WO2024067351A1 - 传输数据的方法和相关装置 - Google Patents

传输数据的方法和相关装置 Download PDF

Info

Publication number
WO2024067351A1
WO2024067351A1 PCT/CN2023/120430 CN2023120430W WO2024067351A1 WO 2024067351 A1 WO2024067351 A1 WO 2024067351A1 CN 2023120430 W CN2023120430 W CN 2023120430W WO 2024067351 A1 WO2024067351 A1 WO 2024067351A1
Authority
WO
WIPO (PCT)
Prior art keywords
scrambling
communication device
data
indication information
terminal device
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2023/120430
Other languages
English (en)
French (fr)
Inventor
哈依那尔
曾宇
耿婷婷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to EP23870583.4A priority Critical patent/EP4583464A4/en
Publication of WO2024067351A1 publication Critical patent/WO2024067351A1/zh
Priority to US19/089,858 priority patent/US20250227685A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/04—Wireless resource allocation
    • H04W72/044—Wireless resource allocation based on the type of the allocated resource
    • H04W72/0466—Wireless resource allocation based on the type of the allocated resource the resource being a scrambling code
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/02—Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/606—Protecting data by securing the transmission between two devices or processes
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
    • G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
    • G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
    • G06F21/6254—Protecting personal data, e.g. for financial or medical purposes by anonymising data, e.g. decorrelating personal data from the owner's identification
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L25/00—Baseband systems
    • H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
    • H04L25/03—Shaping networks in transmitter or receiver, e.g. adaptive shaping networks
    • H04L25/03828—Arrangements for spectral shaping; Arrangements for providing signals with specified spectral properties
    • H04L25/03866—Arrangements for spectral shaping; Arrangements for providing signals with specified spectral properties using scrambling
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/03—Protecting confidentiality, e.g. by encryption

