device, and obtains a probability distribution of a measurement result of the measurement quantity based on the first model. It should be noted that the present application is also applicable to reporting configuration information to the core network element by the terminal device, so as to notify the first model for fitting/training of positioning of the terminal device, so that the analysis and the application of the probability distribution of the measurement result of the measurement quantity by the core network element based on the first model are more accurate, and a specific implementation manner can be seen from the related description of fig. 11 below.

Fig. 11 is a schematic flow chart diagram of a communication method 1100 provided by an embodiment of the present application. As shown in fig. 11, the following steps are included. It should be understood that the method may be performed by the first device and the core network element, or may be performed by a chip or a circuit of the first device and the core network element, which is not limited by the present application. For convenience of description, the following description will be given by taking the first device and the core network element as execution bodies. For convenience of description, the following description will be given by taking the first device and the core network element as execution bodies. It should be noted that, in this implementation, model training/fitting occurs at the first device side, model reasoning/use occurs at the core network element side, or model training/fitting occurs at the OTT or third party device or cloud device side, and model reasoning/use occurs at the OTT or third party device or cloud device side, which is not limited in this application.

S1110, the first device acquires configuration information, wherein the configuration information is used for indicating configuration parameters of the generation model.

Illustratively, the configuration information is used to indicate configuration parameters of the generative model. The content of the configuration information, the generation model and the configuration parameters may refer to the related description of step S1010 of the method 1000.

In one example, the first device may be a terminal device or an access network device and the core network element may be a positioning device, such as a location management function network element (e.g., LMF). The first device may also be called a network element performing channel measurement, or a channel measurement network element, or a reference signal measurement node, etc., and the name of the first device is not limited by the present application.

Alternatively, the configuration information may be dynamically configured (DYNAMICALLY CONFIGURED) through signaling or messaging, or may be autonomously determined by the first device, or may be preconfigured (pre-configured), for example, may be implemented by pre-storing a corresponding code, table, or other manner that may be used to indicate the configuration information in the first device, which is not limited by the present application.

Optionally, the configuration parameters include a first configuration parameter and a second configuration parameter. For example, the configuration information may be used to indicate the first configuration parameter and the second configuration parameter, or the configuration information may be used to indicate a part of the configuration parameters (e.g., the first configuration parameter or the second configuration parameter), and another part of the configuration parameters may be determined according to the mapping relationship, and for specific implementation, reference may be made to the related description of the method 900.

In one implementation, before performing step S1110 described above, the first device obtains the type of the generative model and/or the function of the generative model. The type of the generated model and/or the function of the generated model may be dynamically configured to the first device through signaling or message, or may also be preconfigured, for example, may be implemented by pre-storing corresponding codes, tables or other manners that may be used to indicate the type of the generated model and/or the function of the generated model in the first device, which is not limited by the present application.

The type of generative model and/or the functional content of the generative model may be referred to above in connection with method 1000.

S1120, the first device processes the channel measurement result by using the first model to obtain a probability distribution of the measurement result of the measurement quantity for positioning the terminal device.

Wherein the first model is determined based on the configuration parameters of the generated model, the measurement quantity corresponds to a channel measurement result, the channel measurement result is based on the measurement of the reference signal, and the specific explanation can be referred to the related description of step S1020 of the above method 1000.

By way of example, the measurement may include one or more of RSTD, TDoA, toA, aoA, loS probabilities, loS and NLoS recognition results, a specific interpretation of the measurement, and a specific implementation of this step may be described with reference to step S1020 of method 1000 above.

Optionally, after performing step S1120 described above, the method 1100 further includes step S1130.

S1130, the first device sends all or part of the first information and the configuration information to the core network element, and the core network element receives all or part of the first information and the configuration information from the first device.

Alternatively, all or part of the first information and the configuration information may be sent through one signaling (or one data packet), or may be sent through two signaling (or two data packets) respectively, which is not limited in the present application. Alternatively, all or part of the first information and the configuration information may be sent simultaneously, or may be sent separately, for example, the first device may send the first information first and then send the configuration information, or the first device may send the configuration information first and then send the first information, that is, the sending timing of all or part of the first information and the configuration information is not limited in the present application.

The first information is for example used to indicate a probability distribution of measurement results of measurement quantities for terminal device positioning. For a specific explanation of the first information, reference may be made to the description related to step S1030 of the method 1000.

It should be understood that the configuration information in this step S1130 may be the configuration information obtained in the above step S1110, where the configuration information may indicate all the configuration parameters of the generated model, or may indicate some of the configuration parameters of the generated model, and for a specific implementation, reference may be made to the related description of the method 1000.

Optionally, the configuration information in the step S1130 may also be part of the configuration information obtained in the step S1110, for example, the configuration information obtained in the step S1110 indicates all the configuration parameters of the generation model, the first device may send the first configuration parameter or the second configuration parameter to the core network element according to the mapping relationship in the table 1, so as to save signaling overhead, and the core network element may determine all the configuration parameters of the generation model according to the mapping relationship in the table 1 or the predefined parameters in other protocols.

Alternatively, the configuration information in the step S1130 may be a complete set of the configuration information obtained in the step S1110, for example, the configuration information obtained in the step S1110 indicates the first configuration parameter of the generation model, and the first device may send the corresponding second configuration parameter to the core network element according to the mapping relationship in the table 1, which is not limited in this application. Optionally, after performing step S1130 described above, the method 1100 further includes step S1140.

S1140, the core network element determines the position of the terminal device according to the probability distribution of the measurement result of the measurement quantity and the configuration parameters of the generation model.

For example, assuming that the generation model is GMM, the core network element may determine the location of the terminal device according to the GMM distribution of the measurement quantity and configuration information of the generation model.

