Distributed training method and system, terminal and base station

Through the distributed training method, the control channel signaling interaction between the terminal and the base station is solved, the problem of low indoor positioning accuracy in heavy NLOS scenarios is reduced, and the communication overhead is improved and the positioning accuracy and model prediction capabilities are improved.

CN119089187APending Publication Date: 2024-12-06CHINA TELECOM CORP LTD BEIJING RESEARCH INSTITUTE +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202310658195.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-06-05
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The prior art has low indoor positioning accuracy in heavy NLOS scenarios. Traditional indoor positioning methods rely on LOS paths, making it difficult to achieve high-precision positioning in industrial environments. The data transmission overhead of AI/ML-based centralized training schemes is high.

Method used

Using distributed training method, model training information interaction is performed through control channel signaling between the terminal and the base station. Using the signaling format of scrambling code sequence scramble, the terminal deploys the model locally and reports only the training information. The base station gathers the various terminals. Training information updates model parameters.

Benefits of technology

It reduces the communication overhead during model training, improves positioning accuracy, model prediction accuracy and generalization, and reduces calculation pressure.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089187A_ABST
    Figure CN119089187A_ABST
Patent Text Reader

Abstract

The invention discloses a distributed training method and system, a terminal and a base station, and relates to the field of wireless communication. The distributed training method comprises the steps that a terminal sends a first message to a base station, the terminal is a distributed node of distributed learning, the base station is a center node of distributed learning, and the first message comprises training information of a model deployed for the terminal; the terminal receives a second message sent by the base station, the second message comprising at least one of a parameter update indication and a convergence condition update indication of the model, or comprising a training stop indication; wherein the first message and the second message are control channel signaling and are scrambled by adopting a scrambling code sequence, and the scrambling code sequence is determined according to at least one of a model function, a model identifier, a training mode and a training group to which the terminal belongs. According to the model training method suitable for the distributed wireless network architecture, the physical layer signaling of the air interface required by the model training is defined. According to the scheme, air interface resources can be saved, and communication overhead is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of wireless communications, and in particular to a distributed training method, system, terminal and base station. Background Art

[0002] 3GPP (3rd Generation Partnership Project) Rel-18 (Release 18) studies key wireless artificial intelligence (AI) air interface technologies, focusing on the application of centralized machine learning and AI air interface.

[0003] Positioning enhancement technology based on AI / machine learning (ML) can solve the difficulties and pain points of inaccurate traditional indoor positioning, especially the pain points of traditional indoor positioning in heavy NLOS (Non Line of Sight) scenarios. For example, in the 3GPP InF-DH (Indoor Factory-Denseclutter Highbs) scenario, the positioning accuracy is greater than 15 meters.

[0004] Traditional indoor positioning technology is based on direct or indirect measurement of the direct path of multiple sites to estimate the user's location. Although traditional indoor positioning technologies can provide high accuracy in certain deployment scenarios, they are heavily dependent on the existence of LOS (Line of Sight) paths. There are many obstacles in industrial environments, which lead to refraction, reflection and diffraction of signals. At the same time, there is multipath propagation and long delay in the signal propagation process, making it difficult for traditional positioning methods to achieve high-precision positioning.

[0005] In recent years, deep learning algorithms have been rapidly developed and widely used due to their good performance in various fields. The typical advantages of deep learning methods include the effectiveness of processing raw data, the ability to automatically extract features, the acceleration capability of graphics processing units (GPUs), etc. According to the current 3GPP research and evaluation progress, AI / ML can significantly improve the positioning accuracy of indoor heavy NLOS scenarios, including direct positioning and indirect positioning. Summary of the invention

[0006] After analysis, it is found that the current AI / ML-based positioning enhancement solution in 3GPP is a centralized training solution. The data used for AI / ML model training needs to be concentrated on the base station or terminal or LMF (Location Management Function) side. A large number of data sets (such as measurement signals) used for training need to be transmitted between air interfaces or interfaces, resulting in high transmission overhead.

[0007] A technical problem to be solved by the embodiments of the present invention is: how to reduce the overhead in the model training process.

[0008] According to a first aspect of some embodiments of the present invention, there is provided a distributed training method, comprising: a terminal sends a first message to a base station, wherein the terminal is a distributed node of distributed learning, the base station is a central node of distributed learning, and the first message includes training information of a model deployed by the terminal; the terminal receives a second message sent by the base station, wherein the second message includes at least one of a parameter update indication and a convergence condition update indication of the model, or includes a training stop indication; wherein the first message and the second message are control channel signaling, which are encrypted with a scrambling code sequence, and the scrambling code sequence is determined according to at least one of a model function, a model identifier, a training method, and a training group to which the terminal belongs.