Definitions

  • the embodiments of the present application relate to the field of artificial intelligence, and in particular, to the application of artificial intelligence technology in the field of communication technology, and more specifically, to a method and related apparatus for transmitting data.
  • Artificial Intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
  • artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence.
  • Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.
  • Research in the field of artificial intelligence includes robotics, natural language processing, computer vision, decision-making and reasoning, human-computer interaction, recommendation and search, basic AI theory, etc.
  • the embodiments of the present application provide a method and related device for transmitting data, which can scramble the data in the AI model to ensure the security of data transmission of the AI model.
  • an embodiment of the present application provides a method for transmitting data, the method comprising: a first communication device obtains scrambling strategy indication information, the scrambling strategy indication information is used to indicate the scrambling strategy used by the first communication device; the first communication device scrambles target data according to the scrambling strategy indication information to obtain scrambled data, wherein the target data is data for an AI model; and the first communication device sends the scrambled data to a second communication device.
  • the data in the AI model can be scrambled when private data is transmitted between communication devices, which can ensure the transmission security of the data in the AI model.
  • the first communication device and the second communication device may be communication devices in a mobile communication network.
  • the first communication device may be a terminal device, and the second communication device may be a network device.
  • the first communication device may be a network device, and the second communication device may be a terminal device.
  • the target data includes at least one of the following data: parameters of the AI model, or output data of the AI model.
  • the training process of AI models may involve a large amount of data, which may be obtained and processed by organizations, institutions or companies at great cost, and then a lot of time and money are spent to train AI models to obtain relevant parameters. Therefore, once the parameters of these AI models are leaked, it may cause huge losses to these organizations, institutions or companies.
  • the security of the data of these AI models during transmission can be protected.
  • the target data is input data of the AI model, or the target data is training data for training the AI model.
  • the input data or training data of the AI model usually contains the user's private data.
  • the above technical solution scrambles this data to protect the user's private data during data transmission.
  • the scrambling strategy indication information is specifically used to indicate the computing capability of the second communication device.
  • the first communication device can determine the scrambling strategy according to the computing capability of the second communication device, so that the determined scrambling strategy can be applied to the second communication device, so that the second communication device can use the scrambled data determined by the first communication device.
  • the scrambling strategy indication information is also used to indicate at least one of the following information: the accuracy requirement of the AI model corresponding to the scrambled data, the scrambling level, the storage capacity of the second communication device, or the data scrambling authority.
  • the scrambling strategy indication information in the above technical solution further indicates the capability information of the second communication device, which makes it easier for the first communication device to determine the scrambling strategy applicable to the second communication device.
  • the scrambling strategy indication information is specifically used to indicate at least one scrambling strategy, where the scrambling strategy includes: a scrambling algorithm.
  • the scrambling strategy indication information in the above technical solution can be sent by the second communication device to the first communication device. Therefore, using the above technical solution, the first communication device can directly use the scrambling strategy indicated in the scrambling strategy indication information without spending computing resources to determine the scrambling strategy. In addition, the scrambling strategy indicated by the scrambling strategy indication information can be supported by the second communication device. Therefore, the above technical solution can avoid the situation where the scrambling strategy determined by the first communication device is not supported by the second communication device.
  • the scrambling strategy also includes at least one of the following information: a scrambling level, an accuracy requirement of an AI model corresponding to the scrambled data, or a leakage-proof data type.
  • the scrambling strategy indication information in the above technical solution further indicates specific parameters of the scrambling strategy, which makes it easier for the first communication device to determine the scrambling strategy.
  • the first communication device scrambles the target data according to the scrambling policy indication information, including: the first communication device determines a target scrambling policy from the multiple scrambling policies; the first communication device scrambles the target data according to the target scrambling policy.
  • the method before the first communication device obtains the scrambling strategy indication information, the method also includes: the first communication device sends scrambling capability indication information to the second communication device, and the scrambling capability indication information is used to indicate at least one of the following information: the scrambling algorithm supported by the first communication device, the scrambling level supported by the first communication device, the scrambling data recovery capability of the first communication device, or the difference information between the target data and the scrambled data.
  • the first communication device can send the capability information of the first communication device to the second communication device, so that the second communication device can determine the scrambling strategy that can be supported by the first communication device and send the determined scrambling strategy to the first communication device.
  • the method before the first communication device obtains the scrambling strategy indication information, the method also includes: the first communication device sends privacy level information to the second communication device, and the privacy level information is used to indicate the privacy level of the target data and/or the first communication device.
  • the first communication device can send the privacy level to the second communication device, so that the second communication device can select an appropriate scrambling strategy according to the privacy level. For example, data or communication devices with a lower privacy level can select a simpler scrambling algorithm; data or communication devices with a higher privacy level can select a more complex scrambling algorithm. In this way, the computing resources consumed by the first communication device when scrambling target data with a lower privacy level can be reduced.
  • an embodiment of the present application provides a method for transmitting data, the method comprising: a second communication device determines scrambling strategy indication information, the scrambling strategy indication information is used to indicate the scrambling strategy used by a first communication device; the second communication device sends the scrambling strategy indication information to the first communication device; the second communication device receives scrambled data from the first communication device; the second communication device determines the data of an AI model based on the scrambled data.
  • the data in the AI model can be scrambled when transmitting private data between communication devices, which can ensure the transmission security of the data in the AI model.
  • the first communication device and the second communication device may be communication devices in a mobile communication network.
  • the first communication device may be a terminal device, and the second communication device may be a network device.
  • the first communication device may be a network device, and the second communication device may be a terminal device.
  • the second communication device determines the data of the AI model based on the scrambled data, including: the second communication device data determines the parameters of the AI model or the output data of the AI model based on the scrambled data.
  • the training process of AI models may involve a large amount of data, which may be obtained and processed by organizations, institutions or companies at great cost, and then a lot of time and money are spent to train AI models to obtain relevant parameters. Therefore, once the parameters of these AI models are leaked, it may cause huge losses to these organizations, institutions or companies.
  • the data and output data of the AI model can be encrypted to protect the security of the data of these AI models during transmission.
  • the second communication device determines the data of the AI model based on the scrambled data, including: the second communication device data determines the input data of the AI model based on the scrambled data, or the training data for training the AI model.
  • the input data or training data of the AI model usually contains the user's private data.
  • the above technical solution scrambles this data to protect the user's private data during data transmission.
  • the scrambling strategy indication information is specifically used to indicate the computing capability of the second communication device.
  • the first communication device can determine the scrambling strategy according to the computing capability of the second communication device, so that the determined scrambling strategy can be applied to the second communication device, so that the second communication device can use the scrambled data determined by the first communication device.
  • the scrambling strategy indication information is also used to indicate at least one of the following information: the accuracy requirement of the AI model, the scrambling level, the storage capacity of the second communication device, or the data scrambling authority.
  • the scrambling strategy indication information in the above technical solution further indicates the capability information of the second communication device, which makes it easier for the first communication device to determine the scrambling strategy applicable to the second communication device.
  • the scrambling strategy indication information is specifically used to indicate at least one scrambling strategy, where the scrambling strategy includes: a scrambling algorithm.
  • the scrambling strategy indication information in the above technical solution can be sent by the second communication device to the first communication device. Therefore, using the above technical solution, the first communication device can directly use the scrambling strategy indicated in the scrambling strategy indication information without spending computing resources to determine the scrambling strategy. In addition, the scrambling strategy indicated by the scrambling strategy indication information can be supported by the second communication device. Therefore, the above technical solution can avoid the situation where the scrambling strategy determined by the first communication device is not supported by the second communication device.
  • the scrambling strategy also includes at least one of the following information: the scrambling level, the accuracy requirement of the AI model, or the type of data to be leak-proof.
  • the scrambling strategy indication information in the above technical solution further indicates specific parameters of the scrambling strategy, which makes it easier for the first communication device to determine the scrambling strategy.
  • the method before the second communication device determines the scrambling policy indication information, the method also includes: the second communication device receives scrambling capability indication information from the first communication device, and the scrambling capability indication information is used to indicate at least one of the following information: the scrambling algorithm supported by the first communication device, the scrambling level supported by the first communication device, the scrambled data recovery capability of the first communication device, or the difference information between the data to be scrambled and the scrambled data; the second communication device determines the scrambling policy indication information, including: the second communication device determines the scrambling policy indication information according to the scrambling capability indication information.
  • the first communication device can send the capability information of the first communication device to the second communication device, so that the second communication device can determine the scrambling strategy that can be supported by the first communication device and send the determined scrambling strategy to the first communication device.
  • the method before the second communication device determines the scrambling policy indication information, the method also includes: the second communication device receives privacy level information from the first communication device, and the privacy level information is used to indicate the scrambled data and/or the privacy level of the first communication device; the second communication device determines the scrambling policy indication information based on the scrambling capability indication information, including: the second communication device determines the scrambling policy indication information based on the scrambling capability indication information and the privacy level information.
  • the first communication device can send the privacy level to the second communication device, so that the second communication device can select an appropriate scrambling strategy according to the privacy level. For example, data or communication devices with a lower privacy level can select a simpler scrambling algorithm; data or communication devices with a higher privacy level can select a more complex scrambling algorithm. In this way, the computing resources consumed by the first communication device when scrambling target data with a lower privacy level can be reduced.
  • an embodiment of the present application provides a communication device, which includes a unit for implementing the first aspect or any possible implementation method of the first aspect.
  • an embodiment of the present application provides a communication device, the communication device comprising a communication device for implementing the second aspect or any of the second aspects.
  • a communication device comprising a communication device for implementing the second aspect or any of the second aspects.
  • an embodiment of the present application provides a communication device, which includes a processor, which is used to couple with a memory, read and execute instructions and/or program codes in the memory to execute the first aspect or any possible implementation method of the first aspect.
  • an embodiment of the present application provides a communication device, which includes a processor, which is used to couple with a memory, read and execute instructions and/or program codes in the memory to execute the second aspect or any possible implementation method of the second aspect.
  • an embodiment of the present application provides a chip system, which includes a logic circuit, which is used to couple with an input/output interface and transmit data through the input/output interface to execute the first aspect or any possible implementation method of the first aspect.
  • an embodiment of the present application provides a chip system, which includes a logic circuit, which is used to couple with an input/output interface and transmit data through the input/output interface to execute the second aspect or any possible implementation method of the second aspect.
  • an embodiment of the present application provides a computer-readable storage medium, which stores program code.
  • the computer storage medium runs on a computer, it enables the computer to execute the first aspect or any possible implementation of the first aspect.
  • an embodiment of the present application provides a computer-readable storage medium, which stores program code.
  • the computer storage medium runs on a computer, it enables the computer to execute the second aspect or any possible implementation of the second aspect.
  • an embodiment of the present application provides a computer program product, which includes: a computer program code, when the computer program code runs on a computer, enables the computer to execute the first aspect or any possible implementation of the first aspect.
  • an embodiment of the present application provides a computer program product, which includes: a computer program code, when the computer program code runs on a computer, enables the computer to execute the second aspect or any possible implementation of the second aspect.
  • FIG1 is a schematic diagram of an AI module provided in an embodiment of the present application.
  • FIG. 2 is a schematic flowchart of a method for transmitting data according to an embodiment of the present application.
  • FIG3 is a schematic flowchart of another method for transmitting data provided according to an embodiment of the present application.
  • FIG. 4 is a schematic flowchart of another method for transmitting data provided according to an embodiment of the present application.
  • FIG5 is a schematic flowchart of another method for transmitting data provided according to an embodiment of the present application.
  • FIG6 is a schematic structural block diagram of a communication device provided according to an embodiment of the present application.
  • FIG. 7 is a schematic structural block diagram of another communication device provided according to an embodiment of the present application.
  • FIG. 8 shows a schematic structural diagram of a terminal device.
  • FIG. 9 shows a schematic diagram of a network device structure.
  • references to "one embodiment” or “some embodiments” described in this specification mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment.
  • words such as “exemplary” or “for example” are used to indicate examples, illustrations or explanations. Any embodiment or design described as “exemplary” or “for example” in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs.
  • the use of words such as “exemplary” or “for example” is intended to present related concepts in a specific way.
  • the terms “including”, “comprising”, “having” and their variations all mean “including but not limited to”, unless otherwise specifically emphasized.
  • "used to indicate” may include being used for direct indication and being used for indirect indication.
  • the indication information When describing that a certain indication information is used to indicate A, it may include that the indication information directly indicates A or indirectly indicates A, but it does not mean that the indication information must carry A.
  • the technical solution of the embodiment of the present application can be applied to various communication systems, such as: long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), universal mobile telecommunication system (UMTS), worldwide interoperability for microwave access (Wi-MAX) communication system, fifth generation (5G) system or new radio (NR), future sixth generation (6G) system, intersatellite communication and satellite communication and other non-terrestrial communication network (NTN) systems.
  • LTE long term evolution
  • FDD frequency division duplex
  • TDD LTE time division duplex
  • UMTS universal mobile telecommunication system
  • Wi-MAX worldwide interoperability for microwave access
  • 5G fifth generation
  • NR new radio
  • future sixth generation (6G) system intersatellite communication and satellite communication and other non-terrestrial communication network (NTN) systems.
  • the satellite communication system includes a satellite base station and a terminal device.
  • the satellite base station provides communication services for the terminal device.
  • the satellite can refer to a drone, a hot air balloon, a low-orbit satellite, a medium-orbit satellite, a high-orbit satellite, etc.
  • a satellite can also refer to a non-ground base station or non-ground equipment.
  • the embodiments of the present application can be applied to terminal devices.
  • the terminal device can be a wireless terminal or a wired terminal.
  • the wireless terminal can be a device that provides voice and/or data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem.
  • the wireless terminal can communicate with one or more core networks via a radio access network (abbreviation: RAN).
  • RAN radio access network
  • the wireless terminal can be a mobile terminal, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal, for example, a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device, which exchanges language and/or data with the wireless access network.
  • a wireless terminal may also be called a system, a subscriber unit (SU), a subscriber station (SS), a mobile station (MB), a mobile, a remote station (RS), an access point (AP), a remote terminal (RT), an access terminal (AT), a user terminal (UT), a user agent (UA), a terminal device (UD), or a user equipment (UE).
  • SU subscriber unit
  • SS subscriber station
  • MB mobile station
  • RS remote station
  • AP access point
  • RT remote terminal
  • AT access terminal
  • U user agent
  • U terminal device
  • UE user equipment
  • the device for realizing the function of the terminal device may be the terminal device; or it may be a device capable of supporting the terminal device to realize the function, such as a chip system.
  • the device may be installed in the terminal device or used in combination with the terminal device.
  • the chip system may be composed of a chip, or may include a chip and other discrete devices.
  • the technical solution in the embodiment of the present application can also be applied to access network equipment.
  • the access network equipment can be a device that can access a terminal device to a wireless network.
  • the access network equipment can also be called a radio access network (RAN) node, a radio access network device, or a network device.
  • RAN radio access network
  • the access network equipment can be a base station.
  • the base station in the embodiments of the present application can broadly cover the following various names, or be replaced with the following names, such as: NodeB, evolved NodeB (eNB), base station gNB in 5G network, relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master eNodeB (MeNB), secondary eNodeB (SeNB), multi-standard radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), positioning node, etc.
  • NodeB evolved NodeB
  • gNB in 5G network
  • TRP transmitting and receiving point
  • TP transmitting point
  • MeNodeB master eNodeB
  • SeNB secondary eNodeB
  • MSR multi-standard radio
  • the base station can be a macro base station, a micro base station, a relay node,
  • a base station may also refer to a communication module, a modem or a chip used to be arranged in the aforementioned device or apparatus.
  • a base station may also be a network side device in a 6G network, a device that assumes the function of a base station in a future communication system, etc.
  • a base station may support networks with the same or different access technologies.
  • the base station can be a centralized unit (CU) and distributed unit (DU) separated architecture.
  • RAN can be connected to the core network (for example, it can be the core network of long-term evolution (LTE) or the core network of 5G, etc.).
  • CU and DU can be understood as the division of base stations from the perspective of logical functions.
  • CU and DU can be physically separated or deployed together.
  • Multiple DUs can share one CU.
  • One DU can also be connected to multiple CUs.
  • CU and DU can be connected through an interface, such as an F1 interface.
  • CU and DU can be divided according to the protocol layer of the wireless network.
  • CU is used to perform the functions of the radio resource control (RRC) layer, the service data adaptation protocol (SDAP) layer, and the packet data convergence protocol (PDCP) layer
  • DU is used to perform the functions of the radio link control (RLC) layer, the media access control (MAC) layer, the physical layer, etc.
  • RRC radio resource control
  • SDAP service data adaptation protocol
  • PDCP packet data convergence protocol
  • DU is used to perform the functions of the radio link control
  • RLC radio link control
  • MAC media access control
  • the physical layer etc.
  • CU or DU can be divided into functions with more protocol layers.
  • CU or DU can also be divided into partial processing functions with protocol layers.
  • the functions of CU or DU can also be divided according to the service type or other system requirements. For example, according to the latency, the functions that need to meet the latency requirements are set in the DU, and the functions that do not need to meet the latency requirements are set in the CU.
  • the CU can also have one or more functions of the core network.
  • One or more CUs can be set centrally or separately.
  • the CU can be set on the network side for centralized management.
  • the DU can have multiple RF functions, or the RF function can be set remotely.
  • the functions of CU can be implemented by one entity or by different entities.
  • the functions of CU can be further divided, for example, the control plane (CP) and the user plane (UP) are separated, that is, the control plane (CU-CP) of CU and the user plane (CU-UP) of CU.
  • CU-CP and CU-UP can be implemented by different functional entities and connected through the E1 interface.
  • the CU-CP and CU-UP can be coupled with DU to jointly complete the functions of the base station.
  • the control plane CU-CP of CU also includes a further divided architecture, that is, the existing CU-CP is further divided into CU-CP1 and CU-CP2.
  • CU-CP1 includes various wireless resource management functions
  • CU-CP2 only includes RRC functions and PDCP-C functions (that is, the basic functions of control plane signaling at the PDCP layer).
  • Base stations can be fixed or mobile.
  • a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station.
  • a helicopter or drone can be configured to act as a device that communicates with another base station.
  • Operation, administration and maintenance refers to the division of network management work into three categories: operation, administration and maintenance, based on the actual needs of the operator's network operation. It is referred to as OAM, and OAM can also be called OAM entity or function. Operation mainly completes the analysis, prediction, planning and configuration of daily network and business operations; maintenance mainly involves daily operational activities such as testing and fault management of the network and its services. OAM can detect network operation status, optimize network connection and performance, improve network operation stability, and reduce network maintenance costs.
  • AI model also known as AI algorithm (or AI operator)
  • AI algorithm or AI operator
  • AI model is a general term for mathematical algorithms built on the principles of artificial intelligence, and is also the basis for using AI to solve specific problems.
  • the type of AI model is not limited in the embodiments of the present application.
  • the AI model can be a machine learning model, a deep learning model, a reinforcement learning model, or a federated learning model.
  • Machine learning is a method to achieve artificial intelligence.
  • the goal of this method is to design and analyze some algorithms (also known as models) that allow computers to "learn" automatically.
  • the designed algorithms are called machine learning models.
  • Machine learning models are a type of algorithm that automatically analyzes data to obtain patterns and uses the patterns to predict unknown data. There are many types of machine learning models. Depending on whether the model training needs to rely on the labels corresponding to the training data, machine learning models can be divided into: 1. Supervised learning models; 2. Unsupervised learning models.
  • Deep learning is a new technical field that emerged in the process of machine learning research. Specifically, deep learning is a method in machine learning based on deep representation learning of data. Deep learning interprets data by establishing a neural network that simulates the human brain for analysis and learning. Since in machine learning methods, almost all features need to be determined by industry experts and then encoded. However, deep learning algorithms try to learn features from data by themselves. Algorithms designed based on deep learning ideas are called deep learning models.
  • Reinforcement learning is a special field in machine learning that uses the interaction between an agent and its environment to Reinforcement learning is a process of learning the best strategy, making sequential decisions, and obtaining the maximum reward.
  • reinforcement learning is learning "what to do (i.e., how to map the current situation into actions) to maximize the numerical benefit signal". The agent will not be told what actions to take, but must try to discover which actions will produce the most lucrative benefits.
  • Reinforcement learning is different from supervised learning and unsupervised learning in the field of machine learning. Supervised learning is the process of learning from labeled training data provided externally (task-driven), and unsupervised learning is the process of finding implicit structures in unlabeled data (data-driven).
  • Reinforcement learning is the process of finding a better solution through "trial and error”.
  • the agent must develop existing experience to gain benefits, and also conduct trials so that it can obtain a better action selection space in the future (i.e., learn from mistakes).
  • the algorithm designed based on reinforcement learning is called a reinforcement learning model.
  • Federated learning also known as collaborative learning
  • collaborative learning is a machine learning technique that trains algorithms on multiple decentralized edge devices or servers holding local data samples without exchanging them. This approach is in stark contrast to traditional centralized machine learning techniques, where all local datasets are uploaded to a single server for training.
  • Federated learning enables multiple participants to build a common, robust machine learning model without sharing data, allowing key issues such as data privacy, data security, data access rights, and access to heterogeneous data to be addressed.
  • AI model training refers to the process of using a specified initial model to calculate the training data, and adjusting the parameters in the initial model using a certain method based on the calculation results, so that the model gradually learns certain rules and has specific functions.
  • AI model reasoning is the process of using a trained AI model to calculate the input data and obtain the predicted reasoning results (also called output data).
  • the AI module is a module with AI learning and computing capabilities.
  • the AI module can be located in the OAM, in the gNB (the separation architecture is located in the CU), in some UEs, or as a separate network element entity.
  • the main function of the AI module in the wireless communication system is to perform a series of AI calculations such as model building, training approximation, and reinforcement learning based on input data (for example, in a wireless communication system, the input data can be network operation data provided by the RAN side or monitored by OAM, such as network load, channel quality, etc.).
  • the trained model provided by the AI module has the function of predicting network changes on the RAN side, and can usually be used for load prediction, UE trajectory prediction, etc.
  • the AI module can also perform policy reasoning from the perspectives of network energy saving and mobility optimization based on the prediction results of the trained model on the RAN network performance, so as to obtain reasonable and efficient energy saving strategies, mobility optimization strategies, etc.
  • the AI module When the AI module is located in OAM, its communication with the gNB on the RAN side can reuse the current northbound interface; when the AI module is located in the gNB or CU, the current F1, Xn, Uu and other interfaces can be reused; when the AI module becomes an independent network entity, it is necessary to re-establish the communication link to the OAM and RAN side, such as based on a wired link or a wireless link.
  • FIG1 is a schematic diagram of an AI module provided in an embodiment of the present application.
  • the AI module 100 shown in FIG1 includes a database module 101 , a training module 102 , a model module 103 and an execution module 104 .
  • the database module 101 can store training data.
  • the training data can also come from the terminal device.
  • the training data can come from the network device.
  • the training data can come from the base station (such as gNB) or the functional unit (such as CU or DU) constituting the base station.
  • the training data can come from other network devices other than the base station.
  • a gateway a management entity (such as mobile management (mobile management entity, MME), a core network device, etc.
  • the training module 102 analyzes the training data provided by the database module 101 to obtain an AI model.
  • the training module 102 can send the trained AI model to the model module 103.
  • the training module 102 can also update the trained model and send the update parameters used to update the model to the model module 103.
  • the model module 103 can also collect some model operation data during the operation of the AI model and send the operation data to the training module 102.
  • the training module 102 can update the AI model based on the operation data.
  • the model module 103 can determine the output data based on the AI model and the input data.
  • the output data may include the prediction results of the network operation obtained based on the input data and the AI model.
  • the output data may also include an adjustment strategy determined based on the input data and the AI model.
  • the network device and/or the terminal device may directly send the input data to the model module 103.
  • the database module 101 may also collect data from the network device and/or the terminal device, determine the input data and send the input data to the model module 103.
  • the execution module 104 can be used to execute the adjustment strategy determined by the model module 103.
  • the execution module 104 can also collect the specific performance of the network after the adjustment strategy is applied, such as performance parameters in the network, and feed this information back to the data module 101.
  • the database module 101 can store this feedback information. This feedback information can be used for subsequent model training or improving the AI model.
  • AI models can be used to achieve intelligent collection and Analyze data to improve network performance and user experience.
  • AI can be applied to channel state information (CSI) feedback enhancement.
  • CSI is the channel attribute of the communication link and is the channel quality information reported by the terminal device to the base station.
  • the terminal device reports the downlink channel quality information to the base station so that a more appropriate modulation and coding scheme (MCS) can be selected for the terminal device, so that it can better adapt to the changing wireless channel.
  • MCS modulation and coding scheme
  • AI can also be applied to beam management (BM).
  • BM is mainly used to find the strongest transmit/receive beam pair.
  • AI-based beam prediction can improve prediction accuracy.
  • AI can also be applied to positioning accuracy enhancements.
  • Positioning accuracy is related to the number of total radiated power (TRP) antennas.
  • TRP total radiated power
  • TDOA time difference of arrival
  • RTT round trip time
  • LOS line of sight
  • AI-based positioning can improve positioning accuracy in scenarios with fewer line-of-sight paths.
  • AI can also be applied to network energy saving.
  • Network energy saving can be achieved through cell activation/deactivation, load reduction, coverage improvement or other RAN setting adjustments.
  • the optimal energy saving decision depends on factors such as the load of different RAN nodes, RAN node capabilities, key performance indicators (KPI) requirements, quality of service (QoS) requirements, number of activated users and mobility of terminal devices, and cell utilization.
  • KPI key performance indicators
  • QoS quality of service
  • improving network energy efficiency is a complex process. Wrong cell closure and wrong traffic offloading operations will cause a decrease in network performance and even energy efficiency.
  • AI technology can be used to optimize energy saving decisions by utilizing data collected in the RAN network.
  • AI algorithms can predict the energy efficiency and load status of the next cycle, which can be used to make better decisions on cell activation/deactivation to save energy. Based on the predicted load, the system can dynamically configure energy saving strategies to maintain a balance between system performance and energy efficiency and reduce energy consumption.
  • AI can also be applied to load balancing.
  • load balancing is to evenly distribute the load between cells and between areas within a cell, or to transfer part of the traffic from congested cells, or to allow terminal devices to be diverted on a cell, carrier or access standard to improve network performance. This can be achieved by optimizing switching parameters and switching actions. This optimized automation can provide a high-quality user experience while improving system capacity and minimizing manual intervention in network management and optimization tasks. At present, load balancing decisions that rely on the current/past cell load status are not enough. In addition, the overall network and service performance is difficult to guarantee during load balancing.
  • solutions based on AI models can be introduced to improve load balancing performance, such as inputting various measurements and feedbacks from users and network nodes, historical data, etc. into AI models to improve load balancing performance, so as to provide a higher quality user experience and increase system capacity.
  • AI can also be applied to mobility optimization.
  • Mobility management is a solution to ensure service continuity during the mobility of terminal devices by minimizing dropped calls, radio link failures (RLF), unnecessary handovers, and ping-pong effects.
  • RLF radio link failures
  • ping-pong effects For future high-frequency networks, as the coverage area of a single node decreases, the frequency of terminal devices switching between nodes will become very high, especially for high-mobility terminal devices.
  • QoE quality of experience
  • the process of performing privacy-preserving computing on data can be called scrambling.
  • the plaintext data before scrambling can be called the target data
  • the scrambled result obtained after scrambling the target data can be called the scrambled data.
  • the mainstream privacy-preserving computing solutions are still mainly based on cryptography (differential privacy, homomorphic encryption, and secure multi-party computing). On the basis of ensuring data privacy and security, data can be circulated securely in a "available but invisible" manner.
  • Differential privacy In the interactive differential privacy protection framework, the user submits a query request to the data owner through the query interface. The data owner queries the source data set based on the query request, and then feeds back the query result to the user after adding noise perturbation.
  • Differential privacy can have different scrambling levels. The higher the scrambling level, the higher the protection strength of differential privacy.
  • the protection strength of differential privacy is related to how much perturbation or noise can be added. For example, consider the ( ⁇ , ⁇ )-differential privacy scheme based on the Gaussian mechanism. If different ⁇ values are selected, the added Gaussian noise will be different, and the degree of privacy protection will also be different.
  • the differential privacy parameter ⁇ can be To reflect the scrambling level of differential privacy.
  • the relationship between the differential privacy parameters ( ⁇ , ⁇ ) and the standard deviation ⁇ of the Gaussian noise distribution satisfies the following relationship:
  • Homomorphic encryption An encryption algorithm that satisfies the homomorphic operation property of ciphertext. After the data is homomorphically encrypted, a specific calculation is performed on the ciphertext. The result of the ciphertext calculation is equivalent to the same calculation directly performed on the plaintext data after the corresponding homomorphic decryption. Similarly, homomorphic encryption can have different scrambling levels. The higher the scrambling level, the higher the protection strength of homomorphic encryption. Homomorphic encryption includes fully homomorphic encryption (FHE) and somewhat homomorphic encryption (SWHE). FHE has a huge computational overhead in practical applications, and SWHE has limited support capabilities, but low overhead. At present, there are many algorithms that meet additive homomorphism or multiplicative homomorphism.
  • the classic Rivest Shamir Adleman (RSA) algorithm is an encryption method that meets multiplicative homomorphism.
  • its cryptographic strength is related to the key length (generally just the bit length of the modulus value). For example, from RSA-1024 to RSA-3072, the bit length of the modulus value increased by 200%, and the cryptographic strength also increased by 50% accordingly. Therefore, the protection strength of homomorphic encryption is related to the key length. The longer the key length, the greater the encryption degree (or the greater the degree of scrambling of the original data), the greater the scrambling level, and the higher the privacy protection strength.
  • Secure multi-party computing It can be considered that secure multi-party computing is a set of protocols that can ensure that the computation of aggregated data is allowed without exposing the data of individual entities.
  • the main technologies used are key technologies such as secret sharing, oblivious transmission, obfuscated circuits, homomorphic encryption, and zero-knowledge proof.
  • secure multi-party computing is a set of protocols. Therefore, the scrambling level of secure multi-party computing can be reflected by the key technologies adopted by the secure multi-party algorithm. For example, if the key technology adopted by secure multi-party computing is homomorphic encryption, then the scrambling level of the secure multi-party algorithm is the scrambling level of homomorphic encryption.
  • FIG. 2 is a schematic flowchart of a method for transmitting data according to an embodiment of the present application.
  • the terminal device sends privacy level information to the base station.
  • the privacy level information can be used to indicate the privacy level of data (ie, target data) that needs to be scrambled by the terminal device and then sent to the base station.
  • the target data may be data generated during the operation of the terminal device, and these data may be used as training data for the AI model and/or input data for the AI model.
  • the target data may be different.
  • the terminal device can perform channel estimation based on the received channel state information-reference signal (CSI-RS) to obtain a channel estimation result (such as a channel matrix, a eigenvector obtained by eigendecomposing the channel matrix, etc.).
  • CSI-RS channel state information-reference signal
  • the channel estimation result can be used as training data for an AI model or input data for an AI model.
  • the target data can be the channel estimation result.
  • RSRP reference signal received power
  • ideal beam identifier can be used as training data or input data of the AI model.
  • the target data can be information such as RSRP measured by the terminal device and the ideal beam identifier selected by the terminal device.
  • the location information of the terminal device (such as the latitude and longitude coordinates of the terminal device, the location information of the terminal device relative to the base station, etc.), the movement trajectory of the terminal device and other information can be used as the training data of the AI model or the input data of the AI model.
  • the target data can include the location information, movement trajectory and other information of the terminal device.
  • Table 1 shows the privacy requirements for different data.
  • the privacy level of RSRP is higher than the privacy level of the channel estimation result
  • the privacy level of the ideal beam identifier is higher than the privacy level of RSRP
  • the privacy level of the position confidence and the moving trajectory is higher than the privacy level of the ideal beam identifier.
  • the privacy level information may directly include the privacy level of the target data.
  • the privacy level information may directly include the privacy level corresponding to the location information, that is, privacy level 4.
  • the privacy level information may include the type of the target data.
  • the base station may determine the privacy level of the target data based on the corresponding relationship between the privacy level and the data type.
  • the privacy level information indicates that the target data is the location information of the terminal device.
  • the base station may determine that the privacy level of the target data is 4 based on the corresponding relationship between the privacy level and the data type.
  • the privacy level information may include both the privacy level of the target data and the type of the target data.
  • the privacy level information may be used to indicate the privacy level of the terminal device.
  • Table 2 shows the correspondence between the types of terminal devices and privacy levels.
  • the privacy level of the remote three-meter (electricity meter, water meter, gas meter) data acquisition device is higher than the privacy level of the remote temperature acquisition device
  • the privacy level of mobile phones and tablet computers is higher than the privacy level of the remote three-meter (electricity meter, water meter, gas meter) data acquisition device
  • the privacy level of mobile point of sales (POS) machines is higher than the privacy level of mobile phones and tablet computers. It is understandable that the relationship between the privacy level and the device type shown in Table 2 and the total number of privacy levels are only illustrative, and not a limitation of the embodiments of the present application.
  • the privacy level information may directly include the privacy level of the terminal device.
  • the privacy level information may directly include the privacy level corresponding to the mobile POS machine, that is, privacy level 4.
  • the privacy level information may include the type of the terminal device.
  • the base station may determine the privacy level of the target data based on the corresponding relationship between the privacy level and the device type.
  • the privacy level information may indicate that the terminal device is a mobile POS.
  • the base station may determine that the privacy level of the type of the terminal device is 4 based on the corresponding relationship between the privacy level and the device type.
  • the privacy level information may include both the privacy level of the terminal device and the type of the terminal device.
  • the privacy level information may be a dedicated piece of information. For example, after the terminal device establishes an RRC connection with the base station, if the terminal device needs to send scrambled data to the base station, the terminal device may send the privacy level information to the base station before sending the scrambled data.
  • the privacy level information may be a non-dedicated message.
  • the terminal device may send an RRC resume complete message to the base station during the process of establishing an RRC connection with the base station, and the RRC resume complete message carries the type information of the terminal device.
  • the base station may determine the privacy level of the terminal device according to the type of the terminal device carried by the RRC resume complete message.
  • other RRC messages may also be used to carry the type information of the terminal device, such as an RRC setup complete message, an RRC reestablishment complete message, an RRC reconfiguration complete message, etc.
  • the terminal device may send the privacy level information together with other information to the base station.
  • the terminal device may send the privacy level information together with the scrambling capability information of the terminal device to the base station.
  • the base station obtains the scrambling capability of the terminal device.
  • the scrambling capability of the terminal device includes at least one of the following information: the scrambling algorithm supported by the terminal device, The supported scrambling level, the scrambled data recovery capability of the terminal device, or the difference between the target data and the scrambled data.
  • the scrambling algorithm supported by the terminal device refers to the privacy-preserving computing scheme that the terminal device can use, such as whether the terminal device supports differential privacy, whether the terminal device supports homomorphic encryption, and whether the terminal device supports secure multi-party computing.
  • the scrambling level supported by the terminal device may be the maximum scrambling level of the scrambling algorithm supported by the terminal device.
  • the scrambling level supported by the terminal device may include a Gaussian noise standard deviation.
  • the terminal device may support a standard deviation less than or equal to 1e - 5 , for example, the terminal device may support the addition of Gaussian noise with a differential privacy parameter ⁇ equal to 1e -5 , 1e -6 , or 1e -7 .
  • the scrambled data recovery capability of the terminal device is used to indicate the scrambled data of which scrambling level the terminal device can recover, for example, the scrambled data of which noise/disturbance the terminal device can recover.
  • the difference information between the target data and the scrambled data refers to the degree of difference between the data before and after scrambling (ie, the degree of difference between the target data and the scrambled data), for example, the variance, standard deviation, minimum mean square error, etc. of the data before and after scrambling.
  • the base station may send scrambling capability request information to the terminal device, and the scrambling capability request information is used to request the scrambling capability of the terminal device.
  • the terminal device may send scrambling capability indication information to the base station. The scrambling capability indication information is used to indicate the scrambling capability of the terminal device.
  • the terminal device may actively send the scrambling capability indication information to the base station after establishing an RRC connection with the base station.
  • the scrambling capability indication information can be used to indicate any one or more of the scrambling capabilities of the terminal device.
  • the scrambling capability indication information can be used for one or more of the following information: the scrambling algorithms supported by the terminal device, the scrambling levels supported by the terminal device, the scrambled data recovery capability of the terminal device, or the difference information between the target data and the scrambled data.
  • the scrambling capability indication information does not indicate some scrambling capabilities, it can be considered that the terminal device supports all optional schemes under the capability. For example, if the scrambling capability indication information does not indicate the scrambling algorithms supported by the terminal device, the base station can determine that the terminal device supports all scrambling algorithms. For another example, if the scrambling capability indication information does not indicate the scrambling levels supported by the terminal device, the base station can determine that the terminal device supports all scrambling levels.
  • the scrambling capability indication information does not indicate some scrambling capabilities, it can be considered that the terminal device supports the default solution under the capability or the solution requiring the lowest computing power. For example, assuming that the default scrambling algorithm is differential privacy, if the scrambling capability indication information does not indicate the scrambling algorithm supported by the terminal device, the base station can determine that the terminal device only supports differential privacy. For another example, if the scrambling capability indication information does not indicate the scrambling level supported by the terminal device, the base station can determine that the terminal device only supports the lowest level of scrambling.
