Communication method and related equipment

Abstract

The invention provides a communication method and related equipment, which are used for realizing determination and deployment of an AI model in a communication network through interaction between different communication devices, so that the computing power of the communication devices can be applied to processing of the AI model. In the method, after a first communication device transmits first information for determining a first AI model group, the first communication device may receive second information including a model parameter of the first AI model group or a model parameter of a first AI model in the first AI model group, the first AI model set includes a first AI model deployed in a first communication device and a second AI model deployed in a second communication device.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a communication method and related devices. Background Art

[0002] Wireless communication can be a transmission communication between two or more communication nodes without propagation via conductors or cables. Generally, such communication nodes include network devices and terminal devices.

[0003] Currently, in a wireless communication system, a communication node generally has signal transceiver capabilities and computing capabilities. Taking a network device with computing capabilities as an example, the computing capabilities of the network device mainly provide computing power support for the signal transceiver capabilities (for example, performing transmission processing and reception processing on signals) to enable communication between the network device and other communication nodes.

[0004] However, in a communication network, in addition to providing computing power support for the above communication tasks, the computing capabilities of communication nodes may also have surplus computing capabilities. Therefore, how to utilize these computing capabilities is a technical problem to be solved urgently. Summary of the Invention

[0005] This application provides a communication method and related devices, which are used to determine and deploy an artificial intelligence (AI) model in a communication network through the interaction between different communication devices, so that the computing power of the communication devices can be applied to the processing of the AI model.

[0006] In a first aspect of this application, a communication method is provided. This method is executed by a first communication device. The first communication device can be a communication device (such as a terminal device), or the first communication device can be some components in a communication device (such as a processor, a chip, or a chip system, etc.), or the first communication device can also be a logic module or software that can implement all or part of the functions of a communication device. In this method, the first communication device sends a first message, and the first message is used to determine a first AI model group, and the first AI model group includes the first AI model and the second AI model; wherein, the first AI model is deployed on the first communication device, and the second AI model is deployed on a second communication device; the input of the first AI model includes the output of the second AI model, or the input of the second AI model includes the output of the first AI model; the first communication device receives a second message from the second communication device, and the second message includes the model parameters of the first AI model group or the model parameters of the first AI model.

[0007] Based on the above technical solution, the second communication device acts as a receiver of the first information. The second communication device can determine the first AI model group based on the first information from the first communication device, and deploy the first AI model to the first communication device through the second information. Thus, when the communication device in the communication system acts as an AI participating node, the computing power of the communication device can be applied to the processing of the AI ​​model. At the same time, the first information from the first communication device can also be used as one of the bases for the second communication device to determine the AI ​​model, so that the AI ​​model determined by the second communication device can be adapted to the first communication device as much as possible, so as to improve the processing performance of the subsequent model processing based on the AI ​​model by the first communication device.

[0008] In this application, terms such as AI model, neural network model, AI neural network model, machine learning model, and AI processing model can be used interchangeably.

[0009] It should be understood that the first AI model group includes a first AI model and a second AI model, and it can be understood that the function of the first AI model group is implemented at least through the model processing of the first AI model and the model processing of the second AI model. In other words, after the first communication device receives the second information, the first communication device can deploy the first AI model to the first communication device through the model parameters of the first AI model group or the model parameters of the first AI model contained in the second information, and perform model processing on the first AI model; accordingly, the second communication device can perform model processing on the second AI model deployed on the second communication device. Optionally, the model processing may include one or more of model update processing, model training processing, and model inference processing.

[0010] It can be understood that the second communication device can be implemented in many ways.

[0011] For example, the second communication device may be a terminal device, and accordingly, the first communication device and the second communication device may communicate on a sidelink (SL). In this case, the first AI model and the second AI model may be referred to as an end-to-end model, or an end-to-end collaborative model, etc.

[0012] For another example, the second communication device may be a network device (e.g., an access network device), and accordingly, the first communication device and the second communication device may communicate on uplink and downlink communication links. In this case, the first AI model and the second AI model may be referred to as an edge-end model, an edge-end collaborative model, an edge-end model, an edge-end collaborative model, etc.

[0013] Optionally, when the first AI model group is regarded as one AI model, the first AI model and the second AI model may be understood as two AI sub-models in the one AI model.

[0014] In this application, an AI model is deployed in a communication device (for example, the first AI model is deployed in the first communication device, the second AI model is deployed in the second communication device, etc.). It can be understood that after the communication device obtains the model parameters of the AI model, the communication device obtains / generates / constructs the AI model based on the model parameters of the AI model. Subsequently, the communication device can perform model processing on the AI model.

[0015] Optionally, the model parameters may include one or more of the hyperparameters of the model, the dataset of the model (including the input data of the model and the label data corresponding to the input data), and the structural parameters of the model.

[0016] Optionally, an AI model group may include two or more AI models. For example, in addition to the first AI model and the second AI model, the first AI model group may further include other AI models, and these other AI models may be deployed in communication devices different from the first communication device and the second communication device, which is not limited here.

[0017] It should be understood that wireless communication signals (such as the transceiver of the configuration information of communication resources, the transceiver of reference signals, etc.) can be transmitted between different communication devices (such as the first communication device and the second communication device).

[0018] Optionally, the AI models involved in this application (such as the first AI model, the second AI model, the third to sixth AI models hereinafter, etc.) can be used to manage the wireless communication signals (including at least one of configuration, update, and optimization). For example, the AI model may include one or more of an AI model for modulation and / or demodulation, an AI model for channel prediction, an AI model for beam management, an AI model for assisted positioning, an AI model for channel compression, an AI model for resource scheduling, and an AI model for replacing one or more modules in a transmitter and / or a receiver. Alternatively, the AI models involved in this application may also be AI models for other AI tasks, such as an AI model for image recognition, an AI model for natural language processing, an AI model for computer vision, etc.

[0019] A second aspect of the present application provides a communication method, which is executed by a second communication device. The second communication device may be a communication device (such as a network device or a terminal device), or the second communication device may be a part of components in the communication device (such as a processor, a chip, or a chip system, etc.), or the second communication device may also be a logic module or software that can implement all or part of the functions of the communication device. In this method, the second communication device receives first information; the second communication device determines a first AI model group based on the first information, and the first AI model group includes the first AI model and the second AI model; wherein, the first AI model is deployed on a first communication device, the second AI model is deployed on the second communication device, the input of the first AI model includes the output of the second AI model, or the input of the second AI includes the output of the first AI model; the second communication device sends second information, and the second information includes the model parameters of the first AI model group or the model parameters of the first AI model.

[0020] Based on the above technical solution, as the receiver of the first information, the second communication device can determine the first AI model group based on the first information from the first communication device, and deploy the first AI model to the first communication device through the second information. Thus, when the communication device in the communication system is used as an AI participating node, while enabling the computing power of the communication device to be applied to the processing of the AI model, the first information from the first communication device can also be used as one of the determining bases for the second communication device to determine the AI model, so that the AI model determined by the second communication device can be adapted to the first communication device as much as possible to improve the processing performance of the subsequent first communication device for model processing based on the AI model.

[0021] In a possible implementation manner of the first aspect or the second aspect, the second communication device is a functional entity that determines a list of AI model groups based on the first information, and the list of AI model groups includes one or more AI model groups, and the one or more AI model groups include the first AI model group.

[0022] Based on the above technical solution, the second communication device can communicate with one or more first communication devices, and the second communication device can receive information (such as one or more first information) from the one or more first communication devices to generate / acquire / determine one or more AI model groups. In other words, the second communication device can perform information collection and perform model generation based on the collected information, and then the second communication device can deploy the AI model on the one or more first communication devices.

[0023] Optionally, the AI model group list may include one or more AI model groups, and each AI model group may include two or more AI models. As described above, the relationship between the AI model group and the AI model can also be understood as the relationship between the AI model and the AI sub-model. For this reason, the AI model group list may also be replaced by an AI model list, that is, the AI model list may include one or more AI models.

[0024] Optionally, the list may be replaced by other terms, such as set, dictionary, combination, space, etc.

[0025] In a possible implementation manner of the first aspect or the second aspect, the second communication device is a functional entity that determines the AI model group list based on the first information and selects some or all of the AI model groups used by the first communication device from the AI model group list.

[0026] Based on the above technical solution, after the second communication device determines the AI model group list based on the first information, the functions implemented by the second communication device may further include selecting some or all of the AI model groups used by the first communication device from the AI model group list. In other words, in addition to performing information collection and model generation based on the collected information, the second communication device may also perform model selection so that the second communication device can subsequently deploy AI models adapted to the one or more first communication devices on the one or more first communication devices.

[0027] In a possible implementation manner of the first aspect or the second aspect, the first information includes first dimension information or second dimension information; when the input of the first AI model includes the output of the second AI model, the first dimension information is used to determine the dimension information of the input data of the first AI model or the dimension information of the output data of the second AI model; when the input of the second AI model includes the output of the first AI model, the second dimension information is used to determine the dimension information of the output data of the first AI model or the dimension information of the input data of the second AI model.

[0028] Based on the above technical solution, the second communication device can determine the dimension information of the data transmitted on the communication link through the first information. And when the communication bandwidth between the first communication device and the second communication device is fixed, since the dimension of the data transmitted on the communication link is related to the processing performance of the AI model, in this way, the implementation process of the second communication device for determining the first AI model group can be simplified, the complexity of the second communication device can be reduced, and at the same time, the processing performance of the AI models included in the first AI model group can be improved.

[0029] In a possible implementation of the first aspect or the second aspect, the dimension information includes at least one of the following: the upper limit value of the dimension, the lower limit value of the dimension, the dimension expected by the first communication device (or the dimension not expected by the first communication device), and the value range of the dimension expected by the first communication device (or the value range of the dimension not expected by the first communication device).

[0030] Optionally, the dimension information may include the value of at least one of the above, or the quantization value of the value of at least one of the above, or the index of the value of at least one of the above, the index of the quantization value of the value of at least one of the above, etc., or may be implemented in other ways, which is not limited here.

[0031] Based on the above technical solution, the dimension information determined by the first dimension information or the second dimension information may include at least one of the above to improve the flexibility of the scheme implementation.

[0032] For example, when the above dimension information includes the upper limit value and / or the lower limit value of the dimension, the second communication device may use the range indicated by the upper limit value and / or the lower limit value as one of the determination bases of the AI model, which can improve the flexibility of the scheme implementation.

[0033] For another example, when the above dimension information includes the dimension expected by the first communication device and / or the value range of the dimension expected by the first communication device, the AI model determined by the second communication device based on the dimension information can meet the expectations of the first communication device.

[0034] In a possible implementation of the first aspect or the second aspect, the first dimension information or the second dimension information is determined based on channel state information (CSI).

[0035] Based on the above technical solution, the first dimension information or the second dimension information included in the first information may be determined based on channel state information, so that the first dimension information or the second dimension information can reflect the channel characteristics of the wireless channel between the first communication device and the second communication device to a certain extent, so that the subsequent AI model obtained based on the first information can be adapted to the channel characteristics of the wireless channel, in order to improve the transmission performance of the AI data corresponding to the AI model. And when the AI model obtained based on the first information can be adapted to the channel characteristics of the wireless channel, it can also make the transmitted data of the wireless link meet the channel bandwidth requirements as much as possible, thereby improving the model performance of the AI models included in the first AI model group.

[0036] Optionally, the channel state information may include the channel information between the first communication device and the second communication device, and / or the channel information between the second communication device and the first communication device. Wherein, when the first communication device is a terminal device and the second communication device is a network device, the channel information between the first communication device and the second communication device may be understood as uplink channel information, and the channel information between the second communication device and the first communication device may be understood as downlink channel information.

[0037] Optionally, the channel state information may be obtained based on a reference signal.

[0038] For example, when the first communication device and the second communication device communicate through a sidelink, the reference signal may include a sidelink synchronization signal / physical broadcast channel block (sidelink SSB, SL-SSB, or S-SS / PSBCH block), a sidelink channel state information reference signal (SL-CSI-RS), etc.

[0039] For another example, when the first communication device and the second communication device communicate through uplink and downlink, the reference signal may include a channel state information reference signal (CSI-RS), a sounding reference signal (SRS), etc.

[0040] In a possible implementation manner of the first aspect or the second aspect, the first information includes at least one of the following: the input data of the first AI model and the label data of the input data of the first AI model, the local computing power state information of the first communication device, and the channel state information.

[0041] Based on the above technical solution, the first information may include at least one of the above information. In other words, the second communication device may determine the first AI model group based on at least one of the above information to improve the flexibility of the solution implementation.

[0042] In one implementation example, when the first information includes the input data of the first AI model and the label data of the input data of the first AI model, since the input data can be used as the input of the first AI model and the label data can be used as one of the bases for determining the model processing performance of the first AI model, for the second communication device, the second communication device can obtain an AI model with better performance based on these two pieces of information.

[0043] In addition, for the second communication device, the second communication device can perform mathematical calculations based on mutual information by using these two pieces of information and the AI data (such as the input data of the second AI model or the output data of the second AI model, etc.) transmitted and received by the second communication device on the wireless link, and determine the first AI model group based on the result of the mathematical calculation, so as to improve the model performance of the AI models included in the first AI model group on the premise that the wireless link data meets the bandwidth.

[0044] In another implementation example, when the first information includes the local computing power status information of the first communication device, since the complexity requirements of the model processing of the AI model may be related to the local computing power status of the first communication device. Therefore, for the second communication device, the first AI model group determined by the second communication device based on the local computing power status information can be adapted to the local computing power status of the first communication device, so as to provide the first AI model that meets the local computing power status and improve the success rate of the first communication device in performing model processing based on the first AI model.

