Communication method and apparatus

Abstract

A communication method and apparatus, which are conducive to reducing the resource overheads caused by model training and management, and improving the efficiency of model management. The method comprises: a second communication apparatus compiling statistics on model information of at least one first model associated with a second model, and network configuration parameters applicable to the at least one first model, generating first information, which comprises at least one of the model information of the at least one first model, statistical information corresponding to the model information and statistical information corresponding to the network configuration parameters, and sending the first information to a first communication apparatus; and on the basis of the received first information, the first communication apparatus using as reference experience the model information of the at least one first model, the statistical information corresponding to the model information or the statistical information corresponding to the network configuration parameters, and determining whether to train the second model.

Description

Communication method and apparatus

[0001] The present application claims priority to the Chinese Patent Application No. 202411398366.9, filed on September 30, 2024, and entitled "Communication method and apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] Embodiments of the present application relate to the field of communication, in particular to a communication method and apparatus. BACKGROUND

[0003] In a wireless communication network, as the diversification of service requirements and the enhancement of network functions, service implementation, network planning, configuration, and resource scheduling also become increasingly complex. For example, service implementation, network planning, configuration, and resource scheduling may involve modulation, coding, transmitters, receivers, multi-antenna technology, or positioning technology in a wireless communication system. Network devices (such as base stations, terminals, etc.) in a wireless communication network can implement, for example, signal modulation and demodulation, information encoding and decoding, channel state information (CSI) feedback, or beam management (BM) schemes by performing related operations.

[0004] Currently, in the process of implementing the above schemes through a wireless communication network, a terminal can implement related operations in the above schemes by training a model (which can also be referred to as a characteristic, function, or algorithm) through collection of a large amount of training data, but this approach can result in a large resource overhead. SUMMARY

[0005] The present application provides a communication method and apparatus, which can reduce the resource overhead caused by model training and management, and improve the efficiency of model management.

[0006] In a first aspect, a communication method is provided. The method can be performed by a first communication apparatus, or by a component (such as a processor, circuit, chip, or chip system, etc.) applied to the first communication apparatus, or by a logic node, logic module, or software that can implement all or part of the functions of the first communication apparatus. The method comprises: receiving first information from a second communication apparatus, the first information comprising at least one of the following: model information of at least one first model, statistical information corresponding to the model information of the at least one first model, or statistical information corresponding to at least one network configuration parameter, the at least one network configuration parameter being a network configuration parameter in network configurations applicable to the at least one first model; and determining whether to train a second model according to the first information, the first model and the second model having an association relationship.

[0007] Based on the scheme, in the process of determining whether to train the second model, the first communication device receives first information from the second communication device, the first information including at least one of the following: model information of at least one first model associated with the second model, statistical information corresponding to the model information of the at least one first model, and statistical information corresponding to at least one network configuration parameter, and then the first communication device determines whether to train the second model according to the first information. That is, the first communication device takes the model information of the first model associated with the second model, the statistical information corresponding to the model information of the first model, or the statistical information of the network configuration parameter in the network configuration applicable to the first model as prior information, and determines whether to train the second model according to the prior information. In the process of determining whether to train the second model, there is no need to collect a large amount of training data and analyze the data statistical characteristics of the training data, which is beneficial to reduce the resource overhead required by the first communication device in the process of determining whether to train the second model, and improve the efficiency of the first communication device in training the second model.

[0008] In a second aspect, a communication method is provided. The method can be performed by a second communication device, or by a component (e.g., a processor, a circuit, a chip, or a chip system) applied to the second communication device, or by a logic node, a logic module, or software that can realize all or part of the functions of the second communication device. The method includes determining first information, the first information including at least one of the following: model information of at least one first model, statistical information corresponding to the model information of the at least one first model, or statistical information corresponding to at least one network configuration parameter, the at least one network configuration parameter being a network configuration parameter in a network configuration applicable to the at least one first model; and sending the first information to a first communication device, wherein the first information is used to determine whether to train a second model, and the first model is associated with the second model. The technical effects brought by the second aspect can refer to the technical effects brought by the first aspect, which will not be repeated here.

[0009] In combination with the first aspect, in a possible design, the communication method further includes determining, according to the first information, at least one of the following of the second model: a generalization range, a target performance indicator, a model complexity, or a size of a data set used to train the second model. In combination with the second aspect, in a possible design, the first information is further used to determine at least one of the following of the second model: a generalization range, a target performance indicator, a model complexity, or a size of a data set used to train the second model.

[0010] Based on the scheme, the first communication apparatus can obtain the model information statistical result of the at least one first model according to the first information, accurately obtain the probability of each item of model information of the at least one first model being set to various values, and facilitate the first communication apparatus to determine the target value of one or more items of model information of the second model as prior experience of other models, thereby improving the training efficiency of the second model.

[0011] In a possible design in combination with the first aspect and the second aspect, the model information of the first model indicates at least one of the following: a generalization range of the first model; a state of the first model; a performance indicator of the first model; a size of a first data set used for training or changing the first model; and a model complexity of the first model.

[0012] Based on the scheme, the first communication apparatus can accurately obtain the management information and the model static attribute of each first model in the model training or changing process according to the model information of each first model, and facilitate the first communication apparatus to determine whether to train the second model and guide the training of the second model as prior experience of other models.

[0013] In a possible design in combination with the first aspect and the second aspect, the generalization range includes at least one cell to which the first model is applicable, and / or at least one network configuration to which the first model is applicable.

[0014] In a possible design in combination with the first aspect and the second aspect, the state of the first model includes at least one of the following: a support state, an available state, a suitable state, an active state, or a configuration state.

[0015] With the first aspect and the second aspect, in a possible design, the statistical information corresponding to the model information of the at least one first model indicates at least one of the following: a proportion of the first models in the at least one first model that meet the first target performance indicator; a proportion of the first models in the at least one first model that do not meet the first target performance indicator; a proportion of the first models in the at least one first model that are applicable to the first network configuration; a proportion of the first models in the at least one first model that are applicable to the second network configuration; a proportion of the first models in the at least one first model that meet the first target performance indicator and are applicable to the first network configuration; a proportion of the first models in the at least one first model that meet the first target performance indicator and are applicable to the second network configuration; a proportion of the first models in the at least one first model that are applicable to the third network configuration; a proportion of the first models in the at least one first model that are applicable to the third network configuration and meet the first target performance indicator; a proportion of the first models in the at least one first model that are applicable to the third network configuration and do not meet the first target performance indicator; a proportion of the first models in the at least one first model that are in an activated state; a proportion of the first complexity in the model complexities corresponding to the at least one first model, the first complexity being any one of the model complexities corresponding to the at least one first model; a proportion of the first size in the sizes of the first datasets corresponding to the at least one first model, the first size being the size of any one of the first datasets corresponding to the at least one first model; wherein each network configuration parameter in the first network configuration has one value, at least some network configuration parameters in the second network configuration have multiple values, and the third network configuration is any one of the at least one network configuration.

[0016] Based on this scheme, the first communication apparatus can directly obtain, according to the first information, the probability of one or more model information of the first model taking different values and the model information of the model in the at least one first model that can meet the performance indicator requirement, thereby assisting the first communication apparatus in determining whether to train the first model and effectively guiding the training direction of the second model.

[0017] With the first aspect and the second aspect, the statistical information corresponding to the at least one network configuration parameter includes proportion information of the first network configuration parameter, the first network configuration parameter being any one of the at least one network configuration parameter, and the proportion information including a time proportion corresponding to a first value, the first value being any possible value of the first network configuration parameter.

[0018] Based on this scheme, the first communication apparatus can accurately obtain the probability of each possible value of any one network configuration parameter associated with the second model, so as to facilitate the first communication apparatus in determining whether to train the second model for the network configuration including the certain value of the network configuration parameter according to the probability of different values of the network configuration parameter.

[0019] With the first aspect and the second aspect, the time proportion corresponding to the first value is used to indicate a time proportion in which the first network configuration parameter is set to the first value in the at least one time period.

[0020] Based on the scheme, the first communication device can obtain the occurrence probability of any value of any network configuration parameter at different times, so as to facilitate the first communication device to determine whether to train the second model according to the time period in which the second model is needed to be applied.

[0021] With the first aspect, the communication method further includes: sending second information to the second communication device, the second information being used to request the first information. Correspondingly, with the second aspect, the communication method further includes: receiving the second information from the first communication device, the second information being used to request the first information.

[0022] With the first aspect, the communication method further includes: sending model information of the second model to the second communication device. Correspondingly, with the second aspect, the communication method further includes: receiving the model information of the second model from the first communication device.

[0023] With the first aspect and the second aspect, in a possible design, the at least one first model is a model maintained by at least one third communication device, and the network configuration applicable to the first model contains the network configuration applicable to the second model.

[0024] Based on the scheme, the application scenarios (corresponding network configurations) between the first model and the second model have a strong correlation, and the model information of the first model can effectively guide the first communication device whether to train the second model and the training direction of the second model.

[0025] The third aspect provides a communication device for implementing various methods. The communication device includes modules, units, or means corresponding to the methods, which can be implemented by hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the functions.

[0026] In some possible designs, the communication device can include a processing module and a transceiver module. The processing module can be used to implement the processing functions in any of the aspects and any possible implementation manners thereof. The transceiver module can include a receiving module and a sending module, which are used to implement the receiving functions and the sending functions in any of the aspects and any possible implementation manners thereof.

[0027] In some possible designs, the transceiver module can be composed of a transceiver circuit, a transceiver, a transceiver, or a communication interface.

[0028] In a fourth aspect, a communication apparatus is provided, which comprises: a processor and a memory; the memory is configured to store computer instructions, which, when executed by the processor, cause the communication apparatus to perform the method of any one of the first aspect.

[0029] In a fifth aspect, a communication apparatus is provided, which comprises: a processor and a communication interface; the communication interface is configured to communicate with modules outside the communication apparatus; the processor is configured to execute computer programs or instructions, so as to cause the communication apparatus to perform the method of any one of the first aspect.

[0030] In a sixth aspect, a communication apparatus is provided, which comprises: at least one processor; the processor is configured to execute computer programs or instructions stored in a memory, so as to cause the communication apparatus to perform the method of any one of the first aspect. The memory can be coupled with the processor, or can be independent of the processor.

[0031] In a seventh aspect, a communication apparatus (for example, the communication apparatus can be a chip or a chip system) is provided, which comprises a processor configured to implement the functions involved in any one of the first aspect and the second aspect.

[0032] In some possible designs, the communication apparatus comprises a memory configured to store necessary program instructions and data.

[0033] In some possible designs, when the apparatus is a chip system, the apparatus can be composed of a chip, or can comprise a chip and other discrete devices.

[0034] It can be understood that the communication apparatus provided in the third aspect to the seventh aspect can be the first communication apparatus in the first aspect, or can be a module or unit (for example, a chip, or a chip system, or a circuit) corresponding to the first communication apparatus in executing the method / operation / step / action described in the first aspect, or can be a module or unit capable of matching the first communication apparatus, or can also be a logic node, a logic module or software capable of implementing all or part of the functions of the first communication apparatus; or the communication apparatus can be the second communication apparatus in the second aspect, or can be a module or unit (for example, a chip, or a chip system, or a circuit) corresponding to the second communication apparatus in executing the method / operation / step / action described in the second aspect, or can be a module or unit capable of matching the second communication apparatus, or can also be a logic node, a logic module or software capable of implementing all or part of the functions of the second communication apparatus.

[0035] It can be understood that when the communication apparatus in any one of the third aspect to the seventh aspect is a chip, the sending action / function of the communication apparatus can be understood as outputting information, and the receiving action / function of the communication apparatus can be understood as inputting information.

[0036] In an eighth aspect, a computer-readable storage medium is provided, which stores a computer program or instructions, when executed on a communication device, causes the communication device to perform the method of any one of the first aspect and the second aspect.

[0037] In a ninth aspect, a computer program product is provided, which contains instructions, when executed on a communication device, causes the communication device to perform the method of any one of the first aspect and the second aspect.

[0038] In a tenth aspect, a communication system is provided, which includes a first communication device configured to perform the method of the first aspect and any possible design thereof, and a second communication device configured to perform the method of the second aspect and any possible design thereof.

[0039] The technical effects brought by any one of the designs of the third aspect to the tenth aspect can be referred to the technical effects brought by different designs of the first aspect and the second aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0040] FIG. 1 is a schematic diagram of an architecture of a communication system provided by the present application;

[0041] FIG. 2 is a schematic diagram of an architecture of another communication system provided by the present application;

[0042] FIG. 3 is a schematic diagram of a structure of an O-RAN system provided by the present application;

[0043] FIG. 4 is a flowchart of a communication method provided by the present application;

[0044] FIG. 5 is a schematic diagram of a first information broadcasting method provided by the present application;

[0045] FIG. 6 is a schematic diagram of an application flow of a communication method provided by the present application;

[0046] FIGS. 7-9 are schematic diagrams of structures of communication devices provided by the present application. DETAILED DESCRIPTION

[0047] In the description of the present application, unless otherwise specified, “ / ” represents a “or” relationship between the objects associated before and after, for example, A / B can represent A or B; “and / or” in the present application is only a description of the association between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural.

[0048] In the description of the present application, "a plurality of" means two or more than two, unless otherwise specified. "At least one of the following" or similar expressions means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0049] In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, "first", "second" and the like are used to distinguish the same items or similar items with basically the same function and role. Those skilled in the art can understand that "first", "second" and the like do not limit the quantity and execution order, and "first", "second" and the like do not necessarily mean different.

[0050] In the embodiments of the present application, the words "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design presented as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Rather, the use of the words "exemplary" or "for example" is intended to present concepts in a concrete manner, facilitating understanding.

[0051] It can be understood that the "embodiments" mentioned throughout the specification mean that the specific features, structures or characteristics related to the embodiments are included in at least one embodiment of the present application. Therefore, the various embodiments throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It can be understood that in various embodiments of the present application, the size of the sequence number of each process does not mean the execution order, and the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0052] It can be understood that in the present application, "when" and "if" both refer to making corresponding processing under certain objective circumstances, not limited to time, and do not require judgment actions when implementing, nor mean that there are other limitations.

[0053] It can be understood that some optional features in the embodiments of the present application can be implemented independently in some scenarios without relying on other features, such as the scheme currently based on, to solve the corresponding technical problems and achieve the corresponding effects. In some scenarios, it can also be combined with other features according to demand. Correspondingly, the devices given in the embodiments of the present application can also realize these features or functions, which will not be described here.

[0054] In the present application, the same or similar parts among various embodiments can be mutually referred to, unless otherwise specified. In various embodiments of the present application, the terms and / or descriptions of different embodiments are consistent and can be mutually referred to, unless otherwise specified and logically conflicted, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship. The implementation manners of the present application described below do not constitute a limitation on the protection scope of the present application.

[0055] In order to facilitate the understanding of the technical solutions of the embodiments of the present application, first, a brief introduction of the related technologies of the present application is given as follows.

[0056] 1. Artificial intelligence / machine learning model

[0057] In a wireless communication network, as the diversification of service requirements and the enhancement of network functions, service implementation, network planning, configuration, and resource scheduling also become increasingly complex. For example, service implementation, network planning, configuration, and resource scheduling may involve modulation, coding, transmitters, receivers, multiple antenna technology, or positioning technology in a wireless communication system. Network devices (such as base stations, terminals, etc.) in a wireless communication network can implement one or more wireless communication functions / operations, such as signal modulation and demodulation, information encoding and decoding, CSI feedback, channel equalization, channel estimation, pilot generation, precoding, resource mapping, resource demapping, interference suppression, interference estimation, interference prediction, BM, or mobility management, by performing related operations.

[0058] For example, the communication device can perform the technical solutions in the above various service scenarios through traditional algorithms, or can apply artificial intelligence (AI) / machine learning (ML) technology to the technical solutions in the above service scenarios. AI / ML technology refers to training a model through related data, and then using the trained model to achieve a specific purpose (such as a wireless communication function / operation). The purpose that the model can achieve is related to the data used during training.

[0059] The training data includes data obtained in the communication network, such as signal processing information, channel information, and radio frequency information. The signal processing information includes information generated in a baseband signal processing process, such as at least one of information generated in a signal sampling, modulation, demodulation, coding, decoding, precoding, resource mapping, or digital filtering process. The channel information includes information corresponding to a channel environment, such as at least one of power information, amplitude information, phase information, time delay information, multipath information, signal propagation time information, distance information, speed information, large-scale channel information, small-scale channel information, channel scattering information, or line-of-sight (LOS) / non-line-of-sight (NLOS) information. For example, data in a CSI use case and a BM use case is embodied as channel information CSI, and data in a positioning use case is embodied as channel information and / or position information. The radio frequency information includes information generated in an analog processing process, such as at least one of information generated in a digital-to-analog conversion, analog-to-digital conversion, digital pre-distortion, frequency conversion, radio frequency modulation, radio frequency demodulation, power amplification, low-noise amplification, analog filtering, or duplex processing.