  • the base station can determine the scrambling capability of the terminal device based on the type of the terminal device. For example, the base station can obtain the device type of the terminal device based on the privacy level information, and then determine the scrambling capability of the terminal device based on the device type of the terminal device.
  • the base station can determine the type of the terminal device based on the RRC message obtained during the establishment of the RRC connection (for example, an RRC recovery completion message, an RRC establishment completion message, an RRC reconstruction completion message, or an RRC reconfiguration completion message), and then determine the scrambling capability of the terminal device based on the type of the terminal device.
  • the RRC message obtained during the establishment of the RRC connection (for example, an RRC recovery completion message, an RRC establishment completion message, an RRC reconstruction completion message, or an RRC reconfiguration completion message)
  • the base station is a split architecture, that is, it is split into CP and UP, and the CU is further split into CU-CP and CU-UP, and the CU-CP is further split into CU-CP1 and CU-CP2, CU-CP2 receives and decodes the message sent by the terminal device carrying the scrambling capability indication information, and then CU-CP1 confirms whether different levels of scrambling functions on the terminal device side are supported.
  • the base station determines scrambling strategy indication information.
  • the scrambling strategy indication information is used to indicate the scrambling strategy used by the terminal device.
  • the scrambling strategy indication information may indicate only one scrambling strategy.
  • the scrambling strategy indication information may indicate two or more scrambling strategies.
  • the scrambling strategy includes a scrambling algorithm.
  • the scrambling strategy further includes at least one of the following information: a scrambling level, a precision requirement of an AI model corresponding to the scrambled data, or a type of data to be leak-proof.
  • a scrambling strategy may include one scrambling algorithm or multiple scrambling algorithms. Similarly, a scrambling strategy may include one scrambling level or multiple scrambling levels. A scrambling strategy may include one leakage-proof data type or multiple leakage-proof data types.
  • some of the information included in different scrambling strategies may be the same, but other information is different.
  • the scrambling algorithms included in different scrambling strategies may be the same, but other information (such as the scrambling level, the accuracy requirements of the AI model corresponding to the scrambled data, and/or the type of leakage-proof data) is not exactly the same.
  • the scrambling levels included in different scrambling strategies are the same, but the scrambling algorithms are different or not exactly the same.
  • the base station may not need to receive the privacy level information from the terminal device, and may not obtain the scrambling capability of the terminal device.
  • the base station may determine the scrambling strategy indication information containing one or more scrambling strategies on its own. If the terminal device determines that the terminal device can use the scrambling strategy indicated in the scrambling strategy indication information after receiving the scrambling strategy indication information, then the terminal device uses the corresponding scrambling strategy to scramble the target data. If the terminal device determines that the scrambling strategy indicated by the scrambling strategy indication information is not available for the terminal device after receiving the scrambling strategy indication information, then the terminal device may send a feedback message to the base station. After receiving the feedback information, the base station may redetermine the scrambling strategy and send the redetermined scrambling strategy to the terminal device.
  • the base station may only obtain the privacy level information without obtaining the scrambling capability of the terminal device.
  • the base station may determine the scrambling strategy indication information based on the privacy level information. For example, different privacy levels may correspond to different scrambling strategies.
  • the base station may determine the corresponding scrambling strategy based on the privacy level information.
  • the terminal device may send a feedback message to the base station. After receiving the feedback information, the base station may redetermine the scrambling strategy and send the redetermined scrambling strategy to the terminal device.
  • the base station may only obtain the scrambling capability of the terminal device without obtaining the privacy level information.
  • the base station may determine the scrambling strategy indication information according to the scrambling capability of the terminal device. For example, the base station may select the scrambling algorithm in the scrambling strategy according to the scrambling algorithm supported by the terminal device; and select the scrambling level in the scrambling strategy according to the scrambling level supported by the terminal device.
  • the base station may obtain the scrambling capability and the privacy level information of the terminal device.
  • the base station may determine the scrambling strategy based on the scrambling capability and the privacy level of the terminal device.
  • a privacy level may correspond to multiple scrambling algorithms.
  • the base station may select a scrambling algorithm supported by the terminal device from the multiple scrambling algorithms based on the scrambling algorithms supported by the terminal device.
  • a privacy level may correspond to multiple scrambling levels.
  • the base station may select a scrambling level supported by the terminal device from the multiple scrambling levels (e.g., the highest scrambling level or the lowest scrambling level supported by the terminal device) based on the scrambling levels supported by the terminal device.
  • the base station sends the scrambling strategy indication information to the terminal device.
  • the terminal device receives the scrambling strategy indication information from the base station.
  • the terminal device scrambles the target data according to the scrambling strategy indication information to obtain scrambled data.
  • the scrambling strategy indication information only includes one scrambling strategy.
  • the terminal device can directly scramble the target data according to the scrambling strategy.
  • the terminal device can adapt to the scrambling algorithm specified by the scrambling strategy to scramble the target data.
  • Other parameters used for scrambling can be determined by the terminal device.
  • the embodiment of the present application does not limit the method for determining these parameters that can be determined by the terminal device. Take the scrambling level as an example.
  • the terminal device can determine to use any scrambling level.
  • the terminal device can also determine to use the lowest scrambling level, or the highest scrambling level, or the middle scrambling level.
  • the terminal device can also select the scrambling level based on some other information. For example, different types of data or data with different privacy levels correspond to different scrambling levels.
  • the terminal device can select the scrambling level according to the data type or privacy level of the target data. For example, the terminal device can select the corresponding scrambling level based on the current computing resources of the terminal device.
  • the terminal device can use a higher scrambling level; if the computing resources that the terminal device can currently use for scrambling are insufficient (for example, the resource utilization rate is higher than the preset threshold), then the terminal device can select a lower scrambling level.
  • the terminal device scrambles the target data using the scrambling level indicated in the scrambling policy.
  • some scrambling parameters such as scrambling level, scrambling algorithm, etc.
  • the terminal device may use the scrambling algorithm and scrambling level indicated in the scrambling policy to scramble data of the type of data that is leak-proof.
  • the scrambling strategy indication information may include multiple scrambling strategies.
  • the terminal device may select one of the multiple scrambling strategies as the target scrambling strategy, and use the target scrambling strategy to scramble the target data to obtain the scrambled data.
  • the terminal device may randomly select a scrambling strategy as the target scrambling strategy. For example, if the multiple scrambling strategies are all available to the terminal device, the terminal device may randomly select a scrambling strategy as the target scrambling strategy. For another example, if only some of the multiple scrambling strategies are available to the terminal device, the terminal device may randomly select an available scrambling strategy as the target scrambling strategy.
  • the terminal device may select the target scrambling strategy based on relevant information. For example, the terminal device may select the scrambling strategy based on any one or more information such as the data type, privacy level, and accuracy requirements of the corresponding AI model of the target data. For example, if the privacy level of the target data is high, the terminal device may select a complex scrambling strategy as the target scrambling strategy; if the privacy level of the target data is low, the terminal device may select a simple scrambling strategy as the target scrambling strategy.
  • the terminal device sends the scrambled data to the base station.
  • the base station receives the scrambled data from the terminal device.
  • the base station processes the scrambled data.
  • the base station can train the AI model based on the scrambled data; if the target data is the input data of the AI model, the base station can input the input data into the AI model to obtain the output data of the AI model (i.e., the inference prediction result).
  • the base station can directly process the scrambled data. If the AI module or the module in the AI module responsible for model training and/or data reasoning (such as the training module 102 and the model module 103 in FIG. 1 ) is located in other network devices (such as core network devices), the base station can send the scrambled data to the corresponding network device.
  • the AI module or the module in the AI module responsible for model training and/or data reasoning such as the training module 102 and the model module 103 in FIG. 1
  • the base station can send the scrambled data to the corresponding network device.
  • the base station may first determine whether the scrambled data can be processed normally, or whether the scrambled data can enable the corresponding AI model to maintain a reasoning accuracy higher than a threshold. If the base station cannot process the scrambled data normally, or the scrambled data causes the reasoning accuracy of the AI model to be lower than the threshold, the base station may send a re-scrambling indication message to the terminal device, and the re-scrambling indication message is used to instruct the terminal device to reselect a scrambling strategy to scramble the target data.
  • the re-scrambling indication information may only be used to instruct the terminal device to reselect a scrambling strategy to scramble the target data.
  • the terminal device may reselect a scrambling strategy. For example, a different scrambling level may be selected. For another example, another scrambling algorithm may be selected.
  • the base station may re-determine one or more scrambling strategies, and indicate the re-determined one or more scrambling strategies to the terminal device through the re-scrambling indication information.
  • the terminal device may select one from the one or more scrambling strategies indicated in the re-scrambling indication information to scramble the target data.
  • FIG3 is a schematic flowchart of another method for transmitting data provided according to an embodiment of the present application.
  • a base station obtains scrambling strategy indication information, where the scrambling strategy indication information is used to indicate a scrambling strategy used by the base station.
  • the scrambling strategy indication information may include the computing capability of the terminal device.
  • the computing power of the terminal device can be reflected by the chip model of the terminal device or the clock frequency of the chip.
  • the scrambling strategy indication information can include the chip signal of the terminal device or the clock frequency of the chip.
  • the chip referred to here is the chip in the terminal device responsible for scrambling the target data.
  • the chip that scrambles the target data can be a central processing unit (CPU), a system on chip (SoC), a network processor (NP), a microcontroller (MCU), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a programmable logic device (PLD), other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, or other integrated chips.
  • the computing capability of the terminal device may be reflected by the model of the terminal device.
  • the chips used by the devices have a corresponding relationship. For example, assuming that the terminal device is a mobile phone, after determining the model of the mobile phone, the chip used by the terminal device can be determined based on the corresponding relationship between the model and the chip. In this case, the scrambling strategy indication information can include the model of the terminal device.
  • the computing capability of the terminal device may be reflected by the type of the terminal device.
  • Different types of terminal devices have different computing capabilities. For example, the computing capability of a mobile phone is higher than that of a remote mobile POS machine, and the computing capability of a mobile POS machine is higher than that of a remote information collection device.
  • the scrambling strategy indication information may include the type of the terminal device.
  • the computing capability of the terminal device can be reflected by the available computing resources of the terminal device.
  • the available computing resources are computing resources in the terminal device that can be used to process scrambled data. For example, when the computing resources that the terminal device can use to process scrambled data are relatively small, the computing capability of the terminal device is relatively low; when the computing resources that the terminal device can use to process scrambled data are relatively large, the computing capability of the terminal device is relatively high.
  • the scrambling strategy indication information may also include the available budget resources of the terminal device.
  • the computing capability of the terminal device may be reflected by the current power of the terminal device. For example, when the current power of the terminal device is low, the computing capability of the terminal device is low; when the current power of the terminal device is high, the computing capability of the terminal device is high.
  • the scrambling strategy indication information may also include the current power of the terminal device.
  • the computing capability of the terminal device may be reflected by the scrambling algorithms supported by the terminal device.
  • Terminal devices with different computing capabilities support different scrambling algorithms and/or scrambling levels.
  • the scrambling strategy indication information may include the scrambling algorithms supported by the terminal device.
  • the scrambling strategy indication information may include one or more of the above information to reflect the computing capability of the terminal device.
  • the scrambling strategy indication information may include the scrambling algorithm supported by the terminal device and the current power of the terminal device.
  • the scrambling strategy indication information may include the device type of the terminal device and the available computing resources of the terminal device.
  • the base station can determine the model and/or device type of the terminal device through RRC messages obtained during the RRC connection process (for example, RRC recovery completion message, RRC establishment completion message, RRC reconstruction completion message, or RRC reconfiguration completion message), thereby determining the computing capability of the terminal device based on the model and/or device type of the terminal device.
  • RRC messages obtained during the RRC connection process (for example, RRC recovery completion message, RRC establishment completion message, RRC reconstruction completion message, or RRC reconfiguration completion message), thereby determining the computing capability of the terminal device based on the model and/or device type of the terminal device.
  • the scrambling algorithm supported by the terminal device has a corresponding relationship with the model or type of the terminal device.
  • the base station can save the corresponding relationship.
  • the base station can determine the model and/or device type of the terminal device through an RRC message, and then determine the scrambling algorithm supported by the terminal device based on the corresponding relationship.
  • the base station may send scrambling capability request information to the terminal device after the RRC connection is established, and the scrambling capability request information is used to request the scrambling capability of the terminal device. After receiving the scrambling capability request information, the terminal device may feed back the computing capability of the terminal device to the base station.
  • the scrambling capability request information may be carried by a UE capability request message (UE capability enquiry message).
  • the feedback information carrying the computing capability sent by the terminal device to the base station may be carried by a UE capability information (UE capability information message).
  • the base station when the base station is a split architecture, that is, the base station is split into CP and UP, and the CU is further split into CU-CP and CU-UP, and the CU-CP is further split into CU-CP1 and CU-CP2, CU-CP2 receives and decodes a message from a terminal device, and then CU-CP1 confirms whether the terminal device supports directly processing the encrypted downlink data.
  • the scrambling policy indication information may further include at least one of the following information: the accuracy requirement of the AI model corresponding to the scrambled data, the scrambling level, the storage capacity of the terminal device, or the data scrambling authority.
  • the base station scrambles the target data to obtain scrambled data.
  • the training process of the AI model can be implemented by a network-side device (such as a base station or other network-side device (such as a core network device, etc.)), but the trained model may be deployed in a terminal device.
  • the base station can scramble the parameters of the AI model and send them to the terminal device. Therefore, the target data may be the parameters of the AI model.
  • the parameters of the AI model include the parameters of the AI model, the structural information of the AI model, etc.
  • the parameters of a neural network may include one or more of the following: the number of network layers in the neural network, the order of each network layer, the weights, parameters or calculation formulas in each network layer, and other information.
  • the training and deployment of the AI model can be on the network side.
  • the base station can scramble the output data of the AI model and send it to the terminal device. Therefore, the target data can also be the output data of the AI model.
  • the output data can be specific reasoning results, policy indicators, etc.
  • the inference result may include energy-saving measures, duration, load thresholds for entering and exiting energy-saving states, etc.
  • the inference result may be the scanning beams of the k optimal scanning beams.
  • the inference result may be the intermediate results such as the LOS/NLOS state information derived by inference and the arrival time of the channel of the LOS path.
  • the base station can determine the accuracy requirement of the AI model, or obtain the accuracy requirement of the AI model from the network device that trained the AI model.
  • the scrambling level may correspond to the computing capability of the terminal device.
  • the base station may determine the scrambling level according to the corresponding relationship between the scrambling level and the computing capability after determining the computing capability of the terminal device.
  • the terminal device may also feed back the scrambling level to the base station while feeding back the computing capability.
  • the storage capacity of the terminal device may correspond to the computing capacity of the terminal device.
  • the base station may determine the storage capacity of the terminal device based on the corresponding relationship between the storage capacity of the terminal device and the computing capacity.
  • the terminal device may also feed back the storage capacity of the terminal device to the base station while feeding back the computing capacity.
  • the data scrambling authority is the control authority of the base station for whether the data needs to be scrambled.
  • the terminal device may determine that the base station does not need to scramble all or part of the target data of the terminal device.
  • the base station can obtain the control authority of the terminal device to decide whether the data needs to be scrambled. After obtaining the control authority, the base station can scramble the target data.
  • the data scrambling authority may include the type of data that needs to be scrambled that can be determined by the base station, or the privacy level that needs to be scrambled that can be determined by the base station. In other embodiments, the data scrambling authority can directly indicate that the base station can decide whether the data needs to be scrambled.
  • the data scrambling authority can be requested by the base station to the terminal device. If the terminal device determines that the data scrambling authority can be granted to the base station, then the terminal device can send the data scrambling authority to the base station. In other embodiments, the data scrambling authority can be determined by the model of the terminal device and/or the type of the terminal device. After determining the model of the terminal device and/or the type of the terminal device, the base station can determine the data scrambling authority based on the correspondence between the data scrambling authority and the type (or model) of the terminal device.
  • the base station scrambles the target data according to the scrambling strategy indication information to obtain scrambled data.
  • the base station may determine a scrambling strategy that matches the computing capability of the terminal device according to the computing capability of the terminal device.
  • the scrambling strategy may include a scrambling algorithm, a scrambling level, and the like.
  • the scrambling level in the scrambling strategy determined by the base station may be the same as the scrambling level in the scrambling strategy indication information.
  • the base station may determine the scrambling level in the scrambling strategy according to the type of target data to be scrambled and the scrambling level in the scrambling strategy indication information.
  • the scrambling level in the scrambling strategy indication information is referred to as the first scrambling level
  • the scrambling level in the scrambling strategy is referred to as the second scrambling level.
  • the first scrambling level may be the highest scrambling level that the base station can use.
  • the second scrambling level may be equal to or lower than the first scrambling level. For example, if the privacy level of the target data is low, the second scrambling level may be lower than the first scrambling level; if the privacy level of the target data is high, the second scrambling level may be equal to the first scrambling level.
  • the base station can select a suitable scrambling algorithm for the target data according to the accuracy requirement of the AI model and the computing power of the terminal device.
  • the base station may determine the target data that needs to be scrambled according to the data scrambling authority.
  • the base station sends the scrambled data to the terminal device.
  • the terminal device receives the scrambled data from the base station.
  • the scrambled data may be carried in an RRC reconfiguration message.
  • the terminal device processes the scrambled data.
  • the terminal device may set the AI model according to the scrambled data; if the target data is output data of the AI model, the terminal device may set relevant parameters of the terminal device according to the output data.
  • the terminal device may first determine whether it can process the scrambled data normally, or whether the scrambled data can enable the corresponding AI model to maintain a reasoning accuracy higher than a threshold. If the terminal device cannot process the scrambled data normally, or the scrambled data causes the reasoning accuracy of the AI model to be lower than the threshold, the terminal device may send a re-scrambling indication message to the base station, and the re-scrambling indication message is used to instruct the base station to reselect a scrambling strategy to scramble the target data.
  • FIG. 4 is a schematic flowchart of another method for transmitting data provided according to an embodiment of the present application.
  • the base station sends privacy level information to the terminal device.
  • the privacy level information can be used to indicate the privacy level of data (ie, target data) that needs to be scrambled by the base station and then sent to the terminal device.
  • the target data may be a parameter of an AI model or output data of an AI model.
  • different types of parameters, parameters of AI models in different scenarios, or different types of target data have different privacy requirements.
  • Table 3 shows the privacy requirements for different data.
  • the higher the value of the privacy level the higher the privacy level.
  • the target data is a parameter or output data of an AI model for beam management
  • the privacy level of the target data is higher than the parameter or output data of an AI model for CSI feedback enhancement
  • the target data is a parameter or output data of an AI model for load balancing
  • the privacy level of the target data is higher than the parameter or output data of an AI model for beam management
  • the target data is a parameter or output data of an AI model for mobility optimization
  • the privacy level of the target data is higher than the parameter or output data of an AI model for beam management.
  • the privacy level information may directly include the privacy level of the target data.
  • the target data is a parameter or output data of an AI model for mobility optimization of a base station
  • the privacy level information may directly include the privacy level corresponding to mobility optimization, i.e., privacy level 4.
  • the privacy level information may include the type of AI model of the target data.
  • the terminal device may determine the privacy level of the target data based on the correspondence between the privacy level and the AI model.
  • the privacy level information indicates that the target data is an AI model corresponding to the target data, which is an AI model for mobility optimization.
  • the terminal device may determine that the privacy level of the target data is 4 based on the correspondence between the privacy level and the AI model.
  • the privacy level information may include both the privacy level of the target data and the type of the AI model of the target data.
  • the privacy level information may be used to indicate the privacy level of the base station.
  • Table 4 shows the corresponding relationship between base station types and privacy levels.
  • a higher value of the privacy level indicates a higher privacy level.
  • the privacy level of the pico base station is higher than that of the femto base station
  • the privacy level of the pico base station is higher than that of the pico base station
  • the privacy level of the macro base station is higher than that of the pico base station. It is understood that the relationship between the privacy level and the device type shown in Table 4 and the total number of privacy levels are only illustrative and not limiting of the embodiments of the present application.
  • the privacy level information may directly include the privacy level of the base station.
  • the privacy level information may directly include the privacy level of the macro base station, that is, privacy level 4.
  • the privacy level information may include the type of the base station.
  • the terminal device may determine the privacy level of the target data based on the correspondence between the privacy level and the device type.
  • the privacy level information may indicate that the base station is a macro base station.
  • the terminal device may determine the privacy level of the target data based on the correspondence between the privacy level and the device type.
  • the privacy level of the type is 4.
  • the privacy level information may include both the privacy level of the base station and the type of the base station.
  • the privacy level information may be a dedicated piece of information. For example, after the base station establishes an RRC connection with the terminal device, if the base station needs to send scrambled data to the terminal device, the base station may send the privacy level information to the terminal device before sending the scrambled data.
  • the privacy level information may be a non-dedicated message.
  • the base station may send an RRC message (such as an RRC setup message, an RRC connection reestablishment message, an RRC configuration message, etc.) to the terminal device during the process of establishing an RRC connection with the terminal device, and the RRC message carries the type information of the base station.
  • the terminal device may determine the privacy level of the base station according to the type of base station carried by the RRC message.
  • the base station may send the privacy level information to the terminal device together with other information.
  • the base station may send the privacy level information to the terminal device together with the scrambling capability information of the base station.
  • the terminal device obtains the scrambling capability of the base station.
  • the scrambling capability of the base station includes at least one of the following information: the scrambling algorithm supported by the base station, the scrambling level supported by the base station, the scrambled data recovery capability of the base station, or the difference information between the target data and the scrambled data.
  • the scrambling capability of the base station is similar to the scrambling capability of the terminal device. For a specific description of the scrambling capability of the base station, please refer to the description of the scrambling capability of the terminal device in Figure 2, which will not be repeated here for the sake of brevity.
  • the terminal device determines scrambling strategy indication information.
  • the scrambling strategy indication information is used to indicate the scrambling strategy used by the base station.
  • the content and determination method of the scrambling strategy indication information are similar to those of the scrambling strategy indication information in the embodiment shown in FIG. 2 , and will not be described in detail for the sake of brevity.
  • the terminal device sends the scrambling strategy indication information to the base station.
  • the base station receives the scrambling strategy indication information from the terminal device.
  • the base station scrambles the target data according to the scrambling strategy indication information to obtain scrambled data.
  • the method by which the base station scrambles the target data is similar to the method by which the terminal device scrambles the target data in the embodiment of FIG. 2 , and for the sake of brevity, it will not be described in detail here.
  • the base station sends the scrambled data to the terminal device.
  • the terminal device receives the scrambled data from the base station.
  • the terminal device processes the scrambled data.
  • the specific method for the terminal device to process scrambled data is the same as the method for the terminal device to process scrambled data in the embodiment shown in Fig. 3. For the sake of brevity, it will not be described here.
  • FIG5 is a schematic flowchart of another method for transmitting data provided in the present application.
  • the terminal device obtains scrambling strategy indication information, where the scrambling strategy indication information is used to indicate the scrambling strategy used by the terminal device.
  • the scrambling strategy indication information may include the computing capability of the base station.
  • the computing capability of the base station may be reflected by the type of the base station. In some embodiments, the computing capability of the base station may be reflected by the type of the base station. Different types of base stations have different computing capabilities. For example, the computing capability of a macro base station is higher than that of a micro base station, and the computing capability of a micro base station is higher than that of a pico base station or a femto base station acquisition device. In this case, the scrambling strategy indication information may include the type of the base station.
  • the computing capability of the base station may be reflected by the available computing resources of the base station.
  • the available computing resources are computing resources in the base station that can be used to process scrambled data. For example, when the computing resources that the base station can use to process scrambled data are relatively small, the computing capability of the base station is relatively low; when the computing resources that the base station can use to process scrambled data are relatively large, the computing capability of the base station is relatively high.
  • the scrambling strategy indication information may also include the available budget resources of the base station.
  • the computing capability of the base station may be reflected by the scrambling algorithms supported by the base station.
  • Base stations with different computing capabilities support different scrambling algorithms and/or scrambling levels.
  • the scrambling strategy indication information may include the scrambling algorithms supported by the base station.
  • the scrambling strategy indication information may include one or more of the above information to reflect the computing capability of the base station.
  • the scrambling strategy indication information may include the scrambling algorithms supported by the base station and the current power of the base station.
  • the scrambling strategy indication information may include the device type of the base station and the available computing resources of the base station.
  • the terminal device may determine the type of the base station through an RRC message (e.g., an RRC establishment message, an RRC reconstruction message, or an RRC reconfiguration message) obtained during the RRC connection process, thereby determining the type of the base station according to the type of the base station.
  • RRC message e.g., an RRC establishment message, an RRC reconstruction message, or an RRC reconfiguration message
  • the scrambling algorithm supported by the base station has a corresponding relationship with the type of the base station.
  • the terminal device can save the corresponding relationship.
  • the terminal device can determine the type of the base station through an RRC message, and then determine the scrambling algorithm supported by the base station according to the corresponding relationship.
  • the terminal device may send scrambling capability request information to the base station after the RRC connection is established, and the scrambling capability request information is used to request the scrambling capability of the base station.
  • the base station may feed back the computing capability of the base station to the terminal device.
  • the scrambling strategy indication information may further include at least one of the following information: the accuracy requirement of the AI model corresponding to the scrambled data, the scrambling level, the storage capacity of the base station, or the data scrambling authority.
  • the accuracy requirement of the AI model corresponding to the scrambled data the scrambling level
  • the storage capacity of the base station or the data scrambling authority.
  • the terminal device scrambles the target data according to the scrambling strategy indication information to obtain scrambled data.
  • the specific implementation method of the terminal device scrambling the target data is similar to the specific implementation method of the base station scrambling the target data in the embodiment shown in Figure 3. For the sake of brevity, it will not be repeated here.
  • the terminal device sends the scrambled data to the base station.
  • the base station receives the scrambled data from the terminal device.
  • the base station processes the scrambled data.
  • the specific implementation method of the base station processing scrambled data is similar to the specific implementation method of the base station processing scrambled data in the embodiment shown in FIG. 2 , and will not be described again for the sake of brevity.
  • the network device in the above embodiment is described by taking the base station as an example.
  • the various steps performed by the base station in the above embodiment can also be implemented by other network devices (such as management entities, core network devices, etc.).
  • the management entity can obtain the scrambling capability of the terminal device and determine the scrambling policy indication information, and the management entity sends the determined scrambling policy indication information to the terminal device through the base station; the terminal device determines the scrambled data according to the scrambling policy indication information, and then sends the scrambled data to the management entity through the base station.
  • FIG6 is a schematic structural block diagram of a communication device provided according to an embodiment of the present application.
  • the communication device 600 includes an acquisition unit 601 , a scrambling unit 602 and a sending unit 603 .
  • the acquisition unit 601 is used to acquire scrambling indication information, where the scrambling indication information is used to indicate a scrambling strategy used by the communication device 600.
  • the scrambling unit 601 is used to scramble the target data according to the scrambling strategy indication information to obtain scrambled data, wherein the target data is data used for the AI model.
  • the sending unit 603 is configured to send the scrambled data to another communication device.
  • the communication device 600 may be a terminal device or a component in a terminal device (eg, a chip, a chip system, etc.).
  • the communication device 600 may be a network device or a component in a network device (eg, a chip, a chip system, etc.).
  • the acquisition unit 601 and the scrambling unit 602 may be implemented by a processor or a logic circuit, and the sending unit 603 may be implemented by a transmitter or an input/output interface.
  • FIG7 is a schematic structural block diagram of another communication device provided according to an embodiment of the present application.
  • the communication device 700 includes a processing unit 701 , a sending unit 702 and a receiving unit 703 .
  • the processing unit 701 is used to determine scrambling strategy indication information, where the scrambling strategy indication information is used to indicate a scrambling strategy used by another communication device.
  • the sending unit 702 is configured to send the scrambling strategy indication information to the other communication device.
  • the receiving unit 703 is configured to receive scrambled data from the other communication device.
  • the processing unit 701 is further configured to determine the data of the AI model according to the scrambled data.
  • the communication device 700 may be a terminal device or a component in a terminal device (eg, a chip, a chip system, etc.).
  • the communication device 700 may be a network device or a component in a network device (eg, a chip, a chip system, etc.).
  • the processing unit 701 may be implemented by a processor or a logic circuit, and the sending unit 702 and the receiving unit 703 may be implemented by a transmitter or an input/output interface.
  • processing unit 701 the sending unit 702 and the receiving unit 703 can be found in the above embodiments, and will not be described again here for the sake of brevity.
  • FIG8 shows a simplified schematic diagram of the structure of a terminal device.
  • a mobile phone is used as an example of a terminal device.
  • the terminal device includes a processor, a memory, a radio frequency circuit, an antenna, and an input/output device.
  • the processor is mainly used to process communication protocols and communication data, as well as to control the terminal device, execute software programs, process software program data, etc.
  • the memory is mainly used to store software programs and data.
  • the radio frequency circuit is mainly used for conversion between baseband signals and radio frequency signals and processing of radio frequency signals.
  • the antenna is mainly used to transmit and receive radio frequency signals in the form of electromagnetic waves.
  • Input/output devices such as touch screens, display screens, keyboards, etc., are mainly used to receive data input by users and output data to users. It should be noted that some types of terminal devices may not have input/output devices.
  • the processor When data needs to be sent, the processor performs baseband processing on the data to be sent, and then outputs the baseband signal to the RF circuit.
  • the RF circuit performs RF processing on the baseband signal and then sends the RF signal outward in the form of electromagnetic waves through the antenna.
  • the RF circuit receives the RF signal through the antenna, converts the RF signal into a baseband signal, and outputs the baseband signal to the processor.
  • the processor converts the baseband signal into data and processes the data.
  • FIG8 only one memory and processor are shown in FIG8. In an actual terminal device product, there may be one or more processors and one or more memories.
  • the memory may also be referred to as a storage medium or a storage device, etc.
  • the memory may be set independently of the processor or integrated with the processor, and the embodiments of the present application do not limit this.
  • the antenna and the radio frequency circuit with transceiver functions can be regarded as the transceiver unit of the terminal device, and the processor with processing function can be regarded as the processing unit of the terminal device.
  • the terminal device includes a radio frequency circuit 810, a processor 820, and a memory 830.
  • the radio frequency circuit 810 may also be referred to as a transceiver unit, a transceiver module, a transceiver, a transceiver, a transceiver device, etc.
  • the processor 820 may also be referred to as a processing unit, a processing board, a processing module, a processing device, etc.
  • the device used to implement the receiving function in the radio frequency circuit 810 may be regarded as a receiving unit
  • the device used to implement the sending function in the radio frequency circuit 810 may be regarded as a sending unit, that is, the radio frequency circuit 810 includes a receiving unit and a sending unit.
  • the radio frequency circuit 810 may sometimes also be referred to as a transceiver unit, a transceiver, a transceiver, or a transceiver circuit, etc.
  • the receiving unit may sometimes also be referred to as a receiver, a receiver, or a receiving circuit, etc.
  • the sending unit may sometimes also be referred to as a transmitter, a transmitter, or a transmitting circuit, etc.
  • the memory 830 is used to store instructions and/or program codes.
  • the processor 820 reads and executes the instructions and/or codes stored in the memory 830, and implements the steps in the above method embodiment in combination with the radio frequency circuit 810.
  • the processor 820 is used to execute step 205 in FIG. 2, and the processor 820 is also used to execute other processing steps on the terminal device side in the embodiment of the present application.
  • the RF circuit 810 is also used to execute step 204 shown in FIG. 2, and the RF circuit 810 is also used to execute other transceiver steps on the terminal device side.
  • the processor 820 is used to execute step 304 in Fig. 3.
  • the RF circuit 810 is also used to execute step 303 shown in Fig. 3.
  • the processor 820 is used to execute step 403 in Figure 4, and the processor 820 is also used to execute other processing steps on the terminal device side in the embodiment of the present application.
  • the RF circuit 810 is also used to execute step 404 shown in Figure 4, and the RF circuit 810 is also used to execute other transceiver steps on the terminal device side.
  • the processor 820 is used to execute step 501 in Figure 5, and the processor 820 is also used to execute other processing steps on the terminal device side in the embodiment of the present application.
  • the RF circuit 810 is also used to execute step 503 shown in Figure 5.
  • FIG8 is merely an example and not a limitation, and the terminal device including the RF circuit 810, the processor 820 and the memory 830 may not rely on the structure shown in FIG8.
  • FIG9 shows a simplified schematic diagram of the network device structure.
  • the network device includes a portion 910 and a portion 920.
  • the portion 910 is mainly used for receiving and transmitting radio frequency signals and converting radio frequency signals into baseband signals; the portion 920 is mainly used for baseband processing, controlling the network device, etc.
  • the portion 920 is usually the control center of the network device, which is used to control the network device to perform the processing operations on the network device side in the above method embodiment.
  • the transceiver unit of part 910 may also be referred to as a transceiver or a transceiver, etc., and includes an antenna and a radio frequency unit, wherein the radio frequency unit is mainly used for radio frequency processing.
  • the device used to implement the receiving function in part 910 may be regarded as a receiving unit
  • the device used to implement the sending function may be regarded as a sending unit, that is, part 910 includes a receiving unit and a sending unit.
  • the receiving unit may also be referred to as a receiver, a receiver, or a receiving circuit, etc.
  • the sending unit may be referred to as a transmitter, a transmitter, or a transmitting circuit, etc.
  • Part 920 may include one or more boards, each of which may include one or more processors and one or more memories.
  • the processor is used to read and execute programs in the memory to implement baseband processing functions and control network devices. If there are multiple boards, each board can be interconnected to enhance processing capabilities. As an optional implementation, multiple boards may share one or more processors. processors, or multiple boards share one or more memories, or multiple boards share one or more processors at the same time.
  • the device of part 910 is used to execute step 204 shown in Figure 2, and the transceiver unit of part 910 is also used to execute other transceiver steps on the network device side in the embodiment of the present application.
  • the processor of part 920 is used to execute the processing operation of step 203 in Figure 2, and the processor of part 920 is also used to execute the processing steps on the network device side in the embodiment of the present application.
  • the device of part 910 is used to execute step 303 shown in Figure 3.
  • the processor of part 920 is used to execute the processing operation of step 302 in Figure 3, and the processor of part 920 is also used to execute the processing steps on the network device side in the embodiment of the present application.
  • the device of part 910 is used to execute step 504 shown in Figure 4, and the transceiver unit of part 910 is also used to execute other transceiver steps on the network device side in the embodiment of the present application.
  • the processor of part 920 is used to execute the processing operation of step 405 in Figure 4.
  • the device in part 910 is used to execute step 503 shown in FIG. 5 .
  • the processor in part 920 is used to execute the processing operation of step 504 in FIG. 5 .
  • FIG. 9 is merely an example and not a limitation, and the network device including the transceiver unit and the processing unit may not rely on the structure shown in FIG. 9 .
  • the network device is not limited to the above-mentioned forms, but may also be in other forms: for example, CU and DU separation architecture, or other forms, which are not limited in this application.
  • the processor can be a chip.
  • the processor can be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or other integrated chips.
  • FPGA field programmable gate array
  • ASIC application specific integrated circuit
  • SoC system on chip
  • CPU central processor unit
  • NP network processor
  • DSP digital signal processor
  • MCU microcontroller unit
  • PLD programmable logic device
  • each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software.
  • the steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution.
  • the software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc.
  • the storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.
  • the processor in the embodiment of the present application can be an integrated circuit chip with signal processing capabilities.
  • each step of the above method embodiment can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software.
  • the general processor can be a microprocessor or the processor can also be any conventional processor, etc.
  • the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor to be executed.
  • the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc.
  • the storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
  • the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.
  • the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.
  • the volatile memory can be a random access memory (RAM), which is used as an external cache.
  • RAM random access memory
  • SRAM static RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDR SDRAM double data rate SDRAM
  • ESDRAM enhanced SDRAM
  • SLDRAM synchlink DRAM
  • DR RAM direct rambus RAM
  • the present application also provides a computer program product, which includes: a computer program code, when the computer program code is run on a computer, the computer executes the above embodiment by the terminal device The various steps performed.
  • the present application also provides a computer-readable medium, which stores a program code.
  • the program code runs on a computer, the computer executes the various steps performed by the terminal device in the above embodiment.
  • an embodiment of the present application provides a chip system, which includes a logic circuit, which is used to couple with an input/output interface and transmit data through the input/output interface to execute the various steps performed by the terminal device in the above embodiment.
  • the present application also provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes each step performed by the network device in the above embodiment.
  • the present application also provides a computer-readable medium, which stores a program code.
  • the program code runs on a computer, the computer executes each step performed by the network device in the above embodiment.
  • an embodiment of the present application provides a chip system, which includes a logic circuit, which is used to couple with an input/output interface and transmit data through the input/output interface to execute the various steps performed by the network device in the above embodiment.
  • the embodiment of the present application also provides a system, including a network device and one or more terminal devices.
  • the disclosed systems, devices and methods can be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.
  • Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple 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.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art.
  • the computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Bioethics (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Power Engineering (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请实施例涉及人工智能领域。本申请实施例提供了一种传输数据的方法和相关装置。该方法包括：第一通信设备获取加扰策略指示信息，该加扰策略指示信息用于指示该第一通信设备使用的加扰策略；该第一通信设备根据该加扰策略指示信息，对人工智能AI模型的数据进行加扰，得到加扰数据；该第一通信设备向第二通信设备发送该加扰数据。上述技术方案中，通信设备间传输隐私数据时可以对该AI模型中的数据进行加扰，这样可以保证AI模型中的数据的传输安全。

