WO2022077946A1 - 数据测量方法、装置、电子设备和计算机可读介质 - Google Patents

数据测量方法、装置、电子设备和计算机可读介质 Download PDF

Info

Publication number
WO2022077946A1
WO2022077946A1 PCT/CN2021/101133 CN2021101133W WO2022077946A1 WO 2022077946 A1 WO2022077946 A1 WO 2022077946A1 CN 2021101133 W CN2021101133 W CN 2021101133W WO 2022077946 A1 WO2022077946 A1 WO 2022077946A1
Authority
WO
WIPO (PCT)
Prior art keywords
training
target
model
deep learning
learning network
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/CN2021/101133
Other languages
English (en)
French (fr)
Inventor
张敏
高庆
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.)
Ennew Digital Technology Co Ltd
Original Assignee
Ennew Digital Technology 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 Ennew Digital Technology Co Ltd filed Critical Ennew Digital Technology Co Ltd
Priority to EP21878996.4A priority Critical patent/EP4131082B1/en
Priority to JP2022539397A priority patent/JP7717698B2/ja
Publication of WO2022077946A1 publication Critical patent/WO2022077946A1/zh
Priority to US17/828,028 priority patent/US20220300858A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
    • 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
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/44—Program or device authentication
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units
    • G06F3/147—Digital output to display device ; Cooperation and interconnection of the display device with other functional units using display panels
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/098—Distributed learning, e.g. federated learning
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G2350/00—Solving problems of bandwidth in display systems
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G2354/00—Aspects of interface with display user
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G2358/00—Arrangements for display data security
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G2370/00—Aspects of data communication
    • G09G2370/04—Exchange of auxiliary data, i.e. other than image data, between monitor and graphics controller

