Communication method and apparatus

By exchanging information between network devices to obtain model similarity, and assisting in determining model management strategies, the problem of high complexity in network device model management is solved, and more efficient and resource-efficient model management is achieved.

WO2026233338A1PCT designated stage Publication Date: 2026-11-12HUAWEI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2026/095090
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-09
Filing Date
2026-05-07
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

The process of determining model management strategies for existing network devices is quite complex, resulting in high resource consumption and management complexity.

Method used

The first device sends the first information to the second device, obtains the similarity when the first information is input into the first model, and uses the similarity as auxiliary information to determine the model management strategy, thereby reducing sample data collection and resource consumption.

Benefits of technology

This reduces the complexity and resource overhead of model management strategies, and improves the efficiency and accuracy of model management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2026095090_12112026_PF_FP_ABST
    Figure CN2026095090_12112026_PF_FP_ABST
Patent Text Reader

Abstract

A communication method and apparatus, which facilitate an improvement in the efficiency of a model management strategy used in a process of a device determining a management model, and reduce the complexity of determining the model management strategy. The method comprises: by means of detecting a first reference signal, a first device generating first information that includes measurement information of the first reference signal, and then sending the first information to a second device, such that the second device sends second information to the first device, wherein the second information indicates the similarity between an output from a first model and the first information when the first information is input into the first model, such that the first device acquires the recovery precision of the first model for the first information.
Need to check novelty before this filing date? Find Prior Art

Description

Communication methods and devices

[0001] This application claims priority to Chinese Patent Application No. 202510603139.3, filed with the State Intellectual Property Office of China on May 9, 2025, entitled "Communication Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to communication methods and apparatus. Background Technology

[0003] In wireless communication networks, with the diversification of service requirements and the enhancement of network functions, service implementation, network planning, configuration, and resource scheduling have become increasingly complex. Network devices (such as base stations and terminals) in wireless communication networks can perform related operations through models trained based on artificial intelligence (AI) / machine learning (ML) technologies to achieve schemes such as signal modulation and demodulation, information encoding and decoding, channel state information (CSI) feedback, or beam management (BM).

[0004] To ensure communication quality between network devices, the models used by these devices must have good performance. Therefore, network devices need to manage their models according to predetermined model management strategies (such as model selection, model activation, model deactivation, or model training / retraining) to maintain the performance of the models used by the network devices. Currently, network devices typically determine the model management strategy based on a large number of collected samples.

[0005] However, the process of determining model management strategies for network devices is currently quite complex. Summary of the Invention

[0006] This application provides a communication method and apparatus, which helps to improve the efficiency of determining model management strategies and reduce the complexity of model management.

[0007] Firstly, a communication method is provided, which can be applied to a first device. For example, the first device can be a terminal or a communication module / processing module within a terminal, or a circuit or chip in the terminal responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-a-chip (SoC) chip containing a modem core, or a system-in-package (SIP) chip), or a circuit or chip in the terminal responsible for processing functions (such as a graphics processing unit (GPU), an artificial intelligence (AI) processor, or an application-specific integrated circuit (ASIC)). Alternatively, the first device can also be a network device, a module applied within a network device (such as a processor, chip, or chip system), or a logical node, logical module, or software capable of implementing all or part of the functions of a network device. The method includes: sending first information to a second device, the first information including measurement information of a first reference signal; and receiving second information from the second device, the second information indicating the similarity between the output of the first model and the first information when the first information is input into the first model.

[0008] Based on the above scheme, the first device can obtain the similarity between the output of the first model and the first information when the first information is input into the first model by sending the first information to the second device. That is, it can obtain the recovery accuracy of the first model for the first information. This allows the first device to use the second information as auxiliary information to determine the management strategy of the model. This helps to reduce the complexity and resource overhead of the first device in determining the management strategy of the model used to process the measurement information of the first reference signal, and improves the efficiency of the first device in determining the model management strategy.

[0009] In one possible design, the first model includes a first sub-model and a second sub-model. The input of the first sub-model includes first information, the input of the second sub-model includes the output of the first sub-model, and the output of the first model includes the output of the second sub-model. The first sub-model is used to perform a first operation on the input information, and the second sub-model is used to perform a second operation on the input information. The second operation is the inverse operation of the first operation.

[0010] Based on this scheme, when the first information is used as the input of the first model, the new first information recovered by the second sub-model after the first information has been processed by the first sub-model can be accurately obtained, which facilitates the accurate acquisition of the recovery accuracy of the first model for the measurement information of the first reference signal.

[0011] In one possible design, the second information is used to determine the strategy for the first device to manage the second model, which includes a third sub-model for performing a first operation on the input information.

[0012] Based on this scheme, the first device uses the second information as auxiliary information to determine the strategy for managing the second model. Combined with the recovery accuracy of the first model's measurement information of the first reference information (i.e., the first information), the first device determines the strategy for associating the second model. On the one hand, determining the model management strategy based on the auxiliary information helps reduce the complexity of determining the model management strategy. On the other hand, the first device does not need to collect a large number of samples, which helps reduce the resource overhead of the first device in the process of managing the second model.

[0013] In one possible design, the communication method further includes receiving third information from a second device, the third information including the output of the first sub-model when the first information is input into the first model, and the third information being used to manage the second model.

[0014] Based on this scheme, the first device can accurately obtain the third information used to manage the second model, reducing the difficulty for the first device to obtain sample data used to manage the second model, thereby reducing the complexity of model management for the first device.

[0015] In one possible design, the communication method further includes receiving fourth information from a second device, the fourth information indicating that the third information is associated with the first reference signal or the first information.

[0016] Based on this scheme, it is beneficial to reduce the probability that the first device will associate the third information with the measurement information of other reference signals or with information including information generated based on the measurement information of other reference signals, thereby improving the accuracy of the information cache of the first device.

[0017] In one possible design, the communication method further includes receiving fifth information from a second device, the fifth information indicating at least one of the following information of the first sub-model: model complexity, model backbone, model structure, model output information, model input information, or characteristics of the model implementation.

[0018] Based on this scheme, the first device can determine a model management strategy that is more in line with the application scenario based on the fifth information. On the one hand, this helps to reduce the complexity of the first device in determining the model management strategy, and on the other hand, it helps to improve the accuracy of the first device's model management and reduce the resource consumption of the first device in the model management process.

[0019] In one possible design, the communication method further includes receiving a sixth message from a second device, the sixth message indicating the release of the first message.

[0020] Based on this scheme, it is beneficial to reduce the probability that the first device will use the first information as sample data in the process of managing the second model, improve the quality of the sample data acquired by the first device, and thus improve the model management effect of the first device.

[0021] In one possible design, the communication method further includes: if no third information is received within a first time period after sending the first information, the first information is released, and the third information includes the output of the first sub-model when the first information is input into the first model.

[0022] In one possible design, sending first information to a second device includes: when the first information is input into a second model, if the similarity between the output of the second model and the first information is less than a second threshold, sending the first information to the second device; wherein the second model includes a third sub-model and a fourth sub-model, the third sub-model is used to perform a first operation on the input information, the fourth sub-model is used to perform a second operation on the input information, the input of the third sub-model includes the first information, the input of the fourth sub-model includes the output of the third sub-model, and the output of the second model includes the output of the fourth sub-model.

[0023] Based on this scheme, when the first device detects that the recovery accuracy of the measurement information of the first reference signal by the second model is poor, it can determine, based on the received second information, whether the poor recovery accuracy of the measurement information of the first reference signal is due to the poor training effect of the second model or due to the mismatch between the data characteristics of the first reference signal in the current scenario and the data characteristics of the training data used during the training of the second model. This helps to improve the accuracy of the first device in determining the strategy for managing the second model.

[0024] In one possible design, the communication method also includes receiving a second threshold from a second device.

[0025] In one possible design, if the similarity is greater than or equal to a first threshold, the strategy includes training the second model; or, if the similarity is less than the first threshold, the strategy includes deactivating the second model.

[0026] Secondly, a communication method is provided, which can be applied to a second device. For example, the second device can be a terminal or a communication module / processing module within a terminal, or a circuit or chip in the terminal responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), or a circuit or chip in the terminal responsible for processing functions (such as a GPU, AI processor, or ASIC). Alternatively, the second device can also be a network device, a module applied within a network device (such as a processor, chip, or chip system), or a logical node, logical module, or software capable of implementing all or part of the functions of a network device. The method includes: receiving first information from a first device, the first information being measurement information of a first reference signal; and sending second information to the first device, the second information indicating the similarity between the output of the first model and the first information when the first information is input into the first model.

[0027] In one possible design, the first model includes a first sub-model and a second sub-model. The input of the first sub-model includes first information, the input of the second sub-model includes the output of the first sub-model, and the output of the first model includes the output of the second sub-model. The first sub-model is used to perform a first operation on the input information, and the second sub-model is used to perform a second operation on the input information. The second operation is the inverse operation of the first operation.

[0028] In one possible design, the communication method further includes sending third information to the first device, the third information including the output of the first sub-model when the first information is input into the first model.

[0029] In one possible design, sending third information to the first device includes: sending third information to the first device if the similarity is greater than or equal to a first threshold.

[0030] In one possible design, the communication method further includes sending a fourth message to the first device, the fourth message indicating that the third message is associated with the first reference signal or the first message.

[0031] In one possible design, the communication method further includes sending a fifth message to the first device, the fifth message indicating at least one of the following information of the first sub-model: model complexity, model backbone, model structure, model output information, model input information, or characteristics of model implementation.

[0032] In one possible design, the communication method further includes sending a sixth message to the first device, the sixth message indicating the release of the first message.

[0033] In one possible design, the communication method also includes sending a second threshold to the first device.

[0034] The technical effects of the second aspect and any of its design methods can be referenced from the technical effects of the first aspect or similar design methods in the first aspect, and will not be elaborated here.

[0035] Thirdly, a communication method is provided, which can be applied to a first device. For example, the first device can be a terminal or a communication module / processing module within a terminal, or a circuit or chip responsible for communication functions within the terminal (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), or a circuit or chip responsible for processing functions within the terminal (such as a GPU, AI processor, or ASIC). Alternatively, the first device can also be a network device, a module applied within a network device (such as a processor, chip, or chip system), or a logical node, logical module, or software capable of implementing all or part of the functions of a network device. The method includes: sending first information to a second device, the first information including measurement information of a first reference signal; receiving third information or sixth information from the second device, the third information including the output of a first sub-model when the first information is input into a first model, the first sub-model being used to perform a first operation on the input information, and the sixth information indicating the release of the first information.

[0036] Based on this scheme, the first device can send first information to the second device to obtain the output of the first sub-model when the first information is input into the first model (i.e., the result obtained by the first model after performing the first operation on the input information). This allows the first device to use the third information as auxiliary information to determine the management strategy of the model. This helps to reduce the complexity and resource overhead of the first device in determining the management strategy of the model used to process the measurement information of the first reference signal, and improves the efficiency of the first device in determining the model management strategy.

[0037] In one possible design, the first model includes a first sub-model and a second sub-model. The input of the first sub-model includes first information, the input of the second sub-model includes the output of the first sub-model, the output of the first model includes the output of the second sub-model, and the second sub-model is used to perform a second operation on the input information, which is the inverse operation of the first operation.