Description

传输数据的方法和相关装置
申请要求于2022年09月27日提交中国专利局、申请号为202211184806.1、申请名称为“传输数据的方法和相关装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及人工智能领域，尤其涉及人工智能技术在通信技术领域的应用，更具体地，涉及传输数据的方法和相关装置。
背景技术
人工智能(Artificial Intelligence,AI)是利用数字计算机或者数字计算机控制的机器模拟、延伸和扩展人的智能，感知环境、获取知识并使用知识获得最佳结果的理论、方法、技术及应用系统。换句话说，人工智能是计算机科学的一个分支，它企图了解智能的实质，并生产出一种新的能以人类智能相似的方式作出反应的智能机器。人工智能也就是研究各种智能机器的设计原理与实现方法，使机器具有感知、推理与决策的功能。人工智能领域的研究包括机器人，自然语言处理，计算机视觉，决策与推理，人机交互，推荐与搜索，AI基础理论等。
发明内容
本申请实施例提供一种传输数据的方法和相关装置，可以对AI模型中的数据进行加扰，从而保证AI模型的数据的传输安全。
第一方面，本申请实施例提供一种传输数据的方法，该方法包括：第一通信设备获取加扰策略指示信息，该加扰策略指示信息用于指示该第一通信设备使用的加扰策略；该第一通信设备根据该加扰策略指示信息，对目标数据进行加扰，得到加扰数据，其中，该目标数据是用于AI模型的数据；该第一通信设备向第二通信设备发送该加扰数据。
上述技术方案中，通信设备间传输隐私数据时可以对该AI模型中的数据进行加扰，这样可以保证AI模型中的数据的传输安全。
在一些实施例中，该第一通信设备和该第二通信设备可以是移动通信网络中的通信设备。例如，该第一通信设备可以是终端设备，该第二通信设备可以是网络设备。又如，该第一通信设备可以是网络设备，该第二通信设备可以是终端设备。
在该第一通信设备是网络设备且该第二通信设备是终端设备的情况下，该目标数据包括以下数据中的至少一种：该AI模型的参数，或者，该AI模型的输出数据。
AI模型的训练过程可能涉及到大量的数据，这些数据可能是组织、机构或者公司通过很大的代价获得并处理的，然后经过大量的时间和金钱来训练AI模型得到相关参数。因此，一旦这些AI模型的参数被泄露，可能对这些组织、机构或者公司带来巨大的损失。利用上述技术方案通过对AI模型的参数以及AI模型的输出数据进行加扰，可以保护这些AI模型的数据在传输过程中的安全。
在该第一通信设备是终端设备且该第二通信设备是网络设备的情况下，该目标数据是该AI模型的输入数据，或者，该目标数据是用于训练该AI模型的训练数据。
AI模型的输入数据或训练数据通常会包含用户的隐私数据。上述技术方案对这些数据进行加扰，从而在数据传输过程中保护用户的隐私数据。
结合第一方面，在第一方面的一种可能的实现方式中，该加扰策略指示信息具体用于指示该第二通信设备的计算能力。
利用上述技术方案，第一通信设备可以根据第二通信设备的计算能力确定加扰策略，这样可以使得确定的加扰策略能够适用于该第二通信设备，以便该第二通信设备可以使用该第一通信设备确定的加扰数据。
结合第一方面，在第一方面的一种可能的实现方式中，该加扰策略指示信息，还用于指示以下信息中的至少一种：对应于该加扰数据的AI模型的精确度需求、加扰等级、该第二通信设备的存储能力，或者，数据加扰权限。
上述技术方案中的加扰策略指示信息进一步指示了第二通信设备的能力信息。这样更便于该第一通信设备确定能够适用于该第二通信设备加扰策略。
结合第一方面，在第一方面的一种可能的实现方式中，该加扰策略指示信息具体用于指示至少一个加扰策略，其中该加扰策略包括：加扰算法。
上述技术方案中的加扰策略指示信息可以是第二通信设备发送给第一通信设备的。因此，利用上述技术方案，该第一通信设备可以直接使用加扰策略指示信息中所指示的加扰策略，而无需再花费运算资源来确定加扰策略。此外，该加扰策略指示信息所指示的加扰策略能够被该第二通信设备支持。因此，上述技术方案可以避免第一通信设备确定的加扰策略不被第二通信设备支持的情况发生。
结合第一方面，在第一方面的一种可能的实现方式中，该加扰策略还包括以下信息中的至少一种：加扰等级、对应于该加扰数据的AI模型的精确度需求，或者，防泄漏的数据类型。
上述技术方案中的加扰策略指示信息进一步指示了加扰策略的具体参数。这样更便于该第一通信设备确定加扰策略。
结合第一方面，在第一方面的一种可能的实现方式中，当该加扰策略指示信息用于指示多个加扰策略时，该第一通信设备根据该加扰策略指示信息，对目标数据进行加扰，包括：该第一通信设备从该多个加扰策略中确定目标加扰策略；该第一通信设备根据该目标加扰策略对该目标数据进行加扰。
结合第一方面，在第一方面的一种可能的实现方式中，在该第一通信设备获取加扰策略指示信息之前，该方法还包括：该第一通信设备向第二通信设备发送加扰能力指示信息，该加扰能力指示信息用于指示以下信息中的至少一种：该第一通信设备支持的加扰算法、该第一通信设备支持的加扰等级、该第一通信设备的加扰数据恢复能力，或者，该目标数据与该加扰数据的差异信息。
上述技术方案中，该第一通信设备可以将该第一通信设备的能力信息发送给第二通信设备，这样可以便与该第二通信设备确定能够被第一通信设备支持的加扰策略，并将确定的加扰策略发送给该第一通信设备。
结合第一方面，在第一方面的一种可能的实现方式中，在该第一通信设备获取加扰策略指示信息之前，该方法还包括：该第一通信设备向该第二通信设备发送隐私等级信息，该隐私等级信息用于指示该目标数据和/或该第一通信设备的隐私等级。
上述技术方案中，该第一通信设备可以将该隐私等级发送给第二通信设备，这样可以便与该第二通信设备根据隐私等级选择合适的加扰策略。例如，隐私等级较低的数据或通信设备可以选择较为简单的加扰算法；隐私等级较高的数据或通信设备可以选择较为复杂的加扰算法。这样，可以降低第一通信设备对隐私等级较低的目标数据进行加扰时消耗的运算资源。
第二方面，本申请实施例提供一种传输数据的方法，该方法包括：第二通信设备确定加扰策略指示信息，该加扰策略指示信息用于指示第一通信设备使用的加扰策略；该第二通信设备向该第一通信设备发送该加扰策略指示信息；该第二通信设备接收来自于该第一通信设备的加扰数据；该第二通信设备根据该加扰数据，确定AI模型的数据。
上述技术方案中，通信设备间传输隐私数据时可以对AI模型中的数据进行加扰，这样可以保证AI模型中的数据的传输安全。
在一些实施例中，该第一通信设备和该第二通信设备可以是移动通信网络中的通信设备。例如，该第一通信设备可以是终端设备，该第二通信设备可以是网络设备。又如，该第一通信设备可以是网络设备，该第二通信设备可以是终端设备。
在该第一通信设备是网络设备且该第二通信设备是终端设备的情况下，该第二通信设备根据该加扰数据，确定AI模型的数据，包括：该第二通信设备数据根据该加扰数据确定该AI模型的参数或者该AI模型的输出数据。
AI模型的训练过程可能涉及到大量的数据，这些数据可能是组织、机构或者公司通过很大的代价获得并处理的，然后经过大量的时间和金钱来训练AI模型得到相关参数。因此，一旦这些AI模型的参数被泄露，可能对这些组织、机构或者公司带来巨大的损失。利用上述技术方案通过对AI模型的参 数以及AI模型的输出数据进行加扰，可以保护这些AI模型的数据在传输过程中的安全。
在该第一通信设备是终端设备且该第二通信设备是网络设备的情况下，该第二通信设备根据该加扰数据，确定AI模型的数据，包括：该第二通信设备数据根据该加扰数据确定该AI模型的输入数据，或者，用于训练该AI模型的训练数据。
AI模型的输入数据或训练数据通常会包含用户的隐私数据。上述技术方案对这些数据进行加扰，从而在数据传输过程中保护用户的隐私数据。
结合第二方面，在第二方面的一种可能的实现方式中，该加扰策略指示信息具体用于指示该第二通信设备的计算能力。
利用上述技术方案，第一通信设备可以根据第二通信设备的计算能力确定加扰策略，这样可以使得确定的加扰策略能够适用于该第二通信设备，以便该第二通信设备可以使用该第一通信设备确定的加扰数据。
结合第二方面，在第二方面的一种可能的实现方式中，该加扰策略指示信息，还用于指示以下信息中的至少一种：该AI模型的精确度需求、加扰等级、该第二通信设备的存储能力，或者，数据加扰权限。
上述技术方案中的加扰策略指示信息进一步指示了第二通信设备的能力信息。这样更便于该第一通信设备确定能够适用于该第二通信设备加扰策略。
结合第二方面，在第二方面的一种可能的实现方式中，该加扰策略指示信息具体用于指示至少一个加扰策略，其中该加扰策略包括：加扰算法。
上述技术方案中的加扰策略指示信息可以是第二通信设备发送给第一通信设备的。因此，利用上述技术方案，该第一通信设备可以直接使用加扰策略指示信息中所指示的加扰策略，而无需再花费运算资源来确定加扰策略。此外，该加扰策略指示信息所指示的加扰策略能够被该第二通信设备支持。因此，上述技术方案可以避免第一通信设备确定的加扰策略不被第二通信设备支持的情况发生。
结合第二方面，在第二方面的一种可能的实现方式中，该加扰策略还包括以下信息中的至少一种：加扰等级、该AI模型的精确度需求，或者，防泄漏的数据类型。
上述技术方案中的加扰策略指示信息进一步指示了加扰策略的具体参数。这样更便于该第一通信设备确定加扰策略。
结合第二方面，在第二方面的一种可能的实现方式中，在该第二通信设备确定加扰策略指示信息之前，该方法还包括：该第二通信设备接收来自于第一通信设备加扰能力指示信息，该加扰能力指示信息用于指示以下信息中的至少一种：该第一通信设备支持的加扰算法、该第一通信设备支持的加扰等级、该第一通信设备的加扰数据恢复能力，或者，需要加扰的数据与该加扰数据的差异信息；该第二通信设备确定加扰策略指示信息，包括：该第二通信设备根据该加扰能力指示信息，确定该加扰策略指示信息。
上述技术方案中，该第一通信设备可以将该第一通信设备的能力信息发送给第二通信设备，这样可以便与该第二通信设备确定能够被第一通信设备支持的加扰策略，并将确定的加扰策略发送给该第一通信设备。
结合第二方面，在第二方面的一种可能的实现方式中，在该第二通信设备确定加扰策略指示信息之前，该方法还包括：该第二通信设备接收来自于该第一通信设备的隐私等级信息，该隐私等级信息用于指示该加扰数据和/或该第一通信设备的隐私等级；该第二通信设备根据该加扰能力指示信息，确定该加扰策略指示信息，包括：该第二通信设备根据该加扰能力指示信息和该隐私等级信息，确定该加扰策略指示信息。
上述技术方案中，该第一通信设备可以将该隐私等级发送给第二通信设备，这样可以便与该第二通信设备根据隐私等级选择合适的加扰策略。例如，隐私等级较低的数据或通信设备可以选择较为简单的加扰算法；隐私等级较高的数据或通信设备可以选择较为复杂的加扰算法。这样，可以降低第一通信设备对隐私等级较低的目标数据进行加扰时消耗的运算资源。
第三方面，本申请实施例提供一种通信设备，该通信设备包括用于实现第一方面或第一方面的任一种可能的实现方式的单元。
第四方面，本申请实施例提供一种通信设备，该通信设备包括用于实现第二方面或第二方面的任 一种可能的实现方式的单元。
第五方面，本申请实施例提供一种通信设备，该通信设备包括处理器，该处理器用于与存储器耦合，读取并执行该存储器中的指令和/或程序代码，以执行第一方面或第一方面的任一种可能的实现方式。
第六方面，本申请实施例提供一种通信设备，该通信设备包括处理器，该处理器用于与存储器耦合，读取并执行该存储器中的指令和/或程序代码，以执行第二方面或第二方面的任一种可能的实现方式。
第七方面，本申请实施例提供一种芯片系统，该芯片系统包括逻辑电路，该逻辑电路用于与输入/输出接口耦合，通过该输入/输出接口传输数据，以执行第一方面或第一方面任一种可能的实现方式。
第八方面，本申请实施例提供一种芯片系统，该芯片系统包括逻辑电路，该逻辑电路用于与输入/输出接口耦合，通过该输入/输出接口传输数据，以执行第二方面或第二方面任一种可能的实现方式。
第九方面，本申请实施例提供一种计算机可读存储介质，该计算机可读存储介质存储有程序代码，当该计算机存储介质在计算机上运行时，使得计算机执行如第一方面或第一方面的任一种可能的实现方式。
第十方面，本申请实施例提供一种计算机可读存储介质，该计算机可读存储介质存储有程序代码，当该计算机存储介质在计算机上运行时，使得计算机执行如第二方面或第二方面的任一种可能的实现方式。
第十一方面，本申请实施例提供一种计算机程序产品，该计算机程序产品包括：计算机程序代码，当该计算机程序代码在计算机上运行时，使得该计算机执行如第一方面或第一方面的任一种可能的实现方式。
第十二方面，本申请实施例提供一种计算机程序产品，该计算机程序产品包括：计算机程序代码，当该计算机程序代码在计算机上运行时，使得该计算机执行如第二方面或第二方面的任一种可能的实现方式。
附图说明
图1是本申请实施例提供的一种AI模块的示意图。
图2是根据本申请实施例提供的一种传输数据的方法的示意性流程图。
图3是根据本申请实施例提供的另一传输数据的方法的示意性流程图。
图4是根据本申请实施例提供的另一种传输数据的方法的示意性流程图。
图5是根据本申请实施例提供的另一传输数据的方法的示意性流程图。
图6是根据本申请实施例提供的一种通信设备的示意性结构框图。
图7是根据本申请实施例提供的另一通信设备的示意性结构框图。
图8示出了一种终端设备的结构示意图。
图9示出了一种网络设备结构示意图。
具体实施方式
下面将结合附图，对本申请实施例中的技术方案进行描述。
以下实施例中所使用的术语只是为了描述特定实施例的目的，而并非旨在作为对本申请的限制。如在本申请的说明书和所附权利要求书中所使用的那样，单数表达形式“一个”、“一种”和“该”旨在包括例如“一个或多个”这种表达形式，除非其上下文中明确地有相反指示。还应当理解，在本申请以下各实施例中，“至少一个”、“至少一项”、“一个或多个”是指一个、两个或两个以上。“第一”、“第二”以及各种数字编号只是为了描述方便进行的区分，并不用来限制本申请实施例的范围。“和/或”，用于描述对应对象的对应关系，表示可以存在三种关系，例如，“A和/或B”可以表示：只存在A，只存在B以及同时存在A和B三种情况，其中A，B可以是单数或复数。字符“/”一般表示前后关联对象是一种“或”的关系。下文各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。例如，本申请实施例中，“301”、“401”、“501”等字样仅为了描述方便作出的标识，并不是对执行步骤的次序进行限定。
在本说明书中描述的参考“一个实施例”或“一些实施例”等意味着在本申请的一个或多个实施例中包括结合该实施例描述的特定特征、结构或特点。本申请中，“示例性的”或者“例如”等词用于表示作例子、例证或说明。本申请中被描述为“示例性的”或者“例如”的任何实施例或设计方案不应被解释为比其他实施例或设计方案更优选或更具优势。确切而言，使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念。术语“包括”、“包含”、“具有”及它们的变形都意味着“包括但不限于”，除非是以其他方式另外特别强调。在本申请实施例中，“当……时”、“在……的情况下”、“若”以及“如果”等描述均指在某种客观情况下设备会做出相应的处理，并非是限定时间，且也不要求设备在实现时一定要有判断的动作，也不意味着存在其它限定。
在本申请中，“用于指示”可以包括用于直接指示和用于间接指示。当描述某一指示信息用于指示A时，可以包括该指示信息直接指示A或间接指示A，而并不代表该指示信息中一定携带有A。在本申请实施例中，“当……时”、“在……的情况下”、“若”以及“如果”等描述均指在某种客观情况下设备会做出相应的处理，并非是限定时间，且也不要求设备在实现时一定要有判断的动作，也不意味着存在其它限定。
本申请实施例的技术方案可以应用于各种通信系统，例如：长期演进(long term evolution，LTE)系统、LTE频分双工(frequency division duplex，FDD)系统、LTE时分双工(time division duplex，TDD)、通用移动通信系统(universal mobile telecommunication system，UMTS)、全球互联微波接入(worldwide interoperability for microwave access，Wi-MAX)通信系统、第五代(5th generation，5G)系统或新空口(new radio，NR)、未来的第六代(6th generation，6G)系统、星间通信和卫星通信等非陆地通信网络(non-terrestrial network，NTN)系统。卫星通信系统包括卫星基站以及终端设备。该卫星基站为终端设备提供通信服务。卫星基站也可以与基站进行通信。卫星可作为基站，也可作为终端设备。其中，卫星可以是指无人机，热气球，低轨卫星，中轨卫星，高轨卫星等。卫星也可以是指非地面基站或非地面设备等。
本申请的实施例可以应用于终端设备。终端设备可以是无线终端也可以是有线终端，无线终端可以是指向用户提供语音和/或数据连通性的设备，具有无线连接功能的手持式设备、或连接到无线调制解调器的其他处理设备。无线终端可以经无线接入网(radio access cetwork；缩写：RAN)与一个或多个核心网进行通信，无线终端可以是移动终端，如移动电话(或称为“蜂窝”电话)和具有移动终端的计算机，例如，可以是便携式、袖珍式、手持式、计算机内置的或者车载的移动装置，它们与无线接入网交换语言和/或数据。例如，个人通信业务(personal communication service，PCS)电话、无绳电话、会话发起协议(session initiation protocol，SIP)话机、无线本地环路(wireless local loop，WLL)站、个人数字助理(personal digital assistant，PDA)等设备。无线终端也可以称为系统、订户单元(subscriber unit，SU)、订户站(subscriber station，SS)，移动站(mobile station，MB)、移动台(mobile)、远程站(remote station，RS)、接入点(access point，AP)、远程终端(remote terminal，RT)、接入终端(access terminal，AT)、用户终端(user terminal，UT)、用户代理(user agent，UA)、终端设备(user device，UD)、或用户装备(user equipment，UE)。
本申请实施例中用于实现终端设备的功能的装置可以是终端设备；也可以是能够支持终端设备实现该功能的装置，例如芯片系统。该装置可以被安装在终端设备中或者和终端设备匹配使用。本申请实施例中，芯片系统可以由芯片构成，也可以包括芯片和其他分立器件。
本申请实施例中的技术方案还可以应用于接入网设备。接入网设备可以是能够将终端设备接入到无线网络的设备。该接入网设备还可以称为无线接入网(radio access network，RAN)节点、无线接入网设备、网络设备。示例性的，该接入网设备可以是基站。
本申请实施例中的基站可以广义的覆盖如下中的各种名称，或与如下名称进行替换，比如：节点B(NodeB)、演进型基站(evolved NodeB，eNB)、5G网络中的基站gNB、中继站、接入点、收发点(transmitting and receiving point，TRP)、发射点(transmitting point，TP)、主站(master eNodeB，MeNB)、辅站(secondary eNodeB，SeNB)、多制式无线(multi standard radio，MSR)节点、家庭基站、网络控制器、接入节点、无线节点、接入点(access point，AP)、传输节点、收发节点、基带单元(base band unit，BBU)、射频拉远单元(remote radio unit，RRU)、有源天线单元(active antenna unit，AAU)、射频头(remote radio head，RRH)、定位节点等。基站可以是宏基站、微基站、中继节点、 施主节点或类似物，或其组合。基站还可以指用于设置于前述设备或装置内的通信模块、调制解调器或芯片。基站还可以是6G网络中的网络侧设备、未来的通信系统中承担基站功能的设备等。基站可以支持相同或不同接入技术的网络。
基站可以是集中式单元(centralized unit，CU)和分布式单元(distributed unit，DU)分离架构。RAN可以与核心网相连(例如可以是长期演进(long term evolution，LTE)的核心网，也可以是5G的核心网等)。CU和DU可以理解为是对基站从逻辑功能角度的划分。CU和DU在物理上可以是分离的也可以部署在一起。多个DU可以共用一个CU。一个DU也可以连接多个CU。CU和DU之间可以通过接口相连，例如可以是F1接口。CU和DU可以根据无线网络的协议层划分。例如其中一种可能的划分方式是：CU用于执行无线资源控制(radio resource control，RRC)层、业务数据适配协议(service data adaptation protocol，SDAP)层以及分组数据汇聚层协议(packet data convergence protocol，PDCP)层的功能，而DU用于执行无线链路控制(radio link control，RLC)层，媒体接入控制(media access control，MAC)层，物理(physical)层等的功能。可以理解对CU和DU处理功能按照这种协议层的划分仅仅是一种举例，也可以按照其他的方式进行划分。例如可以将CU或者DU划分为具有更多协议层的功能。例如，CU或DU还可以划分为具有协议层的部分处理功能。在一设计中，将RLC层的部分功能和RLC层以上的协议层的功能设置在CU，将RLC层的剩余功能和RLC层以下的协议层的功能设置在DU。在另一种设计中，还可以按照业务类型或者其他系统需求对CU或者DU的功能进行划分。例如按时延划分，将处理时间需要满足时延要求的功能设置在DU，不需要满足该时延要求的功能设置在CU。在另一种设计中，CU也可以具有核心网的一个或多个功能。一个或者多个CU可以集中设置，也分离设置。例如CU可以设置在网络侧方便集中管理。DU可以具有多个射频功能，也可以将射频功能拉远设置。
CU的功能可以由一个实体来实现也可以由不同的实体实现。例如，可以对CU的功能进行进一步切分，例如，将控制面(control plane，CP)和用户面(user plane，UP)分离，即CU的控制面(CU-CP)和CU用户面(CU-UP)。例如，CU-CP和CU-UP可以由不同的功能实体来实现，并通过E1接口相连，所述CU-CP和CU-UP可以与DU相耦合，共同完成基站的功能。CU的控制面CU-CP还包括一种进一步切分的架构，即把现有的CU-CP进一步切分为CU-CP1和CU-CP2。其中CU-CP1包括各种无线资源管理功能，CU-CP2仅包括RRC功能和PDCP-C功能(即控制面信令在PDCP层的基本功能)。
基站可以是固定的，也可以是移动的。例如，直升机或无人机可以被配置成充当移动基站，一个或多个小区可以根据该移动基站的位置移动。在其他示例中，直升机或无人机可以被配置成用作与另一基站通信的设备。
操作维护管理(operation administration and maintenance，OAM)是指根据运营商网络运营的实际需要，通常将网络的管理工作划分为3大类：操作(operation)、管理(administration)、维护(maintenance)，简称OAM，OAM也可以称为OAM实体或功能。操作主要完成日常网络和业务进行的分析、预测、规划和配置工作；维护主要是对网络及其业务的测试和故障管理等进行的日常操作活动，OAM可以检测网络运行状态、优化网络连接和性能，提升网络运行稳定性，降低网络维护成本。
AI模型也即AI算法(或者AI算子)，是基于人工智能的原理构建的数学算法的统称，也是利用AI解决特定问题的基础。本申请实施例中对AI模型的类型并不限定。例如，AI模型可以是机器学习模型，也可以是深度学习模型，也可以是强化学习模型，还可以是联邦学习等。
机器学习是实现人工智能的一种方法，该方法的目标是设计和分析一些让计算机可以自动“学习”的算法(也即模型)，所设计的算法称为机器学习模型。机器学习模型是一类从数据中自动分析获得规律，并利用规律对未知数据进行预测的算法。机器学习模型包括多种多样，根据模型训练时是否需要依赖训练数据对应的标签，机器学习模型可以分为：1、有监督学习模型；2、无监督学习模型。
深度学习是机器学习研究过程中产生的一个新的技术领域，具体地，深度学习是机器学习中一种基于对数据进行深层次表征学习的方法，深度学习通过建立模拟人脑进行分析学习的神经网络来解释数据。由于在机器学习方法中，几乎所有的特征都需要通过行业专家确定，然后对特征进行编码。然而深度学习算法试图自己从数据中学习特征，根据深度学习思想设计的算法称为深度学习模型。
强化学习是机器学习中的一个特殊领域，是通过智能体(agent)和环境(environment)的相互作 用，不断学习最优策略，做出序列决策，并获得最大回报的过程。通俗言之，强化学习是学习“做什么(即如何把当前的情景映射成动作)才能使得数值化的收益信号最大化”。智能体不会被告知应该采取什么动作，而是必须自己通过尝试去发现哪些动作会产生最丰厚的收益。强化学习与机器学习领域中的有监督学习和无监督学习不同，有监督学习是从外部提供的带标签的训练数据中进行学习的过程(任务驱动型)，无监督学习是寻找未标注的数据中隐含结构的过程(数据驱动型)。强化学习是通过“试探”寻找更优解的过程。智能体必须开发已有的经验来获取收益，同时也要进行试探，使得未来可以获得更好的动作选择空间(即从错误中学习)。根据强化学习设计的算法称为强化学习模型。
联邦学习(也称为协作学习)是一种机器学习技术，它可以在多个分散的边缘设备或持有本地数据样本的服务器上训练算法，而不交换它们。这种方法与传统的集中式机器学习技术形成了鲜明对比，即集中式机器学习中所有本地数据集都上传到一台服务器从而完成训练。联邦学习使多个参与者能够在不共享数据的情况下构建一个共同的、健壮的机器学习模型，从而允许解决数据隐私、数据安全、数据访问权限和访问异构数据等关键问题。
任何一个AI模型在用于解决特定的技术问题之前，都需要经过训练。AI模型的训练是指利用指定初始模型对训练数据进行计算，根据计算的结果采用一定的方法对初始模型中的参数进行调整，使得该模型逐渐学习到一定的规律，具备特定的功能的过程。经过训练后具有稳定功能的AI模型即可用于推理。AI模型的推理是利用训练完成的AI模型对输入数据进行计算，获得预测的推理结果(也可以称为输出数据)的过程。
AI模块为具备AI学习计算能力的模块。在无线通信系统中，AI模块可位于OAM中，也可位于gNB中(分离架构位于CU中)，可以位于部分UE中，也可以单独成为一个网元实体。AI模块在无线通信系统中主要功能为根据输入数据(例如，在无线通信系统中，输入数据可以是RAN侧提供的、或OAM监测的网络运行数据，例如网络负载、信道质量等)，进行模型建立、训练逼近、强化学习等一系列AI计算。AI模块提供的已训练完成的模型，具备针对RAN侧网络变化的预测功能，通常可以用于负载预测，UE轨迹预测等。此外，AI模块还可以根据训练完成的模型对RAN网络性能的预测结果，从网络节能、移动性优化等角度进行策略推理，以得到合理高效的节能策略、移动性优化策略等。当AI模块位于OAM中时，其与RAN侧gNB的通信，可以复用当前的北向接口；当AI模块位于gNB或CU中时，可以复用当前的F1、Xn、Uu等接口；当AI模块独立成一个网络实体时，需要重新建立到OAM和RAN侧等的通信链路，例如基于有线链路，或无线链路。