[0045] In another implementation example, when the first information includes the channel state information, since the channel state information can reflect the channel characteristics of the wireless channel between the first communication device and the second communication device. Therefore, for the second communication device, the first AI model group determined by the second communication device based on the channel state information can be adapted to the channel characteristics, so that the transmission data of the wireless link can meet the channel bandwidth requirements as much as possible, in order to improve the transmission performance of the AI data corresponding to the AI model.

[0046] It can be understood that when the first information includes two or more of the above-mentioned pieces of information, based on the technical gains brought by any one of the above descriptions, further superimposed gains can be obtained through these two or more pieces of information.

[0047] In a possible implementation of the first aspect or the second aspect, the first information is used to determine the first AI model group, including: the first information is used to update the second AI model group to obtain the first AI model group; the second AI model group includes a third AI model and a fourth AI model, the third AI model is deployed on the first communication device, the fourth AI model is deployed on the second communication device, the input of the third AI model includes the output of the fourth AI model, or the input of the fourth AI includes the output of the third AI model.

[0048] Optionally, "update" can be replaced with other terms, such as "modify", "iterate", "optimize", "process", etc.

[0049] Optionally, when the second AI model group is regarded as one AI model, the third AI model and the fourth AI model can be understood as two AI sub-models in the one AI model.

[0050] Based on the above technical solution, for the second communication device, after receiving the first information, the second communication device can update the second AI model group based on the first information to obtain the first AI model group. In other words, the first information sent by the first communication device can be used to update other AI models, making the solution applicable to the AI model update scenario.

[0051] Optionally, the third AI model and the second AI model included in the second AI model group can be general models or dedicated models to achieve the update of different types of models.

[0052] It should be understood that the general model can be called the base model, the large model or the L0 model. The dedicated model can be called the small model, the L1 model, the L2 model, etc.

[0053] Taking the large model as an example, the large model can refer to a machine learning model with a large number of parameters and a complex structure, which can process massive data and complete various complex tasks, such as natural language processing, computer vision, speech recognition, etc.

[0054] Optionally, the large model is usually constructed by a deep neural network and has billions or even hundreds of billions of parameters.

[0055] Optionally, the design purpose of the large model can be to improve the expression ability and prediction performance of the model, and it can process more complex tasks and data.

[0056] Optionally, the large model can learn complex patterns and features by training massive data, has a stronger generalization ability, and can make accurate predictions on unprocessed data.

[0057] In contrast, a small model may refer to a model with fewer parameters and shallower layers. Generally, compared with small models, large models usually have more parameters and deeper layers, with stronger expressive power and higher accuracy, but also require more computing resources and time for training and inference, and are suitable for scenarios with large amounts of data and sufficient computing resources, such as cloud computing, high-performance computing, artificial intelligence, etc.

[0058] Optionally, small models have the advantages of being lightweight, highly efficient, and easy to deploy, and are suitable for scenarios with small amounts of data and limited computing resources, such as mobile applications, embedded devices, the Internet of Things, etc.

[0059] In a possible implementation manner of the first aspect or the second aspect, the first information is information sent periodically, and / or the second information is information sent periodically.

[0060] Based on the above technical solution, the first information can be one of the determination bases of the AI model, and the second information can be used to deploy the AI model. Among them, between the first communication device and the second communication device, by periodically sending the first information and / or the second information, the periodic determination and / or periodic deployment of the AI model can be realized, so as to achieve multiple iterative updates of the AI model through a periodic process.

[0061] In a possible implementation manner of the first aspect or the second aspect, the AI model of the first AI model group is a dedicated model.

[0062] Based on the above technical solution, the first communication device can be a terminal device. Therefore, the AI model deployed on the terminal device can be a dedicated model, and the first information sent by the terminal device can be used to determine the dedicated model. Since different terminal devices may have different end-side characteristics (such as different local data, different local computing powers, different channel characteristics, etc.), by deploying a dedicated model in the terminal device, in this way, the AI model deployed on the terminal device can be adapted to the end-side characteristics of the terminal device, in order to improve the model processing performance of the AI model.

[0063] A third aspect of the present application provides a communication method, which is executed by a second communication device. The second communication device may be a communication device (such as a cloud server or a core network device), or the second communication device may be a part of components in a communication device (such as a processor, a chip, or a chip system, etc.), or the second communication device may also be a logical module or software that can implement all or part of the functions of a communication device. In this method, the second communication device sends third information, which is used to determine a third AI model group. The third AI model group includes the fifth AI model and the sixth AI model; wherein, the fifth AI model is deployed in the first communication device, the sixth AI model is deployed in the second communication device, the input of the fifth AI model includes the output of the sixth AI model, or the input of the sixth AI includes the output of the fifth AI model; the second communication device receives fourth information from a third communication device, and the fourth information includes model parameters of the third AI model group.

[0064] Based on the above technical solution, as the recipient of the third information, the third communication device can determine the third AI model group based on the third information from the second communication device, and enable the subsequent second communication device to deploy the fifth AI model in the first communication device and deploy the sixth AI model in the second communication device through the fourth information. Thus, when the communication device in the communication system is an AI participating node, while the computing power of the communication device can be applied to the processing of the AI model, the third information from the second communication device can also be used as one of the bases for the third communication device to determine the AI model, so that the AI model determined by the third communication device can be as compatible as possible with the second communication device to improve the success rate of the subsequent second communication device in performing model processing on the AI model.

[0065] It should be understood that the third AI model group includes the fifth AI model and the sixth AI model. It can be understood that the function of the third AI model group is at least realized through the model processing of the fifth AI model and the model processing of the sixth AI model. In other words, after the second communication device receives the fourth information, the second communication device can determine the model parameters of the fifth AI model and the model parameters of the sixth AI model, and the second communication device can deploy the fifth AI model in the first communication device and deploy the sixth AI model in the second communication device to implement the model processing of the fifth AI model and the sixth AI model. Optionally, the model processing may include one or more of model update processing, model training processing, and model inference processing.

[0066] Optionally, when the third AI model group is regarded as an AI model, the fifth AI model and the sixth AI model can be understood as two AI sub-models in the one AI model.

[0067] It should be noted that the second communication device and the third communication device can be implemented in various ways. Among them, the second communication device can be a terminal device or an access network device, and the third communication device can be a cloud server or a core network device. For example, when the third communication device is a cloud server, the second communication device can communicate with the cloud server through the core network device. Another example is that when the third communication device is a core network device, the second communication device can be a terminal device, and the terminal device can communicate with the core network device through the access network device. Another example is that when the third communication device is a core network device, the second communication device can be an access network device, and the access network device can communicate through the communication interface between the access network device and the core network device.

[0068] In the fourth aspect of the present application, a communication method is provided. This method is executed by the third communication device. The third communication device can be a network device (such as an access network device, a core network device, a cloud server, etc.), or the third communication device can be some components in the network device (such as a processor, a chip, or a chip system, etc.), or the third communication device can also be a logical module or software that can implement all or part of the network device functions. In this method, the third communication device receives the third information; the third communication device determines a third AI model group based on the third information. The third AI model group includes the fifth AI model and the sixth AI model; among them, the fifth AI model is deployed in the first communication device, and the sixth AI model is deployed in the second communication device; the input of the fifth AI model includes the output of the sixth AI model, or the input of the sixth AI model includes the output of the fifth AI model; the third communication device sends the fourth information, and the fourth information includes the model parameters of the third AI model group.

[0069] Based on the above technical solution, after the third communication device receives the third information for determining the third AI model group, the third communication device can send the fourth information, and the third information includes the model parameters of the third AI model group. In other words, as the receiver of the third information, the third communication device can determine the third AI model group based on the third information from the second communication device, and through the fourth information, enable the subsequent second communication device to deploy the fifth AI model in the first communication device and deploy the sixth AI model in the second communication device. Thus, when the communication device in the communication system is an AI participating node, while enabling the computing power of the communication device to be applied to the processing of the AI model, the third information from the second communication device can also be used as one of the bases for the third communication device to determine the AI model, so that the AI model determined by the third communication device can be as suitable as possible for the second communication device to improve the success rate of the subsequent second communication device in performing model processing on the AI model.

[0070] In a possible implementation of the third aspect or the fourth aspect, the third communication device is a functional entity that determines the third AI model group based on the third information.

[0071] Based on the above technical solution, the third communication device can communicate with one or more second communication devices, and the third communication device can receive information (such as one or more third information) from the one or more second communication devices to generate / obtain / determine the third AI model group. In other words, the second communication device can perform information collection and perform model generation based on the collected information. Subsequently, the second communication device can deploy the AI model in one or more second communication devices (and the corresponding first communication device).

[0072] Optionally, the AI models in the third AI model group are general models. In this way, the third communication device can determine general models through information (such as one or more third information) from the one or more second communication devices. Subsequently, multiple second communication devices and the first communication devices connected to each second communication device can all deploy general models with relatively high generalization and good versatility.

[0073] In a possible implementation of the third aspect or the fourth aspect, the third information includes third-dimensional information or fourth-dimensional information; when the input of the fifth AI model includes the output of the sixth AI model, the third-dimensional information is used to determine the dimensional information of the input data of the fifth AI model or the dimensional information of the output data of the sixth AI model; when the input of the sixth AI model includes the output of the fifth AI model, the fourth-dimensional information is used to determine the dimensional information of the output data of the fifth AI model or the dimensional information of the input data of the sixth AI model.

[0074] Based on the above technical solution, the third communication device can determine the dimensional information of the data transmitted on the communication link between the first communication device and the second communication device through the third information. When the communication bandwidth between the first communication device and the second communication device is fixed, since the dimension of the data transmitted on the communication link is related to the processing performance of the AI model, in this way, the implementation process of the third communication device for determining the first AI model group can be simplified, and while reducing the complexity of the third communication device, the processing performance of the AI models included in the first AI model group can also be improved.

[0075] In a possible implementation of the third aspect or the fourth aspect, the dimensional information includes at least one of the following: the upper limit value of the dimension, the lower limit value of the dimension, the dimension expected by the second communication device (or the dimension not expected by the first communication device), and the value range of the dimension expected by the second communication device (or the value range of the dimension not expected by the first communication device).

[0076] Optionally, the dimension information may include the value of at least one of the above, or the quantization value of the value of at least one of the above, or the index of the value of at least one of the above, the index of the quantization value of the value of at least one of the above, etc., or may be implemented in other ways, which is not limited herein.

[0077] Based on the above technical solution, the dimension information determined by the third dimension information or the fourth dimension information may include at least one of the above, so as to improve the flexibility of the solution implementation.

[0078] For example, when the above dimension information includes the upper limit value of the dimension and / or the lower limit value of the dimension, the third communication device may use the range indicated by the upper limit value and / or the lower limit value as one of the determination bases of the AI model, which can improve the flexibility of the solution implementation.

[0079] For another example, when the above dimension information includes the dimension expected by the second communication device and / or the value range of the dimension expected by the second communication device, the AI model determined by the third communication device based on the dimension information can meet the expectations of the second communication device.

[0080] In a possible implementation manner of the third aspect or the fourth aspect, the third dimension information or the fourth dimension information is determined based on the channel state information.

[0081] Based on the above technical solution, the third dimension information or the fourth dimension information included in the third information may be determined based on the channel state information, so that the third dimension information or the fourth dimension information can reflect the channel characteristics of the wireless channel between the first communication device and the second communication device to a certain extent, so that the AI model obtained based on the third information can be adapted to the channel characteristics of the wireless channel, in order to improve the transmission performance of the AI data corresponding to the AI model. And, when the AI model obtained based on the third information can be adapted to the channel characteristics of the wireless channel, it can also make the transmission data of the wireless link meet the channel bandwidth requirements as much as possible, thereby improving the model performance of the AI models included in the third AI model group.

[0082] In a possible implementation manner of the third aspect or the fourth aspect, the third information includes at least one of the following: the model parameters of the AI models in one or more AI model groups; wherein, each AI model group in the one or more AI model groups includes a dedicated model deployed on the first communication device and a dedicated model deployed on the second communication device; data from one or more first communication devices connected to the second communication device; the input data of the AI model deployed on the second communication device and the label data of the input data of the AI model deployed on the second communication device.

[0083] Based on the above technical solution, the third information can be implemented through the above at least one item to improve the flexibility of the solution implementation.

[0084] In one implementation example, when the third information includes the model parameters of the AI models in one or more AI model groups, the third communication device can obtain one or more dedicated models deployed on the first communication device and the second communication device based on the third information. In this way, the third communication device can obtain the model characteristics of the one or more dedicated models and reflect the obtained characteristics in the third AI model group to improve the generalization (or generality) of the general model included in the third AI model group.

[0085] In another implementation example, when the third information includes data from one or more first communication devices (such as terminal devices) connected to the second communication device, since different terminal devices may have different data characteristics (for example, different data may be collected at different geographical locations, different data may be collected at different times, different data may correspond to different wireless channels of the user, etc.), in this way, the third communication device obtains the third AI model group based on these data characteristics to improve the generalization (or generality) of the general model included in the third AI model group.

[0086] In another implementation example, when the third information includes the input data of the AI model deployed on the second communication device and the label data of the input data of the AI model deployed on the second communication device, since the input data can be used as the input of the sixth AI model and the label data can be used as one of the bases for determining the model processing performance of the sixth AI model, for the third communication device, the third communication device can obtain an AI model with better performance based on these two pieces of information.

[0087] In addition, for the third communication device, the third communication device can perform mathematical calculations based on mutual information based on these two pieces of information and the AI data (such as the input data or output data of the sixth AI model, etc.) transmitted and received by the second communication device on the wireless link, and determine the third AI model group based on the result of the mathematical calculation to improve the model performance of the AI models included in the third AI model group on the premise that the wireless link data meets the bandwidth.