[0038] In one possible design, the communication method further includes receiving fourth information from a second device, the fourth information indicating that the third information is associated with the first reference signal or the first information.

[0039] In one possible design, the communication method further includes receiving fifth information from a second device, the fifth information indicating at least one of the following information of the first sub-model: model complexity, model backbone, model structure, model output information, model input information, or characteristics of the model implementation.

[0040] In one possible design, sending the first information to the second device includes: when the first information is input into the second model, if the similarity between the output of the second model and the first information is less than a second threshold, sending the first information to the second device; wherein the second model includes a third sub-model and a fourth sub-model, the third sub-model is used to perform the first operation on the input information, the fourth sub-model is used to perform the second operation on the input information, the input of the third sub-model includes the first information, the input of the fourth sub-model includes the output of the third sub-model, and the output of the second model includes the output of the fourth sub-model.

[0041] In one possible design, the communication method also includes receiving a second threshold from a second device.

[0042] The technical effects of any design method in the third aspect can be referenced from the technical effects of the first aspect or similar design methods in the first aspect, and will not be elaborated here.

[0043] Fourthly, a communication method is provided, which can be applied to a second device. For example, the second device can be a terminal or a communication module / processing module within a terminal, or a circuit or chip responsible for communication functions within a terminal (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), or a circuit or chip responsible for processing functions within a terminal (such as a GPU, AI processor, or ASIC). Alternatively, the second device can also be a network device, a module applied within a network device (such as a processor, chip, or chip system), or a logical node, logical module, or software capable of implementing all or part of the functions of a network device. The method includes: receiving first information from a first device, the first information including measurement information of a first reference signal; sending third information or sixth information to the first device, the third information including the output of a first sub-model when the first information is input into a first model, the first sub-model being used to perform a first operation on the input information, and the sixth information indicating the release of the first information.

[0044] In one possible design, the first model includes a first sub-model and a second sub-model. The input of the first sub-model includes first information, the input of the second sub-model includes the output of the first sub-model, the output of the first model includes the output of the second sub-model, and the second sub-model is used to perform a second operation on the input information, the second operation being the inverse operation of the first operation.

[0045] In one possible design, sending third information to the first device includes: when the first information is input into the first model, if the similarity between the output of the first model and the first information is greater than or equal to a first threshold, sending the third information to the first device.

[0046] In one possible design, sending the sixth information to the first device includes: when the first information is input into the first model, if the similarity between the output of the first model and the first information is less than a first threshold, sending the sixth information to the first device.

[0047] In one possible design, the communication method further includes sending a fourth message to the first device, the fourth message indicating that the third message is associated with the first reference signal or the first message.

[0048] In one possible design, the communication method further includes sending a fifth message to the first device, the fifth message indicating at least one of the following information of the first sub-model: model complexity, model backbone, model structure, model output information, model input information, or characteristics of model implementation.

[0049] In one possible design, the communication method also includes sending a second threshold to the first device.

[0050] The technical effects of any design method in the fourth aspect can be referenced from the technical effects of the third aspect or similar design methods in the third aspect, and will not be elaborated here.

[0051] Fifthly, a communication device is provided for implementing various methods. The communication device includes modules, units, or means corresponding to the implementation of the methods, which can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the functions.

[0052] In some possible designs, the communication device may include a processing module and a transceiver module. The processing module can be used to implement the processing functions in any of the above aspects and any possible implementations thereof. The transceiver module may include a receiving module and a transmitting module, respectively used to implement the receiving function and the transmitting function in any of the above aspects and any possible implementations thereof.

[0053] In some possible designs, the transceiver module can consist of transceiver circuitry, a transceiver unit, a transceiver interface, or a communication interface.

[0054] A sixth aspect provides a communication device, comprising: a processor and a memory; the memory being used to store computer instructions that, when executed by the processor, cause the communication device to perform the method described in either aspect.

[0055] A seventh aspect provides a communication device, comprising: a processor and a communication interface; the communication interface being used to communicate with a module outside the communication device; the processor being used to execute a computer program or instructions to cause the communication device to perform the method described in any aspect.

[0056] Eighthly, a communication device is provided, comprising: at least one processor; said processor being configured to execute a computer program or instructions stored in a memory to cause the communication device to perform the method described in any of the aspects. The memory may be coupled to the processor, or may be independent of the processor.

[0057] A ninth aspect provides a communication device (e.g., the communication device may be a chip or a chip system), the communication device including a processor for implementing the functions involved in any one of the first to sixth aspects.

[0058] In some possible designs, the communication device includes a memory for storing necessary program instructions and data.

[0059] In some possible designs, when the device is a chip system, it can be composed of chips or contain chips and other discrete components.

[0060] It is understood that the communication device provided in the fifth to ninth aspects may be the first device in the first or third aspect, or a module or unit (e.g., a chip, chip system, or circuit) in the first device that performs the methods / operations / steps / actions described in the first or third aspect, or a module or unit that can be used in conjunction with the first device, or a logic node, logic module, or software that can implement all or part of the functions of the first device; or the communication device may be the second device in the second or fourth aspect, or a module or unit (e.g., a chip, chip system, or circuit) in the second device that performs the methods / operations / steps / actions described in the second or fourth aspect, or a module or unit that can be used in conjunction with the second device, or a logic node, logic module, or software that can implement all or part of the functions of the second device.

[0061] It is understandable that when the communication device provided in any of the fifth to ninth aspects is a chip, the sending action / function of the communication device can be understood as outputting information, and the receiving action / function of the communication device can be understood as inputting information.

[0062] In a tenth aspect, a computer-readable storage medium is provided, which stores a computer program or instructions that, when executed on a communication device, enable the communication device to perform the method described in any one of the first to fourth aspects.

[0063] Eleventhly, a computer program product containing instructions is provided, which, when run on a communication device, enables the communication device to perform the method described in any one of the first to fourth aspects.

[0064] In a twelfth aspect, a communication system is provided, comprising a first device and a second device. The first device is configured to perform the method described in any possible design of the first or third aspect, and the second device is configured to perform the method described in any possible design of the second or fourth aspect.

[0065] The technical effects of any of the design methods in aspects five through twelfth can be found in the technical effects of different design methods in aspects one through four, and will not be repeated here. Attached Figure Description

[0066] Figure 1 is a schematic diagram of a two-sided model for implementing two-end pairing provided in this application;

[0067] Figure 2 is a schematic diagram of a data interaction method provided in this application;

[0068] Figure 3 is a system schematic diagram of a communication system provided in this application;

[0069] Figure 4 is a schematic diagram of another communication system provided in this application;

[0070] Figure 5 is a flowchart illustrating a communication method provided in this application;

[0071] Figure 6 is a flowchart illustrating the processing of first information provided in this application;

[0072] Figure 7 is a schematic diagram of an information interaction provided in this application;

[0073] Figure 8 is a flowchart illustrating another communication method provided in this application;

[0074] Figure 9 is a flowchart illustrating another communication method provided in this application;

[0075] Figures 10-12 are schematic diagrams of the communication device provided in this application. Detailed Implementation

[0076] In the description of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can mean A or B. "And / or" in this application is merely a description of the relationship between the related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

[0077] In the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0078] Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0079] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0080] It is understood that the term "embodiment" used throughout the specification means that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, various embodiments throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It is understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0081] It is understood that in this application, "...when" and "if" both refer to the corresponding processing that will be carried out under certain objective circumstances, and are not limited to a specific time, nor do they require a judgment action to be performed during implementation, nor do they imply any other limitations.

[0082] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the apparatus given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0083] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, unless otherwise specified or there is a logical conflict, the terminology and / or descriptions between different embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships. The following descriptions of the embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0084] To facilitate understanding of the technical solutions of the embodiments of this application, a brief introduction to the relevant technologies of this application is given below.

[0085] 1. Artificial intelligence / machine learning models:

[0086] In wireless communication networks, with the diversification of service requirements and the enhancement of network functions, service implementation, network planning, configuration, and resource scheduling have become increasingly complex. For example, service implementation, network planning, configuration, and resource scheduling may involve modulation, coding, transmitters, receivers, multi-antenna technology, or positioning technologies in the wireless communication system. Communication devices (such as base stations and terminals) in wireless communication networks can perform related operations to achieve 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.

[0087] For example, communication devices can execute the technical solutions in the aforementioned business scenarios using traditional algorithms, or they can apply artificial intelligence (AI) / machine learning (ML) technologies to these solutions. AI / ML technology refers to training a model using relevant data, thereby using the trained model to achieve a specific purpose (such as wireless communication functions / operations). The purpose that the model can achieve is related to the data used during training.

[0088] The training data includes data acquired from the communication network, such as signal processing information, channel information, and radio frequency (RF) information. Signal processing information includes information generated during baseband signal processing, such as at least one of the information generated during signal sampling, modulation, demodulation, encoding, decoding, precoding, resource mapping, or digital filtering. Channel information includes information corresponding to the 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, velocity 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, the data in CSI and BM use cases is represented as channel information (CSI), while the data in the positioning use case is represented as channel information and / or location information. Radio frequency (RF) information includes information generated during analog processing, such as at least one of the information generated during digital-to-analog conversion, analog-to-digital conversion, digital predistortion, frequency conversion, RF modulation, RF demodulation, power amplification, low-noise amplification, analog filtering, or duplex processing.

[0089] For example, taking AI / ML-based CSI feedback scenarios as an example, these scenarios include AI / ML-based CSI compression and AI / ML-based CSI prediction. AI / ML-based CSI compression refers to the terminal compressing downlink CSI (measured by the terminal) using a model trained on AI / ML technology. The terminal can then send the compressed CSI to the network device over the air interface. The network device uses the AI / ML-trained model to restore (decompress) the CSI. Compared to traditional compression algorithms, AI / ML-based compression algorithms have higher compression ratios and better CSI restoration capabilities. Therefore, the terminal can feed back more CSI with less air interface overhead, enabling the network device to perform more accurate downlink precoding. AI / ML-based CSI prediction refers to the network device using an AI / ML-trained model and the current / historical downlink CSI to predict the downlink CSI for future moments, and then performing precoding based on the predicted CSI. This scheme predicts CSI that better matches the channel state when downlink data is scheduled, thus overcoming the channel aging problem and achieving more accurate downlink precoding. In AI / ML-based CSI feedback service scenarios, the training data for the models involved includes CSI.

[0090] Taking a business scenario of beamforming based on AI / ML as an example, network devices and terminals can use AI / ML technology to predict transmit and / or receive beams. For instance, a model trained on AI / ML can infer the optimal beam from a small number of beam scan results. Compared to traditional solutions that require scanning a large number of beams to obtain the optimal beam, AI / ML-based beam prediction reduces the processing overhead of beam scanning. For example, a terminal can scan a small number of beams and then use a model trained on AI / ML to predict the optimal beam from a large number of candidate beams, thus avoiding the need to scan all candidate beams and reducing overhead. The small number of beams scanned by the terminal can be sparse or wide beams, while the candidate beams can be dense or narrow beams. The terminal can input the beam information scanned at the current / historical time into the model to predict the optimal beam at future time points, thus avoiding the need to perform beam scanning again at future time points and improving beam scanning efficiency. In AI / ML-based business scenarios involving BM, the training data for the models includes beam information, such as beam identity document (ID) and / or the reference signal receiving power (RSRP) corresponding to the beam.