[0060] For example, in a service scenario of AI / ML-based CSI feedback, the service scenario of AI / ML-based CSI feedback includes AI / ML-based CSI compression and AI / ML-based CSI prediction. The AI / ML-based CSI compression refers to compression of downlink CSI (measured by a terminal) by a model trained based on AI / ML technology. Then, the terminal can send the compressed CSI to a network device through an air interface. The network device restores (decompresses) the CSI by a model trained based on AI / ML technology. Compared with a traditional compression algorithm, the AI / ML-based compression algorithm has a higher compression rate and better CSI restoration capability. Therefore, the terminal can feed back more CSI through a smaller air interface overhead, so that the network device can perform more accurate downlink precoding. The AI / ML-based CSI prediction refers to prediction of downlink CSI at a future time by a model trained based on AI / ML technology and downlink CSI at a current / historical time, and then precoding according to the predicted CSI. The CSI predicted by this scheme is more matched to the channel state when downlink data is scheduled, so it can overcome the problem of channel aging and achieve more accurate downlink precoding. The training data of the model involved in the service scenario of AI / ML-based CSI feedback includes CSI.

[0061] For example, in a business scenario of AI / ML-based BM, network devices and terminal devices can predict transmitting beams and / or receiving beams through AI / ML technology, for example, a model trained based on AI / ML technology can infer a small amount of beam scanning results to obtain an optimal beam. Compared with a traditional scheme in which a large number of beams need to be scanned to obtain an optimal beam, AI / ML-based beam prediction can reduce the processing overhead of beam scanning. For example, a terminal can scan a small amount of beams, and then predict an optimal beam from a large number of candidate beams through a model trained based on AI / ML technology, so that it is not necessary to scan all candidate beams, thereby reducing the overhead. The small amount of beams scanned by the terminal can be sparse beams or wide beams, and the candidate beams can be dense beams or narrow beams. The terminal can input beam information scanned at a current / historical moment into the model to predict an optimal beam at a future moment, so that it is not necessary to perform beam scanning again at the future moment, thereby improving the efficiency of beam scanning. Training data of the model involved in the business scenario of AI / ML-based BM includes beam information, for example, beam information can be beam identity document (ID) and / or beam-related information such as reference signal receiving power (RSRP) corresponding to the beam.

[0062] For example, in a business scenario of AI / ML-based positioning, a communication device inputs channel information into a model trained based on AL / ML technology to infer an intermediate parameter required for positioning, or directly obtains a position coordinate value. Compared with a traditional positioning algorithm, the intermediate parameter or the position coordinate value obtained based on AL / ML is more accurate. Training data of the model involved in the business scenario of AI / ML-based positioning includes channel information and / or position information, and the channel information includes power information, phase information, time delay information, distance information, speed information, channel scattering information, and LOS / NLOS information.

[0063] 2. Model training and management

[0064] Since the performance of a model on the terminal side can be affected by various factors, for example, network configuration on the base station side, external environment, and terminal internal conditions, in the process of training and maintaining the model, the terminal needs to train the model according to current data characteristics or determine a suitable management strategy to maintain the model, so that the performance indicators of the model can meet the preset performance indicator requirements.

[0065] The network configuration on the base station side mainly includes private configuration and radio resource control (RRC) configuration.

[0066] Exemplarily, the RRC configuration includes: reference signal configuration, data feature configuration, quasi-collocation (QCL) assumption, and beam configuration. The private configuration includes: base station height, inter-site distance (ISD), base station antenna form, antenna downtilt angle, and mapping relationship between beam and radio frequency antenna port, etc.

[0067] For example, the reference signal configuration is configuration information related to channel state information reference signal (CSI-RS), such as CSI-RS resource configuration and CSI reporting configuration, etc.; the data feature configuration is data feature identification; and the beam configuration is mapping relationship between beams, beam set, and beam list.

[0068] Exemplarily, the external environment mainly refers to the channel condition in which the terminal is located. For example, Doppler spread of the channel in which the terminal is located, multipath transmission delay, channel interference intensity, and received signal strength, etc. The internal condition of the terminal mainly includes: power of the terminal, remaining storage space, and computing power, etc. In the case that the terminal is in the condition of insufficient power, insufficient storage space, or insufficient computing power, it is easy to appear the problem that part of the management strategies cannot be supported or there is conflict between the part of the management strategies.

[0069] It should be understood that the data feature configuration in the embodiments of the present application can also be referred to as data feature or data classification feature, wherein the “feature” can also be described as: condition, situation, environment or circumstance, type, status, or data distribution. The feature in other terms “xx feature” (for example, reference feature, physical feature, or feature of the xth data, etc.) in the embodiments of the present application can also be replaced similarly.

[0070] Exemplarily, the data feature identification can also be referred to as associated identification (associated ID), data identification (data ID), data set identification (dataset ID), data categorization identification (data categorization ID), or property identification (property ID).

[0071] The data feature identifier can be used by the terminal to classify the measurement data. The measurement data is used to determine the model input, or to determine the training data (e.g., model output, label) for model training, and can also be used to implement related operations for model inference, for example, the terminal can assume that the downlink transmission beam set / list has the same or similar data features under the same data feature identifier.

[0072] Currently, the commonly used model performance monitoring is achieved by comparing the predicted value / inferred value of the model for a certain parameter with the true value. For example, in the business scenario of AI / ML-based BM, the Top-K accuracy predicted by the model can be compared with the true measurement value, and Top-K can be understood as the proportion of the correct label contained in the top K results with the highest probability in the prediction result.

[0073] As a possible implementation, in the process of training a model applicable to a specific network configuration, the terminal generally needs to obtain the correlation between the specific network configuration and other possible network configurations. In the case where there is a target network configuration with high correlation with the specific network configuration, a model applicable to both the specific network configuration and the target network configuration can be trained. In the case where there is no target network configuration with high correlation with the specific network configuration, a model applicable only to the specific network is trained.

[0074] Currently, the network configuration of different cells is usually defined by each cell individually, for example, the current network configuration can be implicitly indicated by an associated identifier (associated ID). Since different network configurations are defined by each cell individually, the network configurations corresponding to the same associated identifier in different cells can also be completely different or not completely the same, for example, the network configurations corresponding to the same associated identifier in different cells are only similar in terms of antenna beam characteristics. Since the base station and the terminal may have different understandings of a certain attribute, even if the network configurations corresponding to the same associated identifier, the terminal cannot establish the correlation between different network configurations in different cells. In the case where the terminal needs to train a model for different cells, the terminal needs to collect training data under the network configurations corresponding to different associated identifiers in different cells, and determine the correlation between different network configurations by analyzing the collected training data.

[0075] That is, in the process of training a model for a specific network configuration, the terminal will first collect a large amount of training data and analyze the training data to obtain the data statistical characteristics of the training data corresponding to different network configurations, and then determine the specific strategy for model training according to the relationship between the data statistical characteristics of the training data corresponding to other network configurations and the data statistical characteristics of the training data corresponding to the specific network configuration.

[0076] Exemplarily, the data statistical features can include correlation, value range, statistical distribution, speed of change over time, periodicity, value probability, mean value, variance, and other statistical information.

[0077] Therefore, the current commonly used model training process includes the following steps:

[0078] Step one, collect training data.

[0079] When the terminal is preparing to train a model applicable to the current network configuration, it collects a large amount of training data through signaling interaction with the base station, the training data includes training data corresponding to the current network configuration and training data corresponding to other network configurations, and stores the collected training data.

[0080] Step two, analyze the data statistical features of the training data, and determine the training strategy of the model.

[0081] After the terminal completes the collection of a large amount of training data, it performs data analysis on the collected training data according to the type of the network configuration corresponding to the training data, obtains the data statistical features of the training data corresponding to each type of network configuration, and then determines the correlation between the data statistical features of the training data corresponding to the current network configuration and the data statistical features of the training data corresponding to other types of network configurations. In the case where there is a target network configuration corresponding to the data statistical features and the data statistical features corresponding to the current network configuration have a correlation higher than a given threshold, the generalization range of the current network configuration and the target network configuration is taken as the training strategy, that is, a model with a generalization range of the current network configuration and the target network configuration is trained; in the case where there is no target network configuration corresponding to the data statistical features and the data statistical features corresponding to the current network configuration have a correlation higher than a given threshold, the generalization range of the current network configuration is taken as the training strategy, that is, a model with a generalization range of the current network configuration is trained.

[0082] Among them, the model with a generalization range including multiple network configurations can also be called a generalization model, and the multiple network configurations applicable to the generalization model can be multiple network configurations under the same cell or multiple network configurations under different cells. The model performance of the generalization model is relatively robust, which is beneficial to save resource overhead in the model monitoring process, and the model training and management burden is lighter, which is beneficial to reduce the number of models trained to adapt to different network configurations, save model storage space, reduce model switching delay and signaling overhead, but the upper limit of the model performance is lower. The model with a generalization range including one network configuration can also be called a scenario model, and the upper limit of the model performance of the scenario model is higher, but the burden of model training and management is heavier.

[0083] For example, the possible network configurations of the cell in which the terminal resides include network configuration 1 and network configuration 2. In the process of determining the training strategy of the model corresponding to network configuration 1, the terminal can collect training data corresponding to network configuration 1 and training data corresponding to network configuration 2 through signaling interaction with the base station corresponding to the cell, and then obtain the correlation between the data statistical characteristics of the training data corresponding to network configuration 1 and the data statistical characteristics of the training data corresponding to network configuration 2. In the case where the similarity between the data statistical characteristics corresponding to network configuration 1 and the data statistical characteristics corresponding to network configuration 2 is greater than a given threshold, the terminal can set the generalization range as network configuration 1 and network configuration 2 as the training strategy, or set training a generalization model as the training strategy, and perform model training according to the training data corresponding to network configuration 1 and the training data corresponding to network configuration 2; in the case where the similarity between the data statistical characteristics corresponding to network configuration 1 and the data statistical characteristics corresponding to network configuration 2 is less than or equal to the given threshold, the terminal can set the generalization range as network configuration 1 as the training strategy, or set training a scenario-based model as the training strategy, and perform model training only according to the training data corresponding to network configuration 1.

[0084] Optionally, in the case of training a model with a generalization range including multiple network configurations, the following two possible training methods are included:

[0085] Method one: if there is a model applicable to any one of the multiple network configurations, then the model is subjected to transfer learning through a small amount of training data corresponding to other network configurations, to obtain a model that can be used with multiple network configurations.

[0086] Method two: if there is no model applicable to any one of the multiple network configurations, then training data corresponding to different network configurations can be collected respectively, and a model applicable to different network configurations can be generated by directly training the model according to the training data corresponding to different network configurations.

[0087] Optionally, after training a model applicable to different network configurations, it can be determined whether model retraining is needed according to the performance indicators of the model under different network configurations.

[0088] For example, after training a model applicable to network configuration 1 and network configuration 2, the performance indicators of the model under network configuration 1 can meet the preset performance indicator requirements, but the performance indicators of the model under network configuration 2 cannot meet the preset performance indicator requirements. Then, the model can be trained independently according to the training data corresponding to network configuration 1 and the training data corresponding to network configuration 2, to generate a model applicable only to network configuration 1 and a model applicable only to network configuration 2.

[0089] This way relies on collection of a large amount of training data, and thus increases the overhead for collecting the training data (for example, overhead of reference signal signaling / resource in the data collection process, overhead of terminal-side data measurement / storage, overhead of base station-side data transmission power consumption, or overhead of terminal-side data reception power consumption, etc.).

[0090] It should be understood that the model involved in the embodiments of the present application can be described as a function (such as an artificial intelligence (AI) function or a machine learning (ML) function), a feature, or an algorithm, etc., and the model includes an AI model or an ML model, etc. For the sake of simplifying the description, the model / function / feature / algorithm is referred to as a model in the present application, that is, the model in the present application can be replaced by an algorithm / function / feature.

[0091] That is, in the model training process at the terminal side, when the terminal is ready to train a model for a specific network configuration, the terminal needs to collect a large amount of training data, and perform data analysis on the collected training data to obtain the data statistical features of the training data corresponding to the specific network configuration and the correlation between the data statistical features of the training data corresponding to other network configurations, so as to determine whether there is a target network configuration with high correlation with the specific network configuration, and determine the training strategy of the model according to whether the target network configuration exists. The determination of the model training strategy brings a large resource overhead, and the training efficiency of the model is low.

[0092] Based on this, the embodiments of the present application provide a communication method. In the process of determining whether to train a second model, a first communication device receives first information from a second communication device, the first information including at least one of model information of at least one first model associated with the second model, statistical information corresponding to the model information of the at least one first model, and statistical information corresponding to at least one network configuration parameter, and then the first communication device determines whether to train the second model according to the first information. That is, the first communication device takes the model information of the first model associated with the second model, the statistical information corresponding to the model information of the first model, or the statistical information of the network configuration parameter in the network configuration applicable to the first model as prior information, and determines whether to train the second model according to the prior information. In the process of determining whether to train the second model, a large amount of training data does not need to be collected and the data statistical features of the training data do not need to be analyzed, which is beneficial to reduce the resource overhead required by the first communication device in the process of determining whether to train the second model, and improve the efficiency of the first communication device in training the second model.

[0093] The technical solutions of the embodiments of the present application can be applied to various communication systems, which can be a third generation partnership project (3GPP) communication system, for example, a long term evolution (LTE) system, a fourth generation (4G) system, a new radio (NR) system, a fifth generation (5G) system, a system of mixed networking of LTE and 5G, a communication and sensing integrated system, a non-terrestrial network (NTN), a device-to-device (D2D) communication system, a vehicle to everything (V2X) communication system, a machine-type communication (MTC) system, an internet of things (IoT) system, or other future communication systems. The communication system can also be a non-3GPP communication system, which is not limited.

[0094] It should be noted that the above-mentioned communication system to which the present application is applicable is only an example, and the communication system to which the present application is applicable is not limited thereto. The communication system provided by the present application does not cause any limitation to the solutions of the present application. Herein, it is uniformly stated that the following will not be repeated.

[0095] FIG. 1 shows a possible, non-limiting, system diagram. As shown in FIG. 1, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. The RAN 100 includes at least one RAN node (e.g., 110a and 110b in FIG. 1, collectively referred to as 110) and at least one terminal (e.g., 120a-120j in FIG. 1, collectively referred to as 120). Other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in FIG. 1), etc., can also be included in the RAN 100. The terminal 120 is connected to the RAN node 110 in a wireless manner. The RAN node 110 is connected to the core network 200 in a wireless or wired manner. The core network node in the core network 200 and the RAN node 110 in the RAN 100 can be different physical devices, respectively, or can be the same physical device integrated with the logical functions of the core network and the logical functions of the radio access network.

[0096] In a possible implementation, the core network node can refer to a device in the core network 200 that provides service support for the terminal 120. In the embodiments of the present application, the core network node in the core network 200 includes a sensing function (SF) network element, which is mainly used to implement sensing functions, such as sensing control functions and / or sensing calculation functions. Further, the SF network element can also support sensing billing functions when the terminal 120 and / or the RAN node 110 perform sensing. For example, the sensing control function can include determining sensing devices, sensing nodes, and the like. The sensing device can be understood as a device that transmits and / or receives sensing signals, and further, the sensing device also performs corresponding signal processing on the received echo signals to obtain sensing measurement data. For example, the sensing device can be the RAN node 110 or the terminal 120, and the like. The sensing node can refer to a network node participating in the sensing service process in the wireless network. The sensing calculation function can include performing corresponding signal processing on the echo signals received by the sensing device to obtain the sensing measurement data, further processing the sensing measurement data and the application information to obtain the sensing result, and the like.

[0097] For example, the SF network element can also be referred to as a communication device, for example, the SF network element can be understood as a communication device with core network sensing functions. In addition, the SF network element can also be referred to as a sensing server, and the like, without limitation.

[0098] In a possible scenario, the functions of the SF network element can be implemented by a network data analysis function (NWDAF) network element, or the SF network element and the NWDAF network element can be combined.

[0099] Optionally, in addition to the SF network element, the core network nodes in the core network 200 can also include at least one of the following: an access and mobility management function (AMF) network element, a session management function (SMF) network element, a user plane function (UPF) network element, a policy control function (PCF) network element, a unified data management (UDM) network element, an application function (AF) network element, a network exposure function (NEF) network element, a network slice selection function (NSSF) network element, or a location management function (LMF) network element, etc. Of course, the core network 200 can also include other core network nodes, which are not limited.

[0100] The AMF network element is a network element deployed in the core network 200, which provides mobility management and connection management for the network, such as user location update, user registration network, user handover, etc. The AMF network element can be used as an intermediate route of the LMF, the SMF and the RAN 100. The SMF network element is mainly responsible for session management in the mobile network, such as session establishment, modification, release, etc. The UPF network element is a functional network element of the user plane, which is mainly responsible for connecting external networks and processing user packets, such as forwarding, charging, etc. The PCF network element is mainly responsible for providing policies to the AMF and the SMF, such as quality of service (QoS) policies, slice selection policies, etc. The UDM network element is used to store user data, such as subscription information, authentication / authorization information, etc. The AF network element is responsible for providing services to the 3GPP network. The NEF network element is mainly used to open the capabilities of various network functions and is responsible for converting internal and external information. The LMF network element is a device or component deployed in the core network 200, which provides positioning functions for the terminal 120, for example, the LMF network element can initiate a positioning process and perform positioning on a specific terminal.