[0009] In some embodiments, multiple terminals in a training group to which the terminal belongs use the same scrambling code sequence.

[0010] In some embodiments, the first message has a first signaling format determined according to the scrambling code sequence; and / or the second message has a second signaling format determined according to the scrambling code sequence.

[0011] In some embodiments, the first signaling format and the second signaling format include at least one field of a model identifier, a model function identifier, a timestamp, a sequence index, and a training group identifier.

[0012] In some embodiments, the second signaling format includes at least one field of an aggregation algorithm indication, a training stop condition, an initial value of a parameter of the model, a parameter update indication of the model, and a gradient update indication of the model.

[0013] In some embodiments, any one of the parameter update indication of the model and the gradient update indication of the model includes an indication bit, and the value of the indication bit is different from the value of the indication bit in the same indication obtained by the terminal last time.

[0014] In some embodiments, the value of the indicator bit is a first value or a second value.

[0015] In some embodiments, the sizes of the fields in the first signaling format and the second signaling format are default values, or are determined according to a configuration sent by the base station.

[0016] In some embodiments, the training information includes parameters of the trained model, or the training status of the model.

[0017] In some embodiments, the training method also includes: the terminal receives configuration signaling sent by the base station, wherein the configuration signaling includes at least one of model function, model identification, model configuration, and training data collection configuration; the terminal configures the distributed nodes deployed by the terminal according to the configuration signaling.

[0018] In some embodiments, the model functionality represents at least one of mobility optimization, positioning, and beam management.

[0019] In some embodiments, the model function includes at least one of a model function identifier, an area code, a public land mobile network, an operator identification code, a tracking area, a cell group, and a geographic range identification code; and / or, the model identifier includes at least one of a country identification code, an operator identification code, a public land mobile network, a tracking area, a geographic range identification code, and a model identification code.

[0020] In some embodiments, the model configuration includes a lifecycle management configuration of the model or a model property configuration.

[0021] In some embodiments, the model lifecycle management configuration includes at least one of model training configuration, model reasoning configuration, model deployment configuration, model update configuration, and model monitoring configuration; and / or, the model attribute configuration includes at least one of input configuration, output configuration, model structure configuration, interface configuration, and training rule configuration.

[0022] In some embodiments, the collection configuration of the training data includes at least one of a collection object and a collection method; or, the collection configuration of the training data includes a configuration of uplink measurement of a reference signal.

[0023] In some embodiments, the configuration signaling is any one of downlink control information of the physical layer, a control unit of the media access layer, or radio resource control signaling.

[0024] In some embodiments, the distributed learning is federated learning.

[0025] In some embodiments, the model is an indoor positioning model.

[0026] According to a second aspect of some embodiments of the present invention, there is provided a distributed training method, comprising: a base station receives a first message sent by any one of a plurality of terminals, wherein the plurality of terminals are distributed nodes of distributed learning, the base station is a central node of the distributed learning, and the first message includes training information of a model deployed on the terminals; the base station sends a second message to any one of the plurality of terminals, wherein the second message includes at least one of a parameter update indication and a convergence condition update indication of the model, or includes a training stop indication; wherein the first message and the second message are control channel signaling, which are encrypted with a scrambling code sequence, and the scrambling code sequence is determined according to at least one of a model function, a model identifier, a training method, and a training group to which the terminal belongs.

[0027] In some embodiments, the training method further includes: the base station aggregates the models deployed by the multiple terminals according to the training information sent by the multiple terminals to obtain updated model parameters.

[0028] In some embodiments, the training method further includes: the base station sends configuration signaling to any one of the multiple terminals, wherein the configuration signaling includes at least one of a model function, a model identifier, a model configuration, and a collection configuration of training data.

[0029] According to a third aspect of some embodiments of the present invention, there is provided a terminal, comprising: a sending module, configured to send a first message to a base station, wherein the terminal is a distributed node of distributed learning, the base station is a central node of the distributed learning, and the first message includes training information of a model deployed by the terminal; a receiving module, configured to receive a second message sent by the base station, wherein the second message includes at least one of a parameter update indication and a convergence condition update indication of the model, or includes a training stop indication; wherein the first message and the second message are control channel signaling, which are encrypted with a scrambling code sequence, and the scrambling code sequence is determined according to at least one of a model function, a model identifier, a training method, and a training group to which the terminal belongs.

[0030] According to a fourth aspect of some embodiments of the present invention, there is provided a terminal, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute any one of the aforementioned distributed training methods based on instructions stored in the memory.