[0091] Taking AI / ML-based positioning as an example, the communication device inputs channel information into a model trained using AI / ML technology to infer the intermediate parameters required for positioning, or directly obtains the location coordinates. Compared to traditional positioning algorithms, the intermediate parameters or location coordinates obtained based on AI / ML are more accurate. The training data for the model in AI / ML-based positioning scenarios includes channel information and / or location information. Channel information includes power information, phase information, delay information, distance information, velocity information, channel scattering information, and LOS / NLOS information, among other channel-related information.

[0092] 2. Model Management:

[0093] Since the performance of the model used by the communication device is affected by a variety of factors, such as the network configuration on the network device side, the external environment and the internal conditions of the communication device, the communication device needs to determine an appropriate model management strategy to maintain the model based on the actual performance of the model and the current data characteristics, so that the model's performance indicators can meet the preset performance indicator requirements.

[0094] Currently, model management strategies mainly include: model training, model retraining, model updating, model selection, model activation, model deactivation, model switching, model monitoring, model inference, data collection, and data analysis.

[0095] For example, model training can be understood as generating a model based on training data to implement a specific communication function; model retraining can be understood as regenerating a model based on training data to implement a specific communication function; model updating can be understood as further training the current model based on training data, updating model parameters and / or architecture; model selection can be understood as selecting a model to be activated from models used to implement a specific communication function before model activation; model activation can be understood as enabling the selected model and executing a specific communication function through that model; model deactivation can be understood as ending the enabling of the current model and no longer executing a specific communication function through the current model; model switching can be understood as replacing the model executing the current communication function from the current model to another model; model monitoring can be understood as monitoring the performance indicators and other data of the current model; data collection can be understood as acquiring training data during the training, updating, or retraining of the model; and data analysis can be understood as performing data feature analysis and / or comparison on the collected training data.

[0096] 3. Model type:

[0097] Depending on the network element nodes involved in AI / ML inference, the model includes bilateral and unilateral models. For an air interface feature / use case, when the inference of the air interface feature / use case is implemented based on a bilateral model, the network device and the terminal each have an AI / ML model. During the inference process, the AI / ML model on the network device side and the AI / ML model on the terminal side need to be paired to complete the entire inference process of the air interface feature / use case. When the inference of the air interface feature / use case is implemented based on a unilateral model, the entire inference process of the air interface feature / use case can be completed by using only the AI / ML model deployed on the network device side (also known as the network device-side AI / ML model) or only the AI / ML model deployed on the terminal side (also known as the terminal-side AI / ML model).

[0098] For example, taking CSI compression through a bilateral model as an example, the AI / ML model on the terminal side infers the original CSI to achieve compression, and feeds back the inferred CSI (compressed CSI) to the network device via the air interface. After receiving the compressed CSI, the network device uses its own AI / ML model to infer the compressed CSI to achieve decompression, obtaining the restored CSI (also known as recovered CSI or restored CSI). For network device-side AI / ML models and terminal-side AI / ML models with good matching, the restored CSI is close to the original CSI; for network device-side AI / ML models and terminal-side AI / ML models with poor matching, the restored CSI differs significantly from the original CSI.

[0099] For example, taking the implementation of BM (Business Intelligence) or location technology use cases through a one-sided model as an example, the one-sided model includes a network-side model and a terminal-side model. In the case of implementing the reasoning process of BM or location technology use cases through the network device-side model, the terminal reports measurement information to the network device as input data for the network device-side model, and the reasoning of BM or location technology use cases is performed through the network device-side model. In the case of implementing the reasoning process of BM or location technology use cases through the terminal-side model, the terminal uses measurement information as input data for the terminal-side model, performs the reasoning of BM or location technology use cases through the terminal-side model, and then reports the reasoning result or monitoring result to the network device.

[0100] It is worth mentioning that in the reasoning process of implementing an air interface feature / use case through a one-sided model, regardless of whether a network device-side model or a terminal-side model is used, for some use cases, the network device needs to indicate or configure the corresponding resources (such as reference signal resources) to the terminal for the terminal to perform measurement in order to generate the above measurement information.

[0101] Taking CSI compression using a bilateral model as an example, the bilateral model can achieve pairing in the following ways: Referring to Figure 1(a), after the network device trains encoder model 1 and decoder model 1 using the training dataset, it sends encoder model 1 to the terminal, and the terminal directly uses encoder model 1 trained by the network device. Referring to Figure 1(b), after the network device trains encoder model 1 and decoder model 1 using the training dataset, it sends the training dataset and decoder model 1 to the terminal, and the terminal trains a terminal-side decoder model (i.e., decoder model 2) and a terminal-side encoder model (i.e., encoder model 2) based on decoder model 1 and the training dataset. Referring to Figure 1(c), after the network device trains encoder model 1 and decoder model 1 using the training dataset, it sends the trained encoder model 1 and the training dataset to the terminal, and the terminal trains a terminal-side encoder model (i.e., encoder model 3) and a terminal-side decoder model (i.e., decoder model 3) based on the received training dataset and encoder model 1.

[0102] In the process of sending training datasets / models to terminals, network devices can use either air interface transmission or non-air interface transmission. Referring to Figure 2, when using air interface transmission, the network device directly sends the training datasets / models to the terminal via the air interface; when using non-air interface transmission, the network device first sends the training datasets / models to the server that is connected to the terminal, and the server then sends the training datasets / models to the terminal.

[0103] It is worth noting that the models involved in the embodiments of this application can also be described as functions (such as AI functions or ML functions), features, or algorithms, etc., and models include, for example, AI models or ML models. For the sake of simplicity, this application will simply refer to models / functions / features / algorithms as "models," that is, all models in this application can be replaced with algorithms / functions / features.

[0104] Currently, communication devices typically manage models by collecting large amounts of samples as training data for model training / retraining, or by using these large amounts of collected samples to determine whether the performance metrics of the model currently used by the communication device can meet preset performance requirements, thereby determining the model management strategy. However, determining the model management strategy based on a large amount of collected samples incurs significant resource overhead, and the large amount of data involved makes the determination of the model management strategy quite complex.

[0105] Based on this, embodiments of this application provide a communication method in which a first device sends measurement information of a first reference signal to a second device by sending first information, and receives second information from the second device. The second information indicates the similarity between the output of the first model and the first information when the first information is input into the first model. In other words, the first device can obtain the similarity between the output of the first model and the measurement information of the first reference signal after the measurement information of the first reference signal is input into the first model (or, the recovery accuracy of the first model of the measurement information of the first reference signal when the measurement information of the first reference signal is used as input). This allows the first device to use the recovery accuracy of the first model of the measurement information of the first reference signal as auxiliary information for determining a model management strategy. This determines the model management strategy for the model that processes the measurement information of the first reference signal. Using auxiliary information to determine the model management strategy reduces both the complexity of the first device in determining the strategy and the resource overhead.

[0106] This communication system can be a third-generation partnership project (3GPP) communication system, such as fourth-generation (4G) systems like Long Term Evolution (LTE), fifth-generation (5G) systems like New Radio (NR), LTE and 5G hybrid networking systems, integrated communication and sensing systems, non-terrestrial networks (NTN), device-to-device (D2D) communication systems, vehicle-to-everything (V2X) communication systems, machine-type communication (MTC) systems, Internet of Things (IoT) systems, or other future communication systems. This communication system can also be a non-3GPP communication system; there are no restrictions.

[0107] The communication systems described above are merely illustrative examples, and are not limited to those described herein. The communication systems provided in this application do not impose any limitations on the solutions described herein. This will be explained uniformly here and will not be repeated below.

[0108] Figure 3 illustrates a possible, non-limiting system diagram. As shown in Figure 3, the communication system 20 includes a radio access network (RAN) 200 and a core network (CN) 300. RAN 200 includes at least one RAN node (210a and 210b in Figure 2, collectively referred to as 210) and at least one terminal (220a-220j in Figure 3, collectively referred to as 220). RAN 200 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment (not shown in Figure 3). Terminal 220 is wirelessly connected to RAN node 210. RAN node 210 is wirelessly or wired connected to core network 300. The core network equipment in core network 300 and RAN node 210 in RAN 200 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0109] RAN 200 can be a 3GPP-related cellular system, such as a 4G, 5G mobile communication system, or a future-oriented evolution system. RAN 200 can also be an open access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN 200 can also be a communication system that integrates two or more of the above systems.

[0110] RAN node 210, sometimes also referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple RAN nodes 210 in communication system 20 can be of the same type or different types. In some scenarios, the roles of RAN node 210 and terminal 220 are relative. For example, network element 220i in Figure 3 can be a helicopter or drone, which can be configured as a mobile base station. For terminals 220j accessing RAN 200 through network element 220i, network element 220i is a base station; but for base station 210a, network element 220i is a terminal. RAN node 210 and terminal 220 are sometimes both referred to as communication devices. For example, network elements 210a and 210b in Figure 3 can be understood as communication devices with base station functions, and network elements 220a-220j can be understood as communication devices with terminal functions.

[0111] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a next-generation base station in a future mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. A RAN node can be a macro base station (as shown in Figure 3, 210a), a micro base station or indoor station (as shown in Figure 3, 210b), a relay node or donor node, or a radio controller in a CRAN scenario. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). All or part of the functions of the RAN node in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). The RAN node in this application can also be a logical node, logical module, or software capable of implementing all or part of the RAN node functions.

[0112] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with each RAN node performing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be separate entities or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0113] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0114] In one possible scenario, terminal 120 can be a device for implementing wireless communication functions, such as a terminal, a chip or circuit that can be used in the terminal, or an entity associated with the terminal. Specifically, terminal 120 can be user equipment (UE), access terminal, terminal unit, terminal station, mobile station (MS), mobile station, remote station, remote terminal, mobile device, wireless communication equipment, terminal agent or terminal device, subscriber unit, smartphone, wireless data card, tablet computer, wireless modem, laptop computer, machine-type communication (MTC) terminal, tag, etc., in a 5G network or a future evolved public land mobile network (PLMN). Access terminals can be cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handsets with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, in-vehicle devices or wearable devices, virtual reality (VR) terminals, augmented reality (AR) terminals, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical care, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, or terminal nodes (T-nodes) in StarSpark, etc.

[0115] In one possible implementation, terminal 120 can be either mobile or fixed.

[0116] As exemplarily shown in Figure 4, which is an exemplary implementation of the system shown in Figure 3, the communication system may include: an AI / ML node, a first device, and a second device, wherein the second device can provide services to the first device.

[0117] Optionally, the first device may be a terminal in the communication system shown in Figure 3, or the first device may be a RAN node in the communication system shown in Figure 3.

[0118] As one possible implementation, the second device can be any device deployed in the access network in the communication system shown in Figure 3 that can wirelessly communicate with the first device (such as a terminal). It can also be a chip or chip system that can be set in the above-mentioned device, or a logical node or logical module, or a function implemented in software. It is mainly responsible for the wireless physical control function, resource scheduling, wireless resource management, quality of service management, data compression and encryption, wireless access control, and mobility management on the air interface side.

[0119] For example, the second device can be a device that supports wired access or a device that supports wireless access.