图1是本申请实施例提供的一种AI模块的示意图。如图1所示的AI模块100包括数据库模块101，训练模块102，模型模块103和执行模块104。
数据库模块101可以存储训练数据。训练数据还可以来自于终端设备。训练数据可以来自于网络设备。例如，训练数据可以来自于基站(例如gNB)或者组成基站的功能单元(例如CU或DU)。又如，训练数据可以来自于除基站以外的其他网络设备。例如，网关、管理实体(例如移动管理(mobile management entity，MME)、核心网设备等。
训练模块102对数据库模块101提供的训练数据进行分析，得到AI模型。训练模块102可以将训练好的AI模型发送给模型模块103。在完成AI模型训练后，训练模块102还可以更新已训练好的模型，并将用于更新模型的更新参数发送给模型模块103。模型模块103在运行该AI模型的过程中还可以收集一些模型的运行数据，并将这些运行数据发送给训练模块102。训练模块102可以根据这些运行数据更新该AI模型。
模型模块103可以根据该AI模型和输入数据，确定输出数据。输出数据可以包括基于输入数据和AI模型得到的网络运行的预测结果。输出数据还可以包括根据输入数据和AI模型确定的调整策略。在一些实施例中，网络设备和/或终端设备可以直接将输入数据发送给模型模块103。在另一些实施例中，数据库模块101也可以收集来自于网络设备和/或终端设备的数据，确定输入数据并将输入数据发送给模型模块103。
执行模块104可以用于执行模型模块103确定的调整策略。执行模块104还可以收集应用了该调整策略后的网络的具体表现，例如网络中的性能参数等，并将这些信息反馈给数据模块101。该数据库模块101可以存储这些反馈信息。这些反馈信息可以用于后续的模型训练或者改善该AI模型。
下面对于AI移动通信系统中的应用介绍。在移动通信系统中，利用AI模型可以实现智能收集和 分析数据，提升网络性能和用户体验。
例如，AI可以应用于信道状态信息(channel state information，CSI)反馈增强(CSI feedback enhancement)。CSI是通信链路的信道属性，是终端设备上报给基站的信道质量信息。终端设备通过将下行信道质量信息上报给基站，以便为终端设备选择更加合适的调制编码方案(modulation and coding scheme，MCS)，这样可以更好地适应变换的无线信道。
又如，AI还可以应用于波束管理(beam management，BM)。BM主要是用于要发现最强的发射/接收波束对(beam pair)。基于AI的波束预测可以提升预测准确度。
又如，AI还可以应用于定位精度增强(positioning accuracy enhancements)。定位精度和全向辐射功率(total radiated power，TRP)天线数量相关。一般而言，TRP天线数量越多，定位精度越高。利用AI模型可以在较少TRP天线数量的情况下实现较高的定位精度。例如，传统的定位手段，比如到达时间差(time difference of arrival,TDOA)、往返时间(round trip time,RTT)等，依赖于终端设备和TRP天线之间视距(line of sight，LOS)路径的信息收集。对于室内场景，可能没有足够数量的视距路径，传统的定位手段无法很好地工作。因此，基于AI的定位可以改进视距路径较少的场景下的定位准确度。
又如，AI还可以应用于网络节能(network energy saving)。网络节能可以通过小区激活/去激活(cell activation/deactivation)、减少负载、改进覆盖或者其他RAN设置调整。最优的节能决策取决于不同RAN节点的负载情况、RAN节点能力、关键绩效指标(key performance indication，KPI)要求、服务质量(quality of service，QoS)要求、激活用户数和终端设备的移动性、小区利用率等因素。然而提升网络能效是很复杂的过程，错误的小区关闭以及错误的流量卸载操作等都会引起网络性能的下降甚至能效的下降。AI技术可用于通过利用在RAN网络中收集的数据来优化节能决策。AI算法可以预测下一个周期的能效和负载状态，这可以用于更好地决策小区激活/去激活，以节省能源。基于预测的负载，系统可以动态配置节能策略，以保持系统性能和能效之间的平衡，并降低能耗。
又如，AI还可以应用于负载均衡(load balancing)。负载均衡的目的是使得负载在小区之间和小区内各区域之间均匀分布，或将部分流量从拥塞小区转移，或让终端设备在一个小区、载波或接入制式上进行分流，以提高网络性能。这可以通过优化切换参数和切换动作来实现。这种优化的自动化可以提供高质量的用户体验，同时提高系统容量，并最大限度地减少对网络管理和优化任务的人工干预。目前，依赖当前/过去时刻的小区负载状态的负载均衡决策是不够的。另外，负载均衡时整体网络和业务性能难以保证。因此可以引入基于AI模型的解决方案来提高负载均衡性能，如将用户和网络节点的各种测量和反馈、历史数据等输入AI模型来提高负载均衡性能，以提供更高质量的用户体验，提高系统容量。
又如，AI还可以应用于移动性优化(mobility optimization)。移动性管理是通过最大限度地减少掉话、无线链路失败(radio link failure，RLF)、不必要的切换和乒乓效应来保证终端设备移动期间业务连续性的方案。对于未来的高频网络，随着单节点覆盖区域的减少，终端设备在节点之间切换的频率会变得很高，尤其是对于高移动性终端设备。此外，对于可靠性、时延等QoS要求严格的应用，体验质量(quality of experience，QoE)对切换的性能较为敏感，因此移动性管理应避免切换失败，并减少切换过程中的时延。然而，对于传统的方法来说，基于试错的方案要实现几乎零失败的切换是有挑战性的。因此可以利用基于AI的解决方案来在以下几方面增强移动性管理：1)降低意外事件发生的概率，2)终端设备位置/移动性/性能预测，3)流量引导。
下面对常见的隐私保护计算方案进行介绍。对数据进行隐私保护计算的过程可以称为加扰。为了便于描述，加扰前的明文数据可以称为目标数据，对目标数据加扰后得到的加扰结果可以称为加扰数据。目前主流的隐私保护计算方案主要还是以密码学为核心(差分隐私、同态加密、安全多方计算)，在保障数据隐私安全的基础上，可以让数据以“可用不可见”的方式进行安全流通。
差分隐私：在交互式差分隐私保护框架下，用户通过查询接口向数据拥有者递交查询请求，数据拥有者根据查询请求在源数据集中进行查询，然后将查询结果添加噪声扰动之后反馈给用户。差分隐私可以有不同加扰等级，加扰等级越高，差分隐私的保护强度越高。差分隐私的保护强度与能添加多大的扰动或噪声相关。例如，考虑基于高斯机制的(ε,δ)-差分隐私方案，选择不同的δ值，添加的高斯噪声将不同，隐私保护程度也将不同。选择的δ值越小，隐私保护程度越好，加扰数据越难被破译；相反地，选择的δ值越大，隐私保护程度越差，加扰数据越容易被破译。在此情况下，差分隐私参数δ可 以反映差分隐私的加扰等级。在一些实施例中，差分隐私参数(ε,δ)和高斯噪声分布的标准差σ之间的关系满足如下关系：
其中α＝-(σ×ε)2/2且ε<1。本领域技术人员可以理解，添加噪声的机制除了高斯机制外，还有拉普拉斯机制、指数机制、混合机制等。
同态加密：满足密文同态运算性质的加密算法，数据经过同态加密之后，对密文进行特定的计算，得到的密文计算结果在进行对应的同态解密后的明文等同于对明文数据直接进行相同的计算。类似的，同态加密可以有不同加扰等级，加扰等级越高，同态加密的保护强度越高。同态加密包括全同态加密(fully homomorphic encryption，FHE)和半同态加密(somewhat homomorphic encryption，SWHE)。FHE在实际应用中计算开销极大，SWHE支持能力有限，但是开销小。目前已有很多满足加性同态或乘性同态的算法。例如经典的李伟斯特萨莫尔阿德曼(Rivest Shamir Adleman，RSA)算法就是满足乘法同态性的加密方法。以RSA算法为例，其密码强度与密钥长度(一般只是指模值的位长度)有关，例如RSA-1024到RSA-3072，模值的位长度增长了200％，密码强度也相应的增强了50％。因此，同态加密的保护强度与密钥长度有关，密钥长度越长，加密程度越大(或者认为对原数据加扰程度越大)，加扰等级越大，隐私保护强度越高。
安全多方计算：可以认为多方安全计算是一个协议集，该协议集可以保证在不暴露单体的数据情况下允许聚合数据的计算。主要用到的是技术是秘密共享、不经意传输、混淆电路、同态加密、零知识证明等关键技术。如上所述，安全多方计算是协议集。因此，安全多方计算的加扰等级可以通过安全多方算法采用的关键技术体现。例如，如果安全多方计算采用的关键技术是同态加密，那么安全多方算法的加扰等级就是同态加密的加扰等级。
图2是根据本申请实施例提供的一种传输数据的方法的示意性流程图。
201，终端设备向基站发送隐私等级信息。
在一些实施例中，该隐私等级信息可以用于指示需要终端设备加扰后发送给基站的数据(即目标数据)的隐私等级。
在一些实施例中，该目标数据可以是该终端设备运行过程中产生的数据，这些数据可以作为AI模型的训练数据和/或AI模型的输入数据。
根据应用场景的不同，目标数据可以不同。
以信道状态信息(channel state information，CSI)反馈增强(CSI feedback enhancement)场景为例，终端设备可以根据接收的信道状态信息-参考信号(channel state information-reference signal，CSI-RS)进行信道估计，得到信道估计结果(例如信道矩阵、对该信道矩阵进行特征分解后得到的特征向量等)。该信道估计结果可以作为AI模型的训练数据或者AI模型的输入数据。在此情况下，该目标数据可以是该信道估计结果。
以波束管理(beam management，BM)场景为例，参考信号接收功率(reference signal received power，RSRP)、理想波束标识等信息可以作为AI模型的训练数据或AI模型的输入数据。在此情况下，该目标数据可以是终端设备测量的RSRP、终端设备选择的理想波束标识等信息。
如果是移动性优化或负载均衡场景，那么终端设备的位置信息(例如终端设备的经纬度坐标、终端设备相对于基站的位置信息等)、终端设备的移动轨迹等信息可以作为AI模型的训练数据或AI模型的输入数据。在此情况下，该目标数据可以包括终端设备的位置信息、运动轨迹等信息。
不同类型的数据的隐私要求不同。例如，表1示出了不同数据的隐私要求。
表1
如表1所示的隐私等级的值越高，表明隐私等级越高。如表1所示，RSRP的隐私等级高于信道估计结果的隐私等级，理想波束标识的隐私等级高于RSRP的隐私等级，位置信心和移动轨迹的隐私等级高于理想波束标识的隐私等级。可以理解的是，表1所示的隐私等级和数据类型之间的关系以及隐私等级的总等级数只是示意性的，而非是对本申请实施例的限定。
在一些实施例中，该隐私等级信息可以直接包括该目标数据的隐私等级。例如，如果目标数据是终端设备的位置信息，那么该隐私等级信息可以直接包含位置信息对应的隐私等级，即隐私等级4。
在另一些实施例中，该隐私等级信息可以包括该目标数据的类型。在此情况下，基站可以根据隐私等级和数据类型之间的对应关系，确定出该目标数据的隐私等级。例如，该隐私等级信息指示目标数据是终端设备的位置信息。在此情况下，基站可以根据隐私等级和数据类型之间的对应关系确定该目标数据的隐私等级是4。
当然，在另一些实施例中，该隐私等级信息可以同时包含该目标数据的隐私等级和该目标数据的类型。
在另一些实施例中，该隐私等级信息可以用于指示该终端设备的隐私等级。
不同类型的终端设备可以有不同类型的隐私等级。表2示出了终端设备的类型和隐私等级的对应关系。
表2
与表1类似，在表2中，隐私等级的值越高表明隐私等级越高。如表2所示，远程三表(电表、水表、燃气表)数据采集设备的隐私等级高于远程温度采集设备的隐私等级，移动电话和平板电脑的隐私等级高于远程三表(电表、水表、燃气表)数据采集设备的隐私等级，移动销售点(point of sales，POS)机的隐私等级高于移动电话和平板电脑的隐私等级。可以理解的是，表2所示的隐私等级和设备类型之间的关系以及隐私等级的总等级数只是示意性的，而非对本申请实施例的限定。
在一些实施例中，该隐私等级信息可以直接包括该终端设备的隐私等级。例如，如果该终端设备是移动POS机，那么该隐私等级信息可以直接包含移动POS机对应的隐私等级，即隐私等级4。
在另一些实施例中，该隐私等级信息可以包含该终端设备的类型。在此情况下，基站可以根据隐私等级和设备类型之间的对应关系，确定出该目标数据的隐私等级。例如，该隐私等级信息可以指示该终端设备是移动POS。在此情况下，基站可以根据隐私等级和设备类型之间的对应关系确定出该终端设备的类型的隐私等级是4。
当然，在另一些实施例中，该隐私等级信息可以同时包含该终端设备的隐私等级以及该终端设备的类型。
在一些实施例中，该隐私等级信息可以是一条专用的信息。例如，终端设备在与基站建立RRC连接后，如果该终端设备需要向该基站发送加扰数据，那么该终端设备可以在发送该加扰数据之前向该基站发送该隐私等级信息。
在另一些实施例中，该隐私等级信息可以是一条非专用消息。例如，终端设备在与基站建立RRC连接过程中可以向基站发送RRC恢复完成(RRC resume complete)消息，该RRC恢复完成消息中携带有该终端设备的类型信息。在此情况下，该基站可以根据该RRC恢复完成消息携带的终端设备的类型确定该终端设备的隐私等级。可以理解的是，除了RRC恢复完成消息以外，其他RRC消息也可以用于携带该终端设备的类型信息，例如，RRC建立完成(RRC setup complete)消息，RRC重建完成(RRC reestablishment complete)消息，RRC重配置完成(RRC reconfiguration complete)消息等。又如，该终端设备可以将该隐私等级信息与其他信息一起发送给该基站。例如，该终端设备可以将该隐私等级信息与该终端设备的加扰能力信息一起发送给该基站。
202，该基站获取该终端设备的加扰能力。
该终端设备的加扰能力包含以下信息中的至少一种：该终端设备支持的加扰算法，该终端设备支 持的加扰等级，该终端设备的加扰数据恢复能力，或者，目标数据与加扰数据的差异信息。
该终端设备支持的加扰算法是指该终端设备可以使用的隐私保护计算方案。例如该终端设备是否支持差分隐私、该终端设备是否支持同态加密、该终端设备是否支持安全多方计算。
该终端设备支持的加扰等级可以是该终端设备支持的加扰算法的最大加扰等级。例如，如果该终端设备支持差分隐私，那么该终端设备支持的加扰等级可以包含高斯噪声标准差。例如，如果该加扰能力中的终端设备支持的高斯噪声的差分隐私参数δ为1e-5，那么该终端设备可以支持小于或等于1e- 5的标准差，例如该终端设备可以支持添加差分隐私参数δ等于1e-5、1e-6或1e-7的高斯噪声。
该终端设备的加扰数据恢复能力用于表示该终端设备能够恢复采用何种加扰等级的加扰数据。例如，该终端设备能够恢复多大噪声/扰动的加扰数据。
目标数据与加扰数据的差异信息是指加扰前后的数据的差异化程度(即目标数据与加扰数据的差异化程度)。例如，可以是加扰前后的数据的方差、标准差、最小均方误差等。
在一些实施例中，该基站可以向该终端设备发送加扰能力请求信息，该加扰能力请求信息用于请求获取该终端设备的加扰能力。该终端设备在接收到该加扰能力请求信息后，可以向该基站发送加扰能力指示信息。该加扰能力指示信息用于指示该终端设备大家绕能力。
在另一些实施例中，该终端设备可以在与该基站建立RRC连接后主动向该基站发送该加扰能力指示信息。
该加扰能力指示信息可以用于指示该终端设备的加扰能力中的任一种或多种。换句话说，该加扰能力指示信息可以用于以下信息一种或多种：该终端设备支持的加扰算法，该终端设备支持的加扰等级，该终端设备的加扰数据恢复能力，或者，目标数据与加扰数据的差异信息。
在一些实施例中，如果该加扰能力指示信息没有指示一些加扰能力，那么可以认为该终端设备支持该能力下的所有可选的方案。例如，如果该加扰能力指示信息中没有指示该终端设备支持的加扰算法，则该基站可以确定该终端设备支持所有的加扰算法。又如，如果该加扰能力指示信息中没有指示该终端设备支持的加扰等级，则该基站可以确定该终端设备支持所有的加扰等级。
在另一些实施例中，如果该加扰能力指示信息没有指示一些加扰能力，那么可以认为该终端设备支持该能力下的默认方案或者要求计算能力最低的方案。例如，假设默认加扰算法是差分隐私，那么如果该加扰能力指示信息中没有指示该终端设备支持的加扰算法，则该基站可以确定该终端设备仅支持差分隐私。又如，如果该加扰能力指示信息中没有指示该终端设备支持的加扰等级，则该基站可以确定该终端设备仅支持最低等级的加扰等级。
在另一些实施例中，终端设备的类型和终端设备的加扰能力有对应关系。例如，移动POS机可以支持差分隐私和同态加密；移动电话和平板电脑可以支持差分隐私、同态加密和安全多方计算。远程信息采集设备只支持差分隐私。该对应关系可以保存在基站。在情况下，该基站可以根据该终端设备的类型判断该终端设备的加扰能力。例如，该基站可以根据隐私等级信息获取该终端设备的设备类型，然后根据该终端设备的设备类型确定该终端设备的加扰能力。又如，该基站可以根据在建立RRC连接过程中获取的RRC消息(例如，RRC恢复完成消息、RRC建立完成消息、RRC重建完成消息、或RRC重配置完成消息)确定该终端设备的类型，然后根据该终端设备的类型确定该终端设备的加扰能力。
可选的。如果基站是切分架构，即其切分为CP和UP，且该CU进一步切分为CU-CP和CU-UP，且该CU-CP进一步切分为CU-CP1和CU-CP2时，CU-CP2接收解码该终端设备发送的携带有该加扰能力指示信息的消息，然后CU-CP1确认是否支持终端设备侧的不同水平加扰功能。
203，该基站确定加扰策略指示信息。该加扰策略指示信息用于指示该终端设备使用的加扰策略。
在一些实施例中，该加扰策略指示信息可以仅指示一个加扰策略。
在另一些实施例中，该加扰策略指示信息可以指示两个或两个以上的加扰策略。
在一些实施例中，该加扰策略包括加扰算法。
在另一些实施例中，该加扰策略还包括以下信息中的至少一种：加扰等级、对应于该加扰数据的AI模型的精确度需求，或者防泄漏的数据类型。
一个加扰策略可以包括一个加扰算法也可以包括多个加扰算法。类似的，一个加扰策略可以包括一个加扰等级，也可以包括多个加扰等级。一个加扰策略可以包括一种防泄漏的数据类型，也可以包括多个防泄漏的数类型。
在一些实施例中，不同的加扰策略包括的部分信息可以是相同的，但是其他信息不同。例如，不同的加扰策略包括的加扰算法可能是相同的，但是其他信息(例如加扰等级、对应于该加扰数据的AI模型的精确度需求、和/或防泄漏数据类型)不完全相同。不同的加扰策略包括的加扰等级是相同的，但是加扰算法不相同或者不完全相同。
可选的，在一些实施例中，该基站可以不需要接收来自于该终端设备的隐私等级信息，同时也可以不获取该终端设备的加扰能力。在此情况下，该基站可以自行确定包含一个或多个加扰策略的加扰策略指示信息。如果该终端设备在接收到该加扰策略指示信息后确定该终端设备可以使用该加扰策略指示信息中指示的加扰策略，那么该终端设备则使用相应的加扰策略来加扰目标数据。如果该终端设备在接收到该加扰策略指示信息后确定该加扰策略指示信息所指示的加扰策略对于该终端设备都不可用，那么该终端设备可以向该基站发送一个反馈信息。该基站在接收到该反馈信息后，可以重新确定加扰策略并将重新确定的加扰策略发送给该终端设备。
可选的，在另一些实施例中，该基站可以仅获取该隐私等级信息而不获取该终端设备的加扰能力。在此情况下，该基站可以根据该隐私等级信息确定该加扰策略指示信息。例如，不同的隐私等级可以对应于不同的加扰策略。该基站可以根据该隐私等级信息确定出对应的加扰策略。在该实施例中，由于该基站在确定加扰策略时没有考虑到该终端设备的加扰能力，所以有可能该终端设备无法使用该基站确定的加扰策略。在此情况下，该终端设备可以向该基站发送给一个反馈信息。该基站在接收到该反馈信息后，可以重新确定加扰策略并将重新确定的加扰策略发送给该终端设备。
可选的，在另一些实施例中，该基站可以仅获取该终端设备的加扰能力而不获取该隐私等级信息。在此情况下，该基站可以根据该终端设备的加扰能力确定该加扰策略指示信息。例如，该基站可以根据该终端设备支持的加扰算法来选择加扰策略中的加扰算法；根据该终端设备支持的加扰等级来选择加扰策略中的加扰等级。
可选的，在另一些实施例中，该基站可以获取该终端设备的加扰能力和该隐私等级信息。在此情况下，该基站可以根据该终端设备的加扰能力和该隐私等级确定加扰策略。例如，一个隐私等级可以与多个加扰算法对应。该基站可以根据该终端设备的支持的加扰算法，从该多个加扰算法中选择一个该终端设备的支持的加扰算法。又如，一个隐私等级可以对应于多个加扰等级。基站可以根据该终端设备支持的加扰等级，从该多个加扰等级中选择一个该终端设备的支持的加扰等级(例如该终端设备支持的最高的加扰等级或者最低的加扰等级)。
204，该基站将该加扰策略指示信息发送给该终端设备。相应的，该终端设备接收来自于该基站的该加扰策略指示信息。
205，该终端设备根据该加扰策略指示信息，对目标数据进行加扰，得到加扰数据。
在一些实施例中，该加扰策略指示信息仅包含一个加扰策略。在此情况下，该终端设备可以直接根据该加扰策略对该目标数据进行加扰。
例如，如果该加扰策略中只包含加扰算法。那么该终端设备可以适应该加扰策略指定的加扰算法来对目标数据加扰。加扰使用的其他参数(例如加扰等级、需要加扰的数据类型等)可以由该终端设备自行决定。本申请实施例对这些可以由该终端设备自行确定的参数的确定方法并不限定。以加扰等级为例。在一些实施例中，该终端设备可以确定使用任一个加扰等级。在另一些实施例中，该终端设备还可以确定使用最低的加扰等级，或者使用最高的加扰等级，或者使用中间的加扰等级。在另一些实施例中，该终端设备还可以根据一些其他信息来选择加扰等级。例如，不同类型的数据或者不同隐私等级的数据对应于不同的加扰等级。该终端设备可以根据目标数据的数据类型或者隐私等级来选择加扰等级。又如，该终端设备可以根据该终端设备的当前计算资源来选择对应的加扰等级。例如，如果该终端设备当前能够用于加扰的计算资源较为充足(例如，能够用于加扰的计算资源的使用率低于一个预设阈值)，那么该终端设备可以使用较高的加扰等级；如果该终端设备当前能够用于加扰的计算资源不足(例如资源使用率高于该预设阈值)，那么该终端设备可以选择较低的加扰等级。
又如，如果该加扰策略中包含加扰等级，那么该终端设备使用加扰策略中所指示的加扰等级对目标数据进行加扰。
又如，如果该加扰策略中包含对应于该加扰数据的AI模型的精确度需求，那么该终端设备可以根据该精确度需求来选择一些加扰参数，例如加扰等级、加扰算法等。以差分隐私参数的另一个参数ε为 例，在一些实施例中，针对非独立同分布的数据，当ε＝4时，模型推理精确度为78.56％，当ε＝4.5时，模型推理精确度为79.60％，∈＝5时，模型推理精确度为81.28％。那么如果加扰策略中的AI模型精确度需求是高于80％的，那么可以选择ε＝5的差分隐私方案。
又如，如果该加扰策略中包含防泄漏的数据类型，那么该终端设备可以使用加扰策略中所指示的加扰算法和加扰等级，并对类型为该防泄漏的数据类型的数据进行加扰。
在另一些实施例中，该加扰策略指示信息可以包含多个加扰策略。在此情况下，该终端设备可以选择该多个加扰策略中的一个作为目标加扰策略，并使用该目标加扰策略对该目标数据加扰得到该加扰数据。
在一些实施例中，该终端设备可以随机选择一个加扰策略作为该目标加扰策略。例如，如果该多个加扰策略对于该终端设备都是可用的，那么该终端设备可以随机选择一个加扰策略作为目标加扰策略。又如，如果该多个加扰策略中只有部分加扰策略对于该终端设备是可用的，那么该终端设备可以随机选择一个可用的加扰策略作为目标加扰策略。
在另一些实施例中，该终端设备可以根据相关信息来选择该目标加扰策略。例如，该终端设备可以根据该目标数据的数据类型、隐私等级、对应的AI模型的精确度需求等中的任一个或多个信息来选择加扰策略。例如，如果该目标数据的隐私等级较高，那么该终端设备可以选择一个复杂的加扰策略作为该目标加扰策略；如果该目标数据的隐私等级较低，那么该终端设备可以选择一个简单的加扰策略作为该目标加扰策略。
206，该终端设备向该基站发送该加扰数据。相应的，该基站接收来自于该终端设备的该加扰数据。
207，该基站处理该加扰数据。
可选的，如果该目标数据是AI模型训练数据，那么该基站可以根据该加扰数据训练该AI模型；如果该目标数据是AI模型的输入数据，那么该基站可以将该输入数据输入该AI模型，得到该AI模型的输出数据(即推理预测结果)。
可选的，如果AI模块是位于该基站中，那么该基站可以直接处理该加扰数据。如果该AI模块或者该AI模块中负责模型训练和/或数据推理的模块(例如图1中的训练模块102和模型模块103)是位于其他网络设备中(例如核心网设备)，那么该基站可以将该加扰数据发送给对应的网络设备。
在一些实施例中，该基站可以先判断是否能够正常处理该加扰数据，或者，该加扰数据是否能够使得对应的AI模型保持高于阈值的推理精度。如果该基站不能正常处理该加扰数据，或者，该加扰数据使得该AI模型的推理精度都低于该阈值，那么该基站可以向该终端设备发送一个重加扰指示信息，该重加扰指示信息用于指示该终端设备重新选择一个加扰策略来对该目标数据进行加扰。
在一些实施例中，该重加扰指示信息可以仅用于指示该终端设备重新选择一个加扰策略来对该目标数据进行加扰。换句话说，如果该终端设备接收到该冲加扰指示信息，那么该终端设备可以重新选择一个加扰策略。例如，可以从选择一个不同的加扰等级。又如，可以选择另一种加扰算法。
在另一些实施例中，该基站可以重新确定一个或多个加扰策略，并将重新确定的一个或多个加扰策略通过该重加扰指示信息指示给该终端设备。该终端设备可以从该重加扰指示信息中所指示的一个或多个加扰策略中选择一个来对该目标数据进行加扰。
图3是该根据本申请实施例提供的另一传输数据的方法的示意性流程图。
301，基站获取加扰策略指示信息，该加扰策略指示信息用于指示该基站使用的加扰策略。
该加扰策略指示信息可以包括该终端设备的计算能力。
在一些实施例中，该终端设备的计算能力可以通过该终端设备的芯片型号或者芯片的时钟频率体现。在此情况下，该加扰策略指示信息可以包含该终端设备的芯片信号或者芯片的时钟频率。这里所称的芯片是该终端设备中负责对目标数据进行加扰的芯片。对目标数据进行加扰的芯片可以是中央处理器(central processing unit，CPU)，还可以是芯片系统(system on chip，SoC)，还可以是网络处理器(network processor，NP)，还可以是微控制器(micro controller unit，MCU)，还可以是现场可编程门阵列(field programmable gate array，FPGA)，还可以是专用集成芯片(application specific integrated circuit，ASIC)，还可以是可编程控制器(programmable logic device，PLD)、其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件，或其他集成芯片。
在一些实施例中，该终端设备计算能力可以通过该终端设备的型号体现。终端设备的型号与终端 设备使用的芯片有对应关系。例如，假设终端设备是移动电话，那么确定了该移动电话的型号之后，就可以根据型号和芯片的对应关系，确定出该终端设备使用的芯片。在此情况下，该加扰策略指示信息可以包含该终端设备的型号。