Definitions

  • Embodiments of the present disclosure relate to the field of computer technology, and in particular, to a data measurement method, apparatus, electronic device, and computer-readable medium.
  • Some embodiments of the present disclosure propose data measurement methods, apparatuses, electronic devices, and computer-readable media to solve the technical problems mentioned in the background section above.
  • some embodiments of the present disclosure provide a data measurement method, the method includes: acquiring a data set; processing the data set to obtain a processing result; determining the processing result as a measurement result, and controlling A target device with a display function displays the measurement results.
  • some embodiments of the present disclosure provide a data measurement apparatus, the apparatus includes: an acquisition unit configured to acquire a data set; a processing unit configured to process the data set to obtain a processing result; display a unit configured to determine the processing result as a measurement result, and to control a target device having a display function to display the measurement result.
  • some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device on which one or more programs are stored, when one or more programs are stored by one or more The processor executes such that the one or more processors implement the method as described in the first aspect.
  • some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method as described in the first aspect.
  • One of the above embodiments of the present disclosure has the following beneficial effects: by inputting the data set into a pre-trained deep learning network, measurement results that meet user requirements can be obtained. It meets the needs of users for data calculation, and provides convenience for users to use data in the future.
  • FIG. 1 is a schematic diagram of an application scenario of a data measurement method according to some embodiments of the present disclosure
  • FIG. 3 is a flowchart of some embodiments of training of a deep learning network according to the data measurement method of the present disclosure
  • FIG. 4 is a schematic structural diagram of some embodiments of a data measurement device according to the present disclosure.
  • FIG. 5 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure.
  • FIG. 1 is a schematic diagram of an application scenario of a data measurement method according to some embodiments of the present disclosure.
  • the computing device 101 may acquire the data set 102 .
  • the computing device 101 may then input the data set 102 to the pre-trained deep learning network and output the processing result 103 .
  • computing device 101 may determine processing result 103 as measurement result 104 .
  • the computing device 101 may control the target device with display capabilities to display the measurement results 104 .
  • the above computing device 101 may be hardware or software.
  • the computing device When the computing device is hardware, it can be implemented as a distributed cluster composed of multiple servers or terminal devices, or can be implemented as a single server or a single terminal device.
  • a computing device When a computing device is embodied as software, it may be installed in the hardware devices listed above. It can be implemented, for example, as multiple software or software modules for providing distributed services, or as a single software or software module. There is no specific limitation here.
  • FIG. 1 is merely illustrative. There may be any number of computing devices depending on implementation needs.
  • the method may be performed by computing device 101 in FIG. 1 .
  • the data measurement method includes the following steps:
  • Step 201 acquiring a data set.
  • the execution body of the data measurement method may acquire the data set through a wired connection or a wireless connection.
  • the above-mentioned execution body may receive the data set input by the user as the above-mentioned data set.
  • the above-mentioned executive body may connect to other electronic devices through wired connection or wireless connection, and obtain the data set in the database of the connected electronic device as the above-mentioned data set.
  • wireless connection methods may include but are not limited to 3G/4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or developed in the future .
  • Step 202 Input the data set into a pre-trained deep learning network, and output a processing result.
  • the above-mentioned execution body may input the above-mentioned data set to a pre-trained deep learning network, and output a processing result.
  • the input of the deep learning network can be a data set, and the output can be the processing result.
  • the above deep learning network may be a Recurrent Neural Network (RNN) or a Long Short-Term Memory network (LSTM).
  • the data set may be "flue gas temperature, flue gas flow, flue gas humidity, steam flow and economizer outlet temperature".
  • the output processing result may be the oxygen content of the boiler flue gas.
  • the training of the deep learning network includes: in response to receiving a training request from a target user, acquiring the identity information of the target user; verifying the identity information, and determining whether the verification is passed; After the verification of the identity information is passed, the target training engine is controlled to start training.
  • Step 203 Determine the processing result as a measurement result, and control the target device with a display function to display the measurement result.
  • the above-mentioned execution body may determine the above-mentioned processing result as a measurement result. Then, the above-mentioned execution body may push the above-mentioned measurement result to a target device with a display function, and control the above-mentioned target device to display the above-mentioned measurement result.
  • One of the above-mentioned embodiments of the present disclosure has the following beneficial effects: by inputting the data set into a pre-trained deep learning network, measurement results that meet user requirements can be obtained. It meets the needs of users for data calculation, and provides convenience for users to use data in the future.
  • a flowchart 300 of some embodiments of training of a deep learning network according to the data measurement method of the present disclosure is shown.
  • the method may be performed by computing device 101 in FIG. 1 .
  • the data measurement method includes the following steps:
  • Step 301 in response to receiving a training request from a target user, acquire identity information of the target user.
  • the execution body of the data measurement method may acquire the identity information of the target user in response to receiving the training request of the target user.
  • the training request may be an instruction to start training the model.
  • the target user can be a user who has training requirements and has passed the pre-set registration, authentication, etc. verification.
  • Step 302 Verify the identity information to determine whether the verification is passed.
  • the above-mentioned execution subject may verify the above-mentioned identity information, and determine whether the verification is passed.
  • the above-mentioned execution subject searches a pre-built identity information database based on the above-mentioned identity information, and determines whether the above-mentioned identity information exists in the above-mentioned identity information database.
  • the above-mentioned execution body may determine that the above-mentioned verification is successful.
  • Step 303 in response to determining that the identity information verification is passed, control the target training engine to start training.
  • the execution subject may control the target training engine to start training.
  • the training engine can be an engine that supports multiple algorithm selection modules for different business scenarios that need to provide support for training deep learning networks.
  • Step 304 in response to detecting that the target user selects a training model in the training model library, verify the target training engine to determine whether the verification is passed.
  • the execution body in response to detecting the selection operation of the target user on the training model in the training model library, may verify the target training engine.
  • the training model library may be a collection of training models that meet the user's needs for selection by the user.
  • the above-mentioned execution body may perform authority verification on the above-mentioned target training engine to determine whether the above-mentioned target training engine has authority to support the training of the training model selected by the target user.
  • the training model library may be "train model A, train model B, train model C".
  • the training authority of the target engine can be "train model A and train model C”. If the target user selects the training model as "training model B", the above-mentioned execution subject may determine that the verification of the above-mentioned target training engine fails. On the contrary, the above-mentioned executive body may determine that the verification of the above-mentioned target training engine is passed.
  • Step 305 in response to determining that the target training engine has passed the verification, transmit the initial model to the terminal device of the target user.
  • the initial model may be transmitted to the terminal device of the target user through the execution subject in response to determining the target training engine verification.
  • the above-mentioned initial model may be a model that has not been trained, or that does not meet the preset condition after training.
  • the above-mentioned initial model may also be a model with a deep neural network structure.
  • the pre-trained feature extraction model may be a pre-trained neural network model for feature extraction.
  • the neural network model can have various existing neural network structures.
  • the neural network structure may be a Convolutional Neural Network (CNN).
  • the initial model can use extreme gradient boosting (eXtreme Gradient Boosting, XGBoost).
  • XGBoost extreme gradient boosting
  • the storage location of the initial model is also not limited in this disclosure.
  • Step 306 using the obtained training sample set to train the initial model to obtain an initial model that has been trained.
  • the above-mentioned execution body may use the above-mentioned acquired training sample set to start training the above-mentioned initial model, and the training process is as follows: the first step is to select training samples from the above-mentioned training sample set, wherein the training samples include sample data Collection and sample processing results; in the second step, the above-mentioned execution body can input the sample data set in the training sample into the above-mentioned initial model; in the third step, the output processing results are compared with the above-mentioned sample processing results to obtain the processing result loss value; In the fourth step, the above-mentioned execution body can compare the loss value of the above-mentioned processing result with a preset threshold to obtain a comparison result; in the fifth step, according to the comparison result, determine whether the training of the above-mentioned initial model is completed; in the sixth step, in response to the above-mentioned initial training model After the training is completed, the above-mentioned initial model is determined as the