[0120] As another possible implementation, the second device can also be a terminal in the communication system shown in Figure 3 that is connected to the first device (such as a terminal) via a side link.

[0121] The AI / ML node in Figure 4 is used to support the use of AI / ML technology in AI / ML scenarios.

[0122] It is understood that Figure 4 above is merely a schematic diagram and does not constitute a limitation on the applicable scenarios of the technical solutions provided in this application. Those skilled in the art should understand that in specific implementation processes, the communication system shown in Figure 4 may include fewer devices than those shown in Figure 4, or the communication system shown in Figure 4 may also include other devices. At the same time, the number of devices in the communication system shown in Figure 4 can be determined according to specific needs and is not limited.

[0123] It should be noted that the communication system described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0124] The communication method provided in this application will be described below with reference to the communication system shown in Figures 3 and 4, taking the interaction between the first device and the second device as an example. It should be noted that in the following embodiments of this application, the message names, parameter names, or information names between the first device and the second device are just examples, and other names may be used in other embodiments. The method provided in this application does not specifically limit these names.

[0125] It is understood that in the embodiments of this application, the first device or the second device may perform some or all of the steps in the embodiments of this application. These steps or operations are merely examples, and the embodiments of this application may also perform other operations or variations thereof. Furthermore, the steps may be performed in different orders as presented in the embodiments of this application, and it is not necessary to perform all the operations in the embodiments of this application.

[0126] It is understood that this application uses the first device and the second device as examples to illustrate the execution of the interaction, but this application does not limit the execution subject of the interaction. For example, the method executed by the second device in this application can also be executed by a module applied to the second device (e.g., a chip, chip system, or processor), or by a logic node, logic module, or software that can implement all or part of the functions of the second device; similarly, the method executed by the first device in this application can also be executed by a module applied to the first device (e.g., a chip, chip system, or processor), or by a logic node, logic module, or software that can implement all or part of the functions of the first device.

[0127] Furthermore, in this application, "sending information" can be understood as one device sending information to another device, or it can also be understood as one logic module within a device sending information to another logic module. For example, "the second device sending information" can be understood as the second device sending information to another device (such as the first device), or it can be understood as logic module 1 (such as the processing module) in the second device sending information to logic module 2 (such as the transceiver module) in the second device.

[0128] In this application, "receiving information" can be understood as one device receiving information from another device, or it can also be understood as a logical module within a device receiving information from another logical module. For example, "the first device receiving information" can be understood as the first device receiving information from another device (such as the second device), or it can be understood as logical module 1 (such as the processing module) in the first device receiving information from logical module 2 (such as the transceiver module) in the first device.

[0129] In this application, phrases such as "sending information to... (e.g., the first device)" or related illustrations in the accompanying drawings can be understood as the destination of the information being the first device. This can include sending information directly or indirectly to the first device. Similarly, phrases such as "receiving information from... (e.g., the second device)," "receiving information from... (e.g., the second device)," or "receiving information sent (e.g., by the second device)," or related illustrations in the accompanying drawings, can be understood as the source of the information being the second device. This can include receiving information directly or indirectly from the second device. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be interpreted similarly and will not be elaborated further here.

[0130] Referring to Figure 5, which is a flowchart illustrating a communication method provided in an embodiment of this application, the method may include the following steps:

[0131] S501, the first device sends first information to the second device. Correspondingly, the second device receives the first information from the first device. The first information includes measurement information of the first reference signal.

[0132] For example, the first information including the measurement information of the first reference signal can be understood as the first information including the measurement result / detection result obtained by the first device after measuring / detecting the first reference signal; or, it can also be understood as the first information including the measurement report / detection report of the first reference signal generated by the first device based on the measurement result / detection result obtained by measuring / detecting the first reference signal.

[0133] For example, if the first reference signal is a CSI reference signal (RS), then the first information including the measurement information of the first reference signal can be understood as including CSI or a CSI report. If the first reference signal is a cell-specific reference signal, then the first information including the measurement information of the first reference signal can be understood as including the reference signal received power (RSRP), etc. The meanings of the measurement information of the first reference signal when it is a different reference signal will not be listed here. Furthermore, the first reference signal can also be a newly defined reference signal in the standard, and the first information including the measurement information of that reference signal can also be understood as including the characteristics / reports / data determined by measuring that reference signal.

[0134] For example, one of the first device and the second device is a terminal and the other is a network device, and the first device and the second device communicate through an air interface; or, both the first device and the second device are terminals, and the first device and the second device communicate through a sidelink; or, both the first device and the second device are network devices, and the first device and the second device communicate through a wireless interface between network devices.

[0135] For example, if the first device is a terminal and the second device is a network device, the first information can be carried in uplink control information.

[0136] Control information (UCI), or the first information can also be carried in media access control (MAC) signaling, radio resource control (RRC) signaling, or non-access stratum (NAS) signaling, without restriction.

[0137] Optionally, prior to S501, the second device sends a first reference signal to the first device. Correspondingly, the first device receives the first reference signal from the second device. That is, before the first device sends the first information, during the process of the first device acquiring the measurement information of the first reference signal, the second device sends the first reference signal to the first device, so that the first device can acquire the measurement information of the first reference signal.

[0138] For ease of understanding and explanation, the embodiments of this application use CSI-RS as the first reference signal and CSI as the first information as an example. In this case, the first device can be regarded as a terminal, a chip in the terminal, or a communication module in the terminal, and the second device can be regarded as a base station or a node that implements all or part of the functions of the base station.

[0139] S502, the second device sends second information to the first device. Correspondingly, the first device receives the second information from the second device. The second information indicates the similarity between the output of the first model and the first information when the first information is input into the first model.

[0140] For example, the similarity between the output of the first model and the first information can be understood as the degree to which the output of the first model restores the first information, or it can also be understood as the accuracy of the output of the first model in restoring the first information, or it can also be understood as the degree of overlap between the output of the first model and the first information.

[0141] As one possible implementation, the similarity between the output of the first model and the first information can be represented by the cosine similarity between the first vector and the second vector. Here, the first vector is generated based on the first information, and the second vector is generated based on the output of the first model.

[0142] For example, after the second device acquires the output (denoted as information 1) and the first information (denoted as information 2) when the first information is input into the first model, it constructs the first vector and the second vector respectively based on information 1 and information 2 through the same vectorization process (such as feature extraction). Then, it directly uses the cosine similarity between the first vector and the second vector as the similarity between the output of the first model and the first information, or it uses the product of the cosine similarity between the first vector and the second vector and a preset coefficient as the similarity between the output of the first model and the first information, etc.

[0143] As another possible implementation, the similarity between the output of the first model and the first information can be characterized by the normalized mean square error (NMSE) between the first matrix and the second matrix, where the first matrix is ​​generated based on the first information and the second matrix is ​​generated based on the output of the second model.

[0144] For example, after the second device obtains the output (denoted as information 1) and the first information (denoted as information 2) when the first information is input into the first model, it constructs the first matrix and the second matrix respectively through the same matrixing process, and then calculates the NMSE between the first matrix and the second matrix. The NMSE or the product of the NMSE and the preset coefficient is used as the similarity between the output of the first model and the first information.

[0145] In one possible implementation, the first model includes a first sub-model and a second sub-model. The input of the first sub-model includes first information, the input of the second sub-model includes the output of the first sub-model, and the output of the first model includes the output of the second sub-model. The first sub-model is used to perform a first operation on the input information, and the second sub-model is used to perform a second operation on the input information. The second operation is the inverse operation of the first operation.

[0146] For example, the second operation being the reverse of the first operation (or the first and second operations being the reverse of each other) can be understood as follows: after data 1 undergoes the first and second operations in sequence, the result is the restored new data 1; or, it can also be understood as the first and second operations being two opposite data processing methods.

[0147] For example, the first operation is quantization and the second operation is dequantization; or, the first operation is compression and the second operation is decompression; or, the first operation is encoding and the second operation is decoding; or, the first operation is modulation and the second operation is demodulation, etc., which will not be elaborated here.

[0148] In other words, the first model includes two sub-models that operate on the input information. Since the output of the first sub-model is used as the input of the second sub-model and the output of the second sub-model is used as the output of the first model, the first model can recover new first information by outputting the second sub-model after inputting the first information into the first sub-model.

[0149] For example, when the first reference signal is CSI-RS and the first information is CSI, referring to Figure 6, the first model includes an encoder model (first sub-model) and a decoder model (second sub-model). After the first information (i.e., the CSI fed back by the first device) is input into the first model, the first sub-model compresses and encodes the input information (CSI) to generate a compressed CSI, and transmits the generated compressed CSI to the decoder model as input to the decoder model. The decoder model decompresses and / or decodes the compressed CSI and outputs a new CSI (i.e., the recovered CSI) recovered from the compressed CSI.

[0150] Based on this scheme, when the second device uses the first information as input to the first model, it can accurately obtain the new first information recovered by the second sub-model after the first information has been processed by the first sub-model. This enables the first device to accurately obtain the recovery effect of the second sub-model on the measurement information of the first reference signal after the first operation (such as compression or encoding) is performed on the measurement information of the first reference signal according to the first sub-model.

[0151] In one possible implementation, the second information is used to determine a strategy for the first device to manage a second model, the second model including a third sub-model, the third sub-model being used to perform a first operation on the input information.

[0152] In other words, the first device can use the second information as auxiliary / reference information for managing the second model, and determine the strategy for associating the second model based on the similarity between the output of the first model and the first information.

[0153] For example, strategies for managing the second model may include any one of the following model management strategies: model training, model retraining, model updating, model activation, model deactivation, model monitoring, or model inference. The meanings of the aforementioned model management strategies can be found in the relevant descriptions in the foregoing embodiments.

[0154] For example, taking CSI-RS as the first reference signal, CSI as the first information, and the first device not yet training a second model as an example. After receiving the second information, the first device can obtain the similarity between the new CSI restored by the second device / first model after CSI compression and the original CSI (i.e., the first information), i.e., the recovery accuracy of the CSI by the second device / first model. If the similarity indicated by the second information is too low, the first device can determine that the model performance of the first model cannot meet the performance requirements of CSI compression in the current scenario, and CSI compression through the model in the current scenario is prone to CSI distortion. The first device can choose not to train the second model. If the similarity indicated by the second information is high, the first device can determine that the model performance of the first model can meet the performance requirements of CSI compression in the current scenario, and CSI compression through the model in the current scenario is beneficial to reducing the resource overhead caused by CSI reporting. The first device can use model training as a strategy to manage the second model and collect training data to train the second model.

[0155] For example, consider a scenario where the first reference signal is CSI-RS, the first information is CSI, and the first device has not yet activated the trained second model. After receiving the second information, the first device obtains the similarity between the output of the first model and the first information, i.e., the recovery accuracy of the CSI by the second device / first model. If the similarity indicated by the second information is too low, the first device can deactivate the model as a management strategy for the second model and not use the second model for CSI compression. If the similarity indicated by the second information is high, the first device can determine that the performance of the first sub-model can meet the performance requirements for CSI compression in the current scenario. The first device can then activate the model as a management strategy for the second model and compress the CSI through the second model.