[0031] According to a fifth aspect of some embodiments of the present invention, a base station is provided, comprising: a receiving module, configured to receive a first message sent by any one of a plurality of terminals, wherein the plurality of terminals are distributed nodes of distributed learning, the base station is a central node of the distributed learning, and the first message includes training information of a model deployed by the terminals; a sending module, configured to send a second message to any one of the plurality of terminals, wherein the second message includes at least one of a parameter update indication and a convergence condition update indication of the model, or includes a training stop indication; wherein the first message and the second message are control channel signaling, which are encrypted with a scrambling code sequence, and the scrambling code sequence is determined according to at least one of a model function, a model identifier, a training method, and a training group to which the terminal belongs.

[0032] According to a sixth aspect of some embodiments of the present invention, there is provided a base station, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute any one of the aforementioned distributed training methods based on instructions stored in the memory.

[0033] According to a seventh aspect of some embodiments of the present invention, there is provided a distributed training system, comprising: any one of the aforementioned terminals; and any one of the aforementioned base stations.

[0034] According to an eighth aspect of some embodiments of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the aforementioned distributed training methods.

[0035] Some embodiments of the above invention have the following advantages or beneficial effects. The embodiments of the present invention are applicable to the method for model training in the distributed wireless network architecture of 5G-Advanced and 6G networks, and define the physical layer signaling of the air interface required for model training. Through the above-mentioned distributed architecture and interaction process, the terminal can train the locally deployed model and only inform the base station of the training information instead of all the information of the model, thereby saving air interface resources. The base station can reduce the local computing pressure by aggregating the training information provided by each terminal. Therefore, the embodiments of the present invention improve the prediction accuracy, generalization, and convergence speed of the model, and reduce the communication overhead.

[0036] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0038] Figure 1 A schematic diagram of the structure of a distributed training system according to some embodiments of the present invention is shown.

[0039] Figure 2 A schematic flow chart of a distributed training method according to some embodiments of the present invention is shown.

[0040] Figure 3 A schematic flow chart of a configuration method according to some embodiments of the present invention is shown.

[0041] Figure 4 A schematic flow chart of an indoor positioning method according to some embodiments of the present invention is shown.

[0042] Figure 5 A schematic diagram of the structure of a terminal according to some embodiments of the present invention is shown.

[0043] Figure 6 A schematic structural diagram of a base station according to some embodiments of the present invention is shown.

[0044] Figure 7 A schematic structural diagram of an electronic device according to some embodiments of the present invention is shown.

[0045] Figure 8 The schematic diagrams of structures of electronic devices according to other embodiments of the present invention are shown. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] The relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0048] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0049] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0050] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0051] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0052] The inventors realize that this problem can be solved by using a distributed framework to reduce the data information transmission between air interfaces / interfaces.

[0053] Figure 1 FIG. 4 is a schematic diagram showing a distributed training system according to some embodiments of the present invention. Figure 1 As shown, in the network scenario 1, multiple terminals 11 and base stations 12 are included. The terminal 11 is a distributed node, which trains the locally deployed model and reports the training information to the base station 12. The base station 12 is a central node, which aggregates the information reported by each terminal 11 and updates the parameters of the model. When the base station includes a CU (Centralized Unit) and a DU (Distributed Unit), the central node can also be deployed in the CU or DU. Thus, the data information transmission between the air interface / interface can be reduced. In some embodiments, LMF 13 can also be set to perform reasoning after the model training is completed to obtain a prediction result, for example, to perform reasoning on the indoor positioning model to obtain the user's location. As needed, the terminal 11 can also perform reasoning and send the output of the model to LMF 13, and LMF 13 determines the user's location based on the output of the model.

[0054] Reference below Figure 2 An embodiment of the distributed training method of the present invention is described.

[0055] Figure 2 FIG. 2 shows a flow chart of a distributed training method according to some embodiments of the present invention. Figure 2 As shown, the distributed training method of this embodiment includes steps S202 to S204.

[0056] In step S202, the terminal sends a first message to the base station, wherein the terminal is a distributed node of distributed learning, the base station is a central node of distributed learning, and the first message includes training information of a model deployed by the terminal.

[0057] In some embodiments, the training information includes parameters of the trained model, or the training status of the model.

[0058] The parameters of the trained model can be represented in the form of key-value pairs, that is, including the name of each parameter and its value; or, data consisting of the values ​​of each parameter can be directly sent in a default format, such as a matrix, vector, etc., and the parameter name corresponding to the element at each position can be preset to further save transmission resources.

[0059] The training status of the model indicates whether the terminal has completed the current round of training of the model. For example, when the terminal detects that the current model meets the convergence conditions (the maximum number of iterations has been reached, the value of the loss function is less than the pre-configured threshold, etc.), the terminal reports to the base station that the current training has ended.

[0060] In step S204, the terminal receives a second message sent by the base station, wherein the second message includes at least one of a parameter update indication and a convergence condition update indication of the model, or includes a training stop indication. The parameter update indication, the convergence condition update indication, and the training stop indication may be collectively referred to as a training indication.