For example, taking an uplink positioning scenario as an example, a plurality of first devices (e.g. network devices) may each send a GMM distribution of measurement quantities for terminal device positioning to a core network element. Alternatively, the number of single gaussian models included in the first model (i.e., GMM) corresponding to each GMM distribution may be different for the same measurement (e.g., TDoA), and the number of iterations of the first model (i.e., GMM) may be different. Optionally, the core network element may select GMM distribution with higher convergence accuracy, for example, select GMM distribution with a larger number of single gaussian models and a larger number of iterations of the first model, so as to obtain a more accurate estimated value of TDoA, and perform more accurate positioning on the terminal device according to the estimated value of TDoA.

For example, assuming that the generation model is a VAE, the core network element may determine the location of the terminal device according to the variance probability distribution of the measurement quantity and the configuration information of the generation model, and for a specific implementation, reference may be made to the description related to step S1040 of the above method 1000.

For example, taking an uplink positioning scenario as an example, a plurality of first devices (e.g. network devices) may each send a varying probability distribution of measurement quantities for terminal device positioning to a core network element. Alternatively, the values of each variation probability distribution may be different for the same measurement (e.g., TDoA), e.g., the values x, y, z of the probability distributions corresponding to the measurement results t2-t1, t3-t2, t3-t1 in each variation probability distribution may be different. Optionally, the core network element may select a variation probability distribution with a higher value of the probability distribution, so as to obtain a more accurate estimated value of the TDoA, and perform more accurate positioning on the terminal device according to the estimated value of the TDoA.

According to the scheme, the first equipment sends the configuration information to the core network element, so that the core network element and the first equipment can be aligned to generate the configuration information of the model, the first model used for fitting/training of positioning of the terminal equipment can be known to be the same, further, the analysis and the application of the probability distribution of the measurement result of the measurement quantity based on the first model can be more accurate, and the positioning precision of the terminal equipment can be further improved.

The following describes an example of application of the embodiments of the present application in terms of an uplink positioning scenario, a downlink positioning scenario, and a lateral positioning scenario, respectively, with reference to fig. 12 to 17, and it should be understood that the method embodiments shown in fig. 10 to 17 may be combined with each other, and steps in the method embodiments shown in fig. 10 to 17 may be referred to each other. For example, in the embodiments of the present application, the method embodiments shown in fig. 12 to 17 may be regarded as possible implementation manners for implementing the functions of the method embodiments shown in fig. 10 and 11, where fig. 12 and 15 are mainly described with respect to an uplink positioning scenario, fig. 13 and 16 are mainly described with respect to a downlink positioning scenario, and fig. 14 and 17 are mainly described with respect to a lateral positioning scenario.

Fig. 12 is a flow chart of a communication method 1200 according to an embodiment of the present application. As shown in fig. 12, taking the LMF as a core network element, the first device as a gNB, and the second device as a UE as an example, model training/fitting in this implementation occurs on the gNB side, and model reasoning/use occurs on the LMF side. It should be understood that the above description of the embodiments shown in fig. 10 and fig. 11 is equally applicable to this implementation, and the same or similar technical means may exist between fig. 10 to fig. 12, and details already described in the embodiments shown in fig. 12 and fig. 10 and fig. 11 are not repeated.

It should be understood that, taking the generation model as GMM as an example, the gNB obtains a measurement result of the measurement quantity by measuring the SRS. Further, the gNB determines the GMM1 based on the configuration information #1 sent by the LMF, and processes the channel measurement result by using the GMM1 to obtain GMM distribution (corresponding mode one), or the gNB reports the configuration information #1 and parameters of the GMM1 to the LMF (corresponding mode two), so that the gNB and the LMF align the configuration information #1, the GMM1 used for fitting/training of UE positioning is ensured to be the same, further, the analysis and the application of the probability distribution of the measurement result based on the GMM1 to the measurement quantity are ensured to be more accurate, and the positioning precision of the UE is improved.

Mode one:

S1210, the LMF sends configuration information #1 to the gNB, and the gNB receives the configuration information #1 from the LMF.

The content and definition contained in the configuration information #1, and the specific implementation manner may refer to the description related to step S1010 of the method 1000.

S1220, the UE sends SRS to the gNB, and correspondingly, the gNB receives SRS from the UE.

S1230, the gNB determines GMM1 of a measurement amount for UE positioning from the channel measurement result #1 and the configuration information #1.

For example, the gNB measures the SRS to obtain a channel measurement result #1, determines the GMM1 according to the configuration information #1, and uses the channel measurement result #1 as an input of the GMM1, where an output of the GMM1 is GMM1.

The content and definition included in the measurement quantity, the association relationship between the measurement quantity and the channel measurement result #1, and the specific implementation manner of this step may refer to the description related to step S1020 of the above method 1000.

S1240, the gNB sends the parameters of GMM1 to the LMF, which receives the parameters of GMM1 from the gNB, correspondingly.

The content and definition contained in the parameters of GMM1, and the specific implementation of this step may refer to the description related to step S1030 of the method 1000.

S1250, the LMF determines the position of the UE according to the parameters of the configuration information #1 and the GMM 1.

For a specific implementation, reference may be made to the description related to step S1040 of the method 1000.

Mode two:

S1260, the UE transmits SRS to the gNB, and correspondingly, the gNB receives SRS from the UE.

S1270, the gNB determines GMM1 of the measurement amount for UE positioning from the channel measurement result # 1.

Illustratively, the gNB measures the SRS to obtain a channel measurement result #1, and takes the channel measurement result #1 as an input of GMM1, and the output of GMM1 is GMM1.

The content and definition included in the measurement quantity, the association relationship between the measurement quantity and the channel measurement result #1, and the specific implementation manner may refer to the description related to step S1120 of the method 1100.

S1280, the gNB sends the parameters of GMM1 and the configuration information #1 to the LMF, and the LMF receives the parameters of GMM1 and the configuration information #1 from the gNB, correspondingly.

The parameters of GMM1 and the content of configuration information #1 and their definitions, and the specific implementation may refer to the related description of step S1130 of the method 1100.

S1290, the LMF determines the location of the UE according to the parameters of GMM1 and configuration information # 1.

For a specific implementation, reference may be made to the description related to step S1140 of the method 1100.