[0156] Based on this scheme, the first device can use the second information as auxiliary information in the process of determining the strategy for managing the second model. Based on the recovery accuracy of the first model of the measurement information of the first reference information (i.e., the first information), the strategy for associating the second model is determined. On the one hand, determining the model management strategy based on the auxiliary information helps to reduce the complexity of determining the model management strategy. On the other hand, when the model management strategy is determined directly based on the auxiliary information, the first device does not need to collect a large number of samples, which helps to reduce the resource consumption of the first device in the process of managing the second model.

[0157] As one possible implementation, when determining the strategy for managing the second model based on the similarity indicated by the second information, the strategy for managing the second model can be determined based on the relationship between the similarity indicated by the second information and the first threshold.

[0158] For example, if the similarity indicated by the second information is greater than or equal to the first threshold, the strategy for managing the second model includes training the second model (i.e., the strategy for managing the second model includes model training, model retraining, or model updating); or, if the similarity indicated by the second information is less than the first threshold, the strategy for managing the second model includes deactivating the second model (i.e., the strategy for managing the second model includes model deactivation).

[0159] The first threshold can be predefined by a standard, predetermined by the second device, or indicated by the second device to the first device.

[0160] Based on the above scheme, the first device can send the measurement information of the first reference signal to the second device, and obtain the similarity between the output of the first model and the measurement information of the first reference signal after the first information is input into the first model (or the recovery accuracy of the first model for the measurement information of the first reference signal) according to the second information received from the second device. This allows the first device to use the recovery accuracy of the first model for the measurement information of the first reference signal as auxiliary information to determine the model management strategy. By using the second information as auxiliary information to determine the model management strategy of the first device, the complexity of the first device in determining the model management strategy is reduced, and the resource overhead in the process of determining the model management strategy is also reduced.

[0161] The overall process of the communication method provided in this application has been described above. The specific implementation of each step is described below.

[0162] In one possible implementation, in S501, when the first information is input into the second model, if the similarity between the output of the second model and the first information is less than a second threshold, the first device sends the first information to the second device.

[0163] For example, the second model includes a third sub-model and a fourth sub-model. The third sub-model is used to perform a first operation on the input information, and the fourth sub-model is used to perform a second operation on the input information. The input of the third sub-model includes the first information, and the input of the fourth sub-model includes the output of the third sub-model. The output of the second model includes the output of the fourth sub-model.

[0164] The implementation of the second model is similar to that of the first model in the aforementioned embodiments. Refer to the relevant descriptions in the aforementioned embodiments for details. The difference lies in that the second model is a model for the maintenance and management of the first device, while the first model is a model for the maintenance and management of the second device or other devices. These details will not be repeated here. Similarly, the meaning of the similarity between the output of the second model and the first information is similar to the meaning of the similarity between the output of the first model and the first information in the aforementioned embodiments. Refer to the relevant descriptions in the aforementioned embodiments for details for further explanation.

[0165] In other words, after acquiring the measurement information of the first reference signal, if the first device detects that the recovery accuracy of the second model for the measurement information of the first reference signal is insufficient (that is, when the first information is input into the second model, the similarity between the output of the second model and the first information is less than the second threshold), it sends the acquired measurement information of the first reference signal to the first device. The first device then sends the recovery accuracy of the first model for the measurement information of the first reference signal to the first device based on the acquired measurement information of the first reference signal, so that the first device can refer to the recovery accuracy of the first model for the measurement information of the first reference signal to determine the strategy for managing the second model.

[0166] For example, taking the case where the first reference signal is CSI-RS and the first information is CSI, and the first device has activated the second model, if the recovery accuracy of the second model for the acquired CSI is less than a second threshold, the first device sends the CSI to itself. Upon receiving the second information, it obtains the similarity between the output of the first model and the first information, i.e., the recovery accuracy of the second device / first model for the CSI. If the recovery accuracy of the second device / first model for the CSI is too low (e.g., less than the first threshold), the first device can determine that the first model also cannot accurately compress the CSI in the current scenario (or in other words, the first model cannot adapt to the data characteristics of the current scenario). Since the first model is usually maintained on the network device side, its training data is usually more comprehensive, and its model performance is better. Therefore, even if the first model cannot accurately compress the CSI... In the case of compressing CSI in the current scenario, the first device can deactivate the model as a strategy to manage the second model and not use the second model for CSI compression. If the recovery accuracy of the second device / first model for the CSI is high (e.g., greater than or equal to the first threshold), the first device can determine that the model performance of the first model can meet the performance requirements for compressing CSI in the current scenario. Since the model performance of the second model cannot meet the performance requirements for compressing CSI in the current scenario, the first device can determine that the training data of the second model is insufficient / the model is too simple, and use model update / retraining as a strategy to manage the second model. It collects training data to update or retrain the second model and compresses CSI through the new second model.

[0167] Furthermore, if the recovery accuracy of the CSI by the second device / first model is too low, the first device can also determine that the measurement information of the currently acquired first reference signal is unusable. The first device can release the first information, or retain the CSI and receive a compressed CSI sent by the second device after a certain period of time. This compressed CSI is generated by the second device based on the first information using the updated first sub-model after updating the second model. For example, releasing the first information can also be understood as the first device deleting the cached first information, or it can also be understood as the first device not using the first information as information for generating training data for the second model.

[0168] It is worth mentioning that the second threshold can be predefined by a standard, or it can be predetermined by the first device, or it can be indicated by the second device. Optionally, the size of the first threshold and the size of the second threshold can be the same or different; for example, the first threshold may be greater than the second threshold, or the first threshold may be equal to the second threshold, etc.

[0169] Based on this scheme, when the first device detects that the recovery accuracy of the measurement information of the first reference signal by the second model is poor, it can determine, based on the received second information, whether the poor recovery accuracy of the measurement information of the first reference signal is due to the poor training effect of the second model or due to the mismatch between the data features of the first reference signal and the second model in the current scenario. This helps to improve the accuracy of the first device in determining the strategy for managing the second model and further reduces the complexity of the first device in determining the model management strategy.

[0170] Optionally, if the second threshold is indicated by the second device, the second device sends the second threshold to the first device before S501. Accordingly, the first device receives the second threshold from the second device.

[0171] For example, when the first device is a terminal and the second device is a network device, the second device can send the second threshold to the first device by including it in broadcast system information, or by sending the second threshold to the first device via downlink control information (DCI). This application embodiment does not limit the method by which the second device sends the second threshold to the first device. Based on this scheme, the second threshold is configured by the second device, allowing the second device to flexibly adjust the second threshold according to the recovery accuracy of the first information by the first model.

[0172] Optionally, the first device may also send a seventh message to the second device. Correspondingly, the second device receives the seventh message from the first device. This seventh message includes the output of the third sub-model when the first message is input.

[0173] In other words, the first device sends the result of performing a first operation on the first information using the third sub-model to the second device. Upon receiving the result, the second device can perform a second operation on the seventh information based on the second sub-model, determine the similarity between the new first information recovered from the seventh information and the original first information, and send the similarity (denoted as similarity 1) between the recovered first information and the original first information to the first device. Upon receiving similarity 1, the first device can determine a strategy for managing the second model based on similarity 1.

[0174] For example, if the similarity of 1 is greater than or equal to the third threshold, it is determined that the second sub-model in the first model can effectively reconstruct the original first information based on the seventh information. The first device can then collect training data to retrain, update, or deactivate the fourth sub-model included in the second model. If the similarity is less than the third threshold, it is determined that the second sub-model in the first model cannot effectively reconstruct the original first information based on the seventh information. The first device can then collect training data to retrain, update, or deactivate the second model. Based on the above scheme, it is beneficial for the first device to accurately determine whether the poor accuracy of the second model in recovering the first information is due to training problems of the fourth sub-model, thereby improving the accuracy of the first device in determining the strategy for associating the second model.

[0175] In one possible implementation, the second device sends third information to the first device. Correspondingly, the first device receives the third information from the second device. The third information includes the output of the first sub-model when the first information was input into the first model.

[0176] For example, the third information includes the output of the first sub-model when the first information is input into the first model. This can be understood as the third information including the result of performing the first operation on the first information, or in other words, the third information is determined based on the result of performing the first operation on the first information. For example, if the first information is CSI, then the third information may include compressed CSI generated after compressing and encoding the CSI through the encoder model (i.e., the first sub-model).

[0177] In other words, after receiving the first information sent by the first device, the second device can input the first information into the first model, and generate the third information based on the result of the first operation on the first information by the first sub-model, and send the third information to the first device, so that the first device can obtain the result of the first operation on the first information by the first sub-model, and facilitate the first device to manage the second model based on the third information.

[0178] For example, if the first device determines that the management strategy of the second model is model monitoring, it can use the third information and the output of the second model when the first information is input into the second model as labels for the first information to generate a record of abnormal performance indicators of the second model; or, if the first device determines that the management strategy of the second model is model update / training / retraining, it can use the third information as a label for the first information to generate a training data, that is, generate a training data based on the first information and the third information, which includes the first information and the third information, with the third information being the label of the first information.

[0179] As one possible implementation, the second device sends third information to the first device only if the similarity indicated by the second information is greater than or equal to a first threshold. That is, the second device will only send the third information to the first device if it detects that the recovery accuracy of the first model for the first information meets the requirements. If the similarity indicated by the second information is less than the first threshold, the second device may not send the third information to the first device, or, after updating the first model, it may send the result of performing the first operation on the first information based on the updated first sub-model to the first device.

[0180] Based on this scheme, since the second device will send the third information for managing the second model to the first device when the recovery accuracy of the first model meets the requirements, it is beneficial to reduce the number of meaningless information exchanges between the first and second devices, and it is also convenient for the first device to accurately obtain the third information that can be used to manage the second model, thereby further reducing the model management complexity of the first device.

[0181] Optionally, when the second device sends third information to the first device, the second device may also send information indicating the first identifier to the first device, the first identifier indicating the function of the third information in model management.

[0182] For example, taking the case where identifier 1 indicates that the third information is used for model monitoring and identifier 2 indicates that the third information is used for model retraining, when the second device indicates to the first device that the first identifier is identifier 1, the first device, after receiving the third information, generates an anomaly record for monitoring the performance indicators of the second model based on the first information and the third information; when the second device indicates to the first device that the first identifier is identifier 2, the first device, after receiving the third information, generates training data for training the second model based on the first information and the third information. Based on this scheme, the first device can directly determine the function of the third information or even the management strategy of the second model based on the obtained first identifier, which helps to further reduce the complexity of model management for the first device.

[0183] It is worth mentioning that the information indicating the first identifier and the third information can be carried in the same message. For example, the information indicating the first identifier and the third information can both be carried in DCI, or they can be carried in different messages, without restriction.

[0184] In one possible implementation, the second device sends fourth information to the first device. Correspondingly, the first device receives the fourth information from the second device. The fourth information indicates that the third information is associated with the first reference signal or the first information.

[0185] For example, the fourth information indicating the association between the third information and the first reference signal can be understood as the fourth information including the association between the third information and the first reference signal; or, it can also be understood as the fourth information including the identifier of the reference signal (i.e., the first reference signal) associated with the third information. The meaning of the fourth information indicating the association between the third information and the first information is similar and can be referred to the above description.