[0101] It should be noted that the network element in the present application can also be referred to as an entity or a functional entity, for example, the SF network element can also be referred to as an SF entity or an SF functional entity. In addition, the above-mentioned AMF network element, SMF network element, UPF network element, PCF network element, UDM network element, AF network element, NEF network element, and LMF network element can also have other names in future communication systems, which are not limited in the present application.

[0102] In a possible implementation, the RAN 100 can be a 3rd generation partnership project (3GPP) related cellular system, e.g., a 4G, 5G mobile communication system, or a future evolvement thereof. The RAN 100 can also be an open RAN (O-RAN or ORAN), a cloud radio access network (CRAN), an NTN network (e.g., an NTN supporting a transparent mode and / or a regenerative mode, or an NTN supporting a fixed earth mode and / or a moving earth mode), or a wireless fidelity (WiFi) system. The RAN 100 can also be a communication system combining two or more of the above systems.

[0103] The RAN nodes 110, which can also be referred to as access network devices, RAN entities or access nodes, etc., form part of the communication system to help terminals to access the wireless. The RAN nodes 110 in the RAN 100 can be of the same type or of different types. In some scenarios, the roles of the RAN nodes 110 and the terminals 120 are relative, e.g., the network element 120i in Figure 1 can be a helicopter or a drone, which can be configured to be a mobile base station. For a terminal 120j accessing the RAN 100 through the network element 120i, the network element 120i is a base station; but for the base station 110a, the network element 120i is a terminal. The RAN nodes 110 and the terminals 120 are sometimes referred to as communication apparatuses, e.g., the network elements 110a and 110b in Figure 1 can be understood as communication apparatuses with base station functionalities, and the network elements 120a-120j can be understood as communication apparatuses with terminal functionalities.

[0104] For the RAN node 110, in one possible scenario, the RAN node 110 can be a base station, an evolved Node B (eNodeB, also referred to as eNB), an access point (AP), a transmission reception point (TRP), a next generation NodeB (gNB), a next generation NodeB in a future mobile communications system, or an access node in a WiFi system, etc. The RAN node 110 can be a macro base station (e.g., 110a in Figure 1), a micro base station or indoor station (e.g., 110b in Figure 1), a relay node or donor node, or a wireless controller in a CRAN scenario. For example, a satellite base station, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a home base station (e.g., home eNodeB, or home NodeB, HNB), a relay station, a balloon station, a drone station, a wireless backhaul node, or a G node in a starlink, etc. It can be understood that the network device can be a device arranged on the ground, or a non-ground device (such as a satellite, a drone, a high-altitude communication device, etc.). In addition, in a communication system using different wireless access technologies, the name of the network device with base station function may be different, which is not limited in the present application. Optionally, the RAN node 110 can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in the vehicle to everything (V2X) technology can be a road side unit (RSU). The RAN node 110 is also referred to as a next generation-RAN (NG-RAN) node.

[0105] In another possible scenario, a terminal is assisted by multiple RAN nodes 110 to implement wireless access in cooperation, and different RAN nodes 110 respectively implement part of the functions of a base station. For example, a RAN node 110 can be a central unit (CU, also known as a central unit), a distributed unit (DU, also known as a distributed unit), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc. The CU and the DU can be separately arranged, or can also be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, such as a remote radio unit (RRU), an active antenna processing unit (AAU), or a remote radio head (RRH).

[0106] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an ORAN system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, CU-CP, CU-UP, DU and RU are taken as examples for description in this application. Any one of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0107] For the terminal 120, in a possible scenario, the terminal 120 can be a device for implementing a wireless communication function, for example, a terminal or a chip or circuit used in a terminal, or an entity associated with the terminal, etc. Among them, the terminal 120 can be a user equipment (UE), an access terminal, a terminal unit, a terminal station, a mobile station (MS), a mobile station, a remote station, a remote terminal, a mobile device, a wireless communication device, a terminal agent or a terminal device, a subscriber unit, a smart phone, a wireless data card, a tablet computer, a wireless modem, a laptop computer, a machine type communication (MTC) terminal, a tag, etc. in a 5G network or a future evolved public land mobile network (PLMN). The access terminal can be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handset with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device or a wearable device, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, or a terminal node (T node) in starlink, etc. In a possible implementation, the terminal 120 can be mobile or fixed. It can be understood that the terminal and the mobile user can be completely independent. All information related to the user can be stored in a subscriber identity module (SIM) card, which can be used on a terminal device.The terminal can send and / or receive signals through the air interface to complete interaction with the network side device.

[0108] The chip or circuit in the terminal includes at least one of components inside the terminal, such as a chip, a central processing unit (CPU), a network processing unit (NPU), and a terminal radio frequency module.

[0109] The entity associated with the terminal includes a server on the terminal side, a computing / processing node, a computing / processing entity, a computing / processing unit, a server, such as an over the top (OTT) server, etc. OTT refers to a third party other than a network operator providing various services to users based on the operator's network, such as OTT voice communication services, OTT multimedia services, and OTT data processing services, etc. The terminal interacts with relevant information (such as data) through communication with the associated network entity. For example, the associated network entity and the terminal belong to the same manufacturer. Due to model training, model selection, etc., it can not be performed on the terminal, but on the OTT server on the terminal side, so the "terminal" in this embodiment also includes the OTT server on the terminal side.

[0110] It should be understood that the terminal in this embodiment can also be referred to as "terminal side" (UE side) or "terminal part" (UE part).

[0111] For example, as shown in FIG. 2, an exemplary implementation of the system shown in FIG. 1 is provided. The communication system can include an AI / ML node, a first communication device, and a second communication device. The second communication device can provide services for the first communication device.

[0112] Optionally, the second communication device can be any device deployed in an access network that can communicate wirelessly with the first communication device (e.g., a terminal), and can also be a chip or chip system that can be provided in the above-mentioned device, and can also be a logical node or a logical module or a function implemented in software, mainly responsible for wireless physical control functions, resource scheduling, wireless resource management, quality of service management, data compression and encryption, wireless access control, and mobility management, etc. on the air interface. Specifically, the second communication device can be a device supporting wired access, or a device supporting wireless access.

[0113] Optionally, the communication system shown in FIG. 2 can include a network device. For example, the network device can be a server, which can be a single server or a server cluster composed of multiple servers. In some embodiments, the server cluster can also be a distributed cluster. The server can provide services for a chip, and thus can also be referred to as a chip server. Alternatively, the network device can be a first network element in a core network. The network device can deliver a model, model information, or statistical information of model information to the first communication apparatus or the second communication apparatus.

[0114] The AI / ML node in FIG. 2 is used to support the use of AI / ML technology in an AI / ML scenario.

[0115] Optionally, the AI / ML node can be deployed in one or more of the following positions in the communication system shown in FIG. 2: the network device, the first communication apparatus, or the second communication apparatus, etc. Alternatively, the AI / ML node can also be deployed separately, for example, in a position other than any of the above-mentioned devices.

[0116] For example, the AI / ML node can be deployed in a host or a cloud server of an OTT system. When the device in which the AI / ML node is deployed communicates with the second communication apparatus, the device can also act as a terminal in the communication system. When the device in which the AI / ML node is deployed communicates with the terminal, the device can also act as a network device in the communication system.

[0117] It can be understood that the number of AI / ML nodes is not limited in the present application. For example, when there are multiple AI / ML nodes, the multiple AI / ML nodes can be divided based on functions, for example, different AI / ML nodes are responsible for different functions.

[0118] It can also be understood that the AI / ML node can be a separate device, can be integrated into the same device to implement different functions, or can be a network element in a hardware device, or can be a software function running on a dedicated hardware, or a virtualized function instantiated on a platform (e.g., a cloud platform), and the specific form of the AI / ML node is not limited in the present application.

[0119] The AI / ML node can be an AI / ML network element or an AI / ML module.

[0120] It can be understood that the above-mentioned FIG. 2 is only a schematic diagram and does not constitute a limitation on the applicable scenarios of the technical solutions provided in the present application. It should be understood by those skilled in the art that in the specific implementation process, the communication system shown in FIG. 2 can also include fewer devices than those shown in FIG. 2, or the communication system shown in FIG. 2 can also include other devices, and the number of devices in the communication system shown in FIG. 2 can also be determined according to specific needs and is not limited.

[0121] Optionally, each device in FIG. 2, such as the first communication apparatus, the second communication apparatus, and the network device, can be a general device or a special device, and embodiments of the present application do not make specific limitation.

[0122] Optionally, the related functions of each device in FIG. 2 can be implemented by one device, or implemented by multiple devices together, or implemented by one or more functional modules in one device, and embodiments of the present application do not make specific limitation. It can be understood that the above functions can be network elements in a hardware device, or software functions running on a special hardware, or a combination of hardware and software, or virtualized functions instantiated on a platform (for example, a cloud platform).

[0123] In a possible implementation, the network device (for example, an access node or a core network node) in embodiments of the present application and the terminal 120, which can also be referred to as a communication apparatus, can be a general device or a special device, and the network device can include an access node (RAN node), an operation administration and maintenance (OAM) device, or a core network node. For the OAM device, it can include a device in an element management system (EMS), or a device in a network management system (NMS). It should be understood that the network device in the embodiments can also be referred to as a "network side" or a "network part". Embodiments of the present application do not make specific limitation.

[0124] In a possible implementation, the related functions of the terminal 120 or the network device in embodiments of the present application can be implemented by one device, or implemented by multiple devices together, or implemented by one or more functional modules in one device, and embodiments of the present application do not make specific limitation. It can be understood that the above functions can be network elements in a hardware device, or software functions running on a special hardware, or a combination of hardware and software, or virtualized functions instantiated on a platform (for example, a cloud platform).

[0125] It should be noted that the RAN node can be a device or a component in the device in the above NG-RAN, for example, it can be a ng-eNB node, a gNB node, or a transmission point (TP) in the ng-eNB node and the gNB node, a transmission and reception point (TRP), or a central unit (CU) integrated on the NG-RAN. The RAN node can also be a network element with transmission function, such as a transmission measurement function (TMF) network element. In some embodiments, the RAN node can also be an access node in the O-RAN system. The RAN is usually composed of a series of modules, such as antenna, RRU, and BBU modules. The traditional RAN architecture defines the overall reception and output of the RAN node, and does not limit the transmission and contact between internal modules. The O-RAN architecture defines the architecture contact and standardized interface between each module in the RAN, so that the RAN can be decoupled into multiple standard modules, thereby realizing the combination and replacement of modules.

[0126] For example, as shown in FIG. 3, it is a possible, non-limiting structure diagram of an O-RAN system. Among them, the service management and orchestration framework (SMO) is used as the network management device in the O-RAN, which is used to manage the devices in the O-RAN. The non-real time RAN intelligent controller (Non-RT RIC) is located in the SMO module, which is used to realize the non-real time intelligent management of the RAN function, for example, it can realize the AI / ML workflow including model training and model updating, and guide the application / function in the Near-RT RIC based on the policy. The near-real time RAN intelligent controller (Near-RT RIC) is used to realize the near-real time intelligent management of the RAN. Through data collection and related operations on the E2 interface, the near-real time control and optimization of the modules and resources of the O-RAN are realized.

[0127] An O-RAN central unit (O-CU) includes an O-RAN central unit control plane (O-CU-CP) and an O-RAN central unit user plane (O-CU-UP). The O-CU is configured to implement a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, and a service data adaptation protocol (SDAP) layer and other control functions. The O-CU-CP is configured to implement functions of the RRC layer and control plane functions of the PDCP layer. The O-CU-UP is configured to implement functions of the SDAP layer and user plane functions of the PDCP layer.

[0128] An O-RAN distributed unit (O-DU) is configured to implement a radio link control (RLC) layer, a media access control (MAC) layer, and a higher physical layer (Higher PHY). The Higher PHY functions include one or more of forward error correction (FEC) encoding / decoding, scrambling / descrambling, or modulation / demodulation.

[0129] An O-RAN radio unit (O-RU) is configured to implement lower physical layer (Lower PHY) functions and radio frequency functions. The Lower PHY functions include one or more of fast Fourier transform (FFT) transform / inverse fast Fourier transformation (iFFT) transform, digital beamforming, or extraction and filtering of a physical random access channel (PRACH). That is, the O-RU has functions of a radio frequency device such as a TRP or a RRH and Lower PHY processing functions. In addition, the O-RU, the O-CU, and the O-DU can be collectively configured as an O-eNB / gNB to implement the above functions.

[0130] As a cloud computing platform, the O-RAN cloud (O-Cloud) includes physical infrastructure nodes for hosting O-RAN functions such as RIC, O-DU, etc. The O-Cloud supports software components (such as operating systems, virtual machine monitors, container runtimes), management and orchestration functions.

[0131] In a possible scenario, a sensing unit (SU) is further included in the O-RAN system. The SU is mainly used to implement sensing-related functions, such as transmitting a sensing signal and / or receiving an echo signal of the sensing signal, performing corresponding signal processing on the received echo signal to obtain sensing measurement data, and performing sensing-related processing.

[0132] As a possible implementation, the RAN node can include at least one of a CU, a DU, a SU, and a RU. There is a communication interface between the CU and the SU. There can or can not be a communication interface between the SU and the DU. In the case where there is no communication interface between the SU and the DU, the SU and the DU can communicate through the CU.

[0133] Under the O-RAN architecture, the module that receives the difference reporting of the twin channel and the measurement channel can be a CU, a RT RIC, a Non-RT RIC, etc. The DU is responsible for receiving signals, signal processing, multipath measurement, and channel difference calculation.

[0134] For example, the O-RAN system includes communication interfaces between newly added internal components and other communication interfaces. For example, the A1 interface is an interface between the Non-RT RIC and the Near-RT RIC, which is used for intelligent and dynamic control of O-RAN internal wireless resources. The Non-RT RIC can provide policies, rich information, and ML model updates to the Near-RT RIC through the A1 interface, and the Near-RT RIC can provide policy feedback to the Non-RT RIC through the A1 interface.

[0135] The E2 interface is an open interface between two endpoints, used to connect the Near-RT RIC and the RAN node, which includes the CU, the DU in 5G, the O-RAN compatible eNB in 4G, the O-CU (O-CU-CP and / or O-CU-UP) and / or the O-DU in O-RAN, etc. The Near-RT RIC can obtain RAN node data collection and feedback through the E2 node, and the RAN node can obtain control feedback of the Near-RT RIC through the E2 node.

[0136] The O1 interface is an interface between a management entity in the SMO and an O-RAN module, used for operation management, through which network management (for example, fault management, configuration management, billing management, performance management, security management, also known as FCAPS management), software management, and file management are implemented. The O2 interface is an interface between the SMO and an infrastructure management framework supporting O-RAN virtual network functions.

[0137] The open front-haul (FH) CUS-Plane interface includes a control plane C-Plane, a user plane U-Plane, and a synchronization plane S-Plane interface. The control plane is used for real-time control between the O-DU and the O-RU, for example, for the O-DU to transmit the weight value to the O-RU for beamforming, or for the O-DU to perform power control on the O-RU, etc. The user plane is used to transmit communication data between the access network device and the terminal between the DU and the RU. The synchronization plane is used for the O-DU to provide clock synchronization to the O-RU. The Open FH M-Plane interface is a management plane interface, used for connection between the O-RU and the O-DU and the SMO, and can implement management, monitoring, and configuration functions, etc.

[0138] In addition, the NG interface is an interface between a RAN node (for example, a base station, a CU, a CU-CP, and a CU-UP) and a core network, NG-u is a user plane NG interface, and NG-c is a control plane NG interface. The Xn interface is an interface between NR RAN nodes, Xn-u is a user plane Xn interface, and Xn-c is a control plane Xn interface. The X2 interface is an interface between LTE RAN nodes, X2-u is a user plane X2 interface, and X2-c is a control plane X2 interface. In the NR system, the X2 interface is mainly used in the E-UTRA-NR dual connectivity (EN-DC) scenario, in which the master base station is an LTE RAN node, and the master base station is connected to the LTE core network through the X2 interface. The E1 interface is an interface between the CU-CP and the CU-UP, the F1-c interface is an interface between the CU-CP and the DU, and the F1-u interface is an interface between the CU-UP and the DU.

[0139] It should be noted that the communication system described in the embodiments of the present application is used to more clearly illustrate the technical solutions of the embodiments of the present application, and does not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of network architecture and the appearance of new business scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0140] The communication method provided by the embodiments of the present application is described below by taking the first communication device and the second communication device as an example, and by taking the communication system shown in FIG. 1. It should be noted that the names of messages, the names of parameters, or the names of information between the first communication device and the second communication device in the embodiments described below are only examples, and other names can also be used in other embodiments, and the method provided by the present application does not limit the names.

[0141] It can be understood that in the embodiments of the present application, the first communication device or the second communication device can perform some or all of the steps in the embodiments of the present application, and these steps or operations are only examples, and the embodiments of the present application can also perform other operations or variations of various operations. In addition, each step can be performed in a different order according to the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application are performed.

[0142] It can be understood that the first communication device and the second communication device are taken as an example of the execution subject of the interaction in the present application, but the present application does not limit the execution subject of the interaction. For example, the method performed by the first communication device in the present application can also be performed by a module (such as a chip, a chip system, or a processor) applied to the first communication device, and can also be implemented by a logic node, a logic module or software that can realize all or part of the function of the first communication device; the method performed by the second communication device in the present application can also be performed by a module (such as a chip, a chip system, or a processor) applied to the second communication device, and can also be implemented by a logic node, a logic module or software that can realize all or part of the function of the second communication device.