在一些实施例中，该终端设备的计算能力可以通过该终端设备的类型体现。不同类型的终端设备的计算能力不同。例如，移动电话的计算能力高于远程移动POS机的计算能力，移动POS机的计算能力高于远程信息采集设备的计算能力。在此情况下，该加扰策略指示信息可以包含该终端设备的类型。
在一些实施例中，该终端设备的计算能力可以通过该终端设备的可用运算资源体现。该可用运算资源是该终端设备中能够用于处理加扰数据的运算资源。例如，当该终端设备能够用于处理加扰数据的运算资源较少时，那么该终端设备的计算能力较低；当该终端设备能够用于处理加扰数据的运算资源较多时，那么该终端设备的计算能力较高。在此情况下，该加扰策略指示信息还可以包括该终端设备的可用预算资源。
在一些实施例中，该终端设备的计算能力可以通过该终端设备的当前电量体现。例如，当该终端设备的当前电量较低时，那么该终端设备的计算能力较低；当该终端设备当前电量较高时，那么该终端设备的计算能力较高。在此情况下，该加扰策略指示信息还可以包括该终端设备的当前电量。
在一些实施例中，该终端设备的计算能力可以通过该终端设备的支持的加扰算法体现。不同计算能力的终端设备支持的加扰算法和/或加扰等级不同。在此情况下，该加扰策略指示信息可以包含该终端设备支持的加扰算法。
在一些实施例中，该加扰策略指示信息可以包含上述一种或多种信息来体现该终端设备的计算能力。例如该加扰策略指示信息可以包括该终端设备支持的加扰算法和该终端设备的当前电量。又如，该加扰策略指示信息可以包括该终端设备的设备类型以及该终端设备的可用运算资源。
在一些实施例中，该基站可以通过在RRC连接过程中获取到的RRC消息(例如，RRC恢复完成消息、RRC建立完成消息、RRC重建完成消息、或RRC重配置完成消息)来确定该终端设备的型号和/或设备类型，从而根据该终端设备的型号和/或设备类型确定出该终端设备的计算能力。
在另一些实施例中，该终端设备支持的加扰算法与该终端设备的型号或类型具有对应关系。该基站可以保存该对应关系。在此情况下，该基站可以通过RRC消息确定出该终端设备的型号和/或设备类型，然后根据该对应关系确定出该终端设备支持的加扰算法。
在另一些实施例中，该基站可以在RRC建立连接后，向该终端设备发送加扰能力请求信息，该加扰能力请求信息用于请求获取该终端设备的加扰能力。该终端设备在接收到该加扰能力请求信息后可以将该终端设备的计算能力反馈给该基站。
在一些实施例中，该加扰能力请求信息可以由UE能力请求消息(UE capability enquiry message)携带。该终端设备向该基站发送的携带有计算能力的反馈信息可以由UE能力信息(UE capability information message)携带。
在一些实施例中，在基站是切分架构的情况下，即基站切分为CP和UP，且该CU进一步切分为CU-CP和CU-UP，且该CU-CP进一步切分为CU-CP1和CU-CP2时，CU-CP2接收解码来自于终端设备的消息，然后CU-CP1确认该终端设备是否支持直接处理加扰后的下发数据。
在一些实施例中，该加扰策略指示信息还可以进一步包含以下信息中的至少一种：对应于加扰数据的AI模型的精确度需求、加扰等级、该终端设备的存储能力，或者，数据加扰权限。
在图3所示的方法中，该基站对目标数据进行加扰得到加扰数据。
在一些实施例中，AI模型的训练过程可以是由网络侧的设备(例如基站或者其他网络侧设备(例如核心网设备等))来实现，但是训练得到的模型可能部署在终端设备中。在此情况下，该基站可以将该AI模型的参数加扰后发送给该终端设备。因此，该目标数据可以是该AI模型的参数。该AI模型的参数包括该AI模型的参数，该AI模型的结构信息等。以神经网络为例，神经网络的参数可以包含以下一项或多项：神经网络中网络层的层数、各个网络层的顺序、每个网络层中的权重、参数或计算公式等信息。
在另一些实施例中，AI模型的训练和部署都可以是在网络侧。在此情况下，该基站可以将该AI模型的输出数据加扰后发送给该终端设备。因此，该目标数据也可以是该AI模型的输出数据。例如，如果AI模型是应用于网络节能、移动性优化等的场景，那么该输出数据可以是的具体推理结果、策略指 令等。例如，针对网络节能场景，推理结果可以包括节能措施，持续时间，进出节能状态的负载门限等。又如，针对波束管理场景，推理结果可以是k个最优扫描波束的扫描波束。又如，在定位增强场景下，推理结果可以是推理导出的LOS/NLOS状态信息以及LOS路径的信道的到达时间等中间结果。
由于该AI模型是由该基站或者其他网络设备训练得到的。因此，该基站可以确定该AI模型的精确度需求，或者，从训练该AI模型的网络设备中获取该AI模型的精确度需求。
在一些实施例中，加扰等级与终端设备的计算能力可以有对应关系。在此情况下，该基站可以在确定出该终端设备的计算能力后，根据该加扰等级和该计算能力的对应关系，确定出该加扰等级。在另一些实施例中，该终端设备还可以在反馈计算能力的同时将该加扰等级反馈给该基站。
与加扰等级类似，在一些实施例中，该终端设备的存储能力与终端设备的计算能力可以有对应关系。在此情况下，该基站可以在确定出该终端设备的计算能力后，根据该终端设备的存储能力和该计算能力的对应关系，确定出该终端设备的存储能力。在另一些实施例中，该终端设备还可以在反馈计算能力的同时将该终端设备的存储能力反馈给该基站。
该数据加扰权限是该基站对于数据是否需要加扰的控制权限。在一些情况下，该终端设备可以确定该基站发送该终端设备的全部目标数据或者部分目标数据不需要加扰。在此情况下，该基站可以获取该终端设备决定是否需要加扰数据的控制权限。在得到了该控制权限后，该基站可以对目标数据进行加扰。在一些实施例中，该数据加扰权限可以包括能够由该基站决定的需要加扰的数据类型，或者，能够由该基站决定的需要加扰的隐私等级。在另一些实施例中，该数据加扰权限可以直接指示该基站能够自行决定是否需要对数据进行加扰。在一些实施例中，该数据加扰权限可以由该基站向该终端设备请求。如果该终端设备确定能够将该数据加扰权限授予该基站，那么该终端设备可以将该数据加扰权限发送给该基站。在另一些实施例中，数据加扰权限可以与终端设备的型号和/或终端设备的类型确定，该基站可以在确定了该终端设备的型号和/或该终端设备的类型之后，根据数据加扰权限与终端设备的类型(或型号)的对应关系，确定出该数据加扰权限。
302，该基站根据该加扰策略指示信息，对目标数据进行加扰，得到加扰数据。
在一些实施例中，该基站可以根据该终端设备的计算能力，确定出与该计算能力匹配的加扰策略。该加扰策略可以包括加扰算法、加扰等级等。
在一些实施例中，如果该加扰策略指示信息包含该加扰等级，那么该基站确定的加扰策略中的加扰等级可以与该加扰策略指示信息中的加扰等级相同。
在另一些实施例中，该基站可以根据需要加扰的目标数据的类型和该加扰策略指示信息中的加扰等级，确定出该加扰策略中的加扰等级。为了便于描述，以下将该加扰策略指示信息中的加扰等级称为第一加扰等级，将加扰策略中的加扰等级称为第二加扰等级。该第一加扰等级可以是该基站能够使用的最高的加扰等级。在此情况下，该第二加扰等级可以等于或者低于该第一加扰等级。例如，如果该目标数据的隐私等级较低，那么该第二加扰等级可以低于该第一加扰等级；如果该目标数据的隐私等级较高，那么该第二加扰等级可以等于该第一加扰等级。
在一些实施例中，如果该加扰策略指示信息中包含该AI模型的精确度需求。那么该基站可以根据该AI模型的精确度需求和该终端设备的计算能力，为该目标数据选择合适的加扰算法。
在一些实施例中，如果该加扰策略指示信息中包含该数据加扰权限，那么该基站可以根据该数据加扰权限确定需要加扰的目标数据。
303，该基站将该加扰数据发送给该终端设备。相应的，该终端设备接收来自于该基站的加扰数据。
在一些实施例中，该加扰数据可以由在RRC重配置消息(RRC reconfiguration message)携带。
304，该终端设备处理该加扰数据。
可选的，如果该目标数据是AI模型的参数，那么该终端设备可以根据该加扰数据设置该AI模型；如果该目标数据是AI模型的输出数据，那么该终端设备可以根据该输出数据设置该终端设备的相关参数。
类似的，在一些实施例中，该终端设备可以先判断是否能够正常处理该加扰数据，或者，该加扰数据是否能够使得对应的AI模型保持高于阈值的推理精度。如果该终端设备不能正常处理该加扰数据，或者，该加扰数据使得该AI模型的推理精度都低于该阈值，那么该终端设备可以向该基站发送一个重加扰指示信息，该重加扰指示信息用于指示该基站重新选择一个加扰策略来对该目标数据进行加扰。
图4是根据本申请实施例提供的另一种传输数据的方法的示意性流程图。
401，基站向终端设备发送隐私等级信息。
在一些实施例中，该隐私等级信息可以用于指示需要基站加扰后发送给终端设备的数据(即目标数据)的隐私等级。
在一些实施例中，该目标数据可以是AI模型的参数或者AI模型的输出数据。
在一些实施例中，不同类型的参数、不同场景的AI模型的参数，或者不同类型的目标数据的隐私要求不同。例如，表3示出了不同数据的隐私要求。
表3
如表3所示的隐私等级的值越高，表明隐私等级越高。如表3所示，如果目标数据是用于波束管理的AI模型的参数或输出数据，那么该目标数据的隐私等级高于用于CSI反馈增强的AI模型的参数或输出数据；如果目标数据是用于负载均衡的AI模型的参数或输出数据，那么该目标数据的隐私等级高于用于波束管理的AI模型的参数或输出数据；如果目标数据是用于移动性优化的AI模型的参数或输出数据，那么该目标数据的隐私等级高于用于波束管理的AI模型的参数或输出数据。可以理解的是，表2所示的隐私等级和数据类型之间的关系以及隐私等级的总等级数只是示意性的，而非是对本申请实施例的限定。
在一些实施例中，该隐私等级信息可以直接包括该目标数据的隐私等级。例如，如果目标数据是基站的用于移动性优化的AI模型的参数或输出数据，那么该隐私等级信息可以直接包含移动性优化对应的隐私等级，即隐私等级4。
在另一些实施例中，该隐私等级信息可以包括该目标数据的AI模型的类型。在此情况下，终端设备可以根据隐私等级和AI模型之间的对应关系，确定出该目标数据的隐私等级。例如，该隐私等级信息指示目标数据是对应的AI模型是用于移动性优化的AI模型。在此情况下，终端设备可以根据隐私等级和AI模型之间的对应关系确定该目标数据的隐私等级是4。
当然，在另一些实施例中，该隐私等级信息可以同时包含该目标数据的隐私等级和该目标数据的AI模型的类型。
在另一些实施例中，该隐私等级信息可以用于指示该基站的隐私等级。
不同类型的基站可以有不同类型的隐私等级。表4示出了基站的类型和隐私等级的对应关系。
表4
与表3类似，在表4中，隐私等级的值越高表明隐私等级越高。如表4所示，皮基站的隐私等级高于飞基站的隐私等级，皮基站的隐私等级高于皮基站的隐私等级，宏基站的隐私等级高于皮基站的隐私等级。可以理解的是，表4所示的隐私等级和设备类型之间的关系以及隐私等级的总等级数只是示意性的，而非对本申请实施例的限定。
在一些实施例中，该隐私等级信息可以直接包括该基站的隐私等级。例如，如果该基站是宏基站，那么该隐私等级信息可以直接包含宏基站的隐私等级，即隐私等级4。
在另一些实施例中，该隐私等级信息可以包含该基站的类型。在此情况下，终端设备可以根据隐私等级和设备类型之间的对应关系，确定出该目标数据的隐私等级。例如，该隐私等级信息可以指示该基站是宏基站。在此情况下，终端设备可以根据隐私等级和设备类型之间的对应关系确定出该基站 的类型的隐私等级是4。
当然，在另一些实施例中，该隐私等级信息可以同时包含该基站的隐私等级以及该基站的类型。
在一些实施例中，该隐私等级信息可以是一条专用的信息。例如，基站在与终端设备建立RRC连接后，如果该基站需要向该终端设备发送加扰数据，那么该基站可以在发送该加扰数据之前向该终端设备发送该隐私等级信息。
在另一些实施例中，该隐私等级信息可以是一条非专用消息。例如，基站在与终端设备建立RRC连接过程中可以向终端设备发送RRC消息(例如RRC建立(RRC setup)消息、RRC连接重建立(RRC reestablishment)消息、RRC重配置(RRC configuration)消息等)，该RRC消息中携带有该基站的类型信息。在此情况下，该终端设备可以根据该RRC消息携带的基站的类型确定该基站的隐私等级。又如，该基站可以将该隐私等级信息与其他信息一起发送给该终端设备。例如，该基站可以将该隐私等级信息与该基站的加扰能力信息一起发送给该终端设备。
402，该终端设备获取该基站的加扰能力。
类似的，该基站的加扰能力包含以下信息中的至少一种：该基站支持的加扰算法，该基站支持的加扰等级，该基站的加扰数据恢复能力，或者，目标数据与加扰数据的差异信息。该基站的加扰能力与终端设备的加扰能力的类似。关于该基站的加扰能力的具体描述可以参考图2中关于终端设备的加扰能力的描述，为了简洁在此就不再赘述。
403，该终端设备确定加扰策略指示信息。该加扰策略指示信息用于指示该基站使用的加扰策略。
加扰策略指示信息包含的内容以及确定方法与图2所示实施例中的加扰策略指示信息包含的内容以及确定方法类似，为了简洁，在此就不再赘述。
404，该终端设备将该加扰策略指示信息发送给该基站。相应的，该基站接收来自于该终端设备的该加扰策略指示信息。
405，该基站根据该加扰策略指示信息，对目标数据进行加扰，得到加扰数据。
该基站对目标数据的加扰方法与图2实施例中终端设备对目标数据的加扰方法类似，为了简洁，在此就不再赘述。
406，该基站向该终端设备发送该加扰数据。相应的，该终端设备接收来自于该基站的该加扰数据。
407，该终端设备处理该加扰数据。
该终端设备处理加扰数据的具体方法与图3所示的实施例中终端设备处理加扰数据的方法相同。为了简洁，在此就不再赘述。
图5是根据本申请提供的另一传输数据的方法的示意性流程图。
501，终端设备获取加扰策略指示信息，该加扰策略指示信息用于指示该终端设备使用的加扰策略。
该加扰策略指示信息可以包括该基站的计算能力。
在一些实施例中，该基站的计算能力可以通过该基站的类型体现。在一些实施例中，该基站的计算能力可以通过该基站的类型体现。不同类型的基站的计算能力不同。例如，宏基站的计算能力高于微基站的计算能力，微基站的计算能力高于皮基站或飞基站采集设备的计算能力。在此情况下，该加扰策略指示信息可以包含该基站的类型。
在一些实施例中，该基站的计算能力可以通过该基站的可用运算资源体现。该可用运算资源是该基站中能够用于处理加扰数据的运算资源。例如，当该基站能够用于处理加扰数据的运算资源较少时，那么该基站的计算能力较低；当该基站能够用于处理加扰数据的运算资源较多时，那么该基站的计算能力较高。在此情况下，该加扰策略指示信息还可以包括该基站的可用预算资源。
在一些实施例中，该基站的计算能力可以通过该基站的支持的加扰算法体现。不同计算能力的基站支持的加扰算法和/或加扰等级不同。在此情况下，该加扰策略指示信息可以包含该基站支持的加扰算法。
在一些实施例中，该加扰策略指示信息可以包含上述一种或多种信息来体现该基站的计算能力。例如该加扰策略指示信息可以包括该基站支持的加扰算法和该基站的当前电量。又如，该加扰策略指示信息可以包括该基站的设备类型以及该基站的可用运算资源。
在一些实施例中，该终端设备可以通过在RRC连接过程中获取到的RRC消息(例如，RRC建立消息、RRC重建消息、或RRC重配置消息)来确定该基站的类型，从而根据该基站的类型确定出该基 站的计算能力。
在另一些实施例中，该基站支持的加扰算法与该基站的类型具有对应关系。该终端设备可以保存该对应关系。在此情况下，该终端设备可以通过RRC消息确定出该基站的类型，然后根据该对应关系确定出该基站支持的加扰算法。
在另一些实施例中，该终端设备可以在RRC建立连接后，向该基站发送加扰能力请求信息，该加扰能力请求信息用于请求获取该基站的加扰能力。该基站在接收到该加扰能力请求信息后可以将该基站的计算能力反馈给该终端设备。
在一些实施例中，该加扰策略指示信息还可以进一步包含以下信息中的至少一种：对应于加扰数据的AI模型的精确度需求、加扰等级、该基站的存储能力，或者，数据加扰权限。关于这些信息的具体内容可以参考图3所示的实施例，为了简洁，在此就不再赘述。
502，该终端设备根据该加扰策略指示信息，对目标数据进行加扰，得到加扰数据。
该终端设备对目标数据进行加扰的具体实现方法与图3所示实施例中基站对目标数据进行加扰的具体实现方法类似，为了简洁，在此就不再赘述。
503，该终端设备将该加扰数据发送给该基站。相应的，该基站接收来自于该终端设备的加扰数据。
504，该基站处理该加扰数据。
该基站处理加扰数据的具体实现方法与图2所示实施例中基站处理加扰数据的具体实现方法类似，为了简洁，在此就不再赘述。
可以理解的是，上述实施例中的网络设备是以基站为例进行描述的。上述实施例中由基站执行的各个步骤也可以由其他网络设备(例如管理实体、核心网设备等设备)来实现。例如，管理实体可以获取终端设备的加扰能力并确定加扰策略指示信息，该管理实体将确定的加扰策略指示信息通过基站发送给终端设备；该终端设备根据该加扰策略指示信息确定加扰数据，然后将该加扰数据通过该基站发送给该管理实体。
图6是根据本申请实施例提供的一种通信设备的示意性结构框图。如图6所示的通信设备600包括获取单元601，加扰单元602和发送单元603。
获取单元601用于获取加扰指示信息，该加扰指示信息用于指示通信设备600使用的加扰策略。
加扰单元601用于根据该加扰策略指示信息，对目标数据进行加扰，得到加扰数据，其中，该目标数据是用于AI模型的数据。
发送单元603，用于向另一通信设备发送该加扰数据。
在一些实施例中，通信设备600可以是终端设备或终端设备中的部件(例如芯片、芯片系统等)。
在另一些实施例中，通信设备600可以是网络设备或网络设备中的部件(例如芯片、芯片系统等)。
获取单元601和加扰单元602可以由处理器或逻辑电路实现，发送单元603可以由发送器或输入/输出接口实现。
获取单元601，加扰单元602和发送单元603的具体功能和有益效果可以参见上述实施例，为了简洁，在此就不再赘述。
图7是根据本申请实施例提供的另一通信设备的示意性结构框图。如图7所示的通信设备700包括处理单元701、发送单元702和接收单元703。
处理单元701用于确定加扰策略指示信息，该加扰策略指示信息用于指示另一通信设备使用的加扰策略。
发送单元702用于向该另一通信设备发送该加扰策略指示信息。
接收单元703用于接收来自于该另一通信设备的加扰数据。
处理单元701还用于根据该加扰数据，确定AI模型的数据。
在一些实施例中，通信设备700可以是终端设备或终端设备中的部件(例如芯片、芯片系统等)。
在另一些实施例中，通信设备700可以是网络设备或网络设备中的部件(例如芯片、芯片系统等)。
处理单元701可以由处理器或逻辑电路实现，发送单元702和接收单元703可以由发送器或输入输出接口实现。
处理单元701，发送单元702和接收单元703的具体功能和有益效果可以参见上述实施例，为了简洁，在此就不再赘述。
图8示出了一种简化的终端设备的结构示意图。便于理解和图示方便，图8中，终端设备以手机作为例子。如图8所示，终端设备包括处理器、存储器、射频电路、天线以及输入输出装置。处理器主要用于对通信协议以及通信数据进行处理，以及对终端设备进行控制，执行软件程序，处理软件程序的数据等。存储器主要用于存储软件程序和数据。射频电路主要用于基带信号与射频信号的转换以及对射频信号的处理。天线主要用于收发电磁波形式的射频信号。输入输出装置，例如触摸屏、显示屏，键盘等主要用于接收用户输入的数据以及对用户输出数据。需要说明的是，有些种类的终端设备可以不具有输入输出装置。
当需要发送数据时，处理器对待发送的数据进行基带处理后，输出基带信号至射频电路，射频电路将基带信号进行射频处理后将射频信号通过天线以电磁波的形式向外发送。当有数据发送到终端设备时，射频电路通过天线接收到射频信号，将射频信号转换为基带信号，并将基带信号输出至处理器，处理器将基带信号转换为数据并对该数据进行处理。为便于说明，图8中仅示出了一个存储器和处理器，在实际的终端设备产品中，可以存在一个或多个处理器和一个或多个存储器。存储器也可以称为存储介质或者存储设备等。存储器可以是独立于处理器设置，也可以是与处理器集成在一起，本申请实施例对此不做限制。
在本申请实施例中，可以将具有收发功能的天线和射频电路视为终端设备的收发单元，将具有处理功能的处理器视为终端设备的处理单元。
如图8所示，终端设备包括射频电路810、处理器820和存储器830。射频电路810也可以称为收发单元、收发模块、收发器、收发机、收发装置等。处理器820也可以称为处理单元，处理单板，处理模块、处理装置等。可选地，可以将射频电路810中用于实现接收功能的器件视为接收单元，将射频电路810中用于实现发送功能的器件视为发送单元，即射频电路810包括接收单元和发送单元。射频电路810有时也可以称为收发单元、收发机、收发器、或收发电路等。接收单元有时也可以称为接收机、接收器、或接收电路等。发送单元有时也可以称为发射机、发射器或者发射电路等。存储器830用于存储指令和/或程序代码。处理器820读取并执行存储器830存储的指令和/或代码，结合射频电路810实现上述方法实施例中的步骤。
例如，在一种实现方式中，处理器820，用于执行图2中的步骤205，处理器820还用于执行本申请实施例中终端设备侧的其他处理步骤。射频电路810还用于执行图2中所示的步骤204，射频电路810还用于执行终端设备侧的其他收发步骤。
又如，在一种实现方式中，处理器820，用于执行图3中的步骤304。射频电路810还用于执行图3中所示的步骤303。
又如，在一种实现方式中，处理器820，用于执行图4中的步骤403，处理器820还用于执行本申请实施例中终端设备侧的其他处理步骤。射频电路810还用于执行图4中所示的步骤404，射频电路810还用于执行终端设备侧的其他收发步骤。
又如，在一种实现方式中，处理器820，用于执行图5中的步骤501，处理器820还用于执行本申请实施例中终端设备侧的其他处理步骤。射频电路810还用于执行图5中所示的步骤503。
应理解，图8仅为示例而非限定，上述包括射频电路810、处理器820和存储器830的终端设备可以不依赖于图8所示的结构。
图9示出了一种简化的网络设备结构示意图。网络设备包括910部分以及920部分。910部分主要用于射频信号的收发以及射频信号与基带信号的转换；920部分主要用于基带处理，对网络设备进行控制等。920部分通常是网络设备的控制中心，用于控制网络设备执行上述方法实施例中网络设备侧的处理操作。
910部分的收发单元，也可以称为收发机或收发器等，其包括天线和射频单元，其中射频单元主要用于进行射频处理。可选地，可以将910部分中用于实现接收功能的器件视为接收单元，将用于实现发送功能的器件视为发送单元，即910部分包括接收单元和发送单元。接收单元也可以称为接收机、接收器、或接收电路等，发送单元可以称为发射机、发射器或者发射电路等。
920部分可以包括一个或多个单板，每个单板可以包括一个或多个处理器和一个或多个存储器。处理器用于读取和执行存储器中的程序以实现基带处理功能以及对网络设备的控制。若存在多个单板，各个单板之间可以互联以增强处理能力。作为一种可选的实施方式，也可以是多个单板共用一个或多 个处理器，或者是多个单板共用一个或多个存储器，或者是多个单板同时共用一个或多个处理器。
例如，在一种实现方式中，910部分的器用于执行图2中所示的步骤204，910部分的收发单元还用于执行本申请实施例中网络设备侧的其他收发步骤。920部分的处理器用于执行图2中的步骤203的处理操作，920部分的处理器还用于执行本申请实施例中网络设备侧的处理步骤。
又如，在一种实现方式中，910部分的器用于执行图3中所示的步骤303。920部分的处理器用于执行图3中的步骤302的处理操作，920部分的处理器还用于执行本申请实施例中网络设备侧的处理步骤。
又如，在一种实现方式中，910部分的器用于执行图4中所示的步骤504，910部分的收发单元还用于执行本申请实施例中网络设备侧的其他收发步骤。920部分的处理器用于执行图4中的步骤405的处理操作。
又如，在一种实现方式中，910部分的器用于执行图5中所示的步骤503。920部分的处理器用于执行图5中的步骤504的处理操作。
应理解，图9仅为示例而非限定，上述包括收发单元和处理单元的网络设备可以不依赖于图9所示的结构。
另外，网络设备不限于上述形态，也可以是其它形态：例如CU和DU分离架构，还可以为其它形态，本申请不限定。
应理解，上述处理器可以是一个芯片。例如，该处理器可以是现场可编程门阵列(field programmable gate array，FPGA)，可以是专用集成芯片(application specific integrated circuit，ASIC)，还可以是系统芯片(system on chip，SoC)，还可以是中央处理器(central processor unit，CPU)，还可以是网络处理器(network processor，NP)，还可以是数字信号处理电路(digital signal processor，DSP)，还可以是微控制器(micro controller unit，MCU)，还可以是可编程控制器(programmable logic device，PLD)、其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件，或其他集成芯片。
在实现过程中，上述方法的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。为避免重复，这里不再详细描述。
应注意，本申请实施例中的处理器可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。
可以理解，本申请实施例中的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-only memory，ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic RAM，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。应注意，本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
根据本申请实施例提供的方法，本申请还提供一种计算机程序产品，该计算机程序产品包括：计算机程序代码，当该计算机程序代码在计算机上运行时，使得该计算机执行上述实施例中由终端设备 执行的各个步骤。
根据本申请实施例提供的方法，本申请还提供一种计算机可读介质，该计算机可读介质存储有程序代码，当该程序代码在计算机上运行时，使得该计算机执行上述实施例中由终端设备执行的各个步骤。
根据本申请实施例提供的方法，本申请实施例提供一种芯片系统，该芯片系统包括逻辑电路，该逻辑电路用于与输入/输出接口耦合，通过该输入/输出接口传输数据，以执行上述实施例中由终端设备执行的各个步骤。
根据本申请实施例提供的方法，本申请还提供一种计算机程序产品，该计算机程序产品包括：计算机程序代码，当该计算机程序代码在计算机上运行时，使得该计算机执行上述实施例中由网络设备执行的各个步骤。
根据本申请实施例提供的方法，本申请还提供一种计算机可读介质，该计算机可读介质存储有程序代码，当该程序代码在计算机上运行时，使得该计算机执行上述实施例中由网络设备执行的各个步骤。
根据本申请实施例提供的方法，本申请实施例提供一种芯片系统，该芯片系统包括逻辑电路，该逻辑电路用于与输入/输出接口耦合，通过该输入/输出接口传输数据，以执行上述实施例中由网络设备执行的各个步骤。
根据本申请实施例提供的方法，本申请实施例还提供一种系统，包括网络设备和一个或多个终端设备。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (31)