[0088] It can be understood that when the third information includes two or more of the above information, based on the technical gain brought by any one of the above descriptions, further superimposed gains can be obtained through the two or more pieces of information.

[0089] Optionally, each piece of information included in the third information can be part of the information screened by the second communication device from multiple copies.

[0090] In a possible implementation of the third aspect or the fourth aspect, the third information is used to determine a third AI model group, including: the third information is used to update a fourth AI model group to obtain the third AI model group; the fourth AI model group includes a seventh AI model and an eighth AI model, the seventh AI model is deployed on the first communication device, the eighth AI model is deployed on the second communication device, the input of the seventh AI model includes the output of the eighth AI model, or the input of the eighth AI model includes the output of the seventh AI model.

[0091] Optionally, when the fourth AI model group is regarded as one AI model, the seventh AI model and the eighth AI model can be understood as two AI sub-models in the one AI model.

[0092] Based on the above technical solution, for the third communication device, after receiving the third information, the third communication device can update the fourth AI model group based on the third information to obtain the third AI model group. In other words, the third information sent by the second communication device can be used to update other AI models, so that the solution can be applied to the AI model update scenario.

[0093] In a possible implementation of the third aspect or the fourth aspect, the third information is information sent periodically, and / or the fourth information is information sent periodically.

[0094] Based on the above technical solution, the third information can be one of the determination bases of the AI model, and the fourth information can deploy the AI model. Among them, by periodically sending the third information and / or the fourth information between the second communication device and the third communication device, the periodic determination and / or periodic deployment of the AI model can be realized, so as to realize multiple iterative updates of the AI model through a periodic process.

[0095] The fifth aspect of this application provides a communication device, which is the first communication device. The device includes a transceiver unit and a processing unit; the processing unit is used to determine the first information; the transceiver unit is used to send the first information, and the first information is used to determine a first artificial intelligence (AI) model group, and the first AI model group includes the first AI model and the second AI model; wherein, the first AI model is deployed on the first communication device, the second AI model is deployed on the second communication device; the input of the first AI model includes the output of the second AI model, or the input of the second AI model includes the output of the first AI model; the transceiver unit is further used to receive the second information from the second communication device, and the second information includes the model parameters of the first AI model group or the model parameters of the first AI model.

[0096] In the fifth aspect of the present application, the component modules of the communication device can also be used to execute the steps performed in each possible implementation manner of the first aspect and achieve the corresponding technical effects. For details, reference can be made to the first aspect, which will not be elaborated here.

[0097] In the sixth aspect of the present application, a communication device is provided. This device is the second communication device and includes a transceiver unit and a processing unit. The transceiver unit receives the first information. The processing unit is used to determine a first AI model group based on the first information. The first AI model group includes the first AI model and the second AI model. Among them, the first AI model is deployed on the first communication device, and the second AI model is deployed on the second communication device. The input of the first AI model includes the output of the second AI model, or the input of the second AI includes the output of the first AI model. The transceiver unit is also used to send second information, and the second information includes the model parameters of the first AI model group or the model parameters of the first AI model.

[0098] In the sixth aspect of the present application, the component modules of the communication device can also be used to execute the steps performed in each possible implementation manner of the second aspect and achieve the corresponding technical effects. For details, reference can be made to the second aspect, which will not be elaborated here.

[0099] In the seventh aspect of the present application, a communication device is provided. This device is the second communication device and includes a transceiver unit and a processing unit. The processing unit is used to determine the third information. The transceiver unit is used to send the third information, and the third information is used to determine a third AI model group. The third AI model group includes the fifth AI model and the sixth AI model. Among them, the fifth AI model is deployed on the first communication device, and the sixth AI model is deployed on the second communication device. The input of the fifth AI model includes the output of the sixth AI model, or the input of the sixth AI includes the output of the fifth AI model. The transceiver unit is also used to receive fourth information from the third communication device, and the fourth information includes the model parameters of the third AI model group.

[0100] In the seventh aspect of the present application, the component modules of the communication device can also be used to execute the steps performed in each possible implementation manner of the third aspect and achieve the corresponding technical effects. For details, reference can be made to the third aspect, which will not be elaborated here.

[0101] The eighth aspect of the present application provides a communication device, which is a third communication device. The device includes a transceiver unit and a processing unit. The transceiver unit is used to receive third information; the processing unit is used to determine a third AI model group based on the third information. The third AI model group includes the fifth AI model and the sixth AI model. Among them, the fifth AI model is deployed on the first communication device, and the sixth AI model is deployed on the second communication device; the input of the fifth AI model includes the output of the sixth AI model, or the input of the sixth AI model includes the output of the fifth AI model; the transceiver unit is further used to send fourth information, and the fourth information includes the model parameters of the third AI model group.

[0102] In the eighth aspect of the present application, the constituent modules of the communication device can also be used to execute the steps performed in each possible implementation manner of the fourth aspect and achieve the corresponding technical effects. Specifically, reference can be made to the fourth aspect, and details are not repeated here.

[0103] The ninth aspect of the present application provides a communication device, including at least one processor, and the at least one processor is coupled to a memory; the memory is used to store programs or instructions; the at least one processor is used to execute the programs or instructions so that the device implements the method described in any one of the possible implementation manners in any one of the foregoing first aspect to the fourth aspect.

[0104] In a possible implementation manner, the communication device further includes a memory. Optionally, the processor and the memory are integrated together.

[0105] The tenth aspect of the present application provides a communication device, including at least one logic circuit and an input-output interface; the logic circuit is used to execute the method described in any one of the possible implementation manners in any one of the foregoing first aspect to the fourth aspect.

[0106] The eleventh aspect of the present application provides a communication system, which includes the foregoing first communication device and the second communication device. Alternatively, the communication system includes the foregoing second communication device and the third communication device. Alternatively, the communication system includes the foregoing first communication device, the second communication device, and the third communication device.

[0107] The twelfth aspect of the present application provides a computer-readable storage medium, which is used to store one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method described in any one of the possible implementation manners in any one of the foregoing first aspect to the fourth aspect.

[0108] A thirteenth aspect of this application provides a computer program product (or computer program). When the computer program in the computer program product is executed by the processor, the processor executes the method described in any one of the possible implementation manners of any one of the first to fourth aspects above.

[0109] A fourteenth aspect of this application provides a chip system. The chip system includes at least one processor, which is used to support a communication device to implement the method described in any one of the possible implementation manners of any one of the first to fourth aspects above.

[0110] In a possible design, the chip system may further include a memory, which is used to store the necessary program instructions and data of the communication device. The chip system may be composed of chips, or may include chips and other discrete devices. Optionally, the chip system further includes an interface circuit, and the interface circuit provides program instructions and / or data for the at least one processor.

[0111] Among them, for the technical effects brought by any one of the design manners in the third to tenth aspects, reference may be made to the technical effects brought by different design manners in the first to fourth aspects above, and details are not described herein again. BRIEF DESCRIPTION OF THE DRAWINGS

[0112] Figure 1a 、 Figure 1b is a schematic diagram of the communication system provided by this application;

[0113] Figures 2a to 2g is a schematic diagram of the AI processing process involved in this application;

[0114] Figure 3 is an interaction schematic diagram of the communication method provided by this application;

[0115] Figures 4 to 6 is an interaction schematic diagram of the communication method provided by this application;

[0116] Figures 7 to 11 is a schematic diagram of the communication device provided by this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0117] First, some terms in the embodiments of this application are explained to facilitate understanding by those skilled in the art.

[0118] (1) Terminal device: It can be a wireless terminal device that can receive scheduling and indication information from a network device. The wireless terminal device can be a device that provides voice and / or data connectivity to a user, or a handheld device with a wireless connection function, or other processing devices connected to a wireless modem.

[0119] A terminal device can communicate with one or more core networks or the Internet via a radio access network (RAN). The terminal device can be a mobile terminal device, such as a mobile phone (or a "cellular" phone, a mobile phone), a computer, and a data card. For example, it can be a portable, pocket-sized, hand-held, computer-integrated, or vehicle-mounted mobile device that exchanges voice and / or data with the radio access network. For example, devices such as personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), tablets (Pads), and computers with wireless transceiver functions. The wireless terminal device can also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station (MS), a remote station, an access point (AP), a remote terminal device, an access terminal device, a user terminal device, a user agent, a subscriber station (SS), a customer premises equipment (CPE), a terminal, a user equipment (UE), a mobile terminal (MT), etc.

[0120] By way of example and not limitation, in the embodiments of the present application, the terminal device may also be a wearable device. A wearable device may also be referred to as a wearable intelligent device or a smart wearable device, etc. It is a general term for devices developed by applying wearable technology to the intelligent design of daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is directly worn on the body or integrated into the user's clothes or accessories. A wearable device is not only a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable intelligent devices include those with complete functions and large sizes that can realize complete or partial functions without relying on a smart phone, such as smart watches or smart glasses, etc., and those that only focus on a certain type of application function and need to cooperate with other devices such as smart phones, such as various smart bracelets for physical sign monitoring, smart helmets, and smart jewelry.

[0121] The terminal may also be a drone, a robot, a terminal in device-to-device (D2D) communication, a terminal in vehicle-to-everything (V2X) communication, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc.

[0122] In addition, the terminal device may also be a terminal device in a communication system evolved after the fifth-generation (5G) communication system (such as the sixth-generation (6G) communication system, etc.) or a terminal device in a future-evolved public land mobile network (PLMN). Exemplarily, the 6G network can further expand the form and function of 5G communication terminals. 6G terminals include but are not limited to vehicles, cellular network terminals (integrating satellite terminal functions), drones, and Internet of Things (IoT) devices.

[0123] In the embodiments of the present application, the above terminal device may also obtain AI services provided by a network device. Optionally, the terminal device may also have AI processing capabilities.

[0124] (2) Network device: It can be a device in a wireless network. For example, the network device can be a RAN node (or device) that connects a terminal device to a wireless network, and can also be called a base station. Currently, some examples of RAN devices are: base station, evolved NodeB (eNodeB), gNB (gNodeB) in a 5G communication system, transmission reception point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), home base station (e.g., home evolved Node B, or home Node B, HNB), base band unit (BBU), or wireless fidelity (Wi-Fi) access point AP, etc. Additionally, in a network structure, the network device can include a centralized unit (CU) node, or a distributed unit (DU) node, or a RAN device including a CU node and a DU node.

[0125] Optionally, the RAN node can also be a macro base station, a micro base station or an indoor station, a relay node or a donor node, or a radio controller in a cloud radio access network (CRAN) scenario. The RAN node can also be a server, a wearable device, a vehicle or an in-vehicle device, etc. For example, the access network device in V2X technology can be a road side unit (RSU).

[0126] In another possible scenario, multiple RAN nodes cooperate to assist a terminal in achieving wireless access, and different RAN nodes respectively implement partial functions of a base station. For example, the RAN nodes can be a central unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc. The CU and the DU can be set separately, or can also be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, such as included in a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0127] In different systems, the CU (or CU-CP and CU-UP), DU, or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open RAN (O-RAN or ORAN) system, the CU can also be called an O-CU (open CU), the DU can also be called an O-DU, the CU-CP can also be called an O-CU-CP, the CU-UP can also be called an O-CU-UP, and the RU can also be called an O-RU. For the convenience of description, in this application, the CU, CU-CP, CU-UP, DU, and RU are used as examples for description. Any one of the CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0128] The communication between the access network device and the terminal device follows a certain protocol layer structure. The protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: Radio Resource Control (RRC) layer, Packet Data Convergence Protocol (PDCP) layer, Radio Link Control (RLC) layer, Media Access Control (MAC) layer, or Physical (PHY) layer, etc. The user plane protocol layer may include at least one of the following: Service Data Adaptation Protocol (SDAP) layer, PDCP layer, RLC layer, MAC layer, or Physical layer, etc.

[0129] For the correspondence between the network elements in the ORAN system and the protocol layer functions they can implement, refer to Table 1 below.

[0130] Table 1

[0131] ORAN network element Protocol layer functions of 3GPP O-CU-CP RRC+PCDP - Control Plane (PDCP-C) O-CU-UP SDAP+PCDP - User Plane (PDCP-U) O-DU RLC + MAC + PHY-high O-RU PHY-low

[0132] The network device may be other devices that provide wireless communication functions for the terminal device. The specific technologies and device forms adopted by the network device are not limited in the embodiments of the present application. For ease of description, the embodiments of the present application do not limit.

[0133] The network device may further include core network devices, such as a mobility management entity (MME), a home subscriber server (HSS), a serving gateway (S-GW), a policy and charging rules function (PCRF), and a public data network gateway (PDN gateway, P-GW) in a 4th generation (4G) network; network elements such as an access and mobility management function (AMF), a user plane function (UPF), or a session management function (SMF) in a 5G network. In addition, the core network device may further include other core network devices in a 5G network and the next-generation network of the 5G network.

[0134] In the embodiments of this application, the above network device may also be a network node with AI capabilities, which can provide AI services for terminals or other network devices. For example, it can be an AI node, a computing power node, a RAN node with AI capabilities, or a core network element with AI capabilities on the network side (access network or core network).

[0135] In the embodiments of this application, the device for implementing the functions of the network device may be the network device or a device capable of supporting the network device to implement such functions, such as a chip system, and this device may be installed in the network device. In the technical solutions provided in the embodiments of this application, the device for implementing the functions of the network device is taken as an example of the network device to describe the technical solutions provided in the embodiments of this application.

[0136] (3) Configuration and pre-configuration: In this application, both configuration and pre-configuration are used. Among them, configuration means that the network device / server sends the configuration information or value of some parameters to the terminal through messages or signaling, so that the terminal can determine the communication parameters or resources during transmission based on these values or information. Pre-configuration is similar to configuration, and it can be parameter information or parameter values pre-negotiated between the network device / server and the terminal device, or parameter information or parameter values specified by standard protocols for base stations / network devices or terminal devices, or parameter information or parameter values pre-stored in base stations / servers or terminal devices. This application does not limit this.