[0143] In addition, "sending information" in the present application can be understood as one device sending information to another device, or can also be understood as one logic module in a device sending information to another logic module. For example, "the second communication device sending information" can be understood as the second communication device sending information to another device (such as the first communication device), or can be understood as a logic module 1 (such as a processing module) in the second communication device sending information to a logic module 2 (such as a transceiver module) in the second communication device.

[0144] "Receiving information" in the present application can be understood as one device receiving information from another device, or can also be understood as one logic module in a device receiving information from another logic module. For example, "the first communication device receiving information" can be understood as the first communication device receiving information from another device (such as the second communication device), or can be understood as a logic module 1 (such as a processing module) in the first communication device receiving information from a logic module 2 (such as a transceiver module) in the first communication device.

[0145] In the present application, "sending information to (e.g. the first communication device)" or the related illustration in the drawings can be understood as that the destination of the information is the first communication device. It can include directly or indirectly sending information to the first communication device. "Receiving information from (e.g. the second communication device)" or "receiving information from (e.g. the second communication device)" or "receiving information sent by (e.g. the second communication device)", or the related illustration in the drawings can be understood as that the source of the information is the second communication device, which can include directly or indirectly receiving information from the second communication device. The information can be processed between the source and the destination of the information sending, such as format change, etc., but the destination can understand the effective information from the source. Similar expressions in the present application can be similarly understood, which will not be repeated here.

[0146] Referring to FIG. 4, a flowchart of a communication method provided by an embodiment of the present application is shown, which can include the following steps:

[0147] S401, the second communication device determines the first information.

[0148] The first information includes at least one of the following: model information of at least one first model, statistical information corresponding to the model information of at least one first model, or statistical information corresponding to at least one network configuration parameter.

[0149] For example, the first information including the model information of at least one first model can be understood as that the first information includes the model information of each of the at least one first model. The model information can include the generalization range of the first model, the model complexity of the first model, the state of the first model, the performance index of the first model, the size of the data set used for training / altering the first model, etc.

[0150] Similarly, the first information including the statistical information corresponding to the model information of at least one first model can be understood as that the first information includes the statistical results of the model information of one or more of the at least one first model, for example, the proportion of the first model with multiple network configurations in the generalization range of the at least one first model, the at least one generalization range with the largest proportion in the multiple generalization ranges corresponding to the at least one first model, or one or more model complexities with the largest proportion in the multiple model complexities corresponding to the at least one first model, etc.

[0151] Exemplarily, the at least one network configuration parameter is a network configuration parameter in a network configuration to which the at least one first model is applicable. That is, all network configuration parameters included in the at least one network configuration parameter are included in the network configuration parameters in the network configuration to which the at least one first model is applicable, or in other words, each network configuration parameter in the at least one network configuration parameter is included in the network configuration parameters in the network configuration to which the at least one first model is applicable. The statistical information corresponding to the at least one network configuration parameter can be understood as the occurrence probability of different values of the network configuration parameter, or can also be understood as the time proportion corresponding to different values of the network configuration parameter, or can also be understood as the occurrence number corresponding to different values of the network configuration parameter, and the proportion in the configuration number of the network configuration parameter.

[0152] In addition, the proportion of the first model in the generalization range of the plurality of network configurations in the at least one first model can be understood as the ratio between the number of the first model in the generalization range of the plurality of network configurations in the at least one first model and the total number of the at least one first model, or can also be understood as the ratio between the number of the communication apparatuses to which the first model is applicable and the total number of the communication apparatuses maintaining the at least one first model. Similarly, the proportion corresponding to a certain information or a certain value of an information can also be understood as described above, and details are not described herein.

[0153] That is, the second communication apparatus determines at least one of the model information of the at least one first model, the statistical information corresponding to the model information of the at least one first model, and the statistical information corresponding to the at least one network configuration parameter as the first information. For example, the second communication apparatus determines the model information of the at least one first model as the first information, or the second communication apparatus determines the statistical information corresponding to the model information of the at least one first model as the first information, or the second communication apparatus determines the statistical information corresponding to the at least one network configuration parameter as the first information, or the second communication apparatus determines the statistical information corresponding to the at least one network configuration parameter and the statistical information corresponding to the model information of the at least one first model as the first information, and the like, which are not limited in the embodiments of the present application.

[0154] As a possible implementation, the first information is used to determine whether to train the second model, and the first model and the second model have an association relationship.

[0155] Exemplarily, the first information used to determine whether to train the second model can be understood as auxiliary information or indication information used to determine whether to train the second model, or can also be understood as having guiding significance in the process of determining whether to train the second model.

[0156] The association between the first model and the second model can be understood as that the first model and the second model have the same or similar application scenarios, or the first model and the second model are used to implement the same or similar communication functions.

[0157] For example, at least one network configuration (denoted as configuration set 1) to which the second model is applicable is a subset of at least one network configuration (denoted as configuration set 2) to which the first model is applicable, or the network configuration to which the second model is applicable is the same as the network configuration to which the first model is applicable, that is, the network configuration to which the first model is applicable contains the network configuration to which the second model is applicable, and the configuration set 2 contains all elements in the configuration set 1.

[0158] As a possible implementation, the at least one first model is a model maintained by at least one third communication device.

[0159] For example, the at least one first model includes models 1 to 10, wherein models 1 and 2 are maintained by a third communication device 1, models 3 to 5 are maintained by a third communication device 2, model 6 is maintained by a third communication device 3, and models 7 to 10 are maintained by a third communication device 4.

[0160] For example, the at least one first model includes models 1 to 10, wherein models 1 and 2 are maintained by a third communication device 1, models 3 to 5 are maintained by a third communication device 2, model 6 is maintained by a third communication device 3, and models 7 to 10 are maintained by a third communication device 4.

[0161] For example, the at least one first model includes models 1 to 10, wherein models 1 and 2 are maintained by a third communication device 1, models 3 to 5 are maintained by a third communication device 2, model 6 is maintained by a third communication device 3, and models 7 to 10 are maintained by a third communication device 4.

[0162] S402, the second communication device sends first information to the first communication device. Correspondingly, the first communication device receives the first information from the second communication device.

[0163] For example, the first information can be carried in a predefined message. The predefined message can be understood as a message predefined by a protocol, or a message predefined by the first communication device and the second communication device.

[0164] For example, taking the first communication device as a terminal and the second communication device as a base station as an example, the first information can be carried in a system information block (MIB) or downlink control information (DCI).

[0165] S403, the first communication device determines whether to train the second model according to the first information.

[0166] For example, the first communication device determines whether to train the second model for the current network configuration of the camped cell according to the first information.

[0167] For example, taking the case that the first information of the second communication device includes statistical information corresponding to model information of at least one first model as an example, when determining whether to train the second model for the current network configuration of the camped cell, after obtaining the first information, if it is detected that the proportion of the first model with a performance index higher than the first target performance index in the at least one first model is higher than a first threshold, the second model is trained, otherwise the second model is not trained. Alternatively, if it is detected that the proportion of the first model in an activated state in the at least one first model is higher than a second threshold, the second model is trained, otherwise the second model is not trained.

[0168] In addition, the above is described taking the case that the first information includes statistical information corresponding to model information of at least one first model as an example. When the first information includes model information of at least one first model, after the first communication device receives the first information, statistical analysis can be performed on the model information of each first model to obtain statistical information corresponding to the model information of the at least one first model, and then, after triggering the maintenance process of the second model, it is determined whether to train the second model according to the statistical information corresponding to the model information of the at least one first model obtained by statistical analysis. The way of determining whether to train the second model can refer to the related description of the foregoing embodiments, and will not be described again.

[0169] For example, taking the case that the first information includes statistical information corresponding to at least one network configuration parameter as an example, the first communication device can determine the occurrence probability of the current value of one or more network configuration parameters in the current network configuration according to the first information. If the occurrence probability of the current value of each network configuration parameter or the current value of a majority of network configuration parameters in the one or more network configuration parameters is higher than a third threshold, the second model is trained, otherwise the second model is not trained. The values of the third thresholds corresponding to different network configuration parameters can be the same or different. For ease of understanding, the present application embodiment is described taking the case that the values of the third thresholds are the same.

[0170] In addition, when the first information includes two or more of the model information of at least one first model, the statistical information corresponding to the model information of the at least one first model, and the statistical information corresponding to the at least one network configuration parameter, the first communication device can jointly determine whether to train the second model according to the multiple information, or preferentially use the information with a high priority to determine whether to train the second model, without limitation.

[0171] Based on the scheme, in the process of determining whether to train the second model, the first communication device receives first information from the second communication device, the first information including at least one of model information of at least one first model associated with the second model, statistical information corresponding to the model information of the at least one first model, and statistical information corresponding to at least one network configuration parameter, and then the first communication device determines whether to train the second model according to the first information. That is, the first communication device takes the model information of the first model associated with the second model, the statistical information corresponding to the model information of the first model, or the statistical information of the network configuration parameter in the network configuration applicable to the first model as prior information, and determines whether to train the second model according to the prior information. In the process of determining whether to train the second model, there is no need to collect a large amount of training data and analyze the data statistical characteristics of the training data, which is beneficial to reduce the resource overhead required by the first communication device in the process of determining whether to train the second model, and improve the efficiency of the first communication device in training the second model.

[0172] The overall flow of the communication method provided by the present application is described above, and the specific implementation of each step is introduced below.

[0173] In a possible implementation, the first information is further used to determine at least one of the following of the second model: a generalization range, a target performance indicator, a model complexity, or a size of a data set.

[0174] The data set is used to train the second model. For example, the data set used to train the second model can be understood as a data set used in the process of training the first model, or can also be understood as a subset of the data set used in the process of training the first model.

[0175] Optionally, the size of the data set can be understood as the size of the total storage space occupied by all data in the data set, or can also be understood as the total number of data in the data set.

[0176] The target performance indicator can be understood as a target value of the performance indicator in the running process of the trained second model, or can also be understood as a minimum value of the performance indicator at the moment when the training of the second model is completed.

[0177] Exemplarily, the performance in the process of running the second model includes inference performance, prediction performance or monitoring performance. The performance indicator of the inference performance or the prediction performance can be represented by prediction accuracy, which reflects the similarity between the inference result of the second model and the actual measurement result. For example, for the function of CSI compression feedback, the performance indicator of the second model can be the restoration accuracy of restoring (decompressing) the compressed CSI; for the function of CSI prediction, the performance indicator of the second model can be the accuracy of CSI prediction; for the function of beam prediction, the performance indicator of the first model can be the accuracy of beam prediction; for the function of positioning inference, the performance indicator of the first model can be the accuracy of positioning inference.

[0178] Exemplarily, the system performance in the process of running the second model by the communication device includes: throughput, reference signal receiving power (RSRP), signal noise ratio (SNR) / signal to interference plus noise ratio (SINR) or block error rate (BLER) and other parameters for representing system performance.

[0179] The generalization range can be understood as at least one application scenario to which the model is applicable, or can also be understood as at least one application scenario in which the adaptation degree with the model is higher than a preset value. The preset value can be a protocol predefined value or a second communication device pre-indicated value.

[0180] Optionally, the application scenario includes the condition of the communication device maintaining the model (internal condition and / or external condition of the communication device, the internal condition is for example, power, computing power, storage space, etc., the external condition is for example, the channel condition in which the communication device is located) and / or the condition of the network device (the configuration of the network device, such as RRC configuration, or the internal implementation of the network device, such as antenna deployment).

[0181] As a possible implementation, the generalization range of the second model includes at least one cell to which the second model is applicable, and / or at least one network configuration to which the second model is applicable.

[0182] Exemplarily, the generalization range information of the second model can include the cell identifier of at least one cell to which the second model is applicable, or the generalization range information of the second model can include the network configuration identifier corresponding to at least one network configuration to which the second model is applicable, or the generalization range information of the second model includes the cell identifier of at least one cell to which the second model is applicable, and the network configuration identifier of one or more network configurations corresponding to each cell identifier.

[0183] For example, the second model is a cell specific model, and the second model is applicable to three network configurations corresponding to associated ID 1, associated ID 2 and associated ID 3 in a cell corresponding to cell identifier 1. The generalization range information of the second model can include the cell identifier 1, or the generalization range information of the second model can include the cell identifier 1 and the associated ID 1 to the associated ID 3.

[0184] For another example, the second model is a multi-cell model, and the second model is applicable to two network configurations corresponding to associated ID 1 and associated ID 2 in a cell corresponding to cell identifier 1, and a network configuration corresponding to associated ID 1 in a cell corresponding to cell identifier 2. The generalization range information of the first model can include the cell identifier 1 and the cell identifier 2, or the generalization range information of the first model can include the cell identifier 1, the associated ID 1 and the associated ID 2 associated with the cell identifier 1, the cell identifier 2 and the associated ID 1 associated with the cell identifier 2.

[0185] The model complexity of the second model can indicate the computing power level or storage space required to store or run the second model. For example, the model complexity of the second model can include at least one of the following: the storage space size required by the second model, the model order of the second model, or the number of model parameters included in the second model.

[0186] That is, the first communication device can also determine the model information of the second model according to the first information. The model information of the second model includes at least one of the following: the size of the data set used to train the second model, the generalization range of the second model, the target performance indicator of the second model, and at least one of the model complexity of the second model.

[0187] Based on this scheme, in the process of training the second model, the first communication device can obtain the target value of one or more model information of the second model according to the first information, reduce the length of possible meaningless training, accurately guide the second model training of the first communication device, reduce the resources required for the second model training, and improve the training efficiency of the second model.

[0188] In a possible implementation, the model information of the first model indicates at least one of the following: the generalization range of the first model, the state of the first model, the performance indicator of the first model, the size of the first data set, or the model complexity of the first model.

[0189] The generalization range of the first model can be understood as at least one application scenario applicable to the first model, or can also be understood as at least one application scenario with a higher adaptation degree than a preset value with the first model. The preset value can be predefined by a protocol or indicated by the second communication device in advance.

[0190] As a possible implementation, the generalization range of the first model includes at least one cell applicable to the first model, and / or at least one network configuration applicable to the first model. The meaning of the generalization range of the first model is similar to that of the generalization range of the second model, and can be referred to the related description in the foregoing embodiments. The difference is that the generalization range of the first model indicates the cell and / or the network configuration applicable to the first model, which will not be described here again.

[0191] Based on the scheme, the first communication device can accurately obtain the generalization range (such as the applicable cell and / or the network configuration) of each first model, so as to determine the target generalization range of the second model according to the generalization range of each first model in the at least one first model, and guide the training of the second model.

[0192] The state of the first model can be understood as a state of the first model in a communication device maintaining the model, or can also be understood as a capability state of the communication device maintaining the first model in running the first model.

[0193] As a possible implementation, the state of the first model can include at least one of the following: a supported state, an available state, a suitable state, an activated state, or a configured state. The state of the first model is described below by taking the second communication device as a terminal.

[0194] The supported state or simply supported is used to indicate whether the terminal maintaining the first model has the capability to execute the first model. In the case that the terminal has the capability to execute the first model, the state of the first model is the supported state. In the case that the terminal does not have the capability to execute the first model, the state of the first model is the not supported state.

[0195] The available state or simply available is used to indicate whether the terminal maintaining the first model has the capability to obtain / load / store the first model. In the case that the terminal has the capability to obtain / load / store the first model, the state of the first model is the available state. In the case that the terminal does not have the capability to obtain / load / store the first model, the state of the first model is the not available state.

[0196] Applicable state or applicable is used to indicate whether the terminal maintaining the first model is ready to use the first model to perform a specific communication function or inference. In the case that the terminal is ready to use the first model to perform inference, the state of the first model is the applicable state, and in the case that the terminal is not ready to use the first model to perform inference, the state of the first model is the inapplicable state.

[0197] Optionally, the terminal has a condition of executing or running the first model, and / or the terminal has acquired / stored / loaded the first model, and thus can be regarded as the terminal being ready to use the first model to perform inference.

[0198] Configured state is used to indicate whether the terminal maintaining the first model has a configuration of the model management device for executing / running the first model. In the case that the terminal has the configuration of the model management device for executing / running the first model, the state of the first model is the configured state, and in the case that the terminal does not have the configuration of the model management device for executing / running the first model, the state of the first model is the unconfigured state.

[0199] For example, the configuration of the model management device can be configured by the model management device (for example, a base station) to the terminal, for subsequent enabling / activating / instructing the terminal to use / run / execute the first model, that is, the configuration is a configuration related to the use of the first model, such as a configuration related to the input and / or output of the first model. Taking the input of the first model as a reference signal as an example, the configuration can be the resource of the reference signal.

[0200] Activated state or activated is used to indicate whether the terminal maintaining the first model has activated and executed the first model to perform inference. In the case that the terminal has activated and executed the first model to perform inference, the state of the first model is the activated state, and in the case that the terminal has not activated or has not executed the first model to perform inference, the state of the first model is the deactivated state or the inactivated state.

[0201] It is worth mentioning that the state of the first model can be the state of the first model when the first information is generated, or the state at any time during the generation of the first information, which is not limited.