  • the loss value of the processing result stated above may be a value obtained by taking the output processing result and the corresponding sample processing result as parameters and inputting the executed loss function.
  • the loss function (such as square loss function, exponential loss function, etc.) is usually used to estimate the predicted value of the model (such as the above-mentioned sample processing result corresponding to the sample data set) and the real value (such as the processing result obtained by the above steps) degree of inconsistency. It is a non-negative real-valued function.
  • the smaller the loss function the better the robustness of the model.
  • the loss function can be set according to actual needs.
  • the loss function may be a cross entropy loss function (Cross Entropy).
  • the above method further includes: in response to determining that the training of the initial model is not completed, adjusting relevant parameters in the initial model, and reselecting samples from the training sample set, using the adjusted initial model The model is used as the initial model, and the above training steps are continued.
  • the above-mentioned initial model after training can be guaranteed to be continuously uploaded and downloaded between the above-mentioned terminal device and the above-mentioned target training engine under the premise of a compression protocol and a security protocol, and iteratively is continuously updated to update The initial model trained above.
  • Step 307 using the target training engine to aggregate at least one model stored in the terminal device and the initial model after training to obtain a joint training model.
  • the above-mentioned execution body may use the above-mentioned target training engine to aggregate at least one model stored in the above-mentioned terminal device and the above-mentioned initial model after training to obtain a joint training model.
  • the above-mentioned method further includes: in response to detecting the termination joint request of the above-mentioned target user, controlling the above-mentioned target training engine to stop training, and storing the joint training model when the training is stopped to the target Model library.
  • the above-mentioned executive body may generate an interface for the above-mentioned joint training model, and then store the joint training model after the interface is generated in the target model library.
  • the above-mentioned executive body may store the training records related to the above-mentioned joint training model and the state information in the training process in the cloud database.
  • the above method further includes: in response to detecting the query operation of the target user, obtaining a query interface; extracting an interface from the target model library that is the same as the query interface
  • the history record and status information of the model, and the control tool displays the history record and the status information on the target device.
  • the history record can be information for each training in the model training process.
  • the process 300 of the data measurement method in some embodiments corresponding to FIG. 3 reflects the process of how to train a deep learning network and obtain a joint training model. step. Therefore, the solutions described in these embodiments can obtain measurement results that meet user requirements by processing the data set. It meets the needs of users for data calculation, and provides convenience for users to use data in the future.
  • using the joint training model to measure and calculate the data can greatly avoid errors caused by manual calculation, and obtain more accurate measurement results. Users can select training models for different business scenarios, which improves the utilization rate of the models, and the generated joint training models are more in line with user needs, which improves user experience.
  • the present disclosure provides some embodiments of a data measurement apparatus, and these apparatus embodiments correspond to the above-mentioned method embodiments in FIG. 2 , and the apparatus can be specifically applied in various electronic devices.
  • the data measurement apparatus 400 of some embodiments includes: an acquisition unit 401 , a processing unit 402 and a display unit 403 .
  • the acquiring unit 401 is configured to acquire a data set;
  • the processing unit 402 is configured to input the data set to a pre-trained deep learning network, and output a processing result, wherein the deep learning network is configured by training a sample set obtained through training, the training of the deep learning network includes: in response to receiving a training request from a target user, acquiring the identity information of the target user; verifying the identity information, and determining whether the verification is passed; in response to determining the After the identity information verification is passed, the target training engine is controlled to start training; the display unit 403 is configured to determine the processing result as a measurement result, and control the target device with a display function to display the measurement result.
  • the training of the deep learning network includes: in response to detecting that the target user selects a training model in the training model library, verifying the target training engine , determine whether the verification is passed; in response to determining that the target training engine has passed the verification, the initial model is transmitted to the terminal device of the target user; using the obtained training sample set, the initial model is trained, and the training is completed. the initial model; using the target training engine to aggregate at least one model stored in the terminal device and the initial model that has been trained to obtain a joint training model.
  • the training samples in the above-mentioned training sample set include a sample data set and a sample processing result
  • the deep learning network takes the sample data set as an input, and processes the sample using the sample data set as input.
  • the result is obtained by training as the desired output.
  • the data measurement apparatus 400 is further configured to: in response to detecting the termination joint request of the target user, to control the target training engine to stop training, and to stop the training
  • the jointly trained model is stored in the target model repository.
  • the data measurement apparatus 400 is further configured to: in response to detecting the query operation of the target user, obtain a query interface; to extract the interface and the selected interface from the target model library
  • the query interface is the same as the history record and status information of the model, and the control device displays the history record and the status information on the target device.
  • the units recorded in the apparatus 400 correspond to the respective steps in the method described with reference to FIG. 2 . Therefore, the operations, features, and beneficial effects described above with respect to the method are also applicable to the apparatus 400 and the units included therein, and details are not described herein again.
  • FIG. 5 a schematic structural diagram of an electronic device (eg, computing device 101 in FIG. 1 ) 500 suitable for implementing some embodiments of the present disclosure is shown.
  • the server shown in FIG. 5 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.
  • an electronic device 500 may include a processing device (eg, a central processing unit, a graphics processor, etc.) 501 that may be loaded into random access according to a program stored in a read only memory (ROM) 502 or from a storage device 508 Various appropriate actions and processes are executed by the programs in the memory (RAM) 503 . In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored.
  • the processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504.
  • An input/output (I/O) interface 505 is also connected to bus 504 .
  • the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration An output device 507 such as a computer; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509 .
  • Communication means 509 may allow electronic device 500 to communicate wirelessly or by wire with other devices to exchange data.
  • FIG. 5 shows electronic device 500 having various means, it should be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in FIG. 5 can represent one device, and can also represent multiple devices as needed.
  • the processes described above with reference to the flowcharts may be implemented as computer software programs.
  • some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from a network via communication device 509, or from storage device 508, or from ROM 502.
  • the processing device 501 When the computer program is executed by the processing device 501, the above-mentioned functions defined in the methods of some embodiments of the present disclosure are performed.
  • the computer-readable medium described above may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the foregoing two.
  • the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above.
  • a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein.
  • Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, electrical wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.
  • the client and server can use any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol) to communicate, and can communicate with digital data in any form or medium Communication (eg, a communication network) interconnects.
  • HTTP HyperText Transfer Protocol
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks), as well as any currently known or future development network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned apparatus; or may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: acquires a data set; inputs the data set into a pre-trained deep learning network, and outputs processing As a result, the deep learning network is obtained by training the training sample set, and the training of the deep learning network includes: in response to receiving the training request of the target user, obtaining the identity information of the target user; verifying the identity information, and determining whether the verification passes ; in response to determining that the identity information verification is passed, control the target training engine to start training; determine the processing result as a measurement result, and control the target device with a display function to display the measurement result.
  • Computer program code for carrying out operations of some embodiments of the present disclosure may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, or a combination thereof, Also included are conventional procedural programming languages - such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider to via Internet connection).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.
  • the units described in some embodiments of the present disclosure may be implemented by means of software, and may also be implemented by means of hardware.
  • the described unit can also be provided in the processor, for example, it can be described as: a processor includes an acquisition unit, a processing unit and a display unit. Wherein, the names of these units do not constitute a limitation on the unit itself under certain circumstances, for example, the acquisition unit may also be described as a "unit for acquiring a data set".
  • exemplary types of hardware logic components include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on Chips (SOCs), Complex Programmable Logical Devices (CPLDs) and more.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs Systems on Chips
  • CPLDs Complex Programmable Logical Devices