[0137] Furthermore, these values and parameters can be changed or updated.

[0138] (4) The terms "system" and "network" in the embodiments of the present application can be used interchangeably. "Multiple" means two or more. "And / or" describes the association relationship of associated objects and indicates that there can be three relationships. For example, A and / or B can represent: the situation where A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of single item (item) or multiple items (items). For example, "at least one of A, B, and C" includes A, B, C, AB, AC, BC, or ABC. Also, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of the present application are used to distinguish multiple objects and are not used to limit the order, time sequence, priority, or importance of multiple objects.

[0139] (5) "Sending" and "receiving" in the embodiments of the present application represent the direction of signal transmission. For example, "sending information to XX" can be understood as the destination of the information is XX, which can include directly sending through the air interface and also include indirectly sending by other units or modules through the air interface. "Receiving information from YY" can be understood as the source of the information is YY, which can include directly receiving from YY through the air interface and also can include indirectly receiving from YY through the air interface by other units or modules. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface.

[0140] In other words, sending and receiving can be carried out between devices. For example, between a network device and a terminal device, or can be carried out within a device. For example, sending or receiving between components, modules, chips, software modules, or hardware modules within a device through a bus, trace, or interface.

[0141] It can be understood that necessary processing may be performed on the information between the source end and the destination end of the information sending, such as encoding, modulation, etc., but the destination end can understand the valid information from the source end. Similar expressions in the present application can be understood similarly and will not be elaborated further.

[0142] (6) In the embodiments of the present application, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. If the information indicated by a certain piece of information (such as the indication information described below) is called the information to be indicated, then in the specific implementation process, there are many ways to indicate the information to be indicated. For example, but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated, etc. It is also possible to indirectly indicate the information to be indicated by indicating other information, where there is an association relationship between the other information and the information to be indicated; it is also possible to only indicate a part of the information to be indicated, while the other parts of the information to be indicated are known or pre-agreed. For example, the arrangement order of each piece of information pre-agreed (such as protocol pre-definition) can be used to implement the indication of specific information, thereby reducing the indication overhead to a certain extent. The present application does not limit the specific manner of indication. It can be understood that for the sender of the indication information, the indication information can be used to indicate the information to be indicated, and for the receiver of the indication information, the indication information can be used to determine the information to be indicated.

[0143] In the present application, unless otherwise specified, the same or similar parts between various embodiments can be referred to each other. In various embodiments of the present application, as well as in each method / design / implementation manner in each embodiment, if there is no special specification and logical conflict, the terms and / or descriptions between different embodiments, as well as between each method / design / implementation manner in each embodiment, are consistent and can be mutually referred to. The technical features in different embodiments, as well as in each method / design / implementation manner in each embodiment, can be combined to form new embodiments, methods, or implementation manners according to their inherent logical relationships. The embodiments of the present application described below do not constitute a limitation on the protection scope of the present application.

[0144] The present application can be applied to a long term evolution (LTE) system, a new radio (NR) system, or a communication system evolved after 5G (such as 6G, etc.). Among them, the communication system includes at least one network device and / or at least one terminal device.

[0145] Please refer to Figure 1a , which is a schematic diagram of the architecture of the communication system 1000 to which the embodiments of the present application are applied. As Figure 1a shown, the communication system includes a RAN 100 and a core network 200. Optionally, the communication system 1000 may further include the Internet 300. Among them, the RAN 100 includes at least one RAN node (such as Figure 1a 110a and 110b in Figure 1a120a - 120j in it, collectively referred to as 120). RAN 100 may also include other RAN nodes, for example, wireless relay devices and / or wireless backhaul devices ( Figure 1a not shown in the figure). The terminal 120 is connected to the RAN node 110 wirelessly, and the RAN node 110 is connected to the core network 200 wirelessly or by wire. The core network devices in the core network 200 and the RAN nodes 110 in the RAN 100 may be independent different physical devices, or may be the same physical device integrating the logical functions of the core network devices and the logical functions of the RAN nodes. Terminals can be connected to each other, and RAN nodes can be connected to each other, either by wire or wirelessly.

[0146] RAN 100 may be an evolved universal terrestrial radio access (E-UTRA) system, an NR system, and a future wireless access system defined in the 3rd generation partnership project (3GPP). RAN 100 may also include two or more different wireless access systems as described above. RAN 100 may also be an open RAN (O-RAN).

[0147] For ease of description, in the following text, a base station is taken as an example of a RAN node for description.

[0148] The base station and the terminal can be in fixed positions or movable. The base station and the terminal can be deployed on land, including indoor or outdoor, handheld or vehicle-mounted; can also be deployed on water; can also be deployed on airplanes, balloons, and artificial satellites. The embodiments of the present application do not limit the application scenarios of the base station and the terminal.

[0149] The roles of the base station and the terminal can be relative. For example, Figure 1a the helicopter or drone 120i in the figure can be configured as a mobile base station. For those terminals 120j that access the wireless access network 100 through 120i, the terminal 120i is the base station; but for the base station 110a, 120i is the terminal, that is, the communication between 110a and 120i is through the wireless air interface protocol. Of course, the communication between 110a and 120i can also be through the interface protocol between base stations. At this time, relative to 110a, 120i is also the base station. Therefore, the base station and the terminal can both be collectively referred to as communication devices, Figure 1a 110a and 110b in the figure can be referred to as communication devices with base station functions, Figure 1a 120a - 120j in the figure can be referred to as communication devices with terminal functions.

[0150] Communication can be carried out between a base station and a terminal, between base stations, and between terminals through licensed spectrum, through unlicensed spectrum, or simultaneously through licensed and unlicensed spectrum; communication can be carried out through spectrum below 6 gigahertz (GHz), through spectrum above 6 GHz, or simultaneously using spectrum below 6 GHz and spectrum above 6 GHz. Embodiments of this application do not limit the spectrum resources used for wireless communication.

[0151] In embodiments of this application, the functions of a base station can also be performed by a module (such as a chip) in the base station, or by a control subsystem that includes base station functions. Here, the control subsystem that includes base station functions can be a control center in application scenarios such as smart grids, industrial control, intelligent transportation, and smart cities. The functions of a terminal can also be performed by a module (such as a chip or a modem) in the terminal, or by a device that includes terminal functions.

[0152] Figure 1b Another schematic diagram of a communication system provided for embodiments of this application. In Figure 1b this example, a network device is used as a base station for illustration, and both Device 1 and Device 2 are terminal devices. As Figure 1b shown, the communication link between Device 1 and Device 2 can be referred to as a sidelink (SL), and the communication link between Device 1 (or Device 2) and the base station can be referred to as an uplink and downlink, including an uplink and a downlink; it can be seen that the sidelink is a communication mechanism in which different terminal devices communicate directly without passing through a network device.

[0153] Optionally, in a sidelink (SL), generally speaking, the transmitting device and the receiving device can be terminal devices or network devices of the same type, or a roadside unit (RSU) and a terminal device. Among them, from a physical entity perspective, the RSU is a roadside station or a roadside unit, and from a functional perspective, the RSU can be a terminal device or a network device. This application does not limit this. That is, the transmitting device is a terminal device and the receiving device is also a terminal device; or, the transmitting device is a roadside station and the receiving device is also a roadside station; or, the transmitting device is a terminal device and the receiving device is a roadside station. In addition, the sidelink can also be base station devices of the same type or different types. At this time, the function of the sidelink is similar to that of a relay link, but the air interface technology used can be the same or different.

[0154] Exemplarily, broadcasting, unicasting, and multicasting are supported on the sidelink.

[0155] When a terminal device (e.g., Device 1) communicates directly with another terminal device (e.g., Device 2) without passing through a network device, the two terminal devices can communicate based on the proximity-based services communication 5 (PC5) interface.

[0156] A typical application of the sidelink is V2X communication, which utilizes and enhances the current cellular network functions and elements to achieve low-latency and high-reliability communication among various nodes in the vehicle network, including vehicle-to-vehicle (V2V) communication, vehicle-to-pedestrian (V2P) communication, vehicle-to-infrastructure (V2I) communication, and vehicle-to-network (V2N) communication.

[0157] The technical solution provided by this application can be applied to a wireless communication system (e.g., Figure 1a or Figure 1b the system shown), for example, an AI network element can be introduced in the communication system provided by this application to implement some or all of the AI-related operations. The AI network element can also be referred to as an AI node, AI device, AI entity, AI module, AI model, or AI unit, etc. The AI network element can be built into the network element of the communication system. For example, the AI network element can be an AI module built into: a terminal device, an access network device, a core network device, a cloud server, or a network management (operation, administration and maintenance, OAM) to implement AI-related functions. The OAM can be used as the core network device network management and / or as the access network device network management. Alternatively, the AI network element can also be an independently provided network element in the communication system. Optionally, an AI entity can also be included in the terminal or the chip built into the terminal to implement AI-related functions.

[0158] Next, a brief introduction to artificial intelligence (AI) that may be involved in this application will be given.

[0159] Artificial intelligence (AI) enables machines to possess human intelligence. For example, machines can apply computer software and hardware to simulate certain intelligent behaviors of humans. To achieve artificial intelligence, machine learning methods can be adopted. In machine learning methods, a machine learns (or trains) a model using training data. This model represents the mapping from input to output. The learned model can be used for inference (or prediction), that is, the model can be used to predict the output corresponding to a given input. Among them, this output can also be called the inference result (or prediction result).

[0160] Machine learning can include supervised learning, unsupervised learning, and reinforcement learning. Among them, unsupervised learning can also be called non-supervised learning.

[0161] Supervised learning is based on the collected sample values and sample labels, and uses machine learning algorithms to learn the mapping relationship from sample values to sample labels, and expresses the learned mapping relationship with an AI model. The process of training a machine learning model is the process of learning this mapping relationship. During the training process, the sample values are input into the model to obtain the predicted values of the model, and the model parameters are optimized by calculating the error between the predicted values of the model and the sample labels (ideal values). After the mapping relationship learning is completed, the learned mapping can be used to predict new sample labels. The mapping relationship learned by supervised learning can include linear mapping or non-linear mapping. According to the type of labels, the learning tasks can be divided into classification tasks and regression tasks.

[0162] Unsupervised learning is based on the collected sample values and uses algorithms to discover the internal patterns of the samples by itself. In unsupervised learning, there is a type of algorithm that uses the samples themselves as supervision signals, that is, the model learns the mapping relationship from samples to samples, which is called self-supervised learning. During training, the model parameters are optimized by calculating the error between the predicted values of the model and the samples themselves. Self-supervised learning can be used in applications such as signal compression and decompression recovery. Common algorithms include autoencoders and adversarial generative networks, etc.

[0163] Reinforcement learning is different from supervised learning. It is a type of algorithm that learns strategies to solve problems by interacting with the environment. Different from supervised and unsupervised learning, there is no explicit "correct" action label data in reinforcement learning problems. The algorithm needs to interact with the environment to obtain the reward signal feedback from the environment, and then adjust the decision-making actions to obtain a larger numerical value of the reward signal. In downlink power control, for example, the reinforcement learning model adjusts the downlink transmission power of each user according to the total system throughput rate fed back by the wireless network, and then expects to obtain a higher system throughput rate. The goal of reinforcement learning is also to learn the mapping relationship between the environmental state and the optimal (e.g., the best) decision-making actions. However, because the label of the "correct action" cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action". The training of reinforcement learning is achieved through iterative interaction with the environment.

[0164] Neural network (NN) is a specific model in machine learning technology. According to the universal approximation theorem, neural networks can theoretically approximate any continuous function, enabling neural networks to have the ability to learn any mapping. Traditional communication systems need to rely on rich expert knowledge to design communication modules, while deep learning communication systems based on neural networks can automatically discover implicit pattern structures from large datasets, establish the mapping relationship between data, and obtain better performance than traditional modeling methods.

[0165] The idea of neural networks comes from the neuron structure of the brain tissue. For example, each neuron performs a weighted sum operation on its input values and outputs the operation result through an activation function.

[0166] As Figure 2a shown, it is a schematic diagram of the neuron structure. Assume that the input of the neuron is x = [x 0 , x 1 , …, x n , and the weights corresponding to each input are w = [w, w 1 , …, w n , where n is a positive integer, and w i and x i can be various possible types such as decimals, integers (e.g., 0, positive integers, or negative integers, etc.), or complex numbers. w i as the weight of x i is used to weight x i . The bias for weighted summation of the input values according to the weights is, for example, b. There can be various forms of activation functions. Assume that the activation function of a neuron is: y = f(z) = max(0, z), then the output of this neuron is: For another example, if the activation function of a neuron is: y = f(z) = z, then the output of this neuron is: Among them, b can be various possible types such as a decimal number, an integer (such as 0, a positive integer, or a negative integer), or a complex number. The activation functions of different neurons in the neural network can be the same or different.

[0167] In addition, a neural network generally includes multiple layers, and each layer can include one or more neurons. By increasing the depth and / or width of the neural network, the expressive ability of the neural network can be improved, providing a more powerful information extraction and abstract modeling ability for complex systems. Among them, the depth of the neural network can refer to the number of layers included in the neural network, and the number of neurons included in each layer can be called the width of that layer. In one implementation, the neural network includes an input layer and an output layer. The input layer of the neural network processes the received input information through neurons and passes the processing result to the output layer, and the output layer obtains the output result of the neural network. In another implementation, the neural network includes an input layer, a hidden layer, and an output layer. The input layer of the neural network processes the received input information through neurons and passes the processing result to the intermediate hidden layer. The hidden layer calculates the received processing result to obtain a calculation result, and the hidden layer passes the calculation result to the output layer or the next adjacent hidden layer, and finally the output layer obtains the output result of the neural network. Among them, a neural network can include one hidden layer or multiple successively connected hidden layers, without limitation.