[0202] Based on the scheme, the first communication device can accurately acquire whether the first model is supported or in the activated state in the communication device maintaining the first model, which is beneficial for the first communication device to determine whether to train the second model according to the state of at least one first model.

[0203] The performance indicator information of the first model is used to indicate the performance indicator in the running process of the first model, or can also be used to indicate the system performance in the process of calling the first model by the communication device.

[0204] For example, the performance in the running process of the first model includes inference performance, prediction performance or monitoring performance. The performance in the running process of the first model has a similar meaning to the performance in the running process of the second model in the foregoing embodiment, and reference can be made to the related description in the foregoing embodiment, which will not be described herein.

[0205] As a first possible implementation, the performance indicator of the first model indicates the performance indicator of the first model at the current moment, which can be the moment of determining the first information or any moment in the process of determining the first information.

[0206] Based on this scheme, the first communication device can accurately obtain the current performance indicator of each first model, and determine whether to train the second model according to the majority of the current performance indicators of the first models after determining the probability of occurrence of each performance indicator.

[0207] As a second possible implementation, the performance indicator of the first model indicates the performance indicator of the first model at the current moment and the target performance indicator of the first model. The target performance indicator of the first model can be understood as the target value of the performance indicator of the first model in the running process.

[0208] Based on this scheme, the first communication device can accurately obtain the current performance indicator and the target performance indicator of each first model, and determine whether to train the second model according to the majority of the current performance indicators of the first models and / or determine the target performance indicator of the second model according to the majority of the target performance indicators of the first models after determining the probability of occurrence of each performance indicator and target performance indicator.

[0209] As a third possible implementation, the performance indicator of the first model indicates the target performance indicator of the first model. The meaning of the target performance indicator can be referred to the description in the foregoing embodiment, which will not be described herein. Based on this scheme, the first communication device can accurately obtain the target performance indicator of each first model, and determine the target performance indicator of the second model according to the majority of the target performance indicators of the first models.

[0210] Optionally, in the case that the model information of the first model includes the performance indicator of the first model and the at least one first model is a model maintained by the at least one third communication device, the relationship between the at least one third communication device and the first communication device includes the following three possible implementation manners:

[0211] Manner 1: The third communication device and the first communication device are communication devices of the same model.

[0212] The model of the communication device can be understood as the same manufacturer (such as a terminal manufacturer or a chip manufacturer) corresponding to the communication device, or can also be understood as the same chip model included in the communication device.

[0213] That is, in the at least one third communication device maintaining the at least one first model, the model of each third communication device is the same as the model of the first communication device, that is, the proportion of the third communication device that is the same model communication device as the first communication device in the at least one third communication device is 100%, and the proportion of the third communication device that is a different model communication device from the first communication device in the at least one third communication device is 0.

[0214] Optionally, the third communication device is a different model communication device from the first communication device.

[0215] That is, in the at least one third communication device maintaining the at least one first model, there is no third communication device that is the same model as the first communication device, and the model of each third communication device is different from the model of the first communication device. The proportion of the third communication device that is a different model communication device from the first communication device in the at least one third communication device is 100%, and the proportion of the third communication device that is the same model communication device as the first communication device in the at least one third communication device is 0.

[0216] Optionally, the third communication device is a different model communication device from the first communication device.

[0217] That is, in the at least one third communication device maintaining the at least one first model, there is not only a third communication device that is the same model as the first communication device, but also a third communication device that is a different model from the first communication device.

[0218] Optionally, the first information can also indicate or not indicate the proportion of the third communication device that is the same model communication device as the first communication device in the at least one third communication device and / or the proportion of the third communication device that is a different model communication device from the first communication device.

[0219] As a possible implementation, the proportion of the third communication device that is the same model communication device as the first communication device in the at least one third communication device is greater than the proportion of the third communication device that is a different model communication device from the first communication device. For example, the proportion of the third communication device that is the same model communication device as the first communication device in the at least one third communication device is 90%, and the proportion of the third communication device that is a different model communication device from the first communication device is 10%; or the proportion of the third communication device that is the same model communication device as the first communication device in the at least one third communication device is 75%, and the proportion of the third communication device that is a different model communication device from the first communication device is 25%.

[0220] As another possible implementation, the proportion of the third communication devices of the same model as the first communication device in the at least one third communication device is less than or equal to the proportion of the third communication devices of different models as the first communication device in the at least one third communication device.

[0221] For example, the proportion of the third communication devices of the same model as the first communication device in the at least one third communication device is 10%, and the proportion of the third communication devices of different models as the first communication device in the at least one third communication device is 90%; or the proportion of the third communication devices of the same model as the first communication device in the at least one third communication device is 30%, and the proportion of the third communication devices of different models as the first communication device in the at least one third communication device is 70%.

[0222] Based on the scheme, the first communication device can accurately obtain the performance indicators of each first model, and by setting the models of the third communication devices participating in the statistics, the guiding significance of the performance indicators of the first model to whether to train the second model and the second model training strategy is improved, and the accuracy of determining whether to train the second model and the target performance indicators of the second model according to the first information is improved.

[0223] The first data set is used to train or change the first model.

[0224] For example, the first data set used to train the first model can be understood as a data set used in the process of training the first model, or can also be understood as a subset of the data set used in the process of training the first model. The first data set used to change the first model can be understood as a data set used in the process of updating or retraining the first model, or can also be understood as a subset of the data set used in the process of updating or retraining the first model.

[0225] As a possible implementation, in the case of change after the first model is self-trained, the first data set is the data set used in the last change of the first model, and the size of the first data set indicates the size of the data set used in the last change of the first model. In the case where the first model is not changed, the first data set is the data set used in the training of the first model, and the size of the first data set included in the model information of the first model indicates the size of the data set used in the training of the first model.

[0226] Optionally, the size of the first data set can be understood as the size of the total storage space occupied by all data contained in the first data set, or can also be understood as the total number of data contained in the first data set.

[0227] Based on the scheme, the first communication device can acquire the size of the data set adopted by the first model in the training or the last change process, which is beneficial to the first communication device to determine the target size of the data set in the training of the second model, and further reduce the resource overhead of the first communication device in training the second model.

[0228] The model complexity of the first model can include at least one of the following: the required storage space size of the first model, the model order of the first model, or the number of model parameters contained in the first model.

[0229] As a possible implementation, in the case where the first model has been changed after the training is completed, the model complexity of the first model is the model complexity of the first model after the last change. In the case where the first model has not been changed after the training is completed, the model complexity of the first model is the model complexity of the first model at the time when the training is completed.

[0230] Based on the scheme, the first communication device can accurately acquire the model complexity of each first model, determine the model complexity that accounts for a large proportion in at least one first model or that can be met by most first models, which is beneficial to the first communication device to determine the target model complexity of the second model and train the second model according to the target model complexity.

[0231] As a possible implementation, in the case where the first information includes the model information of at least one first model, the first communication device determining whether to train the second model according to the first information can include the following two implementation manners:

[0232] Manner one: determining whether to train the second model according to whether the performance indicators of the first models meet the first target performance indicators.

[0233] Exemplarily, in a case where the model information of the first model includes the performance indicators of the first communication device, the first communication device can determine, according to the first information, whether the current performance indicators of each of the at least one first model satisfy the first target performance indicator, and further determine the proportion (denoted as A1) of the first model in which the current performance indicators are greater than or equal to the first target performance indicator and / or the proportion (denoted as A2) of the first model in which the current performance indicators are less than the first target performance indicator. In a case where A1 is greater than a first threshold or A2 is less than or equal to the first threshold, it is determined that most of the first models can satisfy the first target performance indicator, and the second model can obtain a good probability of benefit, and the training of the second model is performed. In a case where A1 is less than or equal to the first threshold or A2 is greater than the first threshold, it is determined that most of the first models cannot satisfy the first target performance indicator, and the training of the second model can obtain a small probability of benefit, and the training of the second model is not performed. The first threshold can be predetermined by a protocol, or can be agreed by the first communication device and the second communication device in advance.

[0234] That is, in a case where most of the at least one first model cannot satisfy the first target performance indicator, the first communication device does not perform the training of the second model; and in a case where most of the at least one first model can satisfy the first target performance indicator, the first communication device performs the training of the second model.

[0235] Based on the scheme, the first communication device can perform the training of the second model in a case where the second model has a large probability of obtaining a good benefit, and reduce the probability of the first communication device performing the training of a model with a small benefit.

[0236] Option two, determining whether to train the second model according to the states of the first models.

[0237] Exemplarily, in a case where the model information of the first model includes the states of the first model, the first communication device can obtain, according to the first information, the proportion (denoted as A3) of the first model in the at least one first model in an activated state and / or the proportion (denoted as A4) of the first model in the at least one first model in a deactivated state, and in a case where A3 is greater than a second threshold or A4 is less than or equal to the second threshold, it is determined that most of the first models are in the activated state, and the training of the second model can obtain a large probability of benefit, and the training of the second model is performed. In a case where A4 is greater than the second threshold or A3 is less than or equal to the second threshold, it is determined that most of the first models are in the deactivated state, and the training of the second model can obtain a small probability of benefit, and the training of the second model is not performed. The second threshold can be predetermined by a protocol, or can be agreed by the first communication device and the second communication device in advance.

[0238] That is, the first communication device trains the second model when a majority of the at least one first model is in an active state, and does not train the second model when a majority of the at least one first model is in an inactive state.

[0239] In addition, the above scheme takes the active state as an example, and the state of the first model can also be an available state, a suitable state, or other states, which are not limited. Based on the scheme, the first communication device can determine the probability of obtaining a benefit of training the second model according to the state of the first model in the communication device maintaining the model, and perform training of the second model when the probability of obtaining a benefit of the second model is relatively large, thereby reducing the probability of meaningless or non-beneficial model training.

[0240] It is worth mentioning that the above embodiments take the model information of the first model including one item of information of the first model as an example for description, and in the application process, the model information of the first model can include multiple items of information of the first model, and the process of determining whether to train the second model and the training strategy of the second model can be implemented in combination with the multiple items of information. For example, each item of information is assigned a priority or weight, the training strategy of the second model is determined according to the priority of each item of model information, or the training strategy of the second model is determined according to each item of model information respectively, then the weight score corresponding to each training strategy is determined by weighted summation according to the weight of each item of information, and the training strategy with the highest weight score is taken as the training strategy of the second model, which is not limited.

[0241] As a possible implementation manner, when the first information includes model information of at least one first model, the first communication device determining the training strategy of the second model according to the first information can include the following four implementation manners:

[0242] Manner one, when the first information includes the generalization range of the first model, the first communication device can determine the target generalization range of the second model according to the first information.

[0243] The first communication device determining the target generalization range of the second model according to the first information includes the following four possible manners:

[0244] Manner 1, the first information includes the generalization range of the first model, and the first communication device determines the target generalization range of the second model according to the statistical result of the generalization range of the at least one first model.

[0245] For example, the first communication device can obtain, according to the first information, a proportion (denoted as B1) of the first model whose applicable network configuration is the first network configuration and / or a proportion (denoted as B2) of the first model whose applicable network configuration is the second network configuration. When B1 is greater than a first preset value or B2 is less than or equal to the first preset value, the first network configuration is taken as the target network configuration applicable to the second model; when B2 is greater than the first preset value or B1 is less than or equal to the first preset value, the second network configuration is taken as the target network configuration applicable to the second model. The first preset value is defined in advance by a protocol or agreed in advance by the first communication device and the second communication device.

[0246] In the first network configuration, each network configuration parameter has one value, and in the second network configuration, at least part of the network configuration parameters has multiple values. That is, the first network configuration is a network configuration containing only a specific network side resource configuration mode, and the second network configuration is a network configuration containing multiple different network side resource configuration modes. The model whose applicable network configuration is the first network configuration can also be referred to as a scenario model, and the model whose applicable network configuration is the second network configuration can also be referred to as a generalization model.

[0247] That is, in the case that the model type of most of the first models in the at least one first model is a generalization model, the first communication device can train the second model into a generalization model through model training; in the case that the model type of most of the first models in the at least one first model is a scenario model, the first communication device can train the second model into a scenario model through model training.

[0248] In mode 2, the first information includes generalization range information of the first model and performance index information of the first model, and the first communication device can determine the target generalization range of the second model according to the proportion of the first model meeting the first target performance index in the first model applicable to different network configurations.

[0249] For example, the first communication device can acquire, according to the first information, a proportion (denoted as B3) of the first model in which the applicable network configuration is the first network configuration and the performance index meets the first target performance index, and / or a proportion (denoted as B4) of the first model in which the applicable network configuration is the second network configuration and the performance index meets the first target performance index. In a case where B3 is greater than a second preset value or B4 is less than or equal to the second preset value, the first network configuration is taken as the target network configuration applicable to the second model; in a case where B4 is greater than the second preset value or B3 is less than or equal to the second preset value, the second network configuration is taken as the target network configuration applicable to the second model. The meanings of the first network configuration and the second network configuration can refer to the related descriptions in the foregoing embodiments, and will not be described herein again. The second preset value can be predefined by a protocol or can be agreed upon in advance by the first communication device and the second communication device.

[0250] Alternatively, in a case where most of the scenario-based models in the at least one first model can meet the first performance index, the first communication device can train the second model into a scenario-based model through model training; in a case where most of the generalized models in the at least one first model can meet the first performance index, the first communication device can train the second model into a generalized model through model training. The specific modification manner of the second model can refer to the related descriptions in the foregoing embodiments, and will not be described herein again.

[0251] Option 3: The first information includes a generalization range of the first model, and the first communication device determines a target generalization range of the second model according to a statistical result of each generalization range.

[0252] For example, the first communication device can acquire, according to the first information, a proportion of the first model applicable to the third network configuration in the at least one first model, and then the first communication device can directly take one or more third network configurations corresponding to the maximum proportion of the first model as the target network configuration applicable to the second model. The third network configuration is any one of the at least one network configuration applicable to the at least one first model.

[0253] That is, the first communication device can statistically acquire a probability of each network configuration in the plurality of network configurations applicable to the at least one first model, and take one or more network configurations with the maximum probability as the target network configuration applicable to the second model.

[0254] Option 4: The first information includes a generalization range of the first model and a performance index of the first model, and the first communication device determines a target generalization range of the second model according to a proportion of the first model in which the first model corresponding to different generalization ranges can meet the first target performance index.

[0255] Exemplarily, the first communication device can acquire, according to the first information, the first model applicable to the third network configuration from the at least one first model, and then determine, for each third network configuration, a proportion of the first model whose performance index meets the first target performance index in the first model applicable to the third network configuration, and / or a proportion of the first model whose performance index does not meet the first target performance index and is applicable to the third network configuration. The third network configuration with the largest proportion of the first model whose performance index meets the first target performance index is taken as the target network configuration to which the second model is applicable, or the third network configuration with the smallest proportion of the first model whose performance index does not meet the first target performance index is taken as the target network configuration to which the second model is applicable.

[0256] That is, the first communication device can count, for each network configuration, a probability that the first model corresponding to the network configuration meets the first target performance index and / or a probability that the first model corresponding to the network configuration does not meet the first target performance index, from the plurality of network configurations to which the at least one first model is applicable, and take the network configuration with the largest probability that the first model meets the first target performance index as the target network configuration to which the second model is applicable, or take the network configuration with the smallest probability that the first model does not meet the first target performance index as the target network configuration to which the second model is applicable.

[0257] Mode two, when the first information includes the model complexity of the first model, the first communication device can determine, according to the first information, the target model complexity of the second model.

[0258] The first communication device can determine, according to the first information, the target model complexity of the second model in the following two possible implementation manners:

[0259] Mode one, the first information includes the model complexity of the first model, and the first communication device determines, according to the statistical result of the model complexity of each first model, the target model complexity of the second model.

[0260] Exemplarily, the first communication device can acquire, according to the first information, a plurality of model complexities corresponding to the at least one first model, and determine a proportion of a first complexity in the model complexities corresponding to the at least one first model, where the first complexity is any one of the model complexities corresponding to the at least one first model. That is, the first communication device can acquire the proportion of the first model corresponding to each model complexity (which can also be understood as the probability that each model complexity appears in the plurality of model complexities corresponding to the at least one first model). Then the first communication device can take the model complexity with the highest proportion of the corresponding first model as the target model complexity of the second model.

[0261] Or, in the case that the model complexity of the majority of the at least one first model is greater than or equal to P, the first communication device can take P as the target model complexity of the second model.

[0262] In the case that the first information includes the model complexity of the first model and the performance indicator of the first model, the first communication device can determine the target model complexity of the second model according to the model complexity of the first model that meets the first target performance indicator.

[0263] For example, the first communication device can obtain, according to the first information, the model complexity corresponding to each first model that meets the first performance indicator in the at least one first model and the proportion of the first complexity in the model complexity corresponding to the at least one first model, and then the first communication device can take the model complexity corresponding to the first model with the highest proportion as the target model complexity of the second model.

[0264] Or, in the case that the model complexity of the majority of the at least one first model that meets the first performance indicator is greater than or equal to P, the first communication device can take P as the target model complexity of the second model.

[0265] In the case that the first information includes the performance indicator of the first model, the first communication device can determine the target performance indicator of the second model according to the first information.