  1. 一种传输数据的方法，其特征在于，所述方法包括：
    第一通信设备获取加扰策略指示信息，所述加扰策略指示信息用于指示所述第一通信设备使用的加扰策略；
    所述第一通信设备根据所述加扰策略指示信息，对目标数据进行加扰，得到加扰数据，其中，所述目标数据是用于人工智能AI模型的数据；
    所述第一通信设备向第二通信设备发送所述加扰数据。
  2. 根据权利要求1所述的方法，其特征在于，所述加扰策略指示信息具体用于指示所述第二通信设备的计算能力。
  3. 根据权利要求2所述的方法，其特征在于，所述加扰策略指示信息，还用于指示以下信息中的至少一种：对应于所述加扰数据的AI模型的精确度需求、加扰等级、所述第二通信设备的存储能力，或者，数据加扰权限。
  4. 根据权利要求1所述的方法，其特征在于，所述加扰策略指示信息具体用于指示至少一个加扰策略，其中所述加扰策略包括：加扰算法。
  5. 根据权利要求4所述的方法，其特征在于，所述加扰策略还包括以下信息中的至少一种：加扰等级、对应于所述加扰数据的AI模型的精确度需求，或者，防泄漏的数据类型。
  6. 根据权利要求4或5所述的方法，其特征在于，当所述加扰策略指示信息用于指示多个加扰策略时，所述第一通信设备根据所述加扰策略指示信息，对目标数据进行加扰，包括：
    所述第一通信设备从所述多个加扰策略中确定目标加扰策略；
    所述第一通信设备根据所述目标加扰策略对所述目标数据进行加扰。
  7. 根据权利要求4至6中任一项所述的方法，其特征在于，在所述第一通信设备获取加扰策略指示信息之前，所述方法还包括：
    所述第一通信设备向第二通信设备发送加扰能力指示信息，所述加扰能力指示信息用于指示以下信息中的至少一种：所述第一通信设备支持的加扰算法、所述第一通信设备支持的加扰等级、所述第一通信设备的加扰数据恢复能力，或者，所述目标数据与所述加扰数据的差异信息。
  8. 根据权利要求4至7中任一项所述的方法，其特征在于，在所述第一通信设备获取加扰策略指示信息之前，所述方法还包括：
    所述第一通信设备向所述第二通信设备发送隐私等级信息，所述隐私等级信息用于指示所述目标数据和/或所述第一通信设备的隐私等级。
  9. 根据权利要求2至8中任一项所述的方法，其特征在于，所述第一通信设备是网络设备，所述第二通信设备是终端设备。
  10. 根据权利要求9所述的方法，其特征在于，所述目标数据包括以下数据中的至少一种：所述AI模型的参数，或者，所述AI模型的输出数据。
  11. 根据权利要求2至8中任一项所述的方法，其特征在于，所述第一通信设备是终端设备，所述第二通信设备是网络设备。
  12. 根据权利要求11所述的方法，其特征在于，所述目标数据是所述AI模型的输入数据，或者，所述目标数据是用于训练所述AI模型的训练数据。
  13. 一种传输数据的方法，其特征在于，所述方法包括：
    第二通信设备确定加扰策略指示信息，所述加扰策略指示信息用于指示第一通信设备使用的加扰策略
    所述第二通信设备向所述第一通信设备发送所述加扰策略指示信息；
    所述第二通信设备接收来自于所述第一通信设备的加扰数据；
    所述第二通信设备根据所述加扰数据，确定人工智能AI模型的数据，其中所述第一通信设备和所述第二通信设备是移动通信系统中的通信设备。
  14. 根据权利要求13所述的方法，其特征在于，所述加扰策略指示信息具体用于指示所述第二通 信设备的计算能力。
  15. 根据权利要求14所述的方法，其特征在于，所述加扰策略指示信息，还用于指示以下信息中的至少一种：所述AI模型的精确度需求、加扰等级、所述第二通信设备的存储能力，或者，数据加扰权限。
  16. 根据权利要求13所述的方法，其特征在于，所述加扰策略指示信息具体用于指示至少一个加扰策略，其中所述加扰策略包括：加扰算法。
  17. 根据权利要求16所述的方法，其特征在于，所述加扰策略还包括以下信息中的至少一种：加扰等级、所述AI模型的精确度需求，或者，防泄漏的数据类型。
  18. 根据权利要求16或17所述的方法，其特征在于，在所述第二通信设备确定加扰策略指示信息之前，所述方法还包括：
    所述第二通信设备接收来自于第一通信设备加扰能力指示信息，所述加扰能力指示信息用于指示以下信息中的至少一种：所述第一通信设备支持的加扰算法、所述第一通信设备支持的加扰等级、所述第一通信设备的加扰数据恢复能力，或者，需要加扰的数据与所述加扰数据的差异信息；
    所述第二通信设备确定加扰策略指示信息，包括：
    所述第二通信设备根据所述加扰能力指示信息，确定所述加扰策略指示信息。
  19. 根据权利要求18所述的方法，其特征在于，在所述第二通信设备确定加扰策略指示信息之前，所述方法还包括：
    所述第二通信设备接收来自于所述第一通信设备的隐私等级信息，所述隐私等级信息用于指示所述加扰数据和/或所述第一通信设备的隐私等级；
    所述第二通信设备根据所述加扰能力指示信息，确定所述加扰策略指示信息，包括：
    所述第二通信设备根据所述加扰能力指示信息和所述隐私等级信息，确定所述加扰策略指示信息。
  20. 根据权利要求14至19中任一项所述的方法，其特征在于，所述第一通信设备是网络设备，所述第二通信设备是终端设备。
  21. 根据权利要求20所述的方法，其特征在于，所述第二通信设备根据所述加扰数据，确定人工智能AI模型的数据，包括：
    所述第二通信设备数据根据所述加扰数据确定所述AI模型的参数或者所述AI模型的输出数据。
  22. 根据权利要求14至19中任一项所述的方法，其特征在于，所述第一通信设备是终端设备，所述第二通信设备是网络设备。
  23. 根据权利要求22所述的方法，其特征在于，所述第二通信设备根据所述加扰数据，确定人工智能AI模型的数据，包括：
    所述第二通信设备数据根据所述加扰数据确定所述AI模型的输入数据，或者，用于训练所述AI模型的训练数据。
  24. 一种通信设备，其特征在于，包括用于执行根据权利要求1至12中任一项所述方法的模块。
  25. 一种通信设备，其特征在于，包括用于执行根据权利要求13至23中任一项所述方法的模块。
  26. 一种通信设备，其特征在于，包括：处理器，所述处理器用于与存储器耦合，读取并执行所述存储器中的指令和/或程序代码，以执行如权利要求1-12中任一项所述的方法。
  27. 一种通信设备，其特征在于，包括：处理器，所述处理器用于与存储器耦合，读取并执行所述存储器中的指令和/或程序代码，以执行如权利要求13-23中任一项所述的方法。
  28. 一种芯片系统，其特征在于，包括：逻辑电路，所述逻辑电路用于与输入/输出接口耦合，通过所述输入/输出接口传输数据，以执行如权利要求1-12中任一项所述的方法。
  29. 一种芯片系统，其特征在于，包括：逻辑电路，所述逻辑电路用于与输入/输出接口耦合，通过所述输入/输出接口传输数据，以执行如权利要求13-23中任一项所述的方法。
  30. 一种计算机可读介质，其特征在于，所述计算机可读介质存储有程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行如权利要求1-12中任一项所述的方法。
  31. 一种计算机可读介质，其特征在于，所述计算机可读介质存储有程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行如权利要求13-23中任一项所述的方法。
PCT/CN2023/120430 2022-09-27 2023-09-21 传输数据的方法和相关装置 Ceased WO2024067351A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP23870583.4A EP4583464A4 (en) 2022-09-27 2023-09-21 DATA TRANSMISSION METHOD AND ASSOCIATED DEVICE
US19/089,858 US20250227685A1 (en) 2022-09-27 2025-03-25 Data transmission method and related apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211184806.1A CN117792838A (zh) 2022-09-27 2022-09-27 传输数据的方法和相关装置
CN202211184806.1 2022-09-27