In the embodiment of the application, taking the generation model as a GMM as an example, the gNB obtains a measurement result of the measurement quantity by measuring the measurement quantity of the SRS. Furthermore, the gNB and the LMF align the configuration parameters of the GMM1 by sending the configuration information #1, so that the GMM1 used for fitting/training of the UE positioning is the same, further, the analysis and the application of probability distribution of measurement results based on the measurement quantity by the GMM1 are more accurate, and the positioning precision of the UE is improved.

Fig. 13 is a flow chart of a communication method 1300 according to an embodiment of the present application. As shown in fig. 13, taking LMF as a core network element, a first device as a UE, and a second device as a gNB as an example, model training/fitting in this implementation occurs on the UE side, and model reasoning/use occurs on the LMF side. It should be understood that the above description of the embodiments shown in fig. 10 and fig. 11 is equally applicable to this implementation, and the same or similar technical means may exist between fig. 10, fig. 11 and fig. 13, and details already described in the embodiments shown in fig. 13 and fig. 10 and fig. 11 are not repeated.

It should be understood that, taking the generating model as GMM as an example, the UE obtains a measurement result of the measurement quantity by measuring the PRS. Further, the UE determines the GMM2 based on the configuration information #2 sent by the LMF, and processes the channel measurement result by using the GMM2 to obtain GMM distribution (corresponding mode I), or the UE reports the configuration information #2 and parameters of the GMM2 to the LMF (corresponding mode II), so that the UE and the LMF align the configuration information #2, ensure that the GMM2 used for fitting/training of the UE positioning is the same, further ensure that the analysis and the application of the probability distribution of the measurement result based on the GMM2 are more accurate, and improve the positioning precision of the UE.

Mode one:

s1310, the LMF sends configuration information #2 to the UE, and correspondingly, the UE receives the configuration information #2 from the LMF.

The content and definition contained in the configuration information #2, and the specific implementation manner may refer to the description related to step S1010 of the method 1000.

S1320, gNB sends PRS to UE, and correspondingly, UE receives PRS from gNB.

S1330, the UE determines GMM2 for a measurement amount of UE positioning according to the channel measurement result #2 and the configuration information # 2.

For example, the UE measures PRS to obtain a channel measurement result #2, determines GMM2 according to the configuration information #2, and uses the channel measurement result #2 as an input of GMM2, where an output of GMM2 is GMM1.

The content and definition included in the measurement quantity, the association relationship between the measurement quantity and the channel measurement result #2, and the specific implementation may refer to the description related to step S1020 of the method 1000.

S1340, the UE sends the parameters of the GMM2 to the LMF, and correspondingly, the LMF receives the parameters of the GMM2 from the UE.

Wherein the parameters of GMM2 include content and definitions thereof, and specific implementations are described with reference to step S1030 of method 1000.

In S1350, the LMF determines the location of the UE according to the parameters of the GMM2 and the configuration information # 2.

Mode two:

s1360, gNB sends PRS to UE, and correspondingly, UE receives PRS from gNB.

In S1370, the UE determines GMM2 of a measurement amount for UE positioning according to the channel measurement result # 2.

Illustratively, the UE measures PRS to obtain a channel measurement result #2, and takes the channel measurement result #2 as an input of GMM2, where an output of GMM2 is GMM1.

The content and definition included in the measurement quantity, the association relationship between the measurement quantity and the channel measurement result #2, and the specific implementation manner may refer to the description related to step S1120 of the method 1100.

S1380, the UE sends the parameter of the GMM2 and the configuration information #2 to the LMF, and the LMF receives the parameter of the GMM2 and the configuration information #2 from the UE.

The parameters of GMM2 and the content of configuration information #2 and their definitions, and the specific implementation may refer to the related description of step S1130 of the method 1100 described above.

S1390, the LMF determines the location of the UE based on the parameters of the GMM2 and the configuration information # 2.

In the embodiment of the application, taking the generation model as a GMM as an example, the UE obtains a measurement result of the measurement quantity by measuring the measurement quantity of the PRS. Furthermore, the UE and the LMF align the configuration parameters of the GMM2 by sending the configuration information #2, so that the GMM2 used for fitting/training of the UE positioning is the same, further, the analysis and the application of probability distribution of measurement results based on the measurement quantity by the GMM2 are more accurate, and the positioning precision of the UE is improved.

Fig. 14 is a flow chart of a communication method 1400 provided in an embodiment of the application. As shown in fig. 14, taking LMF as a core network element, a first device as ue#1, and a second device as ue#2 as an example, model training/fitting in this implementation occurs on the ue#1 side, and model reasoning/use occurs on the LMF side. It should be understood that the above description of the embodiments shown in fig. 10 and fig. 11 is equally applicable to this implementation, and the same or similar technical means may exist between fig. 10, fig. 11 and fig. 14, and details already described in the embodiments shown in fig. 14 and fig. 10 and fig. 11 are not repeated.

It should be understood that, taking the model of generation as GMM as an example, UE1 obtains a measurement result of the measurement quantity by measuring SL-PRS. Further, the UE1 determines GMM3 based on the configuration information #3 sent by the LMF, and processes the channel measurement result by using the GMM3 to obtain GMM distribution (corresponding mode one), or the UE1 reports parameters of the configuration information #3 and the GMM3 to the LMF (corresponding mode two), so that the UE1 and the LMF align the configuration information #3, ensure that the GMM3 used for fitting/training of UE positioning is the same, further ensure that the analysis and the application of the probability distribution of the measurement result based on the GMM3 on the measurement quantity are more accurate, and improve the positioning precision of the UE.

Mode one:

S1410, the LMF sends configuration information #3 to ue#1, and correspondingly, ue#1 receives configuration information #3 from the LMF.

The content and definition contained in the configuration information #3, and the specific implementation manner may refer to the description related to step S1010 of the method 1000.

S1420, UE#2 transmits the SL-PRS to UE#1, and correspondingly, UE#1 receives the SL-PRS from UE#2.