[0061] The parameter update indication is the updated parameter value obtained by the base station after aggregating the training information reported by the terminals where the multiple distributed nodes are located. Then, the base station can send the updated parameter value to the terminals where the distributed nodes are located.

[0062] The training stop indication is used to instruct the terminal to stop the training process, which can be a response from the base station to determine that the converged model meets the convergence condition.

[0063] The convergence condition update indication is used to notify the terminal that the convergence condition has been updated and to inform the terminal of the new convergence condition.

[0064] The terminal and the base station can interact through control channel signaling, for example, the first message is uplink control information, and the second message is downlink control information. The embodiment of the present invention designs an implementation method of control channel signaling.

[0065] The control channel signaling is scrambled using a scrambling code sequence. First, for the application scenario of distributed training of base stations and terminals, a method for generating the scrambling code sequence used for control channel signaling can be defined. The base station and the terminal can learn that the control information is related to training by demodulating different scrambling codes of the control channel-carrying signaling. The scrambling code sequence is represented by MT-RNTI (Model Training-Radio Network Temporary Identifier, a wireless network temporary identifier used for model training) below. Other names can be used as needed, which will not be repeated here.

[0066] In some embodiments, all terminals in the same training group may use a unified MT-RNTI for their own training process, that is, a default scrambling code sequence corresponding to distributed learning.

[0067] In some embodiments, the scrambling code sequence is determined according to the training method, that is, different training methods are distinguished by different MT-RNTIs, for example: MT-C-RNTI is used for centralized model training, and MT-D-RNTI is used for distributed model training; or, supervised training and unsupervised training are distinguished by different scrambling code sequences.

[0068] In some embodiments, the scrambling code sequence is determined according to a model function or a model identifier. The model function, for example, represents at least one of mobility optimization, positioning, and beam management. The model identifier is represented, for example, by a model ID, and each model has a unique ID. Thus, model training with different model functions or model IDs has different MT-RNTIs, and the MT-RNTI is generated by calculation or derivation according to the model function or model ID.

[0069] In some embodiments, the scrambling code sequence is determined according to the training group to which the terminal belongs. That is, the terminals in the same training group use the same MT-RNTI, and the training group refers to a group consisting of terminals belonging to the same training task.

[0070] Therefore, whether it is a base station or a terminal, after receiving the control channel signaling sent by the other party, it can obtain relevant information about model training such as model function, model identification, training method, training group, etc. by demodulating the different scrambling codes of the control channel carrying signaling.

[0071] Then, a dedicated signaling format may be defined for the first message and the second message. For example, the first message is uplink control information and has a first signaling format determined according to the scrambling sequence; the second message is downlink control information and has a second signaling format determined according to the scrambling sequence. At least one of one or more fields and field sizes may be predefined in each signaling format.

[0072] The first signaling format and the second signaling format include at least one field of a model identifier, a model function identifier, a timestamp, a sequence index, and a training group identifier.

[0073] The second signaling format may also include at least one field of aggregation algorithm indication, training stop condition, initial value of parameters of the model, parameter update indication of the model, and gradient update indication of the model.

[0074] In some embodiments, any one of the parameter update indication and the model gradient update indication includes an indication bit, and the value of the indication bit is different from the value of the indication bit in the same indication obtained by the terminal last time, so as to avoid the terminal confusing the contents of two adjacent indications.

[0075] The value of the indicator bit is a first value and a second value. For example, the optional values ​​of the indicator bit include 0 and 1. The indicator bit in each parameter update indication sent and the gradient update of the model is obtained by inverting the indicator bit in the indication sent last time. As needed, the value of the indicator bit can also be other values, or include other numbers of optional values, which will not be repeated here.

[0076] In some embodiments, the sizes of the fields in the first signaling format and the second signaling format are default values, for example, determined in a standard predefined manner; or determined according to a configuration sent by the base station.

[0077] The embodiments of the present invention are applicable to the method of model training in the distributed wireless network architecture of 5G-Advanced and 6G networks, and define the physical layer signaling of the air interface required for model training. Through the above-mentioned distributed architecture and interaction process, the terminal can train the locally deployed model and only inform the base station of the training information instead of all the information of the model, thereby saving air interface or interface resources. The base station can reduce the local computing pressure by aggregating the training information provided by each terminal. Therefore, the embodiments of the present invention improve the prediction accuracy, generalization, and convergence speed of the model, and reduce the communication overhead.

[0078] The embodiment of the present invention can also be configured for the terminal by the base station. Figure 3 An embodiment of the configuration method of the present invention is described.