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US19/089,858 Continuation US20250227685A1 (en) 2022-09-27 2025-03-25 Data transmission method and related apparatus

Publications (1)

Publication Number Publication Date
WO2024067351A1 true WO2024067351A1 (zh) 2024-04-04

Family

ID=90378692

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/120430 Ceased WO2024067351A1 (zh) 2022-09-27 2023-09-21 传输数据的方法和相关装置

Country Status (4)

Country Link
US (1) US20250227685A1 (zh)
EP (1) EP4583464A4 (zh)
CN (1) CN117792838A (zh)
WO (1) WO2024067351A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118734335A (zh) * 2024-07-03 2024-10-01 中国工商银行股份有限公司 跨境担保数据处理方法及装置
WO2025251323A1 (zh) * 2024-06-07 2025-12-11 Oppo广东移动通信有限公司 无线通信的方法和通信设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021232832A1 (zh) * 2020-05-19 2021-11-25 华为技术有限公司 数据处理方法、联邦学习的训练方法及相关装置、设备
US20220060328A1 (en) * 2020-08-21 2022-02-24 Huawei Technologies Co., Ltd. Method and apparatus for supporting secure data routing
WO2022142366A1 (zh) * 2020-12-31 2022-07-07 华为技术有限公司 机器学习模型更新的方法和装置
WO2022158686A1 (ko) * 2021-01-20 2022-07-28 삼성전자 주식회사 암호화된 정보에 기초하여, 인공지능 모델을 이용한 추론을 수행하는 전자 장치 및 그 동작 방법

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11095618B2 (en) * 2018-03-30 2021-08-17 Intel Corporation AI model and data transforming techniques for cloud edge
CN112651511B (zh) * 2020-12-04 2023-10-03 华为技术有限公司 一种训练模型的方法、数据处理的方法以及装置
CN114692194A (zh) * 2020-12-31 2022-07-01 维沃移动通信有限公司 信息隐私保护的方法、装置、设备及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021232832A1 (zh) * 2020-05-19 2021-11-25 华为技术有限公司 数据处理方法、联邦学习的训练方法及相关装置、设备
US20220060328A1 (en) * 2020-08-21 2022-02-24 Huawei Technologies Co., Ltd. Method and apparatus for supporting secure data routing
WO2022142366A1 (zh) * 2020-12-31 2022-07-07 华为技术有限公司 机器学习模型更新的方法和装置
WO2022158686A1 (ko) * 2021-01-20 2022-07-28 삼성전자 주식회사 암호화된 정보에 기초하여, 인공지능 모델을 이용한 추론을 수행하는 전자 장치 및 그 동작 방법

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4583464A4

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025251323A1 (zh) * 2024-06-07 2025-12-11 Oppo广东移动通信有限公司 无线通信的方法和通信设备
CN118734335A (zh) * 2024-07-03 2024-10-01 中国工商银行股份有限公司 跨境担保数据处理方法及装置

Also Published As

Publication number Publication date
EP4583464A1 (en) 2025-07-09
CN117792838A (zh) 2024-03-29
US20250227685A1 (en) 2025-07-10
EP4583464A4 (en) 2025-12-03

Similar Documents

Publication Publication Date Title
US20230179490A1 (en) Artificial intelligence-based communication method and communication apparatus
CN115462045B (zh) 用于非实时ran智能控制器的功能架构和接口
Manap et al. Survey of radio resource management in 5G heterogeneous networks
US20230010095A1 (en) Methods for cascade federated learning for telecommunications network performance and related apparatus
WO2020080989A1 (en) Handling of machine learning to improve performance of a wireless communications network
WO2018024128A1 (zh) 一种小区配置方法及装置
Gharsallah et al. SDN/NFV‐based handover management approach for ultradense 5G mobile networks
US20230099006A1 (en) Spectral Efficiency Prediction with Artificial Intelligence for Enhancing Carrier Aggregation and Proactive Radio Resource Management
US20250227685A1 (en) Data transmission method and related apparatus
CN118509872A (zh) 通信方法和装置
US20240078439A1 (en) Training Data Set Obtaining Method, Wireless Transmission Method, and Communications Device
US20240236713A9 (en) Signalling support for split ml-assistance between next generation random access networks and user equipment
Madelkhanova et al. Optimization of cell individual offset for handover of flying base stations and users
WO2024093503A1 (zh) 一种处理模型的方法和装置
WO2024169600A1 (zh) 一种通信方法及装置
WO2023198275A1 (en) User equipment machine learning action decision and evaluation
WO2025124214A1 (zh) 通信方法和通信装置
CN116419331A (zh) 切换方法、装置及存储介质
CN118036777A (zh) 模型训练方法、模型测试方法、装置及存储介质
Semov et al. Autonomous learning model for achieving multi cell load balancing capabilities in HetNet
US20250301342A1 (en) AI/ML Model/Functionality Adaptation for RRM Enhancements
CN121368035A (zh) 通信方法及通信装置
WO2026061059A1 (zh) 一种模型注册及访问的方法和装置
WO2025092567A1 (zh) 一种传输人工智能模型的方法和通信装置
Yang et al. Backhaul-aware adaptive TP selection for virtual cell in ultra-dense networks

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23870583

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023870583

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2023870583

Country of ref document: EP

Effective date: 20250401

NENP Non-entry into the national phase

Ref country code: DE

WWP Wipo information: published in national office

Ref document number: 2023870583

Country of ref document: EP