In S1430, the ue#1 determines GMM3 of a measurement quantity for UE positioning from the channel measurement result #3 and the configuration information # 3.

For example, the ue#1 measures the SL-PRS to obtain a channel measurement result#3, determines the GMM3 according to the configuration information#3, and uses the channel measurement result#3 as an input of the GMM3, where an output of the GMM3 is GMM1.

The content and definition included in the measurement quantity, the association relationship between the measurement quantity and the channel measurement result #3, and the specific implementation may refer to the description related to step S1020 of the method 1000.

S1440, the UE#1 transmits the parameters of the GMM3 to the LMF, and the LMF receives the parameters of the GMM3 from the UE#1.

Wherein the parameters of GMM3 include content and definitions thereof, and specific implementations are described with reference to step S1030 of method 1000.

S1450, the LMF determines the position of the UE according to the parameters of the GMM3 and the configuration information # 3.

Mode two:

S1460, UE#2 transmits SL-PRS to UE#1, and correspondingly, UE#1 receives SL-PRS from UE#2.

S1470, ue#1 determines GMM3 of a measurement quantity for UE positioning from channel measurement result # 3.

Illustratively, the ue#1 measures the SL-PRS to obtain a channel measurement result#3, and takes the channel measurement result#3 as an input of the GMM3, and an output of the GMM3 is GMM1.

The content and definition included in the measurement quantity, the association relationship between the measurement quantity and the channel measurement result #3, and the specific implementation manner may refer to the description related to step S1120 of the method 1100.

S1480, ue#1 transmits GMM3 parameters and configuration information #3 to the LMF, and correspondingly, the LMF receives GMM3 parameters and configuration information #3 from ue#1.

The parameters of GMM3 and the content of configuration information #3 and their definitions, and the specific implementation may refer to the related description of step S1130 of the method 1100.

And S1490, the LMF determines the position of the UE according to the parameters of the GMM3 and the configuration information # 3.

In the embodiment of the application, taking the generation model as a GMM as an example, the UE#1 obtains a measurement result of the measurement quantity by measuring the measurement quantity of the SL-PRS. Furthermore, the UE#1 and the LMF align the configuration parameters of the GMM3 by sending the configuration information #3, so that the GMM3 used for fitting/training of the UE positioning is the same, further, the analysis and the application of probability distribution of measurement results based on the measurement quantity by the GMM3 are more accurate, and the positioning precision of the UE is improved.

Fig. 15 is a flow chart of a communication method 1500 according to an embodiment of the present application. As shown in fig. 15, taking the LMF as a core network element, the first device as a gNB, and the second device as a UE as an example, model training/fitting in this implementation occurs on the gNB side, and model reasoning/use occurs on the LMF side. It should be understood that the above description of the embodiments shown in fig. 10 and fig. 11 is equally applicable to this implementation, and the same or similar technical means may exist between fig. 10, fig. 11 and fig. 15, and details already described in the embodiments shown in fig. 15 and fig. 10 and fig. 11 are not repeated.

It should be understood that, taking the generation model as VAE as an example, the gNB obtains a measurement result of the measurement quantity by measuring the SRS. Further, the gNB determines the VAE1 based on the configuration information #4 sent by the LMF, and processes the channel measurement result by using the VAE1 to obtain a variation probability distribution (corresponding mode one), or the gNB reports the configuration information #1 and parameters of the variation probability distribution (corresponding mode two) to the LMF, so that the gNB and the LMF align the configuration information #1, the VAE1 used for fitting/training of the UE positioning is ensured to be the same, further the analysis and the application of the probability distribution of the measurement result based on the VAE1 to the measurement quantity are ensured to be more accurate, and the positioning precision of the UE is improved.

Mode one:

S1510, the LMF sends configuration information #4 to the gNB, and the gNB receives the configuration information #4 from the LMF.

The content and definition contained in the configuration information #4, and the specific implementation manner may refer to the description related to step S1010 of the method 1000.

S1520, the UE transmits the SRS to the gNB, and the corresponding gNB receives the SRS from the UE.

S1530, the gNB determines a variation probability distribution #1 of the measurement quantity for UE positioning from the channel measurement result #4 and the configuration information # 4.

Illustratively, the gNB measures the SRS to obtain a channel measurement result #4, and according to the configuration information #4, VAE1 may be determined, and the channel measurement result #4 is used as an input of the VAE1, and an output of the VAE1 is the variation probability distribution #1.

The content and definition included in the measurement quantity, the association relationship between the measurement quantity and the channel measurement result #4, and the specific implementation may refer to the description related to step S1020 of the method 1000.

S1540, the gNB sends the parameters of the variation probability distribution #1 to the LMF, and the LMF receives the parameters of the variation probability distribution #1 from the gNB.

The content and definition contained in the parameters of the variation probability distribution #1, and the specific implementation manner may refer to the related description of step S1030 of the method 1000.

S1550, the LMF determines the position of the UE according to the configuration information #4 and the parameters of the variation probability distribution # 1.

Mode two:

s1560, the UE transmits the SRS to the gNB, and the corresponding gNB receives the SRS from the UE.

S1570, the gNB determines a variation probability distribution #1 of the measurement quantity for UE positioning from the channel measurement result # 4.

Illustratively, the gNB measures the SRS to obtain a channel measurement result #4, and takes the channel measurement result #4 as an input of VAE1, and the output of VAE1 is the variation probability distribution #1.

The content and definition included in the measurement quantity, the association relationship between the measurement quantity and the channel measurement result #4, and the specific implementation manner may refer to the description related to step S1120 of the method 1100.

S1580, the gNB sends the parameter of the variation probability distribution #1 and the configuration information #4 to the LMF, and correspondingly, the LMF receives the parameter of the variation probability distribution #1 and the configuration information #4 from the gNB.

The parameters of the variation probability distribution #1 and the content of the configuration information #4 and their definitions, and the specific implementation may refer to the related description of step S1130 of the method 1100.