[0079] Figure 3 FIG. 2 shows a flow chart of a configuration method according to some embodiments of the present invention. Figure 3 As shown, the configuration method of this embodiment includes steps S302 to S304.

[0080] In step S302, the terminal receives a configuration signaling sent by the base station, wherein the configuration signaling includes at least one of a model function, a model identifier, a model configuration, and a collection configuration of training data.

[0081] The configuration signaling may be sent via high-layer signaling such as RRC (Radio Resource Control), MAC CE (Media Access Control Control Element), or via DCI (Downlink Control Information) of the physical layer.

[0082] In some embodiments, the model functionality represents at least one of mobility optimization, positioning, and beam management.

[0083] The model function can be embodied as a model function identification code, which includes more relevant information in addition to the model function. It can be a string of M bits, including at least one of the model function identification, area code, PLMN (Public Land Mobile Network), operator identification code, TA (Tracking Area), cell group, and geographic range identification code.

[0084] The model identifier can be reflected as a string of M bits, which, in addition to the model identifier, also includes more relevant information, including at least one of a country identification code, an operator identification code, a PLMN, a TA, a geographic range identification code, and a model identification code (for example, different models within a certain country).

[0085] In some embodiments, the model configuration includes a lifecycle management configuration of the model or a model property configuration.

[0086] The model lifecycle management configuration reflects the configuration required at each stage of model training, for example, including at least one of model training configuration, model reasoning configuration, model deployment configuration, model update configuration, and model monitoring configuration.

[0087] The model attribute configuration includes, for example, at least one of input configuration, output configuration, model structure configuration, interface configuration, and training rule configuration. For example, the terminal receives MLModelTrainingConfiguration (ML model training configuration) sent by the base station, which includes: TrainingType (training type) information element, configured as FederalLearning (federated learning); and information elements such as ModelInput (model input), ModelOutput (model output), ModelStructure (model structure), and TrainingRule (training rule).

[0088] The input configuration and output configuration include, for example, the number of dimensions of the data, the model input type (real number / complex number / integer / float16 / float32 / quantization level, etc.). Taking the input cell ModelInput as an example, the cell configuration model uses one-dimensional data input, and for TOA (Time of Arrival), DL-TDOA (Down Link Time Difference OfArrival), and RSRP (Reference Signal Receiving Power) information, a multi-layer perceptron (MLP) model is used. The input of the model is measurement information such as TOA, DL-TDOA, and RSRP. The data input dimension is 1×18 (18 is the preset number of base stations), indicating that a user receives downlink reference signals sent by 18 base stations and performs channel estimation. Taking the output cell ModelOutput as an example, the output of its configuration model is the predicted value (x, y) of the two-dimensional coordinates of the terminal, where each coordinate is a float16 real number.

[0089] The model structure configuration includes, for example, the model type (DNN, i.e., deep neural network, CNN, i.e., convolutional neural network, Transformer, i.e., Resnet, i.e., residual network, etc.), the number of layers, the number of nodes, the type of activation function (ReLu, i.e., rectified linear unit, LeakyRelu, i.e., leaky rectified linear unit, etc.). For example, the ModelStructure element configures the structure of the model. The configured model uses three-dimensional data input and extracts the features of the three-dimensional data of the channel impulse response (CIR) based on the residual network (Resnet). Each CIR sample is multi-dimensional matrix information, and its input dimension is "18×256×2", and each element is a complex floating point float32 type; the three-dimensional input is generated by the 18 base station CIR information and 256 fast Fourier transform (FFT) sampling points received by the terminal, and 2 represents the real and imaginary parts of the complex number. In the first four Reshape layers of the model, the CIR input is converted to a size of 18×18×64, followed by 12 Con2D (two-dimensional convolution) layers and a 3×3 convolution kernel for convolution operations, and shortcut operations are performed between specific layers.

[0090] The interface configuration is, for example, a model interface standardized file or file type, including ONNX (Open Neural Network Exchange), Torchscript, etc. The standardized file refers to, for example, a model format file with the suffix .onnx.

[0091] The training rule configuration includes, for example, the optimization objective function (NMSE, i.e., normalized mean square error, cross entropy, etc.), the learning rate, the specific method used for gradient descent, etc.

[0092] Of course, the specific implementation methods described above are only exemplary, and those skilled in the art may adopt other specific implementation methods as needed, which will not be described in detail here.

[0093] In some embodiments, the collection configuration of the training data includes at least one of a collection object and a collection method. The collection object is, for example, the type of information collected, and the collection method is, for example, what kind of signal is processed by what means.

[0094] For example, the collection configuration of the training data may instruct the terminal to measure reference signals such as downlink PRS (Positioning Reference Signal) and CSI-RS (Channel State Information Reference Signal) to obtain CIR information, RSRP, and the like.