[0186] In other words, when the second device sends the third information to the first device, it will also send the correlation between the third information and the first reference signal or the first information to the first device through the fourth information, so that the first device can accurately obtain that the third information is generated based on the measurement information of the first reference signal or the first information, which significantly reduces the first device from associating the third information with the measurement information of other reference signals or with information including the measurement information generated based on other reference signals.

[0187] For example, taking the fourth information as including a reference signal associated with the third information (i.e., the first reference signal), the fourth information can be directly implemented through a reserved field in the message carrying the third information. This reserved field contains an identifier of the first reference signal or an identifier of the resources occupied by the first reference signal. After receiving the fourth information, the first device can determine that the third information is determined based on the measurement information of the first reference signal according to the identifier contained in the reserved field.

[0188] As one possible implementation, the fourth information can be carried through the same message or channel as the third information. For example, the fourth information and the third information can be carried through the same DCI, with the third information and the fourth information occupying different fields, or the third information and the fourth information can be carried through different control information multiplexed through the same control channel.

[0189] It is worth mentioning that since the third information is obtained by performing the first operation on the first information through the first sub-model, the first sub-model may determine the same third information based on different first information. When the fourth information and the third information are carried by the same message, the message may include the correlation between other reference signals and the third information.

[0190] Taking the first information as CSI, the third information as compressed CSI, and the fourth information and the third information as carried in the same DCI as an example, when the second device indicates that the compressed CSI is associated with at least one CSI-RS through the fourth information, referring to Figure 7(a), the second device sends three reference signals, CSI-RS1, CSI-RS2, and CSI-RS3, to the first device, and the first device sends the CSI determined based on the different reference signals to the second device through a message. When the second device sends the DCI carrying the third and fourth information to the first device, if the similarity between the recovered new CSI-2 and the original CSI-2 after inputting CSI-2 into the first model is less than a first threshold, then the DCI only includes compressed CSI-1 corresponding to CSI-RS1 and compressed CSI-3 corresponding to CSI-RS3. The format of the issued DCI can be as shown in Figure 7(b), where the field carrying the identifier of the CSI-RS associated with compressed CSI-1 includes the identifier of CSI-RS1, and the field carrying the identifier of the CSI-RS associated with compressed CSI-3 includes the identifier of CSI-RS3; or, as shown in Figure 7(c), the field carrying the compressed CSI associated with CSI-RS1 includes compressed CSI-1, the field carrying the compressed CSI associated with CSI-RS2 is set to blank or negative acknowledgement (NACK), and the field carrying the compressed CSI associated with CSI-RS3 includes compressed CSI-3.

[0191] If, after inputting three CSIs into the first model, the similarity between the output of the first model and the input CSIs is greater than the first threshold, and the compressed CSI-1 corresponding to CSI-1 and the compressed CSI-3 corresponding to CSI-3 are the same, the format of the issued DCI can be as shown in Figure 7(d). The field carrying the identifier of the CSI-RS associated with compressed CSI-1 includes the identifier of CSI-RS1 and the identifier of CSI-RS3, and the field carrying the identifier of the CSI-RS associated with compressed CSI-2 includes the identifier of CSI-RS2.

[0192] In other words, the fourth information can indicate multiple different first information (or measurement information of multiple different reference signals) associated with the third information.

[0193] Furthermore, the association between the third information and the first reference signal or the first information can also be determined by the resources occupied by the third information or the timing of its transmission. For example, if the first device receives the third information after a second period of time following the transmission of the first information, then the third information is associated with the first reference signal or the first information. In other words, the second device does not need to send an additional fourth information to the first device to indicate the association between the third information and the first information or the first reference signal, which helps to reduce the amount of data exchanged between the first and second devices.

[0194] For example, referring to Figure 7(e), if the time elapsed after the first device sends CSI-1 reaches the time interval T (i.e., the second time interval), the second device sends a compressed CSI-1 determined according to CSI-1 to the first device. After receiving the compressed CSI-1, the first device determines the CSI associated with the compressed CSI-1 as CSI-1, or the CSI-RS associated with the compressed CSI-1 as CSI-RS1, based on the resources occupied by the compressed CSI-1. The time interval T can be defined by a standard or predetermined by the first and second devices.

[0195] In one possible implementation, the first device sends fifth information to the second device. Correspondingly, the second device receives the fifth information from the first device. The fifth information indicates at least one of the following: model complexity, model backbone, model structure, model output information, model input information, or characteristics of the model implementation.

[0196] For example, model complexity can be understood as the number of operations performed by the first sub-model during the execution of the first operation, such as the number of multiplication and / or addition operations; the model backbone can be understood as the basic framework type of the model, such as the Transformer model or the convolutional neural network model. The model structure can include the number of model layers (e.g., the number of layers in a neural network used to implement different functions), the number of neural networks included in the model, etc.; the model output information can include the length of the model output (e.g., the number of bits of the output of the first sub-model or the number of bits of the third information), the type of the model output (e.g., the third information is the result of the first information after the first operation, or the third information is the result of quantization processing of the data obtained by the first information after the first operation), etc.; the model input information can include the length of the model input (e.g., the number of bits of information used as input in the training data during the training of the first sub-model or the number of bits of the first information), the type of model input (e.g., the input of the first sub-model is the first information, or the input of the first sub-model is the feature extraction result of the first information), etc.; the characteristics implemented by the model can be understood as the specific type of the first operation performed by the first sub-model, such as spatial and frequency domain compression (SF) of the first information, time, spatial and frequency domain compression (TSF) of the first information, prediction and compression of the first information in the time, spatial and frequency domains, or joint source-channel coding (JSCC) of the first information, etc.

[0197] It is worth mentioning that the characteristics of the model implementation can also be referred to as the functions or algorithms of the model implementation, and these terms can be used interchangeably in the embodiments of this application.

[0198] For example, the fifth information may include an identifier indicating at least one of the above information of the first sub-model, such as an identifier of the model complexity of the first sub-model, an identifier of the model framework of the first sub-model, an identifier of the features implemented by the first sub-model, or an identifier of the length of the output of the first sub-model, etc. Alternatively, the fifth information may also directly include at least one of the above information of the first sub-model, without limitation.

[0199] In other words, while the second device sends the third information to the first device, it will also send the fifth information to the first device, sending at least one model attribute of the first sub-model to the first device. This allows the first device to combine the third and fifth information to determine the management strategy for the second model during the management process.

[0200] Optionally, the fifth information can be carried in the same message as the third information, or the fifth information can be carried in different messages. For example, taking the first information as CSI, the third information as compressed CSI, and the fifth information as an identifier of the model complexity of the first sub-model as an example, referring to Figure 8(a), after the second device sends CSI-RS to the first device, the first device generates and sends CSI-1 to the second device based on the measurement of CSI-RS. After receiving the CSI-1 sent by the first device, if the recovery accuracy of the first model on CSI-1 is greater than the first threshold, the second device sends the compressed CSI-1 obtained after the first sub-model performs the first operation on CSI-1 as the third information to the first device, and sends the identifier 'a' indicating the model complexity of the first sub-model as the fifth information to the first device in the same message carrying the third information.

[0201] Then, the first device determines the strategy for managing the second model based on the received third and fifth information. Taking the model complexity of the first sub-model as an example, which includes the identifier a1 corresponding to high complexity and the identifier a2 corresponding to low complexity, after receiving the fifth and third information, the first device can generate training data for training the third sub-model based on the first and third information, and mark this training data as training data for training the high-complexity third sub-model based on the fifth information (i.e., identifier a). Then, if the management strategy for the second model is determined to be training the third sub-model, or retraining the third sub-model, the first device can train a high-complexity third sub-model based on this training data and multiple training data.

[0202] Referring to Figure 8(b), when the third information is generated by a low-complexity first sub-model, the first device can train a low-complexity third sub-model using the training data generated from the first and third information, based on the third and fifth information. Conversely, when the third information is generated by a high-complexity first sub-model, the first device can train a high-complexity third sub-model using the training data generated from the first and third information, based on the third and fifth information. This reduces the probability that the first device will train a third sub-model with a different complexity than the first sub-model, and increases the probability that the training efficiency and performance indicators of the third sub-model meet the requirements.

[0203] It is worth mentioning that the above embodiment uses the fifth information to indicate one model attribute of the first sub-model as an example. The fifth information can also indicate multiple model attributes of the first sub-model. The implementation of the fifth information indicating at least one other model attribute of the first sub-model is similar to the implementation of the fifth information indicating the model complexity of the first sub-model, and will not be described again here.

[0204] Based on this scheme, the first device can determine a model management strategy that is more in line with the application scenario based on the fifth information. On the one hand, this helps to reduce the complexity of the first device in determining the model management strategy, and on the other hand, it helps to improve the accuracy of the first device's model management and reduce the resource consumption of the first device in the model management process.

[0205] In one possible implementation, the second device sends a sixth message to the first device. Correspondingly, the first device receives the sixth message from the second device. The sixth message indicates the release of the first message.

[0206] For example, the sixth information indicating the release of the first information can be understood as the sixth information indicating the deletion of the first information, or it can also be understood as the sixth information indicating that the first information cannot be used to generate training data for training, updating, or retraining the second model.

[0207] For example, the sixth message can be a NACK message, other response messages defined by the standard, or a response message pre-agreed upon by the first and second devices.

[0208] In other words, the second device can reduce the first device's use of the first information as sample data in the process of managing the second model by sending an instruction to the first device to release the sixth information of the first information, which is beneficial to improving the model management effect of the first device.

[0209] As one possible implementation, if the similarity indicated by the second information is less than a first threshold, the second device sends a sixth piece of information to the first device.

[0210] As another possible implementation, if the similarity indicated by the second information is less than a first threshold, the second device terminates the process on its side. The first device can determine whether to release the first information based on whether it receives the third information. For example, if the third information is not received within a first time period after sending the first information, the first device releases the first information. The meaning of the third information can be referred to the relevant description in the foregoing embodiments. The first time period can be a standard definition or can be predetermined by the first and second devices.

[0211] Taking CSI-RS as the first reference signal and CSI as the first information as an example. Referring to Figure 9, which is a flowchart illustrating a process where a first device manages a second model based on second information, the second device first sends CSI-RS to the first device. The first device generates CSI based on the measurement information obtained from the strategy CSI-RS and sends the generated CSI to the second device. After receiving the CSI, the second device inputs it into the first model and obtains the similarity between the output of the first model and the CSI when the CSI is input. It then sends this similarity between the output of the first model and the CSI to the first device via the second information. Finally, based on the similarity indicated by the second information, the second device determines whether to send third or sixth information to the first device. For example, if the similarity indicated by the second information is greater than the first threshold, the compressed CSI (i.e., the third information) output by the first sub-model when the CSI is input to the second device is sent to the second device. After receiving the compressed CSI, the second device can use the compressed CSI as the label of the CSI and generate training data for training the second model based on the first and third information. If the similarity indicated by the second information is less than the first threshold, a NACK message (i.e., the sixth information) is sent to the second device. After receiving the NACK message, the second device releases the CSI.

[0212] Based on this scheme, the first device can use information from the second device as auxiliary information for managing the second model. The first device can determine the management strategy for the second model based on the information from the second device. Compared with the method of collecting a large amount of sample data to monitor model performance in order to determine the management strategy, this significantly reduces the resource overhead and complexity of the first device in determining the model management strategy.