In S1590, the LMF determines the location of the UE from the parameter of the variation probability distribution #1 and the configuration information # 4.

In the embodiment of the application, taking the generation model as a VAE as an example, gNB obtains a measurement result of the measurement quantity by measuring the measurement quantity of the SRS. Furthermore, the gNB and the LMF align the configuration parameters of the VAE1 by sending the configuration information #4, so that the VAE1 used for fitting/training of the UE positioning is the same, further, the analysis and the application of probability distribution of measurement results based on the measurement quantity by the VAE1 are more accurate, and the positioning precision of the UE is improved.

Fig. 16 is a flow chart of a communication method 1600 according to an embodiment of the present application. As shown in fig. 16, taking the LMF as a core network element, the first device as a UE, and the second device as a gNB as an example, model training/fitting in this implementation occurs on the UE side, and model reasoning/use occurs on the LMF side. It should be understood that the above description of the embodiments shown in fig. 10 and fig. 11 is equally applicable to this implementation, and the same or similar technical means may exist between fig. 10, fig. 11 and fig. 16, and details already described in the embodiments shown in fig. 16 and fig. 10 and fig. 11 are not repeated.

It should be understood that, taking the generating model as a VAE as an example, the UE obtains a measurement result of the measurement quantity by measuring the PRS. Further, the UE determines the VAE2 based on the configuration information #5 sent by the LMF, and processes the channel measurement result by using the VAE2 to obtain a variation probability distribution (corresponding mode one), or the UE reports the configuration information #5 and parameters of the variation probability distribution (corresponding mode two) to the LMF, so that the UE aligns the configuration information #5 with the LMF, ensuring that the VAE2 used for fitting/training of UE positioning is the same, further ensuring that the analysis and the application of the probability distribution of the measurement result based on the VAE2 on the measurement quantity are more accurate, and improving the positioning precision of the UE.

Mode one:

At S1610, the LMF sends configuration information #5 to the UE, and correspondingly, the UE receives configuration information #5 from the LMF.

The content and definition contained in the configuration information #5, and the specific implementation manner may refer to the description related to step S1010 of the method 1000.

S1620, gNB sends PRS to UE, and corresponding UE receives PRS from gNB.

S1630, the UE determines a variation probability distribution #2 of the measurement quantity for UE positioning according to the channel measurement result #5 and the configuration information # 5.

Illustratively, the UE measures PRS to obtain a measurement result #5, determines VAE2 according to the configuration information #5, and uses the measurement result #5 as input of VAE2, where output of VAE2 is a variation probability distribution #2.

The content and definition included in the measurement quantity, the association relationship between the measurement quantity and the channel measurement result #5, and the specific implementation may refer to the description related to step S1020 of the method 1000.

S1640, the UE transmits the parameters of the variation probability distribution #2 to the LMF, which receives the parameters of the variation probability distribution #2 from the UE.

The content and definition contained in the parameters of the variation probability distribution #2, and the specific implementation manner may refer to the related description of step S1030 of the method 1000.

S1650, the LMF determines the location of the UE from the parameters of the configuration information #5 and the variation probability distribution # 2.

Mode two:

s1660, gNB sends PRS to UE, and correspondingly, UE receives PRS from gNB.

S1670, the UE determines a variation probability distribution #2 of the measurement quantity for UE positioning from the channel measurement result # 5.

Illustratively, the UE measures PRS to obtain measurement result #5, and takes the measurement result #5 as input of VAE2, and the output of VAE2 is the variation probability distribution #2.

The content and definition included in the measurement quantity, the association relationship between the measurement quantity and the channel measurement result #5, and the specific implementation manner may refer to the description related to step S1120 of the method 1100.

S1680, the UE transmits the parameter and the configuration information #5 of the variation probability distribution #2 to the LMF, and the LMF receives the parameter and the configuration information #5 of the variation probability distribution #2 from the UE, correspondingly.

The parameters of the variation probability distribution #2 and the content of the configuration information #5 and their definitions, and the specific implementation may refer to the related description of step S1130 of the method 1100.

S1690, the LMF determines the position of the UE according to the parameters of the variation probability distribution #2 and the configuration information # 5.

In the embodiment of the application, taking the generation model as a VAE as an example, the UE obtains the measurement result of the measurement quantity by measuring the measurement quantity of the PRS. Furthermore, the UE and the LMF align the configuration parameters of the VAE2 by sending the configuration information #5, so that the VAE2 used for fitting/training of the UE positioning is the same, further, the analysis and the application of probability distribution of measurement results based on the measurement quantity by the VAE2 are more accurate, and the positioning precision of the UE is improved.

Fig. 17 is a flow chart of a communication method 1700 provided by an embodiment of the present application. As shown in fig. 17, taking LMF as a core network element, a first device as ue#1, and a second device as ue#2 as an example, model training/fitting in this implementation occurs on the ue#1 side, and model reasoning/use occurs on the LMF side. It should be understood that the above description of the embodiments shown in fig. 10 and fig. 11 is equally applicable to this implementation, and the same or similar technical means may exist between fig. 10, fig. 11 and fig. 17, and details already described in the embodiments shown in fig. 17 and fig. 10 and fig. 11 are not repeated.

It should be appreciated that this implementation takes the generation model VAE as an example, and ue#1 obtains a measurement result of the measurement quantity by measuring SL-PRS. Further, the ue#1 determines the VAE3 based on the configuration information #6 sent by the LMF, and processes the channel measurement result by using the VAE3 to obtain a variation probability distribution (corresponding to the first mode), or the ue#1 reports the configuration information #6 and parameters of the variation probability distribution (corresponding to the second mode) to the LMF, so that the ue#1 and the LMF align the configuration information #6, ensuring that the VAE3 used for fitting/training of UE positioning is the same, further ensuring that the analysis and the application of the probability distribution of the measurement result based on the VAE3 on the measurement quantity are more accurate, and improving the positioning precision of the UE.

Mode one:

S1710, the LMF transmits configuration information #6 to the UE #1, and correspondingly, the UE #1 receives the configuration information #6 from the LMF.