[0168] The neural network is, for example, a deep neural network (DNN). According to the construction method of the network, the DNN can include a feedforward neural network (FNN), a convolutional neural network (CNN), and a recurrent neural network (RNN).

[0169] Figure 2b It is a schematic diagram of an FNN network. The characteristic of the FNN network is that neurons between adjacent layers are completely connected in pairs. This characteristic makes the FNN usually require a large amount of storage space and result in a high computational complexity.

[0170] A CNN is a neural network specialized for processing data with a similar grid structure. For example, time series data (discretely sampled on the time axis) and image data (two-dimensionally discretely sampled) can both be considered data with a similar grid structure. Instead of using all the input information for computation at once, a CNN uses a window of a fixed size to intercept partial information for convolution operations, which greatly reduces the computational amount of model parameters. Additionally, according to the different types of information intercepted by the window (such as people and objects in the same picture being different types of information), different convolution kernels can be used for each window, enabling the CNN to better extract the features of the input data.

[0171] An RNN is a type of DNN network that utilizes feedback time series information. Its input includes the new input value at the current moment and its own output value at the previous moment. RNNs are suitable for obtaining sequence features that are relevant in time and are particularly applicable to applications such as speech recognition and channel coding and decoding.

[0172] During the model training process of the above-mentioned machine learning, a loss function can be defined. The loss function describes the gap or difference between the output value of the model and the ideal target value. The loss function can be embodied in various forms, and there is no restriction on the specific form of the loss function. The model training process can be regarded as the following process: by adjusting some or all of the parameters of the model, the value of the loss function is made less than the threshold value or meets the target requirements.

[0173] The model can also be called an AI model, a rule, or other names, etc. An AI model can be considered a specific method for implementing AI functions. An AI model represents the mapping relationship or function between the input and output of the model. AI functions can include one or more of the following: data collection, model training (or model learning), model information release, model inference (or also called model reasoning, reasoning, or prediction, etc.), model monitoring or model verification, or inference result release, etc. AI functions can also be called AI (related) operations or AI-related functions.

[0174] Next, the implementation process of the neural network will be described exemplarily in conjunction with the accompanying drawings.

[0175] 1. Fully connected neural network, also known as a multilayer perceptron (MLP).

[0176] As Figure 2c shown, an MLP contains an input layer (left), an output layer (right), and multiple hidden layers (in the middle). Among them, each layer of the MLP contains several nodes, called neurons. Among them, the neurons in adjacent layers are pairwise connected.

[0177] Optionally, considering neurons in adjacent layers, the output h of a neuron in the next layer is the weighted sum of all the neurons x in the previous layer connected to it, followed by an activation function, and can be expressed as:

[0178] h = f(wx + b).

[0179] Where w is the weight matrix, b is the bias vector, and f is the activation function.

[0180] Further optionally, the output of the neural network can be recursively expressed as:

[0181] y = f n (w n f n-1 (…)+b n ).

[0182] Where n is the index of the neural network layer, 1 <= n <= N, where N is the total number of layers in the neural network.

[0183] In other words, a neural network can be understood as a mapping relationship from an input data set to an output data set. Usually, neural networks are randomly initialized, and the process of obtaining this mapping relationship from random w and b using existing data is called the training of the neural network.

[0184] Optionally, the specific way of training is to evaluate the output result of the neural network using a loss function.

[0185] As Figure 2d shown, the error can be backpropagated, and the neural network parameters (including w and b) can be iteratively optimized by the method of gradient descent until the loss function reaches the minimum value, that is, the "preferred point (such as the optimal point)" in Figure 2d . It can be understood that the neural network parameters corresponding to the "preferred point (such as the optimal point)" in Figure 2d can be used as the neural network parameters in the trained AI model information.

[0186] Further optionally, the process of gradient descent can be expressed as:

[0187]

[0188] Where θ is the parameter to be optimized (including w and b), L is the loss function, η is the learning rate, which controls the step size of gradient descent, represents the derivative operation, represents the derivative of L with respect to θ.

[0189] Further optionally, the process of backpropagation utilizes the chain rule of partial derivatives.

[0190] AsFigure 2e As shown, the gradient of the previous layer's parameters can be recursively calculated from the gradient of the next layer's parameters, which can be expressed as:

[0191]

[0192] where w ij is the weight connecting node j to node i, and s i is the weighted sum of inputs on node i.

[0193] 2. Federated Learning (FL).

[0194] The concept of federated learning effectively solves the dilemmas faced by the current development of artificial intelligence. On the premise of fully protecting the privacy and security of user data, it enables each edge device and the central server to cooperate efficiently to complete the model learning task.

[0195] As Figure 2f shown, the FL architecture is a training architecture in the current FL field. Exemplarily, the FedAvg algorithm is the basic algorithm of FL, and its algorithm process is roughly as follows:

[0196] (1) The central server initializes the model to be trained and broadcasts it to all client devices.

[0197] (2) In the t-th round where t ∈ [1, T], client k ∈ [1, K] trains the received global model on the local dataset for E epochs to obtain the local training result and reports it to the central node.

[0198] (3) The central node aggregates the local training results from all (or part of) the clients. Assuming the set of clients uploading local models in the t-th round is the central server will perform weighted averaging with the number of samples of the corresponding clients as weights to obtain a new global model. The specific update rule is After that, the central server will broadcast the latest version of the global model to all client devices for a new round of training.

[0199] (4) Repeat steps (2) and (3) until the model finally converges or the number of training rounds reaches the upper limit.

[0200] In addition to reporting the local model it is also possible to report the local gradients of the training The central node will average the local gradients and update the global model according to the direction of this average gradient.

[0201] As can be seen, in the FL framework, the dataset exists at the distributed nodes. That is, the distributed nodes collect the local datasets and perform local training, and report the local results (models or gradients) obtained from the training to the central node. The central node itself does not have a dataset and is only responsible for fusing the training results of the distributed nodes to obtain the global model and distributing it to the distributed nodes.

[0202] 3. Decentralized learning. Different from federated learning, another distributed learning architecture is decentralized learning.

[0203] As Figure 2g shown, consider a fully distributed system without a central node. The design goal f(x) of the decentralized learning system is generally the mean of the objective functions f i (x) of each node, that is where n is the number of distributed nodes, x is the parameter to be optimized, and in machine learning, x is the parameter of the machine learning (such as neural network) model. Each node uses the local data and the local objective function f i (x) to calculate the local gradient and then sends it to the neighboring nodes that are communication-reachable. After any node receives the gradient information sent by its neighboring nodes, it can update the parameter x of the local model according to the following formula:

[0204]

[0205] where represents the parameter of the local model after the (k + 1)th (k is a natural number) update in the ith node, represents the parameter of the local model after the kth update in the ith node (if k is 0, it represents the parameter of the local model of the ith node that has not participated in the update), α k represents the tuning coefficient, N i is the set of neighboring nodes of node i, and |N i | represents the number of elements in the set of neighboring nodes of node i, that is, the number of neighboring nodes of node i. Through the information interaction between nodes, the decentralized learning system will finally learn a unified model.

[0206] The technical solution provided by this application can be applied to a wireless communication system (such as Figure 1a or Figure 1b the system shown). In a wireless communication system, communication nodes generally have signal transceiver capabilities and computing capabilities. Taking a network device with computing capabilities as an example, the computing capabilities of the network device mainly provide computing power support for the signal transceiver capabilities (for example: performing transmission processing and reception processing on signals) to achieve the communication tasks between the network device and other communication nodes.

[0207] In a communication network, the computing power of communication nodes may have surplus computing power in addition to providing computing power support for the above communication tasks. Therefore, how to utilize this computing power is a technical problem that needs to be solved urgently.

[0208] In one possible implementation, the communication node can be used as a participating node of the AI ​​learning system, and the computing power of the communication node is applied to a certain link of the AI ​​learning system. With the advent of the era of large models, deep learning models with massive parameters, such as bidirectional encoder representations from transformers (BERT) and generative pre-trained transformer (GPT), can complete more and more complex tasks and achieve better performance. However, for large models, even the reasoning process of the model will be limited by the device capacity, so generally large models are stored on cloud central servers. At the same time, each device in the network generates a huge amount of raw data every day, which requires multiple calls to the large model for reasoning. Generally speaking, the device (such as a communication node) can send data to the central server, the central server uses the data for reasoning, and then the central server returns the reasoning result to the device. This process will consume a lot of communication resources for data transmission, and the privacy of device data will also be at risk.

[0209] In order to better save communication overhead and protect the privacy of user data, scholars have proposed distributed reasoning technology for deep neural networks. The approach is to distribute the model to devices and use the local computing power of the devices to infer the model, thereby reducing communication overhead and obtaining data privacy protection. However, in the communication system, how to determine the AI ​​model used by the communication node (for example, how to generate and how to update it) has not yet been provided in relevant literature.

[0210] See also Figure 3 , is a schematic diagram of an implementation of the communication method provided in this application, and the method includes the following steps.

[0211] It should be noted that in Figure 3 The first communication device and the second communication device ( Figure 6 In the example, the second communication device and the third communication device are used as the execution subject of the interaction indication to illustrate the method, but the present application does not limit the execution subject of the interaction indication. Figure 3 and later Figure 6 In the embodiment, the execution subject of the method can be replaced by a chip, a chip system, a processor, a logic module or software in the communication device. Figure 3Among them, the first communication device may be a network device and the second communication device may be a terminal device, or both the first communication device and the second communication device are terminal devices (for example, this method may be applied to the communication process of different terminal devices in a sidelink communication scenario).

[0212] S301. The first communication device sends first information. Correspondingly, the second communication device receives the first information. Among them, the first information is used to determine a first AI model group, and the first AI model group includes the first AI model and the second AI model; among them, the first AI model is deployed on the first communication device, and the second AI model is deployed on the second communication device; the input of the first AI model includes the output of the second AI model, or the input of the second AI model includes the output of the first AI model.

[0213] S302. The second communication device sends second information. Correspondingly, the first communication device receives the second information. Among them, the second information includes the model parameters of the first AI model group or the model parameters of the first AI model.

[0214] In this application, terms such as AI model, neural network model, AI neural network model, machine learning model, AI processing model, etc. may be used interchangeably.

[0215] It should be understood that the first information sent by the first communication device in step S301 is used to determine the first AI model group. Among them, the first AI model group includes the first AI model and the second AI model. It can be understood that the function of the first AI model group is at least realized through the model processing of the first AI model and the model processing of the second AI model. In other words, after the first communication device receives the second information, the first communication device may deploy the first AI model on the first communication device and perform model processing on the first AI model through the model parameters of the first AI model group or the model parameters of the first AI model included in the second information; correspondingly, the second communication device may perform model processing on the second AI model deployed on the second communication device. Optionally, the model processing may include one or more of model update processing, model training processing, and model inference processing.

[0216] It should be understood that wireless communication signals (such as the transceiver of configuration information of communication resources, the transceiver of reference signals, etc.) may be transmitted between different communication devices (such as the first communication device and the second communication device).

[0217] Optionally, the AI models involved in this application (such as the first AI model, the second AI model, and the third to sixth AI models hereinafter) can be used to manage the wireless communication signal (including at least one of configuration, update, and optimization). For example, the AI model can include one or more of an AI model for modulation and / or demodulation, an AI model for channel prediction, an AI model for beam management, an AI model for assisted positioning, an AI model for channel compression, an AI model for resource scheduling, and an AI model for replacing one or more modules in a transmitter and / or a receiver. Alternatively, the AI models involved in this application can also be AI models for other AI tasks, such as an AI model for image recognition, an AI model for natural language processing, an AI model for computer vision, etc.

[0218] Optionally, when the first AI model group is regarded as one AI model, the first AI model and the second AI model can be understood as two AI sub-models in the one AI model.

[0219] In this application, when an AI model is deployed on a communication device (for example, the first AI model is deployed on the first communication device, and the second AI model is deployed on the second communication device, etc.), it can be understood that after the communication device obtains the model parameters of the AI model, the communication device obtains / generates / constructs the AI model based on the model parameters of the AI model, and subsequently, the communication device can perform model processing on the AI model.

[0220] Optionally, the model parameters can include one or more of the hyperparameters of the model, the data set of the model (including the input data of the model and the label data corresponding to the input data), and the structure parameters of the model.

[0221] Optionally, an AI model group can include two or more AI models. For example, in addition to the first AI model and the second AI model, the first AI model group can also include other AI models, and these other AI models can be deployed on communication devices different from the first communication device and the second communication device, which is not limited here.

[0222] In a possible implementation, the second communication device is a functional entity that determines a list of AI model groups based on the first information. The list of AI model groups includes one or more AI model groups, and the one or more AI model groups include the first AI model group. Specifically, the second communication device can communicate with one or more first communication devices, and the second communication device can receive information (such as one or more first information) from the one or more first communication devices to generate / obtain / determine one or more AI model groups. In other words, the second communication device can perform information collection and perform model generation based on the collected information. Subsequently, the second communication device can deploy AI models on one or more first communication devices.

[0223] Optionally, the list of AI model groups can include one or more AI model groups, and each AI model group can include two or more AI models. As described above, the relationship between an AI model group and an AI model can also be understood as the relationship between an AI model and an AI sub-model. Therefore, the list of AI model groups can also be replaced with a list of AI models, that is, the list of AI models can include one or more AI models.

[0224] Optionally, the list can be replaced with other terms, such as set, dictionary, combination, space, etc.