[0095] In some embodiments, the collection configuration of the training data includes a configuration of uplink measurement of a reference signal.

[0096] For example, the terminal receives the reference signal required for uplink measurement configured by the network side, and the network obtains measurement information such as CIR, TDOA, TOA, etc. through uplink measurement. For example, the measurement data of a terminal is indicated to be reported to a single base station (such as a primary cell) or multiple base stations (such as base stations in a secondary cell group).

[0097] In some embodiments, the training data includes at least one of labeled data and unlabeled data. That is, the collected training data may be labeled data, unlabeled data, or both.

[0098] In step S304, the terminal configures the distributed nodes deployed by the terminal according to the configuration signaling.

[0099] Through the above embodiments, different parameters can be configured for the terminal based on different scenarios, cells, TAs, etc., thereby improving the flexibility of distributed training.

[0100] Reference below Figure 4 , taking the indoor positioning model as an example, the interaction process between the terminal and the base station is described.

[0101] Figure 4 FIG. 2 is a flow chart showing an indoor positioning method according to some embodiments of the present invention. Figure 4As shown, the indoor positioning method of this embodiment includes steps S402 to S414.

[0102] In step S402, the base station as the central node sends a configuration message to the terminal as the distributed node.

[0103] In step S404, the terminal configures the distributed nodes according to the configuration message.

[0104] In step S406, the terminal trains the locally deployed model to obtain training information, and the model is an indoor positioning model.

[0105] In step S408, the terminal sends the training information to the base station through a first message.

[0106] In step S410, when the base station determines that the current model has not converged, it updates the parameters of the model according to the training information sent by the multiple terminals, and sends the updated parameters to the terminal through the second message. Then, returning to step S406, the terminal continues training based on the updated parameters.

[0107] In step S412, when the base station determines that the current model has converged, the base station sends an instruction to stop training to the terminal through a second message.

[0108] In step S414, the LMF determines the location of the terminal based on the inference result of the indoor positioning model. The LMF can perform inference by itself, or send the prediction result of the model to the LMF after the terminal inference.

[0109] Since the user's location information is private data, distributed training is used to prevent the location information collected by the terminal and used for training from being leaked, thereby protecting the security and privacy of the user's location-related data.

[0110] Reference below Figure 5 Embodiments of a terminal of the present invention are described.

[0111] Figure 5 FIG. 2 shows a schematic diagram of the structure of a terminal according to some embodiments of the present invention. Figure 5As shown, the terminal 50 of this embodiment includes: a sending module 510, configured to send a first message to a base station, wherein the terminal is a distributed node of distributed learning, the base station is a central node of distributed learning, and the first message includes training information of a model deployed by the terminal; a receiving module 520, configured to receive a second message sent by the base station, wherein the second message includes at least one of a parameter update indication and a convergence condition update indication of the model, or includes a training stop indication; wherein the first message and the second message are control channel signaling, which are encrypted with a scrambling code sequence, and the scrambling code sequence is determined according to at least one of a model function, a model identifier, a training method, and a training group to which the terminal belongs.

[0112] In some embodiments, multiple terminals in a training group to which the terminal belongs use the same scrambling code sequence.

[0113] In some embodiments, the first message has a first signaling format determined according to the scrambling code sequence; and / or the second message has a second signaling format determined according to the scrambling code sequence.

[0114] In some embodiments, the first signaling format and the second signaling format include at least one field of a model identifier, a model function identifier, a timestamp, a sequence index, and a training group identifier.

[0115] In some embodiments, the second signaling format includes at least one field of an aggregation algorithm indication, a training stop condition, an initial value of a parameter of the model, a parameter update indication of the model, and a gradient update indication of the model.

[0116] In some embodiments, any one of the parameter update indication of the model and the gradient update indication of the model includes an indication bit, and the value of the indication bit is different from the value of the indication bit in the same indication obtained by the terminal last time.

[0117] In some embodiments, the value of the indicator bit is a first value or a second value.

[0118] In some embodiments, the sizes of the fields in the first signaling format and the second signaling format are default values, or are determined according to a configuration sent by the base station.

[0119] In some embodiments, the training information includes parameters of the trained model, or the training status of the model.

[0120] In some embodiments, the receiving module 520 is further configured to receive configuration signaling sent by the base station, wherein the configuration signaling includes at least one of model function, model identification, model configuration, and training data collection configuration; the terminal 50 also includes a configuration module 530, which is configured to configure the distributed nodes deployed by the terminal according to the configuration signaling.

[0121] In some embodiments, the model functionality represents at least one of mobility optimization, positioning, and beam management.