The content and definition contained in the configuration information #6, and the specific implementation manner may refer to the description related to step S1010 of the method 1000.

S1720, UE#2 transmits the SL-PRS to UE#1, and correspondingly, UE#1 receives the SL-PRS from UE#2.

S1730, the ue#1 determines a variation probability distribution #3 of the measurement quantity for UE positioning from the measurement result #6 and the configuration information # 6.

Illustratively, the ue#1 measures the SL-PRS to obtain a channel measurement result#6, determines a VAE3 according to the measurement result#6, and uses the channel measurement result#6 as an input of the VAE3, where an output of the VAE3 is a variation probability distribution #3.

With the content contained in the measurement quantity and its definition, the association relationship between the measurement quantity and the channel measurement result #6, and the specific implementation manner, reference may be made to the description related to step S1020 of the above method 1000.

S1740, ue#1 transmits the parameters of the variation probability distribution #3 to the LMF, and the LMF receives the parameters of the variation probability distribution #3 from ue#1.

The content and definition contained in the parameters of the variation probability distribution #3, and the specific implementation manner may refer to the related description of step S1030 of the method 1000.

S1750, the LMF determines the position of the UE according to the parameters of the configuration information #6 and the variation probability distribution # 3.

Mode two:

s1760, UE#2 transmits the SL-PRS to UE#1, and correspondingly, UE#1 receives the SL-PRS from UE#2.

S1770, the ue#1 determines a variation probability distribution #3 of the measurement quantity for UE positioning from the channel measurement result # 6.

Illustratively, the ue#1 measures the SL-PRS to obtain a measurement result #6, and takes the channel measurement result #6 as an input of the VAE3, and the output of the VAE3 is the variation probability distribution #3.

The content and definition included in the measurement quantity, the association relationship between the measurement quantity and the channel measurement result #6, and the specific implementation manner may refer to the description related to step S1120 of the method 1100.

S1780, the ue#1 transmits the parameter and the configuration information #6 of the variation probability distribution #3 to the LMF, and the LMF receives the parameter and the configuration information #6 of the variation probability distribution #3 from the ue#1.

The parameters of the variation probability distribution #3 and the content of the configuration information #6 and the definition thereof, and the specific implementation may refer to the related description of step S1130 of the method 1100.

S1790, the LMF determines the position of the UE according to the parameters of the variation probability distribution #3 and the configuration information # 6.

In the embodiment of the application, taking the generation model as a VAE as an example, the UE#1 obtains a measurement result of the measurement quantity by measuring the measurement quantity of the SL-PRS. Furthermore, the configuration parameters of the VAE3 are aligned by the UE#1 and the LMF through sending the configuration information #6, so that the VAE3 used for fitting/training of the UE positioning is the same, further, the analysis and the application of probability distribution of measurement results of measurement quantities based on the VAE3 are more accurate, and the positioning precision of the UE is improved.

It should be noted that, the method shown in fig. 15 to 17 above uses a VAE-based measurement result distribution fitting method, and optionally, the technical solution of the present application is also applicable to a GAN-based measurement result distribution fitting method, and the specific implementation manner can refer to the related descriptions of fig. 15 to 17 above, which are not described again for brevity.

The method provided by the embodiment of the application is described in detail above with reference to fig. 1 to 17. The following describes in detail the apparatus provided in the embodiment of the present application with reference to fig. 17 to 18. It should be understood that the descriptions of the apparatus embodiments and the descriptions of the method embodiments correspond to each other, and thus, descriptions of the details not described may be referred to the method embodiments above, and are not repeated herein for brevity.

Fig. 18 is a schematic diagram of a communication device 1800 according to an embodiment of the present application. As shown in fig. 18, the communication apparatus 1800 includes a processing module 1801 and a communication module 1802. The communication apparatus 1800 may be a first device (e.g., an access network device or a terminal device), or may be a communication apparatus, such as a chip, a system-on-a-chip, or a circuit, that is applied to or used in conjunction with the first device and that is capable of implementing a method performed by the first device. Or the communication device 1800 may be a core network element (such as a location management function network element), or may be a communication device, such as a chip, a chip system, or a circuit, applied to or used in combination with a core network element, and capable of implementing a method executed by the core network element.

The communication module may also be referred to as a transceiver module, a transceiver, or a transceiver device. A processing module may also be called a processor, a processing board, a processing unit, a processing device, or the like. Optionally, the communication module is configured to perform the sending operation and the receiving operation of the first device (for example, the access network device or the terminal device) or the core network element (for example, the location management function network element) in the above method, where a device for implementing the receiving function in the communication module may be regarded as a receiving unit, and a device for implementing the sending function in the communication module may be regarded as a sending unit, that is, the communication module includes the receiving unit and the sending unit.

When the communication apparatus 1800 is applied to the first device, the processing module 1801 may be configured to implement the processing function of the first device (e.g., the access network device or the terminal device) in the foregoing embodiments, and the communication module 1802 may be configured to implement the transceiving function of the first device in the foregoing embodiments.

When the communication apparatus 1800 is applied to a core network element, the processing module 1801 may be configured to implement a processing function of the core network element (e.g., a location management function network element) in the foregoing embodiments, and the communication module 1802 may be configured to implement a transceiver function of the first device in the foregoing embodiments.

Furthermore, it should be noted that the foregoing communication module and/or the processing module may be implemented by a virtual module, for example, the processing module may be implemented by a software functional unit or a virtual device, and the communication module may be implemented by a software functional unit or a virtual device. Or the processing module or the communication module may be implemented by physical means, for example if the means are implemented using chips/circuits (e.g. integrated circuits or logic circuits etc.). The communication module may be an input-output circuit and/or a communication interface, and perform input operation (corresponding to the foregoing receiving operation) and output operation (corresponding to the foregoing transmitting operation), and the processing module is an integrated processor or microprocessor or circuit (e.g., an integrated circuit or logic circuit, etc.).