[0266] For example, in the case that the performance indicator of the first model includes the target performance indicator of the first model, the first communication device can count the target performance indicators corresponding to the at least one first model and the proportion of each target performance indicator in the target performance indicators corresponding to the at least one first model (which can also be understood as the probability of any target performance indicator corresponding to the first model), and then take the target performance indicator corresponding to the first model with the highest proportion as the target performance indicator of the second model.

[0267] For another example, in the case that the performance indicator of the first model includes the current performance indicator and the target performance indicator of the first model, the first communication device can count the target performance indicators corresponding to one or more first models that can meet the first target performance indicator included in the at least one first model and the proportion of each target performance indicator in the target performance indicators corresponding to the at least one first model (which can also be understood as the probability of any target performance indicator corresponding to the first model), and then take the target performance indicator corresponding to the first model that meets the first target performance indicator with the highest proportion as the target performance indicator of the second model.

[0268] In the case that the first information includes the first data set size of the first model, the first communication device can determine the data set size of the second model according to the first information.

[0269] The first communication device determines the size of the data set used in training the second model according to the first information (also referred to as a target size) in two possible ways as follows:

[0270] In way 1, the first information includes the size of the first data set of the first model, and the first communication device determines the target size of the data set used in training the second model according to the size of the first data set used by most of the first models.

[0271] For example, the first communication device can obtain the sizes of the first data sets corresponding to the at least one first model according to the first information, and obtain the proportion of the first size in the sizes of the first data sets corresponding to the at least one first model (also understood as the probability of occurrence of the first size in the sizes of the first data sets corresponding to the at least one first model), where the first size is the size of any first data set in the sizes of the first data sets corresponding to the at least one first model. Then the first communication device can determine the target size of the data set used in training the second model according to the first data set size with the highest proportion (denoted as M1). For example, K times of M1 is taken as the target size of the data set used in training the second model by the first communication device, where K is greater than 0, such as 0.25, 0.5, 0.75, 1.5 or 2, etc.

[0272] Optionally, the first communication device can also count the proportion of the first models corresponding to the first data set whose size is not lower than the size of each first data set (denoted as B3), and / or the proportion of the first models corresponding to the first data set whose size is lower than the size of each first data set (denoted as B4), and take B3 or B4 as the proportion corresponding to each first data set size. Then the maximum first data set size in the at least one first data set size corresponding to B5 greater than or equal to a third preset value is taken as the target size of the data set used in training the second model by the first communication device, or the minimum first data set size in the at least one first data set size corresponding to B6 less than the third preset value is taken as the target size of the data set used in training the second model by the first communication device.

[0273] Alternatively, in the case that most of the at least one first model trains or modifies the size of the data set used by the first model, the first communication device can take K times of N as the target size of the data set used in modifying or training the second model.

[0274] In a second mode, the first information includes a size of a first data set of the first model and a performance indicator of the first model, and the first communication device determines the target size of the data set used to train the second model according to the size of the first data set used by the first model that meets the first target performance indicator.

[0275] For example, the first communication device can obtain, according to the first information, the size of the first data set corresponding to each first model and the performance indicator, and the size of each first data set corresponding to the first model that meets the first target performance indicator and the proportion of the size of each first data set in the at least one first model. Then, the first communication device can determine the target size of the data set used in the process of training the second model according to the size of the first data set corresponding to the first model that meets the first performance indicator and having the highest proportion (denoted as M2). For example, K times of M2 is used as the target size of the data set used in the process of training or changing the second model, and K is greater than 0.

[0276] Similarly, the first communication device can also use the proportion of the first model corresponding to the first data set that meets the first performance indicator and having a size not lower than the size of each first data set, and / or the proportion of the first model corresponding to the first data set that meets the first performance indicator and having a size lower than the size of each first data set, as the proportion corresponding to the size of each first data set, and determine the target size of the data set used to change or train the second model according to the relationship between the proportion corresponding to the size of each first data set and a given preset value. The manner of determining the target size in the embodiments of the present application can refer to the related description in the foregoing embodiments, and the difference is that the first models participating in the statistics are changed from the at least one first model to the first models that can meet the first target performance indicator in the at least one first model. The specific determination manner is not described herein.

[0277] Based on the above scheme, when the first information includes the model information of the at least one first model, the first communication device can obtain the proportion of the first models that meet one or more specified conditions (such as meeting the first target performance indicator and / or being applicable to the first network configuration) in the at least one first model by statistical analysis of the model information of each first model, thereby effectively assisting the first communication device to determine whether to train the second model and to determine the training strategy of the second model, and improving the training efficiency of the second model.

[0278] In a possible implementation, the statistical information corresponding to the model information of the at least one first model indicates at least one of the following: a proportion of the first models in the at least one first model that meet the first target performance indicator, a proportion of the first models in the at least one first model that do not meet the first target performance indicator, a proportion of the first models in the at least one first model that are applicable to the first network configuration, a proportion of the first models in the at least one first model that are applicable to the second network configuration, a proportion of the first models in the at least one first model that meet the first target performance indicator and are applicable to the first network configuration, a proportion of the first models in the at least one first model that meet the first target performance indicator and are applicable to the second network configuration, a proportion of the first models in the at least one first model that are applicable to the third network configuration, a proportion of the first models in the at least one first model that are applicable to the third network configuration and meet the first target performance indicator, a proportion of the first models in the at least one first model that are in an activated state, a proportion of the first complexity in the model complexity corresponding to the at least one first model, or a proportion of the first size in the size of the first data set corresponding to the at least one first model.

[0279] The first network configuration includes a value for each network configuration parameter, the second network configuration includes multiple values for at least some network configuration parameters, the third network configuration is any of the at least one network configuration, the first complexity is any of the model complexity corresponding to the at least one first model, and the first size is the size of any of the first data set corresponding to the at least one first model. The meanings of the first data set, the first network configuration, the second network configuration, the first size, the first complexity, and the statistical information corresponding to the model information of the at least one first model can be referred to the related descriptions in the foregoing embodiments, and will not be described herein.

[0280] When the first information includes the statistical information corresponding to the model information of the at least one first model, the first communication device can directly obtain one or more model information statistical results of the at least one first model according to the statistical information included in the first information, and directly determine whether to train the second model and / or the training strategy of the second model, such as the target generalization range of the second model, the target model complexity of the second model, and the like, according to the statistical information corresponding to the model information of the at least one first model included in the first information.

[0281] In an implementation, the first communication device determines whether to train the second model and the implementation of the training strategy of the second model according to statistical information corresponding to the model information of the at least one first model. The implementation is similar to the implementation in the foregoing embodiments, except that the first communication device can directly obtain the statistical analysis result of the model information without additional data statistics and analysis in the process of determining whether to train the second model and the implementation of the training strategy of the second model according to the statistical information corresponding to the model information of the at least one first model. For details, refer to the related description in the foregoing embodiments, which will not be described here again.

[0282] In addition, for ease of understanding, the foregoing solution is described by taking, as an example, that the statistical information corresponding to the model information of the at least one first model is generated according to one or two of the model information, i.e., the model complexity of the first model, the performance indicator of the first model, the generalization range of the first model, the size of the first data set corresponding to the first model, and the state of the first model as the statistical condition.

[0283] In application, the statistical information can also be determined according to other at least two of the foregoing model information. For example, the statistical information corresponding to the model information of the at least one first model can also include: the proportion of the first model in the at least one first model that has a performance indicator satisfying a first target performance indicator and is in an activated state, the proportion of the first model in the at least one first model that has a performance indicator satisfying the first target performance indicator, is applicable to a first network configuration, and has a first complexity, the proportion of the first model in the at least one first model that has a performance indicator satisfying the first target performance indicator, is applicable to the first network configuration, and has the first complexity, the proportion of the first model in the at least one first model that is in the activated state and is applicable to the first network configuration, or the proportion of the first model in the at least one first model that is in the activated state and is applicable to a second network configuration. Other possible ways of generating the statistical information corresponding to the model information of the at least one first model according to the statistical result of at least two model information will not be listed here.

[0284] In a possible implementation, the statistical information corresponding to the at least one network configuration parameter includes proportion information of the first network configuration parameter, and the proportion information includes a time proportion corresponding to a first value. The first network configuration parameter is any network configuration parameter in the at least one network configuration parameter, and the first value is any possible value of the first network configuration parameter.

[0285] For example, the time proportion corresponding to the first value can be understood as a ratio between a time length during which the first network configuration parameter is set to the first value in any time interval and a total time length of the time interval. That is, the statistical information corresponding to the at least one network configuration parameter can be understood as a probability of any possible value of any network configuration parameter, or can also be understood as a time proportion of any network configuration parameter being set to any possible value.

[0286] Optionally, the proportion information can explicitly indicate a ratio between a time length during which the first network configuration parameter is set to the first value in a time interval and a total time length of the time interval, for example, 50%, 75%, or 20%, etc. The proportion information can also implicitly indicate a relationship between a time length during which the first network configuration parameter is set to the first value in a time interval and a total time length of the time interval.

[0287] For example, the proportion information can be used to indicate a high or low probability of the first value appearing in any time interval, or can be used to indicate a high or low time proportion of the first value in any time interval. For example, taking a case where the proportion information is implemented by 1 bit as an example, in a case where a bit corresponding to the proportion information of the first value in the first time interval is set to 0, the proportion information indicates that the time proportion of the first value in the first time interval is high, or the probability of the first network configuration parameter being set to the first value in the first time interval is high. In a case where a bit corresponding to the proportion information of the first value in the first time interval is set to 1, the proportion information indicates that the time proportion of the first value in the first time interval is low, or the probability of the first network configuration parameter being set to the first value in the first time interval is low. Alternatively, in a case where a bit corresponding to the proportion information of the first value in the first time interval is set to 0, the proportion information indicates that the time proportion of the first value in the first time interval is low, or the probability of the first network configuration parameter being set to the first value in the first time interval is low. In a case where a bit corresponding to the proportion information of the first value in the first time interval is set to 1, the proportion information indicates that the time proportion of the first value in the first time interval is high, or the probability of the first network configuration parameter being set to the first value in the first time interval is high.

[0288] As a possible implementation, the time proportion corresponding to the first value is used to indicate a time proportion of the first network configuration parameter being set to the first value in at least one time period.

[0289] For example, the time proportion corresponding to the first value can indicate a time proportion or probability of the first network configuration parameter being set to any value in a time period 1, and a time proportion or probability of the first network configuration parameter being set to any value in a time period 2.

[0290] Optionally, in the at least one time period indicated by the time proportion of the first value, there can be no intersection between any two time periods, or any two adjacent time periods or at least part of the adjacent time periods in the at least one time period are continuous time periods.

[0291] For example, the at least one time period includes time period 1 and time period 2, time period 1 is 0 to 12, and time period 2 is 12 to 24. For another example, the at least one time period includes time period 1 to time period 3, time period 1 is 0 to 8, time period 2 is 10 to 12, and time period 3 is 12 to 22.

[0292] In addition, the time period included in the at least one time period can be at least one future time period, at least one current time period, or at least one past time period. In the case of at least one future time period, the time proportion of the first value can be inferred from historical data.

[0293] In a possible implementation, the statistical information corresponding to the at least one network configuration parameter includes proportion information of the first network configuration parameter, and the proportion information includes a frequency proportion corresponding to the first value. The first network configuration parameter is any network configuration parameter in the at least one network configuration parameter, and the first value is any possible value of the first network configuration parameter.

[0294] For example, the frequency proportion corresponding to the first value can be understood as the ratio between the number of times that the first network configuration parameter is set to the first value in a time interval and the total number of times that the first network configuration parameter is configured in the time interval. That is, the statistical information corresponding to the at least one network configuration parameter can be understood as the frequency of any possible value of any network configuration parameter.

[0295] Optionally, the proportion information can explicitly indicate the ratio between the number of times that the first network configuration parameter is set to the first value in a time interval and the total number of times that the first network configuration parameter is configured in the time interval, for example, 1 / 5, 2 / 5, or 5 / 12, etc. The proportion information can also implicitly indicate the relationship between the number of times that the first network configuration parameter is set to the first value in a time interval and the total number of times that the first network configuration parameter is configured in the time interval.

[0296] For example, taking the case of the proportion information being implemented by 1 bit, in the case that the bit of the proportion information corresponding to the first value in the first time interval is set to 0, the proportion information indicates that the number of times of being set to the first value in the first time interval is more; in the case that the bit of the proportion information corresponding to the first value in the first time interval is set to 1, the proportion information indicates that the number of times of being set to the first value in the first time interval is less. Or, in the case that the bit of the proportion information corresponding to the first value in the first time interval is set to 0, the proportion information indicates that the number of times of being set to the first value in the first time interval is less; in the case that the bit of the proportion information corresponding to the first value in the first time interval is set to 1, the proportion information indicates that the number of times of being set to the first value in the first time interval is more.

[0297] As a possible implementation, in the case that the first information comprises the statistical information corresponding to the at least one network configuration parameter, the first communication apparatus can determine whether to train the second model according to the proportion information of each network configuration parameter.

[0298] The first communication apparatus can determine whether to train the second model according to the proportion information of each network configuration parameter can include the following two possible manners:

[0299] Manner one, the first communication apparatus determines whether to train the second model according to the proportion information of each network configuration parameter.

[0300] For example, in the case that the first communication apparatus determines whether to train the second model applicable to the current network configuration, the first communication apparatus can determine, according to the statistical information corresponding to the at least one network configuration parameter, the proportion (denoted as C1) of the network configuration parameters with the probability greater than the first probability and / or the proportion (denoted as C2) of the network configuration parameters with the probability not greater than the first probability among the network configuration parameters contained in the current network configuration. In the case that C1 is greater than or equal to a first given value or C2 is less than the first given value, it is determined that the probability of the current network configuration appearing is large, and the second model is trained; in the case that C2 is greater than or equal to the first given value or C1 is less than the first given value, it is determined that the probability of the current network configuration appearing is small, and the second model is not trained. The first given value and the first probability can be predefined by a protocol, or can be previously agreed by the second communication apparatus and the first communication apparatus.

[0301] That is, the first communication apparatus can determine whether to train the second model according to whether the probability of each network configuration parameter in the network configuration applicable to the second model is greater than the first probability, so as to avoid training the second model with a low probability.

[0302] As a possible implementation, the first given value is 1. That is, the second model is trained in the case that the occurrence probability of each network configuration parameter contained in the current network configuration is greater than the first probability, and the second model is not trained in the case that there is a network configuration parameter in the network configuration parameters contained in the current network configuration whose occurrence probability is less than the first probability.

[0303] Optionally, in the case that the first given value is 1, the occurrence probability of each network configuration parameter in the current network configuration can be directly indicated by the occurrence probability or the time proportion of the current network configuration.

[0304] For example, the first communication device determines whether to train the second model applicable to the current network configuration of the camped cell, the camped cell includes network configuration 1 and network configuration 2, the statistical information corresponding to the at least one network configuration parameter includes the time proportion corresponding to network configuration 1 and the time proportion corresponding to network configuration 2, and the first probability is 50%. In the first information, the associated ID1 corresponding to network configuration 1 is implicitly indicated as having a time proportion of 30%, and the associated ID2 corresponding to network configuration 2 is implicitly indicated as having a time proportion of 70%. In the case that the current network configuration is network configuration 1, the occurrence probability of each network configuration parameter in the current network configuration is less than 50%, and the second model is not trained. In the case that the current network configuration is network configuration 2, the occurrence probability of each network configuration parameter in the current network configuration is greater than 50%, and the second model is trained.

[0305] For another example, the first communication device determines whether to train the second model applicable to the current network configuration of the camped cell, the statistical information corresponding to the at least one network configuration parameter includes the time proportion corresponding to the current network configuration of the camped cell, and the first probability is 50%. In the case that the associated ID corresponding to the current network configuration of the camped cell is implicitly indicated as having a time proportion greater than 50% in the first information, such as the associated ID corresponding to the current network configuration of the camped cell being indicated as having a time proportion of 60%, the occurrence probability of each network configuration parameter in the current network configuration is greater than 50%, and the second model is trained. In the case that the associated ID corresponding to the current network configuration of the camped cell is indicated as having a time proportion not greater than 50%, such as the associated ID corresponding to the current network configuration of the camped cell being indicated as having a time proportion of 10%, the occurrence probability of each network configuration parameter in the current network configuration is less than 50%, and the second model is not trained.

[0306] Optionally, the time proportion or occurrence probability corresponding to the associated ID1 can be understood as the number of occurrences of the associated ID1 / (the number of occurrences of the associated ID1+the number of occurrences of the associated ID2), or can also be understood as the time of occurrence of the associated ID1 / (the time of occurrence of the associated ID1+the time of occurrence of the associated ID2). Similarly, the meaning of the time proportion or occurrence probability corresponding to the associated ID2 can refer to the meaning of the time proportion or occurrence probability corresponding to the associated ID1.

[0307] In the second mode, the first communication device determines whether to train the second model according to the time proportion of the first value of each network configuration parameter in at least one time period.