[0122] In some embodiments, the model function includes at least one of a model function identifier, an area code, a public land mobile network, an operator identification code, a tracking area, a cell group, and a geographic range identification code; and / or, the model identifier includes at least one of a country identification code, an operator identification code, a public land mobile network, a tracking area, a geographic range identification code, and a model identification code.

[0123] In some embodiments, the model configuration includes a lifecycle management configuration of the model or a model property configuration.

[0124] In some embodiments, the model lifecycle management configuration includes at least one of model training configuration, model reasoning configuration, model deployment configuration, model update configuration, and model monitoring configuration; and / or, the model attribute configuration includes at least one of input configuration, output configuration, model structure configuration, interface configuration, and training rule configuration.

[0125] In some embodiments, the collection configuration of the training data includes at least one of a collection object and a collection method; or, the collection configuration of the training data includes a configuration of uplink measurement of a reference signal.

[0126] In some embodiments, the configuration signaling is any one of downlink control information of the physical layer, a control unit of the media access layer, or radio resource control signaling.

[0127] In some embodiments, the distributed learning is federated learning.

[0128] In some embodiments, the model is an indoor positioning model.

[0129] Reference below Figure 6 An embodiment of a base station of the present invention is described.

[0130] Figure 6 FIG. 2 shows a schematic diagram of the structure of a base station according to some embodiments of the present invention. Figure 6As shown, the base station 60 of this embodiment includes: a receiving module 610, configured to receive a first message sent by any one of a plurality of terminals, wherein the plurality of terminals are distributed nodes of distributed learning, the base station is a central node of distributed learning, and the first message includes training information of a model deployed by the terminal; a sending module 620, configured to send a second message to any one of the plurality of terminals, wherein the second message includes at least one of a parameter update indication and a convergence condition update indication of the model, or includes a training stop indication; wherein the first message and the second message are control channel signaling, which are encrypted with a scrambling code sequence, and the scrambling code sequence is determined according to at least one of a model function, a model identifier, a training method, and a training group to which the terminal belongs.

[0131] In some embodiments, the base station 60 further includes: an aggregation module 630 configured to aggregate models deployed by multiple terminals according to training information sent by multiple terminals to obtain updated model parameters.

[0132] In some embodiments, the sending module 620 is further configured to send configuration signaling to any one of the multiple terminals, wherein the configuration signaling includes at least one of a model function, a model identifier, a model configuration, and a collection configuration of training data.

[0133] Figure 7 FIG. 1 is a schematic diagram showing the structure of an electronic device according to some embodiments of the present invention, wherein the electronic device is a base station or a terminal. Figure 7 As shown, the electronic device 70 of this embodiment includes: a memory 710 and a processor 720 coupled to the memory 710 , and the processor 720 is configured to execute the distributed training method in any one of the aforementioned embodiments based on instructions stored in the memory 710 .

[0134] The memory 710 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.

[0135] Figure 8 FIG. 1 is a schematic diagram showing the structure of an electronic device according to some other embodiments of the present invention, wherein the electronic device is a base station or a terminal. Figure 8As shown, the electronic device 80 of this embodiment includes: a memory 810 and a processor 820, and may also include an input / output interface 830, a network interface 840, a storage interface 850, etc. These interfaces 830, 840, 850 and the memory 810 and the processor 820 may be connected, for example, via a bus 860. Among them, the input / output interface 830 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 840 provides a connection interface for various networked devices. The storage interface 850 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0136] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements any of the aforementioned distributed training methods.

[0137] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0138] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0139] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0141] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A distributed training method, include: The terminal sends a first message to the base station, wherein the terminal is a distributed node of distributed learning, the base station is a central node of distributed learning, and the first message includes training information of the model deployed by the terminal; The terminal receives a second message sent by the base station, wherein the second message includes at least one of a parameter update indication and a convergence condition update indication of the model, or includes a training stop indication; The first message and the second message are control channel signaling, which are scrambled using a scrambling code sequence, and the scrambling code sequence is determined according to at least one of a model function, a model identifier, a training method, and a training group to which the terminal belongs.

2. The training method according to claim 1, in, Multiple terminals in the training group to which the terminal belongs use the same scrambling code sequence.

3. The training method according to claim 1, in: The first message has a first signaling format determined according to the scrambling code sequence; and / or, The second message has a second signaling format determined according to the scrambling code sequence.

4. The training method according to claim 3, in, The first signaling format and the second signaling format include at least one field of a model identifier, a model function identifier, a timestamp, a sequence index, and a training group identifier.

5. The training method according to claim 3, in, The second signaling format includes at least one field of an aggregation algorithm indication, a training stop condition, an initial value of a parameter of the model, a parameter update indication of the model, and a gradient update indication of the model.