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computer Security & Cryptography (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Hardware Design (AREA)
  • Human Computer Interaction (AREA)
  • Medical Informatics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • User Interface Of Digital Computer (AREA)
  • Debugging And Monitoring (AREA)

Abstract

一种数据测量方法、装置、电子设备和计算机可读介质，该方法包括：获取数据集合（102）；将数据集合（102）输入至预先训练的深度学习网络，输出处理结果（103），其中，深度学习网络是通过训练样本集合训练得到的，深度学习网络的训练包括：响应于接收到目标用户的训练请求，获取目标用户的身份信息；对身份信息进行核验，确定核验是否通过；响应于确定身份信息核验通过，控制目标训练引擎开启训练；将处理结果（103）确定为测量结果（104），以及控制具有显示功能的目标设备显示测量结果（104）。通过将数据集合（102）输入预先训练的深度学习网络，可以得到符合用户需求的测量结果（104）。满足了用户针对数据计算的需求，为用户后续利用数据提供了便利。

Description

数据测量方法、装置、电子设备和计算机可读介质 技术领域
本公开的实施例涉及计算机技术领域，具体涉及数据测量方法、装置、电子设备和计算机可读介质。
背景技术
随着互联网技术的发展，人们进入了大数据的时代。不同领域不同行业会产生不同的数据，人们常常利用得到的数据进行计算来了解行业发展和产业生产。由于数据量庞大，通常会借助一些程序、服务软件来满足用户对数据计算的需求。由此，需要一种高效的、易于管理的数据测量方法。
发明内容
本公开的内容部分用于以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。本公开的内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
本公开的一些实施例提出了数据测量方法、装置、电子设备和计算机可读介质，来解决以上背景技术部分提到的技术问题。
第一方面，本公开的一些实施例提供了一种数据测量方法，该方法包括：获取数据集合；对所述数据集合进行处理，得到处理结果；将所述处理结果确定为测量结果，以及控制具有显示功能的目标设备显示所述测量结果。
第二方面，本公开的一些实施例提供了一种数据测量装置，装置包括：获取单元，被配置成获取数据集合；处理单元，被配置成对所述数据集合进行处理，得到处理结果；显示单元，被配置成将所述处理结果确定为测量结果，以及控制具有显示功能的目标设备显示所述测量结果。
第三方面，本公开的一些实施例提供了一种电子设备，包括：一个或多个处理器；存储装置，其上存储有一个或多个程序，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现如第一方面中所描述的方法。
第四方面，本公开的一些实施例提供了一种计算机可读介质，其上存储有计算机程序，其中，程序被处理器执行时实现如第一方面中所描述的方法。
本公开的上述各个实施例中的一个实施例具有如下有益效果：通过将数据集合输入预先 训练的深度学习网络，可以得到符合用户需求的测量结果。满足了用户针对数据计算的需求，为用户后续利用数据提供了便利。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，元件和元素不一定按照比例绘制。
图1是根据本公开的一些实施例的数据测量方法的一个应用场景的示意图；
图2是根据本公开的数据测量方法的一些实施例的流程图；
图3是根据本公开的数据测量方法的深度学习网络的训练的一些实施例的流程图；
图4是根据本公开的数据测量装置的一些实施例的结构示意图；
图5是适于用来实现本公开的一些实施例的电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例。相反，提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互组合。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
下面将参考附图并结合实施例来详细说明本公开。
图1是根据本公开一些实施例的数据测量方法的一个应用场景的示意图。
在图1的应用场景中，首先，计算设备101可以获取数据集合102。然后，计算设备101可以将数据集合102输入至预先训练的深度学习网络输出处理结果103。最后，计算设备101 可以将处理结果103确定为测量结果104。另外，计算设备101可以控制具有显示功能的目标设备显示测量结果104。
需要说明的是，上述计算设备101可以是硬件，也可以是软件。当计算设备为硬件时，可以实现成多个服务器或终端设备组成的分布式集群，也可以实现成单个服务器或单个终端设备。当计算设备体现为软件时，可以安装在上述所列举的硬件设备中。其可以实现成例如用来提供分布式服务的多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。
应该理解，图1中的计算设备的数目仅仅是示意性的。根据实现需要，可以具有任意数目的计算设备。
继续参考图2，示出了根据本公开的数据测量方法的一些实施例的流程200。该方法可以由图1中的计算设备101来执行。该数据测量方法，包括以下步骤：
步骤201，获取数据集合。
在一些实施例中，数据测量方法的执行主体(如图1所示的计算设备101)可以通过有线连接方式或无线连接方式获取数据集合。例如，上述执行主体可以接收用户输入的数据集合作为上述数据集合。再例如，上述执行主体可以通过有线连接方式或无线连接方式连接其他电子设备，获取所连接的电子设备的数据库中的数据集合作为上述数据集合。
需要指出的是，上述无线连接方式可以包括但不限于3G/4G连接、WiFi连接、蓝牙连接、WiMAX连接、Zigbee连接、UWB(ultra wideband)连接、以及其他现在已知或将来开发的无线连接方式。
步骤202，将所述数据集合输入至预先训练的深度学习网络，输出处理结果。
在一些实施例中，上述执行主体可以将上述数据集合输入至预先训练的深度学习网络，输出处理结果。这里，深度学习网络的输入可以是数据集合，输出可以是处理结果。作为示例，上述深度学习网络可以是循环神经网络(Recurrent Neural Network,RNN)，也可以是长短期记忆网络(Long Short-Term Memory networks，LSTM)。
作为示例，数据集合可以是“烟气温度、烟气流量、烟气湿度、蒸汽流量和节能器出口温度”。输出的处理结果可以是锅炉烟气含氧量。
在一些实施例中，上述深度学习网络的训练包括：响应于接收到目标用户的训练请求，获取所述目标用户的身份信息；对所述身份信息进行核验，确定核验是否通过；响应于确定所述身份信息核验通过，控制目标训练引擎开启训练。
步骤203，将所述处理结果确定为测量结果，以及控制具有显示功能的目标设备显示所 述测量结果。
在一些实施例中，上述执行主体可以将上述处理结果确定为测量结果。然后，上述执行主体可以将上述测量结果推送至具有显示功能的目标设备，以及控制上述目标设备显示上述测量结果。
本公开的上述各个实施例中的一个实施例具有如下有益效果：通过将数据集合输入预先训练的深度学习网络，可以得到符合用户需求的测量结果。满足了用户针对数据计算的需求，为用户后续利用数据提供了便利。
继续参考图3，示出了根据本公开的数据测量方法的深度学习网络的训练的一些实施例的流程图300。该方法可以由图1中的计算设备101来执行。该数据测量方法，包括以下步骤：
步骤301，响应于接收到目标用户的训练请求，获取所述目标用户的身份信息。
在一些实施例中，数据测量方法的执行主体(如图1所示的计算设备101)响应于接收到上述目标用户的训练请求，上述执行主体可以获取上述目标用户的身份信息。这里，训练请求可以是对模型开启训练的指令。目标用户可以是有训练需求的、已通过预先设置的注册、认证等核验的用户。
步骤302，对所述身份信息进行核验，确定核验是否通过。
在一些实施例中，上述执行主体可以对上述身份信息进行核验，确定核验是否通过。作为示例，上述执行主体基于上述身份信息，对预先构建的身份信息库进行检索，确定上述身份信息库中是否存在上述身份信息。响应于确定存在，上述执行主体可以确定上述核验成功。
步骤303，响应于确定所述身份信息核验通过，控制目标训练引擎开启训练。
在一些实施例中，响应于确定上述身份信息核验通过，上述执行主体可以控制目标训练引擎开启训练。训练引擎可以是支持多种算法选择模块，以供不同业务场景需要为训练深度学习网络提供支持的引擎。
步骤304，响应于检测到所述目标用户针对训练模型库中训练模型的选择操作，对所述目标训练引擎进行校验，确定校验是否通过。
在一些实施例中，响应于检测到上述目标用户针对训练模型库中训练模型的选择操作，上述执行主体可以对上述目标训练引擎进行校验。这里，训练模型库可以是供用户选择的满足用户需求的训练模型的集合。作为示例，上述执行主体可以对上述目标训练引擎进行权限校验，确定上述目标训练引擎是否有权限支持目标用户选择的训练模型的训练。
作为示例，训练模型库可以是“训练模型A，训练模型B，训练模型C”。目标引擎的 训练权限可以是“训练模型A和训练模型C”。若目标用户选择训练模型为“训练模型B”，那么，上述执行主体可以确定对上述目标训练引擎的校验不通过。反之，上述执行主体可以确定对上述目标训练引擎的校验通过。
步骤305，响应于确定所述目标训练引擎校验通过，将初始模型传输至所述目标用户的终端设备。
在一些实施例中，响应于确定上述目标训练引擎校验通过上述执行主体可以将初始模型传输至上述目标用户的终端设备。这里，上述初始模型可以是未经训练，或者训练后未达到预设条件的模型。上述初始模型也可以是具有深度神经网络结构的模型。预先训练的特征提取模型可以是预先训练好的用于提取特征的神经网络模型。该神经网络模型可以具有现有的各种神经网络结构。例如，神经网络结构可以是卷积神经网络(Convolutional Neural Network，CNN)。初始模型可以采用极端梯度提升(eXtreme Gradient Boosting，XGBoost)。初始模型的存储位置在本公开中同样不限制。