The division of the modules in the present application is schematically shown, and is merely a logic function division, and there may be another division manner in actual implementation, and in addition, each functional module in each example of the present application may be integrated in one processor, or may exist separately and physically, or two or more modules may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules.

Fig. 19 is a schematic diagram of another communication apparatus 1900 according to an embodiment of the application. As shown in fig. 19, the communication apparatus 1900 may alternatively be the aforementioned first device or core network element, or a chip or chip system for the aforementioned first device or core network element. Alternatively, the chip system of the present application may be formed by a chip, or may include a chip and other discrete devices.

The communications apparatus 1900 can be configured to implement the functionality of any of the network elements (e.g., core network element or first device, optionally, a location management function element, and the first device is an access network device or a terminal device) in the communications system described in the foregoing examples. The communications apparatus 1900 may include a processing circuit 1910. The processing circuit 1910 is optionally coupled to a memory, which may be located within the apparatus, or may be integrated with the processor, or may be located external to the apparatus. For example, communications device 1900 may also include at least one memory 1920. The memory 1920 holds the computer programs, computer programs or instructions and/or data necessary to implement any of the examples described above, and the processing circuitry 1910 may execute the computer programs stored in the memory 1920 to perform the methods of any of the examples described above.

The communication apparatus 1900 may further include a transceiver circuit 1930, and the communication apparatus 1900 may perform information exchange with other devices through the transceiver circuit 1930. By way of example, the transceiver circuitry 1930 may be a transceiver, circuit, bus, module, pin, or other type of communication interface. When the communication device 1900 is a chip-type device or circuit, the transceiver circuit 1930 in the device 1900 may be an input/output circuit or an interface circuit, and may input information (or called "receive information") and output information (or called "transmit information"). When the communications apparatus 1900 is a core network element, a network device or a terminal device, the transceiver circuit may be a transmitter, a receiver or a transceiver, or a communications interface, which is not limited herein.

Wherein the processing circuitry 1910 may be one or more processors, or all or part of the processing circuitry in one or more processors. The processing circuit 1910 is an integrated processor, microprocessor, integrated circuit or logic circuit, etc., and the processor can determine output information based on input information.

The coupling in the present application is an indirect coupling or communication connection between devices, units or modules, which may be in electrical, mechanical or other form for the exchange of information between the devices, units or modules. The processing circuitry 1910 may operate in conjunction with the memory 1920 and transceiver circuitry 1930. The specific connection medium between the processing circuit 1910, the memory 1920, and the transceiver circuit 1930 is not limited to this application.

Optionally, as shown in fig. 19, the processing circuit 1910, the memory 1920, and the transceiver circuit 1930 are connected to each other through a bus 1940. Alternatively, the bus may comprise an address bus, a data bus, a control bus, or the like. Further, for ease of illustration, one bus 1940 is shown in FIG. 19, but does not represent only one bus or one type of bus.

It is to be appreciated that the processors referred to in embodiments of the present application may be central processing units (central processing unit, CPU) or some circuitry for processing functions in other general purpose processors, digital Signal Processors (DSP), application Specific Integrated Circuits (ASIC), off-the-shelf programmable gate arrays (field programmable GATE ARRAY, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It should also be understood that the memory referred to in embodiments of the present application may be volatile memory and/or nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an erasable programmable ROM (erasable PROM), an electrically erasable programmable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM). For example, RAM may be used as an external cache. By way of example, and not limitation, RAM includes various forms of static random access memory (STATIC RAM, SRAM), dynamic random access memory (DYNAMIC RAM, DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (doubledata RATE SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCHLINK DRAM, SLDRAM), and direct memory bus random access memory (direct rambus RAM, DR RAM).

It should be noted that when the processor is a general purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, the memory (storage module) may be integrated into the processor.

It should also be noted that the memory described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

In the embodiment of the present application, the method described in the foregoing embodiment may be performed by the first device and the core network element, or may be performed by a chip, a chip system, or a circuit of the first device and the core network element, where the chip, the chip system, or the circuit may be installed in the first device and the core network element.

The embodiment of the application provides a computer readable storage medium, on which computer instructions for implementing the method executed by the device (such as the first device, and also such as the core network element) in the above method embodiments are stored.

For example, the computer program when executed by a computer may enable the computer to implement the method performed by the device (e.g. the first device, and also e.g. the core network element, etc.) in the embodiments of the method described above.

Embodiments of the present application provide a computer program product comprising instructions which, when executed by a computer, implement a method performed by a device (e.g., a first device, and also a core network element (or positioning device), etc.) in the above method embodiments.

The embodiment of the application provides a communication system, which comprises the first device and/or the core network element in each embodiment. For example, the system comprises the first device and/or the core network element in the above embodiments. As another example, the system comprises the first device and/or the core network element in the above embodiments.

The explanation and beneficial effects of the related content in any of the above-mentioned devices can refer to the corresponding method embodiments provided above, and are not repeated here.

In order to facilitate understanding of the above embodiments provided by the present application, the following description is made:

In the present application, if there is no special description or logic conflict, terms and/or descriptions between different embodiments have consistency and may mutually refer, and technical features in different embodiments may be combined to form new embodiments according to their inherent logic relationships.

In the present application, "at least one" means one or more, and "a plurality" means two or more. "and/or" describes an association of associated objects, meaning that there may be three relationships, e.g., A and/or B, and that there may be A alone, while A and B are present, and B alone, where A, B may be singular or plural. In the text description of the present application, the character "/" generally indicates that the front-rear associated object is an or relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one of a, b and c may represent a, or b, or c, or a and b, or a and c, or b and c, or a, b and c. Wherein a, b and c can be single or multiple respectively.

In the present application, "first", "second" and various numerical numbers indicate distinction for convenience of description, and are not intended to limit the scope of embodiments of the present application. For example, distinguishing between different messages, etc. does not require a particular order or sequence of parts. It is to be understood that the objects so described may be interchanged where appropriate to enable description of aspects other than those of the embodiments of the application.