[0225] Optionally, the second communication device is a functional entity that determines a list of AI model groups based on the first information, including: the second communication device determines a list of AI model groups based on the first information, and a functional entity that selects some or all of the AI model groups used by the first communication device from the list of AI model groups. Specifically, after the second communication device determines the list of AI model groups based on the first information, the functions implemented by the second communication device can also include selecting some or all of the AI model groups used by the first communication device from the list of AI model groups. In other words, in addition to performing information collection and performing model generation based on the collected information, the second communication device can also perform model selection so that the second communication device can subsequently deploy AI models adapted to the one or more first communication devices on the one or more first communication devices.

[0226] For ease of understanding, the following will use Figure 4 and Figure 5 as shown in the example to give an example description of the AI models deployed by the first communication device and the second communication device.

[0227] As Figure 4In the example shown, the first AI model is deployed on the first communication device, the second AI model is deployed on the second communication device, and the input of the first AI model deployed on the first communication device includes the output of the second AI model deployed on the second communication device. In this example, taking the input data of the second AI model as X, after processing by the second AI model, the second communication device can obtain and send data Z; after transmission through the wireless channel, the data received by the first communication device is represented as (It is understandable that due to the transmission path loss and noise interference on the wireless channel, It may not be the same as Z. It can be understood as an estimate of Z or a measured value of Z, etc.). Thereafter, the first communication device can As the input of the first AI model, the data is processed by the first AI model to obtain

[0228] like Figure 5 In the example shown, the first AI model is deployed on the first communication device, the second AI model is deployed on the second communication device, and the input of the second AI model includes the output of the first AI model. In this example, taking the input data of the first AI model as X, after being processed by the first AI model, the first communication device can obtain and send data Z; after transmission through the wireless channel, the data received by the second communication device is represented as Thereafter, the second communication device may transmit the data As the input of the second AI model, the data is processed by the second AI model

[0229] It can be understood that the first communication device and the second communication device may be implemented in many ways.

[0230] For example, the second communication device may be a terminal device, and accordingly, the first communication device and the second communication device may communicate on a sidelink (SL). In this case, the first AI model and the second AI model may be referred to as an end-to-end model, or an end-to-end collaborative model, etc.

[0231] For another example, the second communication device may be a network device (e.g., an access network device), and accordingly, the first communication device and the second communication device may communicate on the uplink and downlink communication links. In this case, the first AI model and the second AI model may be referred to as an edge-end model, an edge-end collaborative model, an edge-end model, an edge-end collaborative model, etc. Exemplarily, when the first communication device is a terminal device and the second communication device is an access network device, Figure 4 The scenario shown can be understood as end-edge collaboration based on the downlink scenario. Figure 5 The scenario shown can be understood as end-edge collaboration implemented based on the uplink scenario.

[0232] It should be noted that in Figure 4 and Figure 5 the data Y can be the labeled data corresponding to the data X, and the correlation between the labeled data Y and the processing results of the first AI model and the second AI model can be used to detect or determine the processing performance of the first AI model and the second AI model. For example, this correlation can be determined by means of gradient information, loss function, etc.

[0233] From Figure 3 the implementation process shown, for the second communication device, after receiving the first information in step S301, the second communication device can perform the process of generating a model based on the first information to obtain a first group of AI models. The process by which the second communication device determines the first group of AI models based on the first information will be described exemplarily below.

[0234] First, the theoretical basis for the generation of the AI model is described through the implementation process of the following Method A.

[0235] Generally, in a traditional connection- or session-oriented network, the design goal between different communication devices (i.e., transceivers) is: to enable the receiver to accurately and errorlessly reply to all the data sent by the transmitter, that is, to pursue lossless data transmission. However, when facing future intelligent networks, due to the existence of massive data and the different purposes of different AI tasks, it may no longer be necessary to transmit all the data, but to transmit the data valuable for AI tasks. Therefore, the network may transmit the minimum amount of wireless data to optimize the performance of the AI model (for example, to maximize the accuracy of the AI model). To achieve this goal, in Figure 4 and Figure 5 the example shown, the performance of the AI model can be characterized based on the mutual information between different data.

[0236] As an implementation example, in Figure 4 and Figure 5 for the input data X of the AI model, the labeled data Y corresponding to the input data X, and the data Figure 4 received by the receiving party (such as the first communication device in Figure 5 or the second communication device in satisfy Method A:

[0237]

[0238] where I(a; b) represents the mutual information amount between variable a and variable b. Specifically, represents the data transmitted through the wireless channel The mutual information with the label data Y (the label data Y can be understood as the correct result / expected result of the AI task). The larger the value of this mutual information, the more the data transmitted through the wireless channel contains the information of the label data Y, which can be understood as the higher the accuracy of the AI model, that is, the better the model performance of the AI model. represents the mutual information quantity between the original input data X and the wireless link data The smaller this mutual information quantity is, the less data is transmitted in the wireless link, that is, the smaller the wireless communication overhead. The configurable parameter β (the value range of β can be [0, 1]) can control the ratio between the two mutual informations. Therefore, minimizing the above formula means: on the premise of ensuring that the wireless communication overhead is as small as possible, ensure that the correctness of the processing result of the AI model is maximized. The subscript "IB" of represents the information bottleneck (information bottleneck, IB) theory (or distributed information bottleneck, deterministic information bottleneck, other information theory, etc.). In other words, can be replaced by other symbols. This is just an implementation example here.

[0239] Exemplarily, based on the implementation of method A, during the generation of the AI model, the generation basis of the model can include one or more of the following data A to data C, that is, an AI model group can be generated based on the following data A to data C (for example, the second communication device can generate the first AI model group). The following will give an exemplary description of the data A to data C.

[0240] Data A. M pairs of data and labels as the input data (where M is the size of the batch data (batch size), x m represents the input data of the mth pair of data, and y m represents the label data of the mth pair of data).

[0241] Data B. The dimension of the data transmitted in the wireless link (for example Figure 4 or Figure 5 in Or the dimension of Z). Exemplarily, the dimension of the data can be represented as the number of tokens / words / markers (hereinafter uniformly referred to as tokens), or the dimension of the data can be represented as the dimension of the embedding vector. It can be understood that Token: a concept similar to "word", which can be understood as the basic unit of splitting the intermediate transmission quantity; Embedding: the vector representation of the intermediate transmission quantity. Tokens can be understood as each component unit in the Embedding vector, that is, the number of component units in the Embedding can be the dimension of the tokens.

[0242] Data C. Channel state information.

[0243] Optionally, the process of generating an AI model group based on one or more of Data A to Data C can be implemented by a neural network. That is, the input data of the neural network includes one or more of Data A to Data C, and after being processed by the neural network, the model parameters of an AI model group are obtained.

[0244] As an implementation example, the loss function of the neural network can be expressed as Method B:

[0245]

[0246] As another implementation example, in order to reduce the solution complexity, the calculation of the variational mutual information can be introduced. For example, the loss function of the neural network can be expressed as Method C:

[0247]

[0248] The subscript "VIB" of

[0249] φ: Neural network or model parameters arranged on the user side (such as the first communication device);

[0250] θ: Neural network or model parameters arranged on the base station side (such as the second communication device);

[0251] β: Lagrange multiplier, weighing the accuracy of the AI processing result and the wireless communication overhead;

[0252] P: The conditional probability density of given x;

[0253] q represents the variational probability density of

[0254] p and q actually represent different probability density functions.

[0255] Denotes the expectation / mean of the part in {·} given the known probability density function p(x,y).

[0256] Denotes the known probability density function given which, the expectation / mean of the part in {·} is taken.

[0257] Denotes the conditional probability distribution with parameter θ, which is a variational distribution form that can approximate the conditional probability

[0258] Denotes the conditional probability distribution with parameter φ.

[0259] Denotes the variational distribution form of the approximate probability distribution

[0260] Denotes the probability distribution and the probability distribution The Kullback-Leibler (KL) divergence between them.

[0261] As another implementation example, given the constraint of the wireless link bandwidth on the tokens / embedding dimension, the loss function of the neural network can be expressed as Method D:

[0262]

[0263] where s.t. Denotes that the constraint condition is Th_1 represents the maximum threshold of the wireless link bandwidth, and the physical meaning of the constraint condition is that the data volume transmitted on the wireless link satisfies the air interface bandwidth constraint. In other words, through Method D, the accuracy of the AI task can be maximized given that the information transmitted on the wireless channel satisfies the bandwidth constraint.

[0264] As another implementation example, given the constraint of the wireless link bandwidth on the tokens / embedding dimension, the loss function of the neural network can be expressed as Method E:

[0265]

[0266] where s.t. Denotes that the constraint condition is ​​Th_2 represents the lowest threshold value of the AI task accuracy, and the constraint condition The physical meaning of is that the accuracy of the AI task is greater than the lowest threshold value. In other words, through this method E, the amount of information transmitted over the wireless channel can be minimized on the premise that the accuracy of the AI task is greater than the lowest threshold value.

[0267] Based on the above implementation process, on the premise of constraining the tokens / embedding dimension according to the bandwidth, the inference accuracy of the obtained AI model is relatively high. Exemplarily, based on different data sets, the simulation results using the above method C are as follows: Canadian Institute for Advanced Research (CIFAR) data set test: training cycle (epoch)=319, intermediate output dimension (intermediate dim)=20, accuracy=92.37%.

[0268] Mixed National Institute of Standards and Technology database (MNIST) data set test: epoch=400, intermediate dim=64, accuracy=97.62%.

[0269] Among them, the intermediate output dimension is the dimension of the above Z / The accuracy is the accuracy of the AI task.

[0270] As can be seen from the previous description, the first information sent by the first communication device in step S301 can be used to determine the first AI model group. Based on the parameters involved in the processes shown in the above methods A to E, the first information may include one or more of the following information A to information E. In other words, the second communication device can obtain the parameters required by methods A to D through one or more of the information A to information E included in the following first information, and generate the first AI model group according to one of methods A to E.

[0271] Information A. First dimension information. Among them, when the input of the first AI model includes the output of the second AI model, the first dimension information is used to determine the dimension information of the input data of the first AI model or the dimension information of the output data of the second AI model.

[0272] Information B. Second dimension information. When the input of the second AI model includes the output of the first AI model, the second dimension information is used to determine the dimension information of the output data of the first AI model or the dimension information of the input data of the second AI model.

[0273] Information C. Input data of the first AI model and labeled data of the input data of the first AI model.

[0274] Information D. Local computing power status information of the first communication device.

[0275] Information E. Channel status information.

[0276] For Information A or Information B, the second communication device can determine the dimension information of the data transmitted on the communication link through the first information. For example, the dimension information can be the number of tokens, or the dimension of the embedding vector. When the communication bandwidth between the first communication device and the second communication device is fixed, since the dimension of the data transmitted on the communication link is related to the processing performance of the AI model, in this way, the process of the second communication device determining the first AI model group can be simplified, reducing the complexity of the second communication device while also improving the processing performance of the AI models included in the first AI model group.

[0277] Optionally, the dimension information includes at least one of the following: the upper limit value of the dimension, the lower limit value of the dimension, the dimension expected (or not expected) by the first communication device, and the value range of the dimension expected (or not expected) by the first communication device.

[0278] For example, when the above dimension information includes the upper limit value and / or the lower limit value of the dimension, the second communication device can use the range indicated by the upper limit value and / or the lower limit value as one of the bases for determining the AI model, which can improve the flexibility of the solution implementation.

[0279] For another example, when the above dimension information includes the dimension expected by the first communication device and / or the value range of the dimension expected by the first communication device, the AI model determined by the second communication device based on this dimension information can meet the expectations of the first communication device.

[0280] Optionally, in Information A or Information B, the first-dimensional information or the second-dimensional information is determined based on channel state information (CSI). Specifically, the first-dimensional information or the second-dimensional information included in the first information may be determined based on the channel state information, so that the first-dimensional information or the second-dimensional information can reflect to a certain extent the channel characteristics of the wireless channel between the first communication device and the second communication device, so that the AI model obtained based on the first information can be adapted to the channel characteristics of the wireless channel, in order to improve the transmission performance of the AI data corresponding to the AI model. Moreover, when the AI model obtained based on the first information can be adapted to the channel characteristics of the wireless channel, it can also make the transmission data of the wireless link meet the channel bandwidth requirements as much as possible, thereby improving the model performance of the AI models included in the first AI model group.

[0281] Optionally, the channel state information may include the channel information between the first communication device and the second communication device, and / or the channel information between the second communication device and the first communication device. Among them, when the first communication device is a terminal device and the second communication device is a network device, the channel information between the first communication device and the second communication device can be understood as uplink channel information, and the channel information between the second communication device and the first communication device can be understood as downlink channel information.

[0282] Optionally, the channel state information may be obtained based on a reference signal.

[0283] For example, when the first communication device and the second communication device communicate via a sidelink, the reference signal may include a sidelink - synchronization signal / physical broadcast channel block (sidelink SSB, SL-SSB, or S-SS / PSBCH block), a sidelink - channel state information reference signal (SL-CSI-RS), etc.

[0284] For another example, when the first communication device and the second communication device communicate via uplink and downlink, the reference signal may include a channel state information reference signal (CSI-RS), a sounding reference signal (SRS), etc.

[0285] For information C, when the first information includes the input data of the first AI model and the label data of the input data of the first AI model, since the input data can be used as the input of the first AI model and the label data can be used as one of the bases for determining the model processing performance of the first AI model, for the second communication device, the second communication device can obtain an AI model with better performance based on these two pieces of information.

[0286] In addition, for the second communication device, the second communication device can perform mathematical calculations based on mutual information with the AI data (such as the input data of the second AI model or the output data of the second AI model, etc.) transmitted and received by the second communication device on the wireless link based on these two pieces of information, and determine the first AI model group based on the result of the mathematical calculation, so as to improve the model performance of the AI models included in the first AI model group on the premise that the wireless link data meets the bandwidth.