步骤306，利用获取的训练样本集合，对所述初始模型进行训练，得到训练完成的初始模型。
在一些实施例中，上述执行主体可以利用上述获取的训练样本集合，对上述初始模型开始训练，训练过程如下：第一步，从上述训练样本集合中选取训练样本，其中，训练样本包括样本数据集合和样本处理结果；第二步，上述执行主体可以将训练样本中的样本数据集合输入上述初始模型；第三步，将输出的处理结果与上述样本处理结果进行比较，得到处理结果损失值；第四步，上述执行主体可以将上述处理结果损失值与预设阈值进行比较，得到比较结果；第五步，根据比较结果确定上述初始模型是否训练完成；第六步，响应于上述初始训练模型训练完成，将上述初始模型确定为训练完成的初始模型。这里，上述获取的训练样本集合可以是目标用户的终端设备本地的数据。
上文陈述的处理结果损失值可以是将上述输出的处理结果与对应的样本处理结果作为参数，输入执行的损失函数中得到的值。这里，损失函数(例如平方损失函数、指数损失函数等)通常是用来估量模型的预测值(例如该样本数据集合对应的上述样本处理结果)与真实值(例如通过上述步骤得到的处理结果)的不一致程度。它是一个非负实值函数。一般情况下，损失函数越小，模型的鲁棒性就越好。损失函数可以根据实际需求来设置。作为示例，损失函数可以是交叉熵损失函数(Cross Entropy)。
在一些实施例的一些可选的实现方式中，上述方法还包括：响应于确定初始模型未训练完成，调整初始模型中的相关参数，以及从上述训练样本集中重新选取样本，使用调整后的 初始模型作为初始模型，继续执行上述训练步骤。
在一些实施例的一些可选的实现方式中，上述训练完成的初始模型可以保证在压缩协议、安全协议的前提下，不断在上述终端设备与上述目标训练引擎之间上传下载，不断迭代以更新上述训练完成的初始模型。
步骤307，利用所述目标训练引擎，将所述终端设备存储的至少一个模型与所述训练完成的初始模型进行聚合，得到联合训练模型。
在一些实施例中，上述执行主体可以利用上述目标训练引擎，对上述终端设备存储的至少一个模型与上述训练完成的初始模型进行聚合，得到联合训练模型。
在一些实施例的一些可选的实现方式中，上述方法还包括：响应于检测到上述目标用户的终止联合请求，控制上述目标训练引擎停止训练，以及将停止训练时的联合训练模型存储至目标模型库。这里，上述执行主体可以将上述联合训练模型生成接口，然后将生成接口后的联合训练模型存储至目标模型库。上述执行主体可以将于上述联合训练模型相关的训练记录、训练过程中的状态信息存储至云数据库中。
在一些实施例的一些可选的实现方式中，上述方法还包括：响应于检测到所述目标用户的查询操作，获取查询接口；从所述目标模型库中抽取出接口与所述查询接口相同的模型的历史记录和状态信息，以及控制具所述目标设备显示所述历史记录和所述状态信息。这里，历史记录可以是用于模型训练过程中每一次训练的信息。
从图3中可以看出，与图2对应的一些实施例的描述相比，图3对应的一些实施例中的数据测量方法的流程300体现了对如何训练深度学习网络、得到联合训练模型的步骤。由此，这些实施例描述的方案可以通过对数据集合的处理，可以得到符合用户需求的测量结果。满足了用户针对数据计算的需求，为用户后续利用数据提供了便利。另外，利用联合训练模型对数据进行测量计算可以大大避免人工计算时造成的误差，得到较为精准的测量结果。用户可以针对不同业务场景对训练模型进行选择，提高了模型的利用率，生成的联合训练模型也更加符合用户需求，侧面提高了用户体验。
进一步参考图4，作为对上述各图上述方法的实现，本公开提供了一种数据测量装置的一些实施例，这些装置实施例与图2上述的那些方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图4所示，一些实施例的数据测量装置400包括：获取单元401、处理单元402和显示单元403。其中，获取单元401，被配置成获取数据集合；处理单元402，被配置成将所述数据集合输入至预先训练的深度学习网络，输出处理结果，其中，所述深度学习网络是通过 训练样本集合训练得到的，所述深度学习网络的训练包括：响应于接收到目标用户的训练请求，获取所述目标用户的身份信息；对所述身份信息进行核验，确定核验是否通过；响应于确定所述身份信息核验通过，控制目标训练引擎开启训练；显示单元403，被配置成将所述处理结果确定为测量结果，以及控制具有显示功能的目标设备显示所述测量结果。
在一些实施例的一些可选的实现方式中，上述深度学习网络的训练，包括：响应于检测到所述目标用户针对训练模型库中训练模型的选择操作，对所述目标训练引擎进行校验，确定校验是否通过；响应于确定所述目标训练引擎校验通过，将初始模型传输至所述目标用户的终端设备；利用获取的训练样本集合，对所述初始模型进行训练，得到训练完成的初始模型；利用所述目标训练引擎，将所述终端设备存储的至少一个模型与所述训练完成的初始模型进行聚合，得到联合训练模型。
在一些实施例的一些可选的实现方式中，上述训练样本集合中的训练样本包括样本数据集合和样本处理结果，所述深度学习网络是以所述样本数据集合作为输入，以所述样本处理结果用于作为期望输出训练得到的。
在一些实施例的一些可选的实现方式中，数据测量装置400被进一步配置成：响应于检测到所述目标用户的终止联合请求，控制所述目标训练引擎停止训练，以及将停止训练时的联合训练模型存储至目标模型库。
在一些实施例的一些可选的实现方式中，数据测量装置400被进一步配置成：响应于检测到所述目标用户的查询操作，获取查询接口；从所述目标模型库中抽取出接口与所述查询接口相同的模型的历史记录和状态信息，以及控制具所述目标设备显示所述历史记录和所述状态信息。
可以理解的是，该装置400中记载的诸单元与参考图2描述的方法中的各个步骤相对应。由此，上文针对方法描述的操作、特征以及产生的有益效果同样适用于装置400及其中包含的单元，在此不再赘述。
下面参考图5，其示出了适于用来实现本公开的一些实施例的电子设备(例如图1中的计算设备101)500的结构示意图。图5示出的服务器仅仅是一个示例，不应对本公开的实施例的功能和使用范围带来任何限制。
如图5所示，电子设备500可以包括处理装置(例如中央处理器、图形处理器等)501，其可以根据存储在只读存储器(ROM)502中的程序或者从存储装置508加载到随机访问存储器(RAM)503中的程序而执行各种适当的动作和处理。在RAM 503中，还存储有电子设备500操作所需的各种程序和数据。处理装置501、ROM 502以及RAM 503通过总线504 彼此相连。输入/输出(I/O)接口505也连接至总线504。
通常，以下装置可以连接至I/O接口505：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置506；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置507；包括例如磁带、硬盘等的存储装置508；以及通信装置509。通信装置509可以允许电子设备500与其他设备进行无线或有线通信以交换数据。虽然图5示出了具有各种装置的电子设备500，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。图5中示出的每个方框可以代表一个装置，也可以根据需要代表多个装置。
特别地，根据本公开的一些实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的一些实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的一些实施例中，该计算机程序可以通过通信装置509从网络上被下载和安装，或者从存储装置508被安装，或者从ROM 502被安装。在该计算机程序被处理装置501执行时，执行本公开的一些实施例的方法中限定的上述功能。
需要说明的是，本公开的一些实施例上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开的一些实施例中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开的一些实施例中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol， 超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述装置中所包含的；也可以是单独存在，而未装配入该电子设备中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：获取数据集合；将数据集合输入至预先训练的深度学习网络，输出处理结果，其中，深度学习网络是通过训练样本集合训练得到的，深度学习网络的训练包括：响应于接收到目标用户的训练请求，获取目标用户的身份信息；对身份信息进行核验，确定核验是否通过；响应于确定身份信息核验通过，控制目标训练引擎开启训练；将所述处理结果确定为测量结果，以及控制具有显示功能的目标设备显示所述测量结果。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的一些实施例的操作的计算机程序代码，上述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)——连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开的一些实施例中的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括获取单 元、处理单元和显示单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，获取单元还可以被描述为“获取数据集合的单元”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
以上描述仅为本公开的一些较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开的实施例中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开的实施例中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (8)