[0213] Furthermore, it is worth mentioning that the above embodiments of this application all illustrate the following example: after receiving the first information sent by the first device, the second device first sends the second information to the first device via S502, and then sends the third, fourth, and fifth information, etc. In application, S502 can also be an optional step. That is, after receiving the first information sent by the first device, the second device does not execute S502 (i.e., does not send the second information to the first device), and directly sends the third or sixth information, etc., to the first device, so that the first device uses the third or sixth information as auxiliary information to help determine the model management strategy.

[0214] For example, taking the first reference signal as CSI-RS and the first information as CSI, if the second device sends the third information (i.e., compressed CSI) or the sixth information directly to the first device after receiving the first information, the information interaction process between the first device and the second device is similar to the process shown in Figure 9. The difference is that the second device does not perform the step of sending the second information, but directly selects to send the third information or the sixth information to the first device based on the similarity between the output of the first model and the CSI when the CSI sent by the first device is input into the first model.

[0215] Furthermore, when the second device sends a third message to the first device, it can also send other messages such as a fourth or fifth message to the first device. For example, if the second device also sends a fifth message to the first device, the interaction process between the first and second devices is similar to that in Figure 8(a).

[0216] It is worth mentioning that the meanings of the first, second, third, fourth, fifth, and sixth information, as well as the implementation method of the second device sending the fourth and fifth information to the first device when the third information is sent, can be referred to the relevant descriptions in the foregoing embodiments, and will not be repeated here.

[0217] Optionally, the second device may also choose whether to execute S502 based on the request of the first device.

[0218] Based on the above scheme, after receiving the first information from the first device, the second device can provide the first device with auxiliary information for determining the model management strategy by sending the third or sixth information to the first device. This enables the first device to determine the model management strategy based on the auxiliary information, which helps to reduce the difficulty for the first device to determine the model management strategy.

[0219] The method provided in this application has been described above. In addition, this application also provides a communication device for implementing the functions described in the above method embodiments.

[0220] It is understood that, in order to achieve the aforementioned functions, the communication device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by 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 this application.

[0221] This application embodiment can divide the communication device into functional modules according to the above method embodiment. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0222] Figure 10 shows a schematic diagram of a communication device 100. The communication device 100 includes a processing module 1001 and a transceiver module 1002. The communication device 100 can be used to implement the functions of the first device or the second device described above.

[0223] In some embodiments, the communication device 100 may further include a storage module (not shown in FIG10) for storing program instructions and data.

[0224] In some embodiments, the transceiver module 1002, also referred to as a transceiver unit, is used to implement sending and / or receiving functions. The transceiver module 1002 may consist of a transceiver circuit, a transceiver, a transceiver unit, or a communication interface.

[0225] In some embodiments, the transceiver module 1002 may include a receiving module and a sending module, respectively configured to perform the receiving and sending steps performed by the first device or the second device in the above method embodiments, and / or other processes to support the technology described herein; the processing module 1001 may be configured to perform the processing steps performed by the first device or the second device in the above method embodiments, and / or other processes to support the technology described herein.

[0226] When the communication device 100 is used to implement the function of the first device, the processing module 1001 is used to send first information to the second device through the transceiver module 1002. The first information includes measurement information of the first reference signal. The second information receives second information from the second device. The second information indicates the similarity between the output of the first model and the first information when the first information is input into the first model.

[0227] In one possible implementation, the transceiver module 1002 is used to receive third information from the second device, the third information including the output of the first sub-model when the first information is input into the first model, and the third information is used to manage the second model.

[0228] In one possible implementation, the transceiver module 1002 is used to receive fourth information from the second device, the fourth information indicating that the third information is associated with the first reference signal or the first information.

[0229] In one possible implementation, the transceiver module 1002 is configured to receive fifth information from the second device, the fifth information indicating at least one of the following information of the first sub-model: model complexity, model architecture (backboom), number of model layers, number of neural networks contained in the model, length of model output, length of model input, or characteristics implemented by the model.

[0230] In one possible implementation, the transceiver module 1002 is used to receive a sixth message from the second device, the sixth message indicating the release of the first message.

[0231] In one possible implementation, the processing module 1001 is configured to release the first information if no third information is received within a first time period after the first information is sent, wherein the third information includes the output of the first sub-model when the first information is input into the first model.

[0232] In one possible implementation, the processing module 1001 is used to send the first information to the second device via the transceiver module 1002 when the similarity between the output of the second model and the first information is less than a second threshold when the first information is input into the second model; wherein the second model includes a third sub-model and a fourth sub-model, the third sub-model is used to perform a first operation on the input information, the fourth sub-model is used to perform a second operation on the input information, the input of the third sub-model includes the first information, the input of the fourth sub-model includes the output of the third sub-model, and the output of the second model includes the output of the fourth sub-model.

[0233] In one possible implementation, the transceiver module 1002 is used to receive a second threshold from a second device.

[0234] When the communication device 100 is used to implement the function of the second device, the processing module 1001 is used to receive first information from the first device through the transceiver module 1002, the first information including measurement information of the first reference signal; and send second information to the first device, the second information indicating the similarity between the output of the first model and the first information when the first information is input into the first model.

[0235] In one possible implementation, the transceiver module 1002 is used to send third information to the first device, the third information including the output of the first sub-model when the first information is input into the first model.

[0236] In one possible implementation, the processing module 1001 is used to send third information to the first device through the transceiver module 1002 when the similarity is greater than or equal to a first threshold.

[0237] In one possible implementation, the transceiver module 1002 is used to send fourth information to the first device, the fourth information indicating that the third information is associated with the first reference signal or the first information.

[0238] In one possible implementation, the transceiver module 1002 is used to send fifth information to the first device, the fifth information indicating at least one of the following information of the first sub-model: model complexity, model architecture (backboom), number of model layers, number of neural networks contained in the model, length of model output, length of model input, or characteristics implemented by the model.

[0239] In one possible implementation, the transceiver module 1002 is used to send a sixth message to the first device, the sixth message indicating the release of the first message.

[0240] In one possible implementation, the transceiver module 1002 is used to send a second threshold to the first device.

[0241] All relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0242] In this application, the communication device 100 can be presented in an integrated manner by dividing it into various functional modules. Here, "module" can refer to an application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, integrated logic circuits, and / or other devices that can provide the above functions.

[0243] In some embodiments, when the communication device 100 in FIG10 is a chip or chip system, the function / implementation process of the transceiver module 1002 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 1001 can be implemented through the processor (or processing circuit) of the chip or chip system.

[0244] Since the communication device 100 provided in this embodiment can execute the above method, the technical effects it can achieve can be referred to the above method embodiment, and will not be repeated here.

[0245] As a possible product form, the first or second device described in the embodiments of this 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 circuits, or any combination of circuits capable of performing the various functions described throughout this application.

[0246] As another possible product form, the first or second device described in this application embodiment can be implemented using a general bus architecture. For ease of explanation, refer to FIG11, which is a schematic diagram of the structure of a communication device 1100 provided in an embodiment of this application. The communication device 1100 includes a processor 1101 and a transceiver 1102. The communication device 1100 can be a first device, or a chip or chip system therein; or, the communication device 1100 can be a second device, or a chip or module therein. FIG11 only shows the main components of the communication device 1100. In addition to the processor 1101 and transceiver 1102, the communication device may further include a memory 1103 and input / output devices (not shown in the figure).

[0247] Optionally, the processor 1101 is mainly used to process communication protocols and communication data, control the entire communication device, execute software programs, and process the data of the software programs, thereby implementing the methods provided in the above-described method embodiments. The memory 1103 is mainly used to store software programs and data. The transceiver 1102 may include a radio frequency (RF) circuit and an antenna. The RF circuit is mainly used for converting baseband signals to RF signals and processing RF signals. The antenna is mainly used for transmitting and receiving RF signals in the form of electromagnetic waves. Input / output devices, such as touch screens, displays, and keyboards, are mainly used to receive user input data and output data to the user.

[0248] Optionally, the processor 1101, transceiver 1102, and memory 1103 can be connected via a communication bus.

[0249] When the communication device is powered on, the processor 1101 can read the software program in the memory 1103, interpret and execute the instructions of the software program, and process the data of the software program. When data needs to be transmitted wirelessly, the processor 1101 performs baseband processing on the data to be transmitted and outputs the baseband signal to the radio frequency (RF) circuit. The RF circuit processes the baseband signal and transmits the RF signal outward in the form of electromagnetic waves through the antenna. When data is sent to the communication device, the RF circuit receives the RF signal through the antenna, converts the RF signal into a baseband signal, and outputs the baseband signal to the processor 1101. The processor 1101 converts the baseband signal into data and processes the data.

[0250] In another implementation, the radio frequency circuitry and antenna can be set up independently of the processor performing baseband processing. For example, in a distributed scenario, the radio frequency circuitry and antenna can be arranged remotely, independent of the communication device.

[0251] In some embodiments, those skilled in the art will recognize that the above-described communication device 100 can take the form of the communication device 1100 shown in FIG11 in terms of hardware implementation.

[0252] As an example, the function / implementation process of the processing module 1001 in Figure 10 can be implemented by the processor 1101 in the communication device 1100 shown in Figure 11 calling computer execution instructions stored in the memory 1103. The function / implementation process of the transceiver module 1002 in Figure 10 can be implemented by the transceiver 1102 in the communication device 1100 shown in Figure 11.

[0253] As another possible product form, the first device or the second device in this application may adopt the composition structure shown in FIG12, or include the components shown in FIG12. FIG12 is a schematic diagram of the composition of a communication device 1200 provided in this application. The communication device 1200 may be the first device or a chip or system-on-a-chip in the first device; or, it may be the second device or a module or chip or system-on-a-chip in the second device.

[0254] As shown in Figure 12, the communication device 1200 includes at least one processor 1201 and at least one communication interface (Figure 12 is merely an example illustrating the inclusion of a communication interface 1204 and a processor 1201). Optionally, the communication device 1200 may also include a communication bus 1202 and a memory 1203.

[0255] Processor 1201 can be a general-purpose central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a PLD, or any combination thereof. Processor 1201 can also be other devices with processing functions, such as circuits, devices, or software modules, without limitation.

[0256] The communication bus 1202 is used to connect different components in the communication device 1200, enabling communication between them. The communication bus 1202 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used in Figure 12, but this does not indicate that there is only one bus or one type of bus.

[0257] Communication interface 1204 is used for communicating with other devices or communication networks. For example, communication interface 1204 can be a module, circuit, transceiver, or any device capable of communication. Optionally, the communication interface 1204 can also be an input / output interface located within processor 1201, used to implement signal input and signal output for the processor.

[0258] The memory 1203 may be a device with storage function, used to store instructions and / or data. The instructions may be computer programs.

[0259] For example, the memory 1203 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and / or instructions; it may also be a random access memory (RAM) or other type of dynamic storage device capable of storing information and / or instructions; it may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, etc., without limitation.

[0260] It should be noted that the memory 1203 can exist independently of the processor 1201, or it can be integrated with the processor 1201. The memory 1203 can be located inside or outside the communication device 1200, without limitation. The processor 1201 can be used to execute the instructions stored in the memory 1203 to implement the methods provided in the following embodiments of this application.