6. The training method according to claim 5, in, Any one of the parameter update indication of the model and the gradient update indication of the model includes an indication bit, and the value of the indication bit is different from the value of the indication bit in the same indication obtained by the terminal last time.

7. The training method according to claim 6, in, The value of the indicator bit is a first value or a second value.

8. The training method according to claim 3, in, The sizes of the fields in the first signaling format and the second signaling format are default values ​​or are determined according to the configuration sent by the base station.

9. The training method according to claim 1, in, The training information includes the parameters of the model after training, or the training status of the model.

10. The training method according to claim 1, further comprising: include: The terminal receives a configuration signaling sent by the base station, wherein the configuration signaling includes at least one of a model function, a model identifier, a model configuration, and a collection configuration of training data; The terminal configures the distributed nodes deployed by the terminal according to the configuration signaling.

11. The training method according to claim 10, in, The model function represents at least one of mobility optimization, positioning, and beam management.

12. The training method according to claim 10, in: The model function includes at least one of a model function identifier, an area code, a public land mobile network, an operator identifier, a tracking area, a cell group, and a geographic range identifier; and / or, The model identification includes at least one of a country identification code, an operator identification code, a public land mobile network, a tracking area, a geographic range identification code, and a model identification code.

13. The training method according to claim 10, in, The model configuration includes the lifecycle management configuration or model attribute configuration of the model.

14. The training method according to claim 13, in: The model lifecycle management configuration includes at least one of a model training configuration, a model reasoning configuration, a model deployment configuration, a model update configuration, and a model monitoring configuration; and / or, The model attribute configuration includes at least one of input configuration, output configuration, model structure configuration, interface configuration, and training rule configuration.

15. The training method according to claim 10, in: The collection configuration of the training data includes at least one of a collection object and a collection method; or, The collection configuration of the training data includes a configuration for uplink measurement of a reference signal.

16. The training method according to claim 10, in, The configuration signaling is any one of downlink control information of the physical layer, a control unit of the media access layer, or radio resource control signaling.

17. The training method according to any one of claims 1 to 16, in, The distributed learning is federated learning.

18. The training method according to any one of claims 1 to 16, in, The model is an indoor positioning model.

19. A distributed training method, include: The base station receives a first message sent by any one of a plurality of terminals, wherein the plurality of terminals are distributed nodes of distributed learning, the base station is a central node of the distributed learning, and the first message includes training information of a model deployed on the terminal; The base station sends a second message to any one of the multiple terminals, wherein the second message includes at least one of a parameter update indication and a convergence condition update indication of the model, or includes a training stop indication; The first message and the second message are control channel signaling, which are scrambled using a scrambling code sequence, and the scrambling code sequence is determined according to at least one of a model function, a model identifier, a training method, and a training group to which the terminal belongs.

20. The training method according to claim 19, further comprising: include: The base station aggregates the models deployed by the multiple terminals according to the training information sent by the multiple terminals to obtain updated parameters of the model.

21. The training method according to claim 19, further comprising: include: The base station sends a configuration signaling to any one of the multiple terminals, wherein the configuration signaling includes at least one of a model function, a model identifier, a model configuration, and a collection configuration of training data.

22. A terminal, include: A sending module, configured to send a first message to a base station, wherein the terminal is a distributed node of distributed learning, the base station is a central node of distributed learning, and the first message includes training information of a model deployed on the terminal; A receiving module, configured to receive a second message sent by the base station, wherein the second message includes at least one of a parameter update indication and a convergence condition update indication of the model, or includes a training stop indication; The first message and the second message are control channel signaling, which are scrambled using a scrambling code sequence, and the scrambling code sequence is determined according to at least one of a model function, a model identifier, a training method, and a training group to which the terminal belongs.

23. A terminal, include: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the distributed training method according to any one of claims 1 to 18 based on instructions stored in the memory.

24. A base station, include: A receiving module is configured to receive a first message sent by any one of a plurality of terminals, wherein the plurality of terminals are distributed nodes of distributed learning, the base station is a central node of distributed learning, and the first message includes training information of a model deployed on the terminal; A sending module, configured to send a second message to any one of the multiple terminals, wherein the second message includes at least one of a parameter update indication and a convergence condition update indication of the model, or includes a training stop indication; The first message and the second message are control channel signaling, which are scrambled using a scrambling code sequence, and the scrambling code sequence is determined according to at least one of a model function, a model identifier, a training method, and a training group to which the terminal belongs.

25. A base station, include: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the distributed training method according to any one of claims 19 to 21 based on instructions stored in the memory.

26. A distributed training system, include: The terminal according to claim 22 or 23; as well as The base station as claimed in claim 24 or 25.

27. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the distributed training method according to any one of claims 1 to 21.

Citation Information

Cited By

  • Communication method and apparatus

    WO2026124306A1