[0287] For information D, when the first information includes the local computing power status information of the first communication device, since the complexity requirements of the model processing of the AI model may be related to the local computing power status of the first communication device. Therefore, for the second communication device, the first AI model group determined by the second communication device based on the local computing power status information can be adapted to the local computing power status of the first communication device, so as to provide the first AI model that meets the local computing power status and improve the success rate of the first communication device in performing model processing based on the first AI model.

[0288] For information E, when the first information includes the channel state information, since the channel state information can reflect the channel characteristics of the wireless channel between the first communication device and the second communication device. Therefore, for the second communication device, the first AI model group determined by the second communication device based on the channel state information can be adapted to the channel characteristics, so that the transmitted data on the wireless link can meet the channel bandwidth requirements as much as possible, in order to improve the transmission performance of the AI data corresponding to the AI model.

[0289] It can be understood that when the first information includes two or more of the above information A to information E, based on the technical gain brought by any one of the above descriptions, further superimposed gains can be obtained through these two or more pieces of information.

[0290] In a possible implementation, the first communication device sends first information in step S301. This first information is used to determine a first AI model group, including: this first information is used to update a second AI model group to obtain the first AI model group; the second AI model group includes a third AI model and a fourth AI model. The third AI model is deployed on the first communication device, and the fourth AI model is deployed on a second communication device. The input of the third AI model includes the output of the fourth AI model, or the input of the fourth AI includes the output of the third AI model. Specifically, for the second communication device, after receiving the first information, the second communication device can update the second AI model group based on the first information to obtain the first AI model group. In other words, the first information sent by the first communication device can be used to update other AI models, enabling the solution to be applicable to the AI model update scenario.

[0291] Optionally, "update" can be replaced with other terms, such as "modify", "iterate", "optimize", "process", etc.

[0292] Optionally, when the second AI model group is regarded as one AI model, the third AI model and the fourth AI model can be understood as two AI sub-models in this one AI model.

[0293] Optionally, the third AI model and the second AI model included in the second AI model group can be general models or dedicated models to achieve the update of different types of models.

[0294] It should be understood that a general model can be called a base model, a large model, or an L0 model. A dedicated model can be called a small model, an L1 model, an L2 model, etc.

[0295] Taking the large model as an example, a large model can refer to a machine learning model with a large number of parameters and a complex structure, capable of processing massive amounts of data and completing various complex tasks, such as natural language processing, computer vision, speech recognition, etc.

[0296] Optionally, a large model is usually constructed by a deep neural network and has billions or even hundreds of billions of parameters.

[0297] Optionally, the design purpose of a large model can be to improve the model's expressive ability and prediction performance, and it can handle more complex tasks and data.

[0298] Optionally, a large model can learn complex patterns and features by training massive amounts of data, has a stronger generalization ability, and can make accurate predictions for unprocessed data.

[0299] In contrast, a small model may refer to a model with fewer parameters and shallower layers. Generally, compared with small models, large models usually have more parameters and deeper layers, with stronger expressive power and higher accuracy, but also require more computing resources and time for training and inference, and are suitable for scenarios with large amounts of data and sufficient computing resources, such as cloud computing, high-performance computing, artificial intelligence, etc.

[0300] Optionally, small models have the advantages of being lightweight, highly efficient, and easy to deploy, and are suitable for scenarios with small amounts of data and limited computing resources, such as mobile applications, embedded devices, the Internet of Things, etc.

[0301] In a possible implementation manner, the first information sent by the first communication device in step S301 is information sent periodically, and / or the second information sent by the second communication device in step S302 is information sent periodically. Specifically, the first information may be one of the determining bases of the AI model, and the second information may deploy the AI model. Among them, by periodically sending the first information and / or the second information between the first communication device and the second communication device, the periodic determination and / or periodic deployment of the AI model can be realized, so as to achieve multiple iterative updates of the AI model through a periodic process.

[0302] In a possible implementation manner, the first information sent by the first communication device in step S301 is used to determine the first group of AI models, and the AI models in the first group of AI models are dedicated models. Specifically, the first communication device may be a terminal device. Therefore, the AI model deployed on the terminal device may be a dedicated model, and the first information sent by the terminal device may be used to determine the dedicated model. Since different terminal devices may have different end-side characteristics (such as different local data, different local computing powers, different channel characteristics, etc.), by deploying dedicated models in terminal devices, in this way, the AI models deployed in terminal devices can be adapted to the end-side characteristics of terminal devices, with a view to improving the model processing performance of the AI models.

[0303] Based on Figure 3In the technical solution shown, after the first communication device sends the first information for determining the first AI model group in step S301, the first communication device may receive second information in step S302. The second information includes the model parameters of the first AI model group or the model parameters of the first AI model in the first AI model group. In other words, as the receiver of the first information, the second communication device may determine the first AI model group based on the first information from the first communication device, and deploy the first AI model to the first communication device through the second information. Thus, when the communication device in the communication system is an AI participating node, while enabling the computing power of the communication device to be applied to the processing of the AI model, the first information from the first communication device can also be used as one of the bases for the second communication device to determine the AI model, so that the AI model determined by the second communication device can be adapted to the first communication device as much as possible to improve the processing performance of the subsequent first communication device based on the AI model for model processing.

[0304] Please refer to Figure 6 , which is a schematic diagram of an implementation of the communication method provided by this application. The method includes the following steps.

[0305] S601. The second communication device sends third information. Correspondingly, the third communication device receives the third information. The third information is used to determine a third AI model group, and the third AI model group includes the fifth AI model and the sixth AI model. The fifth AI model is deployed on the first communication device, and the sixth AI model is deployed on the second communication device. The input of the fifth AI model includes the output of the sixth AI model, or the input of the sixth AI includes the output of the fifth AI model.

[0306] S602. The third communication device sends fourth information. Correspondingly, the second communication device receives the fourth information. The fourth information includes the model parameters of the third AI model group.

[0307] It should be noted that the second communication device and the third communication device may have multiple implementation manners. Among them, the second communication device may be a terminal device or an access network device, and the third communication device may be a cloud server or a core network device. For example, when the third communication device is a cloud server, the second communication device may communicate with the cloud server through the core network device. Another example is that when the third communication device is a core network device, the second communication device may be a terminal device, and the terminal device may communicate with the core network device through the access network device. Another example is that when the third communication device is a core network device, the second communication device may be an access network device, and the access network device may communicate through the communication interface between the access network device and the core network device.

[0308] It should be understood that the third AI model group includes a fifth AI model and a sixth AI model. It can be understood that the functions of the third AI model group are at least realized through the model processing of the fifth AI model and the model processing of the sixth AI model. In other words, after the second communication device receives the fourth information, the second communication device can determine the model parameters of the fifth AI model and the model parameters of the sixth AI model. Moreover, the second communication device can deploy the fifth AI model in the first communication device and deploy the sixth AI model in the second communication device to implement the model processing of the fifth AI model and the sixth AI model. Optionally, the model processing may include one or more of model update processing, model training processing, and model inference processing.

[0309] Optionally, when the third AI model group is regarded as an AI model, the fifth AI model and the sixth AI model can be understood as two AI sub-models in the one AI model.

[0310] In a possible implementation manner, the third communication device is a functional entity that determines the third AI model group based on the third information. Specifically, the third communication device can communicate with one or more second communication devices, and the third communication device can receive information (such as one or more third information) from the one or more second communication devices to implement the generation / obtaining / determination of the third AI model group. In other words, the second communication device can perform information collection and perform model generation based on the collected information. Subsequently, the second communication device can deploy AI models in one or more second communication devices (and corresponding first communication devices).

[0311] Optionally, the AI models of the third AI model group are general models. In this way, the third communication device can determine general models through information (such as one or more third information) from the one or more second communication devices. Subsequently, multiple second communication devices and the first communication devices connected to each second communication device can all deploy general models with relatively high generalization and good versatility.

[0312] As can be seen from the foregoing description, the third information sent by the second communication device in step S601 can be used to determine the third AI model group. Based on the processes shown in the above-mentioned method A to method E, the third information includes one or more of the following information 1 to information 5. In other words, the third communication device can obtain the parameters required by method A to E through one or more of the information 1 to information 5 included in the following third information, and generate the third AI model group according to one of method A to E.

[0313] Information 1. Third-dimensional information. When the input of the fifth AI model includes the output of the sixth AI model, the third-dimensional information is used to determine the dimensional information of the input data of the fifth AI model or the dimensional information of the output data of the sixth AI model.

[0314] Information 2. Fourth-dimensional information. When the input of the sixth AI model includes the output of the fifth AI model, the fourth-dimensional information is used to determine the dimensional information of the output data of the fifth AI model or the dimensional information of the input data of the sixth AI model.

[0315] Information 3. Model parameters of the AI models in one or more groups of AI models; wherein, each group of AI models in the one or more groups of AI models includes a dedicated model deployed on the first communication device and a dedicated model deployed on the second communication device.

[0316] Information 4. Data from one or more first communication devices connected to the second communication device.

[0317] Information 5. Input data of the AI model deployed on the second communication device and label data of the input data of the AI model deployed on the second communication device.

[0318] For Information 1 and Information 2, the third communication device can determine the dimensional information of the data transmitted on the communication link between the first communication device and the second communication device through the third information. For example, the dimensional information can be the number of tokens, or the dimension of the embedding vector. When the communication bandwidth between the first communication device and the second communication device is fixed, since the dimension of the data transmitted on the communication link is related to the processing performance of the AI model, in this way, the implementation process for the third communication device to determine the first group of AI models can be simplified, reducing the complexity of the third communication device while also improving the processing performance of the AI models included in the first group of AI models.

[0319] Optionally, the dimensional information includes at least one of the following: the upper limit value of the dimension, the lower limit value of the dimension, the dimension expected by the second communication device (or the dimension not expected by the first communication device), the value range of the dimension expected by the second communication device (or the value range of the dimension not expected by the first communication device). Specifically, the dimensional information determined by the third-dimensional information or the fourth-dimensional information can include at least one of the above to improve the flexibility of the solution implementation.

[0320] Optionally, the dimensional information can include the value of at least one of the above, or the quantization value of the value of at least one of the above, or the index of the value of at least one of the above, the index of the quantization value of the value of at least one of the above, etc., or can be implemented in other ways, which is not limited here.

[0321] For example, when the above-mentioned dimensional information includes an upper limit value and / or a lower limit value of the dimension, the third communication device can use the range indicated by the upper limit value and / or the lower limit value as one of the bases for determining the AI ​​model, thereby improving the flexibility of the implementation of the solution.

[0322] For example, when the above-mentioned dimensional information includes the dimension expected by the second communication device and / or the value range of the dimension expected by the second communication device, the AI ​​model determined by the third communication device based on the dimensional information can meet the expectations of the second communication device.

[0323] Optionally, the third dimension information or the fourth dimension information is determined based on channel state information. Specifically, the third dimension information or the fourth dimension information contained in the third information can be determined based on the channel state information, so that the third dimension information or the fourth dimension information can reflect the channel characteristics of the wireless channel between the first communication device and the second communication device to a certain extent, so that the AI ​​model that can be obtained based on the third information can be adapted to the channel characteristics of the wireless channel, in order to improve the transmission performance of the AI ​​data corresponding to the AI ​​model. Moreover, in the case where the AI ​​model obtained based on the first information can be adapted to the channel characteristics of the wireless channel, the transmission data of the wireless link can also meet the channel bandwidth requirements as much as possible, thereby improving the model performance of the AI ​​model included in the first AI model group.

[0324] For information 3, when the third information includes model parameters of AI models in one or more AI model groups, the third communication device can obtain one or more dedicated models deployed in the first communication device and the second communication device based on the third information. In this way, the third communication device can obtain the model characteristics of the one or more dedicated models, and embody the obtained characteristics in the third AI model group to enhance the generalization (or universality) of the general model contained in the third AI model group.

[0325] For information 4, when the third information includes data from one or more first communication devices (such as terminal devices) connected to the second communication device, since different terminal devices may have different data characteristics (for example, different data may be collected at different geographical locations, different data may be collected at different times, different data may correspond to different wireless channels where users are located, etc.), in this way, the third communication device obtains a third AI model group based on these data characteristics to improve the generalization (or universality) of the general model contained in the third AI model group.

[0326] For Information 5, when the third information includes the input data of the AI model deployed in the second communication device and the label data of the input data of the AI model deployed in the second communication device, since the input data can be used as the input of the sixth AI model and the label data can be used as one of the bases for determining the model processing performance of the sixth AI model, for the third communication device, the third communication device can obtain an AI model with better performance based on these two pieces of information.

[0327] In addition, for the second communication device, the second communication device can perform mathematical calculations based on mutual information based on these two pieces of information and the AI data (such as the input data of the sixth AI model or the output data of the sixth AI model, etc.) transmitted and received by the second communication device on the wireless link, and determine the third AI model group based on the result of the mathematical calculation, so as to improve the model performance of the AI models included in the third AI model group on the premise that the wireless link data meets the bandwidth.

[0328] It can be understood that when the third information includes two or more of the above Information 1 to Information 5, based on the technical gain brought by any one of the above descriptions, further superimposed gains can be obtained through these two or more pieces of information.

[0329] Optionally, each piece of information included in the third information can be part of the information obtained by the second communication device by screening multiple pieces of information. The following will take the third information including Information 3 as an example for exemplary description.

[0330] As an implementation example, when the third information includes Information 3, the first communication device and the second communication device can deploy N (N is greater than or equal to 2) AI model groups. Each AI model group includes a dedicated model deployed in the first communication device and a dedicated model deployed in the second communication device. The Information 3 can include the model parameters of k (k is a positive integer) AI model groups among the N AI model groups.