[0261] As an optional implementation, the communication device 1200 may also include an output device 1205 and an input device 1206. The output device 1205 communicates with the processor 1201 and can display information in various ways. For example, the output device 1205 may 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 1206 communicates with the processor 1201 and can receive user input in various ways. For example, the input device 1206 may be a mouse, keyboard, touchscreen device, or sensing device, etc.

[0262] In some embodiments, those skilled in the art will recognize that the communication device 100 shown in FIG10 can take the form of the communication device 1200 shown in FIG12 in terms of hardware implementation.

[0263] As an example, the function / implementation process of the processing module 901 in Figure 10 can be implemented by the processor 1201 in the communication device 1200 shown in Figure 12 calling computer execution instructions stored in the memory 1203. The function / implementation process of the transceiver module 902 in Figure 9 can be implemented by the communication interface 1204 in the communication device 1200 shown in Figure 12.

[0264] It should be noted that the structure shown in Figure 12 does not constitute a specific limitation on the first or second device. For example, in other embodiments of this application, the first or second device may include more or fewer components than shown in the figure, or combine some components, or split some components, or have different component arrangements. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0265] In some embodiments, this application also provides a communication device, which includes a processor for implementing the methods in any of the above method embodiments.

[0266] As one possible implementation, the communication device also includes a memory. This memory stores necessary computer programs and data. The computer program may include instructions, which a processor can invoke to instruct the communication device to execute the methods described in any of the above method embodiments. Alternatively, the memory may not be present in the communication device.

[0267] As another possible implementation, the communication device also includes an interface circuit, which is a code / data read / write interface circuit, used to receive computer execution instructions (which are stored in memory and may be read directly from memory or may be transmitted through other devices) and transmit them to the processor.

[0268] As another possible implementation, the communication device also includes a communication interface for communicating with modules outside the communication device.

[0269] It is understood that the communication device can be a chip or a chip system. When the communication device is a chip system, it can be composed of chips or may include chips and other discrete devices. This application does not specifically limit this.

[0270] This application also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a computer, implements the functions of any of the above-described method embodiments.

[0271] This application also provides a computer program product that, when executed by a computer, implements the functions of any of the above method embodiments.

[0272] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0273] It is understood that the systems, apparatuses, and methods described in this application can also be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0274] The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. The components shown as units may or may not be physical units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0275] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0276] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This 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 this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive (SSD)). In this embodiment, the computer may include the aforementioned apparatus.

[0277] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0278] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the scope of this application. Accordingly, this specification and drawings are merely illustrative descriptions of the application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Thus, if such modifications and modifications fall within the scope of the claims and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A communication method, characterized in that, Applied to a first device, the method includes: Send first information to the second device, the first information including measurement information of the first reference signal; Receive second information from a second device, the second information indicating the similarity between the output of the first model and the first information when the first information is input into the first model.

2. The method according to claim 1, characterized in that, The first model includes a first sub-model and a second sub-model. The input of the first sub-model includes the first information, the input of the second sub-model includes the output of the first sub-model, and the output of the first model includes the output of the second sub-model. The first sub-model is used to perform a first operation on the input information, and the second sub-model is used to perform a second operation on the input information. The second operation is the inverse operation of the first operation.

3. The method according to claim 2, characterized in that, The second information is used to determine the strategy of the first device managing the second model, the second model including a third sub-model, the third sub-model being used to perform the first operation on the input information.

4. The method according to claim 3, characterized in that, The method further includes: Receive third information from the second device, the third information including the output of the first sub-model when the first information is input into the first model, the third information being used to manage the second model.

5. The method according to claim 4, characterized in that, The method further includes: Receive fourth information from the second device, the fourth information indicating that the third information is associated with the first reference signal or the first information.

6. The method according to any one of claims 2-5, characterized in that, The method further includes: Receive fifth information from the second device, the fifth information indicating at least one of the following information of the first sub-model: model complexity, model backbone, model structure, model output information, model input information, or characteristics of model implementation.

7. The method according to claim 3, characterized in that, The method further includes: A sixth message is received from the second device, the sixth message indicating the release of the first message.

8. The method according to claim 3, characterized in that, The method further includes: If no third information is received within a first time period after the first information is sent, the first information is released. The third information includes the output of the first sub-model when the first information is input into the first model.

9. The method according to any one of claims 2-8, characterized in that, Sending the first information to the second device includes: When the first information is input into the second model, if the similarity between the output of the second model and the first information is less than a second threshold, the first information is sent to the second device. The second model includes a third sub-model and a fourth sub-model. The third sub-model is used to perform the first operation on the input information, and the fourth sub-model is used to perform the second operation on the input information. The input of the third sub-model includes the first information, and the input of the fourth sub-model includes the output of the third sub-model. The output of the second model includes the output of the fourth sub-model.

10. The method according to claim 9, characterized in that, The method further includes: Receive the second threshold from the second device.

11. The method according to any one of claims 1-10, characterized in that, If the similarity is greater than or equal to a first threshold, the strategy includes training the second model; or, if the similarity is less than the first threshold, the strategy includes deactivating the second model.

12. A communication method, characterized in that, Applied to a second device, the method includes: Receive first information from a first device, the first information including measurement information of a first reference signal; Send a second message to the first device, the second message indicating the similarity between the output of the first model and the first message when the first message is input into the first model.

13. The method according to claim 12, characterized in that, The first model includes a first sub-model and a second sub-model. The input of the first sub-model includes the first information, the input of the second sub-model includes the output of the first sub-model, and the output of the first model includes the output of the second sub-model. The first sub-model is used to perform a first operation on the input information, and the second sub-model is used to perform a second operation on the input information. The second operation is the inverse operation of the first operation.

14. The method according to claim 12 or 13, characterized in that, The method further includes: Send third information to the first device, the third information including the output of the first sub-model when the first information is input into the first model.

15. The method according to claim 14, characterized in that, The sending of the third information to the first device includes: If the similarity is greater than or equal to the first threshold, the third information is sent to the first device.

16. The method according to claim 14 or 15, characterized in that, The method further includes: A fourth message is sent to the first device, the fourth message indicating that the third message is associated with the first reference signal or the first message.

17. The method according to any one of claims 13-16, characterized in that, The method further includes: Send a fifth message to the first device, the fifth message indicating at least one of the following information of the first sub-model: model complexity, model backbone, model structure, model output information, model input information, or characteristics of model implementation.

18. The method according to claim 12, characterized in that, The method further includes: A sixth message is sent to the first device, the sixth message indicating the release of the first message.

19. The method according to any one of claims 12-18, characterized in that, The method further includes: Send the second threshold to the first device.

20. A communication method, characterized in that, Applied to a first device, the method includes: Send first information to the second device, the first information including measurement information of the first reference signal; Receive third or sixth information from the second device, the third information including the output of the first sub-model when the first information is input into the first model, the first sub-model being used to perform a first operation on the input information, and the sixth information indicating the release of the first information.

21. The method according to claim 20, characterized in that, The first model includes a first sub-model and a second sub-model. The input of the first sub-model includes the first information, the input of the second sub-model includes the output of the first sub-model, and the output of the first model includes the output of the second sub-model. The first sub-model is used to perform a first operation on the input information, and the second sub-model is used to perform a second operation on the input information. The second operation is the inverse operation of the first operation.

22. The method according to claim 20 or 21, characterized in that, The method further includes: Receive fourth information from the second device, the fourth information indicating that the third information is associated with the first reference signal or the first information.

23. The method according to any one of claims 20-22, characterized in that, The method further includes: Receive fifth information from the second device, the fifth information indicating at least one of the following information of the first sub-model: model complexity, model backbone, model structure, model output information, model input information, or characteristics of model implementation.

24. The method according to any one of claims 20-23, characterized in that, Send the first message to the second device, including: When the first information is input into the second model, if the similarity between the output of the second model and the first information is less than a second threshold, the first information is sent to the second device. The second model includes a third sub-model and a fourth sub-model. The third sub-model is used to perform the first operation on the input information, and the fourth sub-model is used to perform the second operation on the input information. The input of the third sub-model includes the first information, and the input of the fourth sub-model includes the output of the third sub-model. The output of the second model includes the output of the fourth sub-model.

25. The method according to any one of claims 20-24, characterized in that, The method further includes: Receive a second threshold from the second device.

26. A method of communication, comprising: Applied to a second device, the method includes: Receive first information from a first device, the first information including measurement information of a first reference signal; Send a third message or a sixth message to the first device. The third message includes the output of the first sub-model when the first message is input into the first model. The first sub-model is used to perform a first operation on the input message. The sixth message indicates the release of the first message.

27. The method according to claim 26, characterized in that, The first model includes a first sub-model and a second sub-model. The input of the first sub-model includes the first information, the input of the second sub-model includes the output of the first sub-model, and the output of the first model includes the output of the second sub-model. The first sub-model is used to perform a first operation on the input information, and the second sub-model is used to perform a second operation on the input information. The second operation is the inverse operation of the first operation.

28. The method according to claim 26 or 27, characterized in that, Sending third information to the first device, including: When the first information is input into the first model, if the similarity between the output of the first model and the first information is greater than or equal to a first threshold, the third information is sent to the first device.

29. The method according to any one of claims 26-28, characterized in that, Send the sixth message to the first device, including: When the first information is input into the first model, if the similarity between the output of the first model and the first information is less than a first threshold, the sixth information is sent to the first device.

30. The method according to any one of claims 26-29, characterized in that, The method further includes: A fourth message is sent to the first device, the fourth message indicating that the third message is associated with the first reference signal or the first message.

31. The method according to any one of claims 26-30, characterized in that, The method further includes: Send a fifth message to the first device, the fifth message indicating at least one of the following information of the first sub-model: model complexity, model backbone, model structure, model output information, model input information, or characteristics of model implementation.

32. The method according to any one of claims 26-31, characterized in that, The method further includes: Send the second threshold to the first device.

33. A communication device, characterized in that, The communication device includes a module for performing the method as described in any one of claims 1-11, or includes a module for performing the method as described in any one of claims 12-19, or includes a module for performing the method as described in any one of claims 20-25, or includes a module for performing the method as described in any one of claims 26-32.

34. A communication device, characterized in that, 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 claimed in any one of claims 1-11, or to cause the communication device to perform the method as claimed in any one of claims 12-19, or to cause the communication device to perform the method as claimed in any one of claims 20-25, or to cause the communication device to perform the method as claimed in any one of claims 26-32.

35. A chip or chip system, characterized in that, 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 claimed in any one of claims 1-11 to be executed, or cause the method as claimed in any one of claims 12-19 to be executed, or cause the method as claimed in any one of claims 20-25 to be executed, or cause the method as claimed in any one of claims 26-32 to be executed.

36. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions or programs that, when executed on a computer, 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 12-19 to be performed, or cause the method as described in any one of claims 20-25 to be performed, or cause the method as described in any one of claims 26-32 to be performed.

37. A computer program product, characterized in that, The computer program product includes computer instructions; when some or all of the computer instructions are executed on a computer, they cause the method of any one of claims 1-11 to be performed, or the method of any one of claims 12-19 to be performed, or the method of any one of claims 20-25 to be performed, or the method of any one of claims 26-32 to be performed.