  1. 一种数据测量方法，其特征在于，包括：
    获取数据集合；
    将所述数据集合输入至预先训练的深度学习网络，输出处理结果，其中，所述深度学习网络是通过训练样本集合训练得到的，所述深度学习网络的训练包括：
    响应于接收到目标用户的训练请求，获取所述目标用户的身份信息；
    对所述身份信息进行核验，确定核验是否通过；
    响应于确定所述身份信息核验通过，控制目标训练引擎开启训练；
    将所述处理结果确定为测量结果，以及控制具有显示功能的目标设备显示所述测量结果。
  2. 根据权利要求1所述的方法，其特征在于，所述深度学习网络的训练，包括：
    响应于检测到所述目标用户针对训练模型库中训练模型的选择操作，对所述目标训练引擎进行校验，确定校验是否通过；
    响应于确定所述目标训练引擎校验通过，将初始模型传输至所述目标用户的终端设备；
    利用获取的训练样本集合，对所述初始模型进行训练，得到训练完成的初始模型；
    利用所述目标训练引擎，将所述终端设备存储的至少一个模型与所述训练完成的初始模型进行聚合，得到联合训练模型。
  3. 根据权利要求2所述的方法，其特征在于，所述训练样本集合中的训练样本包括样本数据集合和样本处理结果，所述深度学习网络是以所述样本数据集合作为输入，以所述样本处理结果用于作为期望输出训练得到的。
  4. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    响应于检测到所述目标用户的终止联合请求，控制所述目标训练引擎停止训练，以及将停止训练时的联合训练模型存储至目标模型库。
  5. 根据权利要求4所述的方法，其特征在于，所述方法还包括：
    响应于检测到所述目标用户的查询操作，获取查询接口；
    从所述目标模型库中抽取出接口与所述查询接口相同的模型的历史记录和状态信息，以及控制具所述目标设备显示所述历史记录和所述状态信息。
  6. 一种数据测量装置，其特征在于，包括：
    获取单元，被配置成获取数据集合；
    处理单元，被配置成将所述数据集合输入至预先训练的深度学习网络，输出处理结果，其中，所述深度学习网络是通过训练样本集合训练得到的，所述深度学习网络的训练包括：
    响应于接收到目标用户的训练请求，获取所述目标用户的身份信息；
    对所述身份信息进行核验，确定核验是否通过；
    响应于确定所述身份信息核验通过，控制目标训练引擎开启训练；
    显示单元，被配置成将所述处理结果确定为测量结果，以及控制具有显示功能的目标设备显示所述测量结果。
  7. 一种电子设备，包括：
    一个或多个处理器；
    存储装置，其上存储有一个或多个程序；
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1所述的方法。
  8. 一种计算机可读介质，其上存储有计算机程序，其中，所述程序被处理器执行时实现如权利要求1所述的方法。
PCT/CN2021/101133 2020-10-14 2021-06-21 数据测量方法、装置、电子设备和计算机可读介质 Ceased WO2022077946A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP21878996.4A EP4131082B1 (en) 2020-10-14 2021-06-21 Data measurement method and apparatus, and electronic device and computer-readable medium
JP2022539397A JP7717698B2 (ja) 2020-10-14 2021-06-21 データ測定方法、装置、電子機器及びコンピュータ可読媒体
US17/828,028 US20220300858A1 (en) 2020-10-14 2022-05-30 Data measurement method and apparatus, electronic device and computer-readable medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011095139.0A CN114372569A (zh) 2020-10-14 2020-10-14 数据测量方法、装置、电子设备和计算机可读介质
CN202011095139.0 2020-10-14