[0308] For example, when the first communication device determines whether to train the second model applicable to the current network configuration, it can first determine the possible use time of the second model, i.e., the time period (denoted as time period T) that the first communication device stays in the current cell. When the statistical information corresponding to at least one network configuration parameter includes the time proportion of the network configuration parameter in different time periods, the first communication device can determine the time proportion or occurrence probability of each network configuration parameter contained in the current network configuration in the time period T according to the statistical information corresponding to at least one network configuration parameter, and determine whether to train the second model according to the time proportion or occurrence probability of each network configuration parameter in the time period T.

[0309] The mode of determining whether to train the second model according to the time proportion or occurrence probability of each network configuration parameter in the time period T is similar to the mode of determining whether to train the second model according to the occurrence probability of each network configuration parameter in the foregoing embodiments, and the related description in the foregoing embodiments can be referred to and will not be repeated here.

[0310] That is, the first communication device can determine whether to train the second model in combination with the time period that it may stay in the current cell, and the time proportion or occurrence probability of the current network configuration or the current value of each network configuration parameter in the current network configuration in the time period that the first communication device stays in the current cell, thereby reducing the probability of training the second model with low use probability.

[0311] Based on this scheme, the first communication device can determine the probability of training the second model applicable to the current network configuration to obtain a benefit (which can also be referred to as the probability of activating the second model to implement the communication function) according to the received first information, thereby determining whether to train the second model, and avoiding the waste of resources caused by training the second model with low or no benefit.

[0312] As a possible implementation, in a case where the first information comprises statistical information corresponding to the at least one network configuration parameter, the first communication apparatus can determine a target data set for training the second model according to the proportion information of each network configuration parameter.

[0313] For example, in a case where the first communication apparatus determines whether to train the second model applicable to the current cell, the first communication apparatus can first determine a possible use time of the second model, i.e., a time period (denoted as time period T) during which the first communication apparatus camps on the current cell. In a case where the statistical information corresponding to the at least one network configuration parameter comprises time proportions of multiple network configurations in different time periods, the first communication apparatus can determine, according to the statistical information corresponding to the at least one network configuration parameter, time proportions or occurrence probabilities of different network configurations of the current cell in the time period T, take a network configuration with a larger time proportion or occurrence probability as a target network configuration to which the second model is applicable, collect training data under the network configuration to determine a target data set for training the second model, and train the second model applicable to the network configuration according to the target data set.

[0314] That is, in the process of training the second model, the first communication apparatus can determine, according to the statistical information corresponding to the at least one network configuration parameter, time proportions of one kind of network configuration parameter in one or more time periods and / or time proportions of one kind of network configuration in one or more time periods, and then determine types or sources of training data included in a target data set for training the second model in combination with a possible use time of the second model.

[0315] Based on the scheme, it is possible to effectively reduce acquisition of a large amount of invalid data by the first communication apparatus in the process of training the second model, reduce resource consumption in the process of training the second model, and improve training efficiency and training effect of the second model.

[0316] In a possible implementation, the first information comprises first indication information and / or second indication information, the first indication information is used to indicate whether to train the second model, and the second indication information is used to indicate a training strategy of the second model (which can also be understood as a target value of at least one item of model information of the second model).

[0317] For example, the first indication information can be implemented by a predefined bit, in a case where the bit is set to 1, it is indicated that the second model is trained, and in a case where the bit is set to 0, it is indicated that the second model is not trained. Alternatively, in a case where the bit is set to 1, it is indicated that the second model is not trained, and in a case where the bit is set to 0, it is indicated that the second model is trained.

[0318] Exemplarily, the second indication information can be implemented by a bitmap containing a plurality of bit sequences, or can also be implemented by an information block containing a plurality of information elements, each bit sequence or information element being used to indicate a target value of a piece of model information, for example, a generalization range of training the second model, a target performance index of the second model, a model complexity of the second model, or a size of a data set for training the second model, etc.

[0319] Optionally, the first information can include one or more of the first indication information, the second indication information, the model information of the at least one first model, or statistical information corresponding to the model information of the at least one first model, without limitation.

[0320] In a possible implementation, before step S402, the first communication device can further send second information to the second communication device. Correspondingly, the second communication device receives the second information from the second communication device. The second information is used to request the first information.

[0321] That is, the first communication device can send the second information used to request the first information to the first communication device before training the second model, and then the second communication device triggers the second communication device to send the first information to the first communication device after receiving the second information of the first communication device.

[0322] Optionally, after receiving the second information from the first communication device, the second communication device performs step S401, including the following two possible implementation manners:

[0323] Manner 1: The second communication device requests the model information of the at least one first model from at least one third communication device, and generates the first information according to the received model information.

[0324] Manner 2: The second communication device determines the model information of the at least one first model from the model information of a plurality of communication devices stored in advance, and generates the first information according to the model information of the at least one first model.

[0325] In addition, the above embodiment is that the first information is generated by the second communication device performing statistical analysis on the model information of a plurality of third communication devices in communication connection with the second communication device. In the application process, the manner of the second communication device to determine the first information can also be that the second communication device receives the first information from a core network device, and sends the first information from the core network device to the first communication device.

[0326] That is, the model information of the first communication device and the model information of the third communication device can be reported by the second communication device or directly reported to the core network device. In the case that the first communication device requests the first information, the second communication device can send the request information of the first information to the core network device, and then the core network device generates the first information by statistical analysis on the maintained model information according to the request information of the second communication device, and sends the first information to the first communication device through the second communication device. This is conducive to reducing the storage space and computing power consumption of the second communication device in determining the first information.

[0327] In a possible implementation, the first communication device sends the model information of the second model to the second communication device. Correspondingly, the second communication device receives the model information of the second model from the second communication device.

[0328] That is, the first communication device can report the model information of the second model trained by the first communication device to the second communication device in communication connection with the first communication device, and the second communication device can store the model information of the second model after receiving the model information reported by the first communication device.

[0329] As a possible implementation, in the case that the fourth communication device requests the first information, the first information requested by the fourth communication device can be generated according to the model information of the second model. That is, the model information of the second model reported by the first communication device can be used as the model information of a first model in generating the first information requested by other communication devices, and the model information of the first model contained in the first information received by the first communication device can also be the model information reported by the third communication device in communication connection with the second communication device.

[0330] In a possible implementation, the second communication device broadcasts the first information in the case that a preset condition is met.

[0331] As a first possible implementation, referring to (a) in FIG. 5, the second communication device determines the current first information and broadcasts it periodically according to a preset period interval after completing the broadcast of the first information once. That is, the second communication device can periodically determine the current first information and broadcast it according to the preset period interval.

[0332] As a second possible implementation, referring to (b) in FIG. 5, the second communication device can dynamically maintain the model information from multiple communication devices, and monitor the model information of the communication devices (the third communication device and the first communication device) in communication connection with the second communication device, the statistical information corresponding to the model information, and the statistical information of the at least one network configuration parameter, and determine whether the model information, the statistical information corresponding to the model information, and the statistical information of the at least one network configuration parameter are changed. In the case where any of the above three is changed, the first information is broadcasted.

[0333] As a third possible implementation, referring to (c) in FIG. 5, the second communication device sends the first information to the second communication device or broadcasts the first information in the case where it is detected that the first communication device requests the training data under any network configuration (for example, network configuration 1). That is, the second communication device triggers the broadcast of the first information according to the training data request of any communication device in communication connection therewith.

[0334] In addition, in the case where the time proportion or occurrence probability corresponding to the network configuration 1 is low, the second communication device can also send the first indication to the first communication device, the first indication being used to reject the training data collection of the first communication device for the network configuration 1, and indicating the reason for rejecting the training data collection. The first indication can be sent through the same message as the first information, or can be sent through a different message from the first information.

[0335] Optionally, the performance index of the model of the communication device in communication connection with the second communication device can be obtained by monitoring the performance of the communication device, or can be obtained by receiving the performance index from the communication device, that is, the performance index of the model maintained by any communication device can be monitored by the second communication device, or can be monitored by the communication device and fed back to the second communication device.

[0336] In a possible implementation, referring to (a) in FIG. 6, the first communication device sends the third information to the second communication device, and receives the fourth information from the second communication device. Correspondingly, the second communication receives the third information, and sends the fourth information to the first communication device.

[0337] The third information is used to request the training data under the target network configuration and the generalization range of the second model.

[0338] As a possible implementation, the fourth information is the training data under the target network configuration.

[0339] Exemplarily, in a case that the performance indicators of the majority of the first models with the same generalization range as the second model are higher than the first target performance indicator in the at least one first model, or in a case that the majority of the first models with the applicable network configuration including the target network configuration are in the active state in the at least one first model, the fourth information is the training data under the target network configuration.

[0340] That is, the second communication device verifies the second model training strategy of the first communication device according to the statistical information of the maintained model information or the statistical information of the network configuration parameters, and sends the training data under the target network configuration to the first communication device in a case that the second model training strategy of the first communication device is appropriate, so as to further reduce the probability of meaningless model training of the first communication device.

[0341] As another possible implementation, the fourth information includes a first indication and first information. The meaning of the first indication can refer to the related description in the foregoing embodiments, and will not be described herein again.

[0342] Exemplarily, in a case that the performance indicators of the majority of the first models with the same generalization range as the second model are lower than the first target performance indicator in the at least one first model, or in a case that the majority of the first models with the applicable network configuration including the target network configuration are in the inactive state in the at least one first model, the fourth information includes the first indication and the first information.

[0343] That is, the second communication device verifies the second model training strategy of the first communication device according to the statistical information of the maintained model information or the statistical information of the network configuration parameters, and sends the training data under the target network configuration to the first communication device in a case that the second model training strategy of the first communication device is appropriate, so as to further reduce the probability of meaningless model training of the first communication device.

[0344] In a possible implementation, the first communication device sends fifth information to the second communication device. Correspondingly, the second communication device receives the fifth information from the second communication device.

[0345] The fifth information is used to indicate the current model training / maintenance capability of the first communication device. Exemplarily, the fifth information can include at least one of the following: the current computing power level of the first communication device, the remaining storage space of the first communication device, or the remaining power of the first communication device.

[0346] Optionally, in a case where the second communication device determines, according to the fifth information, that the capability of the first communication device is not limited, the second communication device sends, to the first communication device, at least one of the following: model information of the at least one first model, statistical information corresponding to the model information of the at least one first model, or statistical information corresponding to the at least one network configuration parameter; in a case where the second communication device determines, according to the fifth information, that the capability of the first communication device is limited, the second communication device sends, to the first communication device, the first indication information and / or the second indication information. The meanings of the first indication information and the second indication information can be referred to the related descriptions in the foregoing embodiments, and will not be described herein.

[0347] For example, taking the first communication device as a terminal, the second communication device as a base station, and the second model as a model applicable to a current cell as an example, and taking the fifth information indicating that the number of models capable of being trained by the terminal as 1 as an example. The network configuration of the current cell in which the terminal resides includes two network configurations corresponding to associated ID1 and associated ID2. After receiving the fifth information from the terminal, the base station determines the time proportion of associated ID1 and the time proportion of associated ID2, and instructs the terminal to train a second model applicable to a network configuration with a larger time proportion of the corresponding associated ID.

[0348] Alternatively, the base station determines the time proportion of associated ID1 and the time proportion of associated ID2 in time period 1, and the time proportion of associated ID1 and the time proportion of associated ID2 in time period 2, and in combination with the residence time in which the terminal can reside in the current cell, instructs the terminal to train a second model applicable to a network configuration with a larger time proportion of the corresponding associated ID in time period 1 in a case where the residence time in which the terminal can reside in the current cell is time period 1, and instructs the terminal to train a second model applicable to a network configuration with a larger time proportion of the corresponding associated ID in time period 1 in a case where the residence time in which the terminal can reside in the current cell is time period 2.

[0349] For example, the first communication device is a terminal, the second communication device is a base station, the second model is a model applicable to a current cell, and the fifth information indicates that the maximum model complexity maintained by the terminal is H. The network configuration of the current cell in which the terminal resides includes two network configurations corresponding to associated ID1 and associated ID2. After receiving the fifth information from the terminal, the base station determines the proportion of the first model applicable to the network configuration corresponding to associated ID1 and the proportion of the first model applicable to the network configuration corresponding to associated ID2 in the at least one first model applicable to the current cell and containing a model complexity less than or equal to H. In the case that the proportion of the first model applicable to the network configuration corresponding to associated ID2 is greater, the terminal is instructed to train a second model applicable to the network configuration corresponding to associated ID2. In the case that the proportion of the first model applicable to the network configuration corresponding to associated ID1 is greater, the terminal is instructed to train a second model applicable to the network configuration corresponding to associated ID1.

[0350] That is, in the case that the first communication device is limited in capability, the second communication device can directly display one or more of the following information to the first communication device through the first information: whether to train a second model, the collection method of the data set used in the training of the second model (such as the size of the data set, the network configuration associated with the training data included in the data set, etc.), the target generalization range of the second model, the target model complexity or the target model structure of the second model.

[0351] For example, the limitation in capability can be understood as that the current computing power of the first communication device is lower than a first value, the remaining storage space of the first communication device is less than a second value, or the remaining power of the first communication device is lower than a third value. The first value, the second value, and the third value can be predefined by a protocol or agreed upon by the first communication device and the second communication device in advance.

[0352] (b) of FIG. 6 is a service flow diagram of applying the communication method in the above embodiment, referring to (b) of FIG. 6, taking the first communication device as terminal 1, the third communication device as terminal 2, the second communication device as a base station, and the first information as model information of at least one first model as an example. After the random access is completed, the terminal 1 and the terminal 2 can receive a model information query request of the base station or a preset rule, and report model information of part or all models maintained by the terminal to the base station. The base station statistics model information of the models maintained by the terminals connected therewith. In the case that the terminal 1 prepares to train a second model applicable to the current network configuration of the base station, or in the case that the terminal 1 requests statistical information associated with the model applicable to the current network configuration, the base station statistics model information of the models of other terminals (such as the terminal 2) under the current network configuration, generates statistical information (first information) corresponding to model information of a plurality of models applicable to the same network configuration as the second model, and sends the first information to the terminal 1. After receiving the first information, the terminal 1 determines whether to train the second model and the training strategy of the second model according to the first information.

[0353] Based on the above scheme, in the process of determining whether to train the second model, the first communication device receives the first information from the second communication device, the first information includes at least one of model information of at least one first model having an associated relationship with the second model, statistical information corresponding to the model information of the at least one first model, and statistical information corresponding to at least one network configuration parameter, and then the first communication device determines whether to train the second model according to the first information. That is, the first communication device takes the model information of the first model having an associated relationship with the second model, the statistical information corresponding to the model information of the first model, or the statistical information of the network configuration parameter in the network configuration applicable to the first model as prior information, and determines whether to train the second model according to the prior information. In the process of determining whether to train the second model, a large amount of training data does not need to be collected and the data statistical characteristics of the training data do not need to be analyzed, which is beneficial to reduce the resource overhead required by the first communication device in the process of determining whether to train the second model, and improve the efficiency of the first communication device in managing the second model.

[0354] The above describes the method provided by the present application, in addition, the present application also provides a communication device for implementing the functions described in the above method embodiments.

[0355] It should be noted that the communication apparatus includes hardware structure and / or software module corresponding to each function in order to realize the above functions. Those skilled in the art can clearly understand the units and algorithm steps of each example described in combination with the embodiments disclosed in the present document. The present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is realized in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0356] The embodiments of the present application can divide the functional modules of the communication apparatus according to the above-mentioned method embodiments. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The integrated module can be realized in the form of hardware or software functional module. It should be noted that the division of modules in the embodiments of the present application is illustrative, and is only a logical functional division. There can be another division manner in actual implementation.

[0357] FIG. 7 shows a structural schematic diagram of a communication apparatus 70. The communication apparatus 70 includes a processing module 701 and a transceiver module 702. The communication apparatus 70 can be used to realize the functions of the first communication apparatus or the second communication apparatus.

[0358] In some embodiments, the communication apparatus 70 can further include a storage module (not shown in FIG. 7) for storing program instructions and data.

[0359] In some embodiments, the transceiver module 702, which can also be referred to as a transceiver unit, is used to realize the sending and / or receiving functions. The transceiver module 702 can be composed of a transceiver circuit, a transceiver, a transceiver, or a communication interface.

[0360] In some embodiments, the transceiver module 702 can include a receiving module and a sending module, which are respectively used to perform the receiving and sending steps of the first communication apparatus or the second communication apparatus in the above-mentioned method embodiments, and / or are used to support other processes of the technologies described herein; the processing module 701 can be used to perform the processing steps of the first communication apparatus or the second communication apparatus in the above-mentioned method embodiments, and / or are used to support other processes of the technologies described herein.

[0361] When the communication apparatus 70 is used to realize the functions of the first communication apparatus, in one possible implementation, the transceiver module 702 is configured to send second information to the second communication apparatus, the second information being used to request the first information.

[0362] In a possible implementation, the transceiver module 702 is further configured to send model information of the second model to the second communication apparatus.

[0363] In the case that the communication apparatus 70 is configured to implement the function of the second communication apparatus, in a possible implementation, the transceiver module 702 is configured to receive second information from the second communication apparatus, the second information being used to request the first information.

[0364] In a possible implementation, the transceiver module 702 is configured to receive model information of the second model from the second communication apparatus.

[0365] All the related contents of the steps involved in the method embodiments described above can be referred to the function description of the corresponding functional modules, and will not be repeated here.