In the present disclosure, the terms "comprises" and "comprising," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

In the present application, "for indicating" may include for direct indication and for indirect indication. When describing that certain indication information is used for indicating A, the indication information may be included to directly indicate A or indirectly indicate A, and does not represent that the indication information is necessarily carried with A. The direct indication information A comprises the information A, and the implicit indication information A indicates the information A through the corresponding relation between the information A and the information B and the direct indication information B. The correspondence between the information a and the information B may be predefined, pre-stored, pre-burned, or pre-configured.

It will be appreciated that some optional features of the various embodiments of the application may, in some circumstances, be independent of other features or may, in some circumstances, be combined with other features without limitation.

It will also be appreciated that in some of the embodiments described above, the transmission information is referred to multiple times. For example, the network element a sends the information a "to the network element B, which may be understood as the network element B, or an intermediate network element in the destination end of the information a or a transmission path between the destination end and the network element B, and may include directly or indirectly sending the information to the network element B. "network element B receives information a from network element a" is understood to mean that the source of the information a or an intermediate network element in the transmission path with the source is network element a, and may include receiving information directly or indirectly from network element a. The information may be subjected to necessary processing, such as format change, etc., between the source and destination of the information transmission, but the destination can understand the valid information from the source. Similar expressions in the present application can be understood similarly, and are not repeated here.

It will also be appreciated that in some of the above embodiments, the AI model is described as being primarily exemplified as the AI model for positioning, and that the AI model may be used for other purposes as well.

It is also to be understood that the aspects of the embodiments of the application may be used in any reasonable combination, and that the explanation or illustration of the various terms presented in the embodiments may be referred to or explained in the various embodiments without limitation.

It should also be understood that, in the foregoing embodiments of the method and operations implemented by the first device or the positioning device, the method and operations may also be implemented by a component (such as a chip or a circuit) of the first device or the positioning device, which is not limited thereto.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. The storage medium includes a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.

The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of communication, performed by a first device or a chip or circuit of a first device, the method comprising:

receiving configuration information from a core network element, wherein the configuration information is used for indicating configuration parameters of a generation model;

And processing the channel measurement result by using a first model to obtain probability distribution of measurement results of measurement quantities for positioning of the terminal equipment, wherein the first model is determined based on configuration parameters of the generation model, and the measurement quantities correspond to the channel measurement results.

2. The method according to claim 1, wherein the method further comprises:

And sending first information to the core network element, wherein the first information is used for indicating the probability distribution.

3. The method according to claim 1 or 2, characterized in that the method further comprises:

And obtaining the type of the generated model and/or the function of the generated model.

4. A method of communication, performed by a first device or a chip or circuit of a first device, the method comprising:

acquiring configuration information, wherein the configuration information is used for indicating configuration parameters of a generation model;

5. The method according to claim 4, wherein the method further comprises:

And sending all or part of the first information and the configuration information to a core network element, wherein the first information is used for indicating the probability distribution.

6. The method according to any of claims 1 to 5, wherein the channel measurement result is based on a measurement of a reference signal.

7. The method according to any one of claims 1 to 6, wherein the generative model is any one of the following:

a Gaussian mixture model;

A variation self-encoder;

An antagonizing network is generated.

8. The method according to any one of claims 1 to 7, wherein the generative model is a gaussian mixture model, and the configuration parameters of the generative model comprise one or more of the following:

the generation method of the Gaussian mixture model;

a convergence threshold of the Gaussian mixture model;

the maximum value of the iteration times of the Gaussian mixture model;

Model parameters of the Gaussian mixture model;

The maximum value M of the number of the single Gaussian models included in the Gaussian mixture model is a positive integer;

the maximum value N of the single Gaussian mixture model expected value is positive number;

the Gaussian mixture model comprises a maximum value A of variance or covariance of a single Gaussian model, wherein A is a positive number;

The gaussian mixture model includes the duty cycle of one or more single gaussian models in the gaussian mixture model.

9. The method according to any one of claims 1 to 8, wherein the generative model is a variational self-encoder, and the configuration parameters of the generative model include one or more of the following:

The variation is from the structural parameter of the encoder;

the variation is from the type of neural network used by the encoder;

The variation divides the number of layers of the neural network used by the encoder;

the variable is from the number of neurons that the neural network that the encoder uses includes;

the variation is derived from the input and/or output dimensions of the encoder;

The variation is derived from the value of the model parameters of the encoder.

10. The method of any one of claims 1 to 9, wherein the measured quantity comprises one or more of:

Reference signal time difference RSTD;

Time difference of arrival TDoA;

time of arrival, toA;

Angle of arrival AoA;

Line of sight LoS probability.

11. The method of claim 2 or 5, wherein the generated model is a gaussian mixture model, the gaussian mixture model comprising k single gaussian models, k being an integer greater than or equal to1, the first information comprising one or more of:

Taking k expected values;

The value of k variances or covariances;

The duty ratio of the k single Gaussian models in the Gaussian mixture model is valued;

wherein the k expected values, the k variances or covariances are in one-to-one correspondence with the k single gaussian models.

12. The method of claim 2 or 5, wherein the generative model is a variational self-encoder, and the first information comprises one or more of:

the variation is from the value of the model parameter of the encoder;

The variance is derived from the value of the probability distribution output by the encoder.

13. The method according to any of claims 6 to 12, wherein the channel measurement result is based on a measurement of a reference signal, comprising any of:

the first device is an access network device, and the channel measurement result is obtained based on a first channel measurement, wherein the first channel measurement comprises measurement of a sounding reference signal from a terminal device, or

The first device is a terminal device, and the channel measurement result is obtained based on a second channel measurement, wherein the second channel measurement comprises measuring a positioning reference signal or a channel state information reference signal from an access network device, or

The first device is a first terminal device, and the channel measurement result is obtained based on a third channel measurement, wherein the third channel measurement comprises measurement of a lateral positioning reference signal from a second terminal device.

14. A communication device comprising means for performing the method of any of claims 1-13.