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/828,028 Continuation US20220300858A1 (en) 2020-10-14 2022-05-30 Data measurement method and apparatus, electronic device and computer-readable medium

Publications (1)

Publication Number Publication Date
WO2022077946A1 true WO2022077946A1 (zh) 2022-04-21

Family

ID=81138480

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/101133 Ceased WO2022077946A1 (zh) 2020-10-14 2021-06-21 数据测量方法、装置、电子设备和计算机可读介质

Country Status (5)

Country Link
US (1) US20220300858A1 (zh)
EP (1) EP4131082B1 (zh)
JP (1) JP7717698B2 (zh)
CN (1) CN114372569A (zh)
WO (1) WO2022077946A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114881180A (zh) * 2022-07-11 2022-08-09 浙江瑞邦科特检测有限公司 混凝土抗压强度数据的管理方法、装置、设备及存储介质
CN115168733A (zh) * 2022-07-28 2022-10-11 中国银行股份有限公司 手机应用界面推送方法及装置
CN115862807A (zh) * 2022-09-02 2023-03-28 深圳市智云医康医疗科技有限公司 基于机器学习的健身训练方法、系统、介质及电子设备
CN115879006A (zh) * 2022-12-27 2023-03-31 北京火山引擎科技有限公司 数据处理方法及装置

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115567227B (zh) * 2022-12-02 2023-04-07 华南师范大学 一种基于大数据安全的身份认证方法及系统
CN116663614B (zh) * 2022-12-22 2025-10-28 阿里巴巴（中国）有限公司 深度学习网络结构的生成方法及装置
CN116187587A (zh) * 2023-04-24 2023-05-30 中国科学院地理科学与资源研究所 指数预测方法、装置、设备及计算机可读存储介质
CN116702168B (zh) * 2023-05-19 2024-01-12 国网物资有限公司 供应端信息检测方法、装置、电子设备和计算机可读介质
CN116614757B (zh) * 2023-07-18 2023-09-26 江西斐耳科技有限公司 一种基于深度学习的助听器验配方法及系统
CN116974561A (zh) * 2023-07-31 2023-10-31 中电金信软件有限公司 一种页面展示方法、装置、电子设备及存储介质
CN116757100B (zh) * 2023-08-18 2023-12-15 国科大杭州高等研究院 推力预测模型训练及推力预测方法、装置、设备、介质
CN116894163B (zh) * 2023-09-11 2024-01-16 国网信息通信产业集团有限公司 基于信息安全的充放电设施负荷预测信息生成方法和装置
CN118194159B (zh) * 2024-03-18 2024-12-17 北京德风新征程科技股份有限公司 智能边缘作业设备、边缘环境监测方法、电子设备和介质
CN119512854A (zh) * 2024-10-17 2025-02-25 济南浪潮数据技术有限公司 数据分析方法、装置、计算机设备和存储介质
CN118963977B (zh) * 2024-10-21 2025-03-14 瓴羊智能科技有限公司 分布式训练方法、系统、设备、存储介质及程序产品
CN120671795B (zh) * 2025-08-22 2025-11-21 中化现代农业有限公司 模型协同处理方法和装置、电子设备以及计算机存储介质
CN121392880B (zh) * 2025-12-25 2026-03-27 中汽信息科技(天津)有限公司 一种基于大模型的多场景文本识别方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107766940A (zh) * 2017-11-20 2018-03-06 北京百度网讯科技有限公司 用于生成模型的方法和装置
CN109492771A (zh) * 2018-11-12 2019-03-19 北京百度网讯科技有限公司 交互方法、装置和系统
CN110263930A (zh) * 2019-06-28 2019-09-20 北京百度网讯科技有限公司 用于发送信息的方法和装置
CN110543946A (zh) * 2018-05-29 2019-12-06 百度在线网络技术（北京）有限公司 用于训练模型的方法和装置