[0366] In the present application, the communication apparatus 70 can be in the form of integrated division of various functional modules. The "module" here can refer to a specific application-specific integrated circuit (ASIC), a circuit, a processor and a memory executing one or more software or firmware programs, an integrated logic circuit, and / or other devices that can provide the above functions.

[0367] In some embodiments, when the communication apparatus 70 in FIG. 7 is a chip or a chip system, the function / implementation process of the transceiver module 702 can be implemented through the input / output interface (or communication interface) of the chip or chip system, and the function / implementation process of the processing module 701 can be implemented through the processor (or processing circuit) of the chip or chip system.

[0368] Since the communication apparatus 70 provided by the present embodiment can execute the above method, the technical effects that can be obtained thereby can be referred to the above method embodiments, and will not be repeated here.

[0369] As a possible product form, the first communication apparatus or the second communication apparatus described in the embodiments of the present application can be implemented using one or more field programmable gate arrays (FPGAs), programmable logic devices (PLDs), controllers, state machines, gate logic, discrete hardware components, any other suitable circuit, or any combination of circuits capable of performing the various functions described throughout the present application.

[0370] As another possible product form, the first communication device or the second communication device described in the embodiments of the present application can be implemented by a general bus architecture. For ease of illustration, refer to FIG. 8, which is a structural schematic diagram of a communication device 800 provided by the embodiments of the present application, the communication device 800 including a processor 801 and a transceiver 802. The communication device 800 can be a first communication device, or a chip or chip system therein; or the communication device 800 can be a second communication device, or a chip or module therein. FIG. 8 only shows the main components of the communication device 800. In addition to the processor 801 and the transceiver 802, the communication device can further include a memory 803, and an input and output device (not shown in the figure).

[0371] Optionally, the processor 801 is mainly used for processing communication protocols and communication data, and controlling the entire communication device, executing software programs, processing data of the software programs, so as to implement the methods provided in the method embodiments described above. The memory 803 is mainly used for storing software programs and data. The transceiver 802 can include a radio frequency circuit and an antenna, the radio frequency circuit being mainly used for conversion between a baseband signal and a radio frequency signal and processing the radio frequency signal. The antenna is mainly used for transceiving radio frequency signals in the form of electromagnetic waves. The input and output device, such as a touch screen, a display screen, a keyboard, etc., is mainly used for receiving data input by a user and outputting data to the user.

[0372] Optionally, the processor 801, the transceiver 802, and the memory 803 can be connected through a communication bus.

[0373] When the communication device is powered on, the processor 801 can read the software programs in the memory 803, interpret and execute instructions of the software programs, and process data of the software programs. When data needs to be transmitted wirelessly, the processor 801 performs baseband processing on the data to be transmitted, and outputs a baseband signal to the radio frequency circuit, the radio frequency circuit performs radio frequency processing on the baseband signal, and transmits the radio frequency signal in the form of electromagnetic waves through the antenna. When data is transmitted to the communication device, the radio frequency circuit receives the radio frequency signal through the antenna, converts the radio frequency signal into a baseband signal, and outputs the baseband signal to the processor 801, the processor 801 converts the baseband signal into data and processes the data.

[0374] In another implementation, the radio frequency circuit and the antenna can be arranged independently of the processor performing baseband processing, for example, in a distributed scenario, the radio frequency circuit and the antenna can be arranged remotely from the communication device.

[0375] In some embodiments, in a hardware implementation, those skilled in the art can conceive that the above-mentioned communication device 70 can adopt the form of the communication device 800 shown in FIG. 8.

[0376] As an example, the function / implementation process of the processing module 701 in FIG. 7 can be implemented by invoking the computer-executed instructions stored in the memory 803 by the processor 801 in the communication apparatus 800 shown in FIG. 8. The function / implementation process of the transceiver module 702 in FIG. 7 can be implemented by the transceiver 802 in the communication apparatus 800 shown in FIG. 8.

[0377] As yet another possible product form, the first communication apparatus or the second communication apparatus in the present application can adopt the constituent structure shown in FIG. 9, or include the components shown in FIG. 9. FIG. 9 is a constituent diagram of a communication apparatus 900 provided in the present application, which can be a chip or a system on chip in the first communication apparatus or the second communication apparatus; or can be a module or a chip or a system on chip in the second communication apparatus.

[0378] As shown in FIG. 9, the communication apparatus 900 includes at least one processor 901, and at least one communication interface (only one communication interface 904 is shown in FIG. 9 by way of example, and the processor 901 is taken as an example for description). Optionally, the communication apparatus 900 can further include a communication bus 902 and a memory 903.

[0379] The processor 901 can be a general central processing unit (CPU), a general processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a PLD, or any combination thereof. The processor 901 can also be other apparatuses with processing function, such as a circuit, a device, or a software module, without limitation.

[0380] The communication bus 902 is used to connect different components in the communication apparatus 900, so that different components can communicate. The communication bus 902 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in FIG. 9, but it does not mean that there is only one bus or only one type of bus.

[0381] The communication interface 904 is configured to communicate with other devices or communication networks. For example, the communication interface 904 can be a module, a circuit, a transceiver, or any device capable of realizing communication. Alternatively, the communication interface 904 can also be an input / output interface in the processor 901, configured to realize signal input and signal output of the processor.

[0382] The memory 903 can be a device with a storage function, configured to store instructions and / or data. The instructions can be a computer program.

[0383] For example, the memory 903 can be a read-only memory (ROM) or other type of static storage device that can store static information and / or instructions, or can be a random access memory (RAM) or other type of dynamic storage device that can store information and / or instructions, or can be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magneto-optical disk, a magnetic disk storage medium or other magnetic storage device, and the like, without limitation.

[0384] It should be noted that the memory 903 can exist independently of the processor 901, or can be integrated with the processor 901. The memory 903 can be located in the communication device 900, or can be located outside the communication device 900, without limitation. The processor 901 can be configured to execute instructions stored in the memory 903 to realize the method provided in the embodiments described below.

[0385] As an optional implementation manner, the communication device 900 can further include an output device 905 and an input device 906. The output device 905 communicates with the processor 901, and can display information in various ways. For example, the output device 905 can be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 906 communicates with the processor 901, and can receive user input in various ways. For example, the input device 906 can be a mouse, a keyboard, a touch screen device, a sensor device, etc.

[0386] In some embodiments, the communication apparatus 70 shown in FIG. 7 can take the form of the communication apparatus 900 shown in FIG. 9, which can be implemented in hardware.

[0387] As an example, the function / implementation process of the processing module 701 in FIG. 7 can be implemented by invoking the computer-executed instructions stored in the memory 903 by the processor 901 in the communication apparatus 900 shown in FIG. 9. The function / implementation process of the transceiver module 702 in FIG. 7 can be implemented by the communication interface 904 in the communication apparatus 900 shown in FIG. 9.

[0388] It should be noted that the structure shown in FIG. 9 does not constitute a specific limitation on the first communication apparatus or the second communication apparatus. For example, in some other embodiments of the present application, the first communication apparatus or the second communication apparatus can include more or fewer components than those shown, or combine certain components, or split certain components, or different arrangement of components. The components shown can be implemented in hardware, software, or a combination of software and hardware.

[0389] In some embodiments, the present application also provides a communication apparatus, which includes a processor for implementing the method in any of the above method embodiments.

[0390] As a possible implementation, the communication apparatus further includes a memory. The memory is used to save necessary computer programs and data. The computer programs can include instructions, and the processor can invoke the instructions in the computer programs stored in the memory to instruct the communication apparatus to perform the method in any of the above method embodiments. Of course, the memory can also not be in the communication apparatus.

[0391] As another possible implementation, the communication apparatus further includes an interface circuit, which is a code / data read-write interface circuit, and is used to receive computer-executed instructions (computer-executed instructions are stored in the memory, which can be directly read from the memory or can pass through other devices) and transmit them to the processor.

[0392] As yet another possible implementation, the communication apparatus further includes a communication interface, which is used to communicate with modules outside the communication apparatus.

[0393] It can be understood that the communication apparatus can be a chip or a chip system. When the communication apparatus is a chip system, it can be composed of a chip or can include a chip and other discrete devices, and the embodiments of the present application do not make a specific limitation thereon.

[0394] The present application also provides a computer-readable storage medium, which stores a computer program or instructions, and the computer program or instructions are executed by a computer to realize the functions of any of the above method embodiments.

[0395] The application further provides a computer program product, which, when executed by a computer, realizes the functions of any of the method embodiments described above.

[0396] Those skilled in the art can understand that, for the convenience and brevity of description, the specific working processes of the system, device and unit described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0397] It can be understood that the system, device and method described in the present application can also be implemented in other manners. For example, the described device embodiments are merely schematic, and the division of the units is merely a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0398] The units described as separated components can or can not be physically separated, and can be located in one place, or can be distributed on a plurality of network units. The components displayed as units can or can not be physical units. According to actual needs, some or all of the units can be selected to achieve the purposes of the embodiments of the present application.

[0399] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0400] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or include one or more data storage devices such as servers, data centers, etc. integrated with the medium. The available medium can be magnetic medium (such as floppy disk, hard disk, magnetic tape), optical medium (such as DVD), or semiconductor medium (such as solid state drive (SSD)) and the like. In the embodiments of the present application, the computer can include the device described above.

[0401] Although the present application is described herein in conjunction with various embodiments, it is understood that other variations of the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from an inspection of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude a plurality. A single processor or other unit can fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0402] Although the present application is described herein in conjunction with specific features and embodiments thereof, it is understood that modifications and combinations can be made thereto within the scope of the application. Accordingly, the description and drawings are to be regarded as illustrative in nature and are not to be regarded as limiting the scope of the application as defined in the appended claims. Obviously, many modifications and variations of this application are possible in light of its teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, this application can be practiced otherwise than as specifically described.

Claims

1. A communication method characterized by comprising: The method is applied to a first communication device, and the method comprises: receiving first information from a second communication device, the first information comprising at least one of the following: model information of at least one first model, statistical information corresponding to the model information of the at least one first model, or statistical information corresponding to at least one network configuration parameter, the at least one network configuration parameter being a network configuration parameter in a network configuration applicable to the at least one first model; determining, according to the first information, whether to train a second model, the first model and the second model having an association relationship.

2. The method of claim 1, wherein, The method further comprises determining, according to the first information, at least one of the following of the second model: a generalization range, a target performance indicator, a model complexity, or a size of a data set used for training the second model.

3. The method according to claim 1 or 2, characterized in that, The model information of the first model indicates at least one of the following: a generalization range of the first model; a state of the first model; a performance indicator of the first model; a size of a first data set used for training or changing the first model; a model complexity of the first model.

4. The method of claim 3, wherein, The generalization range comprises at least one cell applicable to the first model and / or at least one network configuration applicable to the first model.

5. The method according to claim 3 or 4, characterized in that, The state of the first model comprises at least one of the following: a support state, an available state, an applicable state, an active state, or a configuration state.

6. The method according to claim 4 or 5, characterized in that, The statistical information corresponding to the model information of the at least one first model indicates at least one of the following: a proportion of first models in the at least one first model that meet a first target performance indicator; a proportion of first models in the at least one first model that do not meet the first target performance indicator; a proportion of first models in the at least one first model that are applicable to a first network configuration; a proportion of first models in the at least one first model that are applicable to a second network configuration; a proportion of first models in the at least one first model that meet the first target performance indicator and are applicable to the first network configuration; a proportion of first models in the at least one first model that meet the first target performance indicator and are applicable to the second network configuration; a proportion of first models in the at least one first model that are applicable to a third network configuration; a proportion of first models in the at least one first model that are applicable to the third network configuration and meet the first target performance indicator; a proportion of first models in the at least one first model that are applicable to the third network configuration and do not meet the first target performance indicator; a proportion of first models in the at least one first model that are in an active state; a proportion of a first complexity in model complexities corresponding to the at least one first model, the first complexity being any one of the model complexities corresponding to the at least one first model; a proportion of a first size in sizes of first data sets corresponding to the at least one first model, the first size being a size of any one of the first data sets corresponding to the at least one first model; The first network configuration has one value for each network configuration parameter, and the second network configuration has multiple values for at least part of the network configuration parameters. The third network configuration is any network configuration in the at least one network configuration.

7. The method according to any one of claims 1 to 6, characterized in that, The statistical information corresponding to the at least one network configuration parameter includes proportion information of a first network configuration parameter, the first network configuration parameter being any network configuration parameter in the at least one network configuration parameter, and the proportion information including a time proportion corresponding to a first value, the first value being any possible value of the first network configuration parameter.

8. The method of claim 7, wherein, The time proportion corresponding to the first value is used to indicate a time proportion in which the first network configuration parameter is set to the first value in at least one time period.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: sending second information to the second communication device, the second information being used to request the first information.

10. The method according to any one of claims 1 to 9, characterized in that, The method further includes: sending model information of the second model to the second communication device.

11. The method according to any one of claims 1 to 10, characterized in that, The at least one first model is a model maintained by at least one third communication device, and a network configuration to which the first model is applicable includes a network configuration to which the second model is applicable.

12. A communication method, comprising: Applied to a second communication device, the method includes: determining first information, the first information including at least one of the following: model information of at least one first model, statistical information corresponding to the model information of the at least one first model, or proportion information of at least one network configuration parameter, the at least one network configuration parameter being a network configuration parameter in a network configuration to which the at least one first model is applicable; sending the first information to a first communication device; The first information is used to determine whether to train a second model, and the first model and the second model have an association relationship.

13. The method of claim 12, wherein, The first information is also used to determine at least one of the following of the second model: a generalization range, a target performance indicator, a model complexity, or a size of a data set used to train the second model.

14. The method according to claim 12 or 13, characterized in that, The model information of the first model indicates at least one of the following: a generalization range of the first model; a state of the first model; a performance indicator of the first model; a size of a first data set used to train or change the first model; a model complexity of the first model.

15. The method of claim 14, wherein, The generalization range includes at least one cell to which the first model is applicable, and / or at least one network configuration to which the first model is applicable.

16. The method according to claim 14 or 15, characterized in that The state of the first model includes at least one of the following: a support state, an available state, an applicable state, an activated state, or a configured state.

17. The method according to claim 15 or 16, characterized in that The statistical information corresponding to the model information of the at least one first model indicates at least one of the following: a proportion of first models in the at least one first model that meet a first target performance indicator; a proportion of first models in the at least one first model that do not meet the first target performance indicator; a proportion of first models in the at least one first model that are applicable to a first network configuration; a proportion of first models in the at least one first model that are applicable to a second network configuration; The percentage of the first models that meet the first target performance index and are applicable to the first network configuration in the at least one first model; The percentage of the first models that meet the first target performance index and are applicable to the second network configuration in the at least one first model; The proportion of the first models that are applicable to the third network configuration in the at least one first model; The percentage of the first models that are adapted to the third network configuration and meet the first target performance index in the at least one first model; The percentage of the first models that use the third network configuration and do not meet the first target performance index in the at least one first model; The percentage of first models that are in an active state in the at least one first model; The first complexity is the proportion of the model complexity corresponding to the at least one first model, where the first complexity is any model complexity among the model complexities corresponding to the at least one first model. The first size is the proportion of the size of the first dataset corresponding to the at least one first model, where the first size is the size of any first dataset in the first dataset corresponding to the at least one first model. In the first network configuration, each network configuration parameter has one possible value; in the second network configuration, at least some network configuration parameters have multiple possible values; and the third network configuration is any one of the at least one network configurations.

18. The method according to any one of claims 12 to 17, characterized in that, The statistical information corresponding to the at least one network configuration parameter includes the proportion information of the first network configuration parameter, where the first network configuration parameter is any one of the at least one network configuration parameters. The proportion information includes the time proportion corresponding to a first value, where the first value is any possible value of the first network configuration parameter.

19. The method of claim 18, wherein, The time percentage corresponding to the first value is used to indicate the percentage of time during which the first network configuration parameter is set to the first value within at least one time period.

20. The method of any one of claims 12-19, wherein, The method further includes: receiving second information from the second communication device, the second information being used to request the first information.

21. The method according to any one of claims 12 to 20, characterized in that, The method further includes: receiving model information of the second model from the second communication device.

22. The method of any one of claims 12-21, wherein, The at least one first model is a model maintained by at least one third communication device, and the network configuration to which the first model applies includes the network configuration to which the second model applies.

23. A communications device, characterized by The communication device includes a processor; the processor is configured to run a computer program or instructions to cause the communication device to perform the method as described in any one of claims 1-11, or to cause the communication device to perform the method as described in any one of claims 12-22.

24. A chip or chip system, characterized by The chip or chip system includes a processor coupled to a memory for storing programs or instructions that, when executed by the processor, cause the method as described in any one of claims 1-11 to be performed, or cause the method as described in any one of claims 12-22 to be performed.

25. A computer-readable storage medium, characterized in that, A computer readable storage medium stores computer instructions or programs that, when run on a computer, cause the method of any one of claims 1-11 to be performed, or cause the method of any one of claims 12-22 to be performed.

26. A computer program product, characterised in that, The computer program product comprises computer instructions; when part or all of the computer instructions are run on a computer, cause the method of any one of claims 1-11 to be performed, or cause the method of any one of claims 12-22 to be performed.

Images