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018075995A1 (en) * 2016-10-21 2018-04-26 DataRobot, Inc. Systems for predictive data analytics, and related methods and apparatus
WO2019164981A1 (en) * 2018-02-20 2019-08-29 Pearson Education, Inc. Systems and methods for automated evaluation model customization
CN109670600B (zh) * 2018-12-14 2019-10-25 启元世界(北京)信息技术服务有限公司 基于云平台的决策方法和系统
CN111612153B (zh) * 2019-02-22 2024-06-14 华为技术有限公司 训练模型的方法和装置
CN110009059B (zh) * 2019-04-16 2022-03-29 北京字节跳动网络技术有限公司 用于生成模型的方法和装置
CN110929880B (zh) * 2019-11-12 2025-01-24 深圳前海微众银行股份有限公司 一种联邦学习方法、装置及计算机可读存储介质
CN111008704B (zh) * 2019-11-29 2023-08-04 上海能塔智能科技有限公司 电动汽车联邦学习的处理方法、装置、设备与存储介质
CN111401367B (zh) * 2020-03-20 2025-07-18 深圳前海微众银行股份有限公司 基于联邦ocr模型的字符检测方法、装置、设备和介质
CN111340242B (zh) * 2020-05-15 2020-08-04 支付宝(杭州)信息技术有限公司 保护隐私的模型联合训练方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107766940A (zh) * 2017-11-20 2018-03-06 北京百度网讯科技有限公司 用于生成模型的方法和装置
CN110543946A (zh) * 2018-05-29 2019-12-06 百度在线网络技术（北京）有限公司 用于训练模型的方法和装置
CN109492771A (zh) * 2018-11-12 2019-03-19 北京百度网讯科技有限公司 交互方法、装置和系统
CN110263930A (zh) * 2019-06-28 2019-09-20 北京百度网讯科技有限公司 用于发送信息的方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4131082A4 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114881180A (zh) * 2022-07-11 2022-08-09 浙江瑞邦科特检测有限公司 混凝土抗压强度数据的管理方法、装置、设备及存储介质
CN115168733A (zh) * 2022-07-28 2022-10-11 中国银行股份有限公司 手机应用界面推送方法及装置
CN115862807A (zh) * 2022-09-02 2023-03-28 深圳市智云医康医疗科技有限公司 基于机器学习的健身训练方法、系统、介质及电子设备
CN115862807B (zh) * 2022-09-02 2024-02-02 深圳市智云医康医疗科技有限公司 基于机器学习的健身训练方法、系统、介质及电子设备
CN115879006A (zh) * 2022-12-27 2023-03-31 北京火山引擎科技有限公司 数据处理方法及装置

Also Published As

Publication number Publication date
JP7717698B2 (ja) 2025-08-04
JP2023545593A (ja) 2023-10-31
US20220300858A1 (en) 2022-09-22
EP4131082A1 (en) 2023-02-08
EP4131082B1 (en) 2025-11-19
CN114372569A (zh) 2022-04-19
EP4131082A4 (en) 2023-10-25

Similar Documents

Publication Publication Date Title
WO2022077946A1 (zh) 数据测量方法、装置、电子设备和计算机可读介质
KR102308002B1 (ko) 정보 생성 방법 및 장치
CN109447156B (zh) 用于生成模型的方法和装置
CN107766940A (zh) 用于生成模型的方法和装置
WO2020087979A1 (zh) 生成模型的方法和装置
CN111402220A (zh) 用于获取信息的方法及装置
CN115471307A (zh) 基于知识图谱的审计评估信息生成方法、装置和电子设备
CN110084298B (zh) 用于检测图像相似度的方法及装置
CN111898753B (zh) 音乐转录模型的训练方法、音乐转录方法以及对应的装置
CN112856478A (zh) 燃气锅炉的空燃比调节方法、装置、设备和介质
CN113468344A (zh) 实体关系抽取方法、装置、电子设备和计算机可读介质
WO2022077948A1 (zh) 基于联合学习的物联网数据服务方法、装置、设备和介质
CN115022328B (zh) 服务器集群以及服务器集群的测试方法、装置和电子设备
CN111787041A (zh) 用于处理数据的方法和装置
CN114582433A (zh) 用于确定烟气含氧量的方法及装置
CN117057681B (zh) 软件质量评估方法、装置、设备和存储介质
CN113255290A (zh) 电力项目信息展示方法、设备和计算机可读介质
CN116129440B (zh) 异常用户端告警方法、装置、电子设备和介质
CN110991661A (zh) 用于生成模型的方法和装置
CN113128677A (zh) 模型生成方法和装置
CN114547491A (zh) 时序图谱构建方法、装置、设备及介质
CN112508257A (zh) 负荷预测结果生成方法、装置、电子设备和介质
CN114764539A (zh) 燃气轮机的排烟含氧量确定方法、装置、设备和介质
CN118427417B (zh) 用户信息存储方法、装置、电子设备和计算机介质
CN118445882B (zh) 一种基于bim技术的高层建筑施工现场的管理方法及系统

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: 21878996

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2022539397

Country of ref document: JP

ENP Entry into the national phase

Ref document number: 2021878996

Country of ref document: EP

Effective date: 20221026

NENP Non-entry into the national phase

Ref country code: DE

WWG Wipo information: grant in national office

Ref document number: 2021878996

Country of ref document: EP