[0331] As an example of information 3, the second communication device can determine k AI model groups from the N AI model groups based on target information (the target information can be used to determine a general AI model group, a general AI model, a benchmark AI model, etc.; or the target information can be the general AI model group itself, the general AI model itself, the benchmark AI model itself, etc.). For example, the second communication device can determine the difference between the characterization parameters (such as Logits) of the N AI model groups and the characterization parameters of the AI ​​model / AI model group determined by the target information (such as the cosine (cos) value corresponding to Logits), that is, the second communication device can determine N difference values, and determine the corresponding k AI model groups based on the larger k difference values ​​among the N difference values, and carry the model parameters of the k AI model groups in information 3.

[0332] As another example of information 3, the N AI model groups may include 2N dedicated models. For example, N of the 2N dedicated models are deployed in the first communication device, and the remaining N of the 2N dedicated models are deployed in the second communication device. For ease of reference, the N dedicated models deployed in the first communication device are hereinafter referred to as N. 1 The N dedicated models deployed in the second communication device are denoted as N 2 Thereafter, the second communication device may determine k AI model groups from the 2N AI models based on the target information (the target information may be used to determine a general AI model, a benchmark AI model, etc.; or the target information may be a general AI model itself, a benchmark AI model itself, etc.).

[0333] In addition, for any one of the 2N dedicated models, the second communication device can determine the difference between the characterization parameters (such as Logits) of the any one of the AI ​​models and the characterization parameters of the AI ​​model determined by the target information (such as the cosine (cos) value between Logits), that is, the second communication device can determine the 2N difference values ​​corresponding to the 2N dedicated models. Subsequently, the second communication device can determine N based on the 2N difference values. 1 The k AI model groups corresponding to the k AI model groups are determined by using the k larger difference values ​​among the N difference values ​​corresponding to the dedicated models, and the model parameters of the k AI model groups are carried in the information 3; or, the second communication device can determine N AI model groups based on the 2N difference values. 2 The k largest difference values ​​among the N difference values ​​corresponding to the dedicated models determine the corresponding k AI model groups, and the model parameters of the k AI model groups are carried in information 3.

[0334] Optionally, the target information may be pre-configured in the second communication device, or may be configured by a third communication device (or other equipment) to the second communication device, which is not limited here.

[0335] Similarly, in the case where the third information includes Information 1, Information 2, Information 4, or Information 5, the above implementation can also be referred to, and details are not described here.

[0336] In a possible implementation manner, the second communication device may send third information in step S601. The third information is used to determine a third AI model group, including: the third information is used to update a fourth AI model group to obtain the third AI model group; the fourth AI model group includes a seventh AI model and an eighth AI model. The seventh AI model is deployed on the first communication device, and the eighth AI model is deployed on the second communication device. The input of the seventh AI model includes the output of the eighth AI model, or the input of the eighth AI includes the output of the seventh AI model. Specifically, for the third communication device, after receiving the third information, the third communication device may update the fourth AI model group based on the third information to obtain the third AI model group. In other words, the third information sent by the second communication device can be used to update other AI models, so that the solution can be applied to the AI model update scenario. Optionally, when the fourth AI model group is regarded as one AI model, the seventh AI model and the eighth AI model can be understood as two AI sub-models in the one AI model.

[0337] In a possible implementation manner, the third information sent by the second communication device in step S601 is information sent periodically, and / or the fourth information sent by the third communication device in step S602 is information sent periodically. Specifically, the third information can be one of the determination bases of the AI model, and the fourth information can deploy the AI model. Among them, by periodically sending the third information and / or the fourth information between the second communication device and the third communication device, the periodic determination and / or periodic deployment of the AI model can be realized, so as to achieve multiple iterative updates of the AI model through a periodic process.

[0338] Based on Figure 6In the technical solution shown, after the second communication device sends the third information for determining the third AI model group in step S601, the second communication device may receive the fourth information in step S602. The third information includes the model parameters of the third AI model group. In other words, as the recipient of the third information, the third communication device may determine the third AI model group based on the third information from the second communication device, and enable the subsequent second communication device to deploy the fifth AI model in the first communication device and deploy the sixth AI model in the second communication device through the fourth information. Thus, when the communication device in the communication system is an AI participating node, while enabling the computing power of the communication device to be applied to the processing of the AI model, the third information from the second communication device can also be used as one of the bases for the third communication device to determine the AI model, so that the AI model determined by the third communication device can be as suitable as possible for the second communication device to improve the success rate of the subsequent second communication device in performing model processing on the AI model.

[0339] Please refer to Figure 7 In an embodiment of the present application, a communication device 700 is provided. The communication device 700 can implement the functions of the second communication device or the first communication device in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments. In the embodiment of the present application, the communication device 700 may be the first communication device (or the second communication device), or an integrated circuit or component inside the first communication device (or the second communication device), such as a chip.

[0340] It should be noted that the transceiver unit 702 may include a sending unit and a receiving unit, which are respectively used to perform sending and receiving.

[0341] In a possible implementation, when the device 700 is used to execute the method performed by the first communication device in the foregoing embodiments, the device 700 includes a processing unit 701 and a transceiver unit 702; the processing unit 701 is used to determine the first information; the transceiver unit 702 is used to send the first information, and the first information is used to determine the first artificial intelligence AI model group, and the first AI model group includes the first AI model and the second AI model; wherein, the first AI model is deployed in the first communication device, and the second AI model is deployed in the second communication device; the input of the first AI model includes the output of the second AI model, or the input of the second AI model includes the output of the first AI model; the transceiver unit 702 is further used to receive the second information from the second communication device, and the second information includes the model parameters of the first AI model group or the model parameters of the first AI model.

[0342] In a possible implementation, when the device 700 is used to execute the method performed by the second communication device in the foregoing embodiments, the device 700 includes a processing unit 701 and a transceiver unit 702; the transceiver unit 702 receives first information; the processing unit 701 is configured to determine a first AI model group based on the first information, and the first AI model group includes the first AI model and the second AI model; wherein, the first AI model is deployed on a first communication device, the second AI model is deployed on the second communication device, the input of the first AI model includes the output of the second AI model, or the input of the second AI includes the output of the first AI model; the transceiver unit 702 is further configured to send second information, and the second information includes the model parameters of the first AI model group or the model parameters of the first AI model.

[0343] In a possible implementation, when the device 700 is used to execute the method performed by the first communication device in the foregoing embodiments, the device 700 includes a processing unit 701 and a transceiver unit 702; the processing unit 701 is configured to determine third information; the transceiver unit 702 is configured to send third information, and the third information is used to determine a third AI model group, and the third AI model group includes the fifth AI model and the sixth AI model; wherein, the fifth AI model is deployed on the first communication device, the sixth AI model is deployed on the second communication device, the input of the fifth AI model includes the output of the sixth AI model, or the input of the sixth AI includes the output of the fifth AI model; the transceiver unit 702 is further configured to receive fourth information from a third communication device, and the fourth information includes the model parameters of the third AI model group.

[0344] In a possible implementation, when the device 700 is used to execute the method performed by the second communication device in the foregoing embodiments, the device 700 includes a processing unit 701 and a transceiver unit 702; the transceiver unit 702 is configured to receive third information; the processing unit 701 is configured to determine a third AI model group based on the third information, and the third AI model group includes the fifth AI model and the sixth AI model; wherein, the fifth AI model is deployed on the first communication device, the sixth AI model is deployed on the second communication device; the input of the fifth AI model includes the output of the sixth AI model, or the input of the sixth AI model includes the output of the fifth AI model; the transceiver unit 702 is further configured to send fourth information, and the fourth information includes the model parameters of the third AI model group.

[0345] It should be noted that for the content such as the information execution process of the units of the communication device 700 above, reference may be specifically made to the description in the method embodiments shown in the foregoing of this application, and details are not described herein again.

[0346] Please refer to Figure 8, which is another schematic structural diagram of the communication device 800 provided by this application. The communication device 800 includes a logic circuit 801 and an input / output interface 802. Among them, the communication device 800 can be a chip or an integrated circuit.

[0347] Among them, Figure 7 the shown transceiver unit 702 can be a communication interface, and this communication interface can be Figure 8 the input / output interface 802 in it. The input / output interface 802 can include an input interface and an output interface. Alternatively, this communication interface can also be a transceiver circuit, and this transceiver circuit can include an input interface circuit and an output interface circuit.

[0348] Optionally, the logic circuit 801 is used to determine the first information; the input / output interface 802 is used to send the first information, and the first information is used to determine the first artificial intelligence (AI) model group. The first AI model group includes the first AI model and the second AI model; among them, the first AI model is deployed in the first communication device, and the second AI model is deployed in the second communication device; the input of the first AI model includes the output of the second AI model, or the input of the second AI model includes the output of the first AI model; the input / output interface 802 is further used to receive the second information from the second communication device, and the second information includes the model parameters of the first AI model group or the model parameters of the first AI model.

[0349] Optionally, the input / output interface 802 receives the first information; the logic circuit 801 is used to determine the first AI model group based on the first information. The first AI model group includes the first AI model and the second AI model; among them, the first AI model is deployed in the first communication device, and the second AI model is deployed in the second communication device. The input of the first AI model includes the output of the second AI model, or the input of the second AI includes the output of the first AI model; the input / output interface 802 is further used to send the second information, and the second information includes the model parameters of the first AI model group or the model parameters of the first AI model.

[0350] Optionally, the logic circuit 801 is used to determine the third information; the input / output interface 802 is used to send the third information, and the third information is used to determine the third AI model group. The third AI model group includes the fifth AI model and the sixth AI model; among them, the fifth AI model is deployed in the first communication device, and the sixth AI model is deployed in the second communication device. The input of the fifth AI model includes the output of the sixth AI model, or the input of the sixth AI includes the output of the fifth AI model; the input / output interface 802 is further used to receive the fourth information from the third communication device, and the fourth information includes the model parameters of the third AI model group.

[0351] Optionally, the input / output interface 802 is used to receive third information; the logic circuit 801 is used to determine a third AI model group based on the third information, and the third AI model group includes the fifth AI model and the sixth AI model; wherein, the fifth AI model is deployed on the first communication device, and the sixth AI model is deployed on the second communication device; the input of the fifth AI model includes the output of the sixth AI model, or the input of the sixth AI model includes the output of the fifth AI model; the input / output interface 802 is further used to send fourth information, and the fourth information includes the model parameters of the third AI model group.

[0352] Wherein, the logic circuit 801 and the input / output interface 802 may also perform other steps executed by the first communication device or the second communication device in any of the embodiments and achieve corresponding beneficial effects, which will not be elaborated here.

[0353] In a possible implementation manner, Figure 7 the processing unit 701 shown may be Figure 8 the logic circuit 801 in

[0354] Optionally, the logic circuit 801 may be a processing device, and the functions of the processing device may be implemented partially or entirely by software. Among them, the functions of the processing device may be implemented partially or entirely by software.

[0355] Optionally, the processing device may include a memory and a processor. Among them, the memory is used to store a computer program, and the processor reads and executes the computer program stored in the memory to perform corresponding processing and / or steps in any method embodiment.

[0356] Optionally, the processing device may only include a processor. The memory for storing the computer program is located outside the processing device, and the processor is connected to the memory through a circuit / wire to read and execute the computer program stored in the memory. Among them, the memory and the processor may be integrated together or physically independent of each other.

[0357] Optionally, the processing device may be one or more chips or one or more integrated circuits. For example, the processing device may be one or more field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), system on chips (SoCs), central processor units (CPUs), network processors (NPs), digital signal processing circuits (DSPs), microcontroller units (MCUs), programmable logic devices (PLDs), or other integrated chips, or any combination of the above chips or processors, etc.

[0358] Please refer to Figure 9 , for the communication device 900 involved in the above embodiments provided by the embodiments of the present application. The communication device 900 may specifically be the communication device as the terminal device in the above embodiments. Figure 9 The example shown is implemented by the terminal device (or a component in the terminal device).

[0359] Among them, a possible schematic logical structure of the communication device 900 is shown. The communication device 900 may include but is not limited to at least one processor 901 and a communication port 902.

[0360] Among them, Figure 7 The shown transceiver unit 702 may be a communication interface, and this communication interface may be Figure 9 the communication port 902 in it. The communication port 902 may include an input interface and an output interface. Alternatively, the communication port 902 may also be a transceiver circuit, and this transceiver circuit may include an input interface circuit and an output interface circuit.

[0361] Further optionally, the device may further include at least one of a memory 903 and a bus 904. In the embodiments of the present application, the at least one processor 901 is used to control and process the actions of the communication device 900.

[0362] In addition, the processor 901 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, and so on. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0363] It should be noted that Figure 9 The communication device 900 shown can specifically be used to implement the steps implemented by the terminal device in the foregoing method embodiments and achieve the corresponding technical effects of the terminal device. Figure 9 For the specific implementation manners of the communication device shown, reference can be made to the descriptions in the foregoing method embodiments, and details will not be repeated here.

[0364] Please refer to Figure 10 , which is a schematic structural diagram of the communication device 1000 involved in the foregoing embodiments provided by the embodiments of this application. The communication device 1000 can specifically be the communication device acting as a network device in the foregoing embodiments. Figure 10 The example shown is implemented by a network device (or a component in the network device). Among them, the structure of the communication device can refer to Figure 10 the structure shown.

[0365] The communication device 1000 includes at least one processor 1011 and at least one network interface 1014. Further optionally, the communication device further includes at least one memory 1012, at least one transceiver 1013, and one or more antennas 1015. The processor 1011, the memory 1012, the transceiver 1013, and the network interface 1014 are connected, for example, through a bus. In the embodiments of this application, this connection can include various interfaces, transmission lines, or buses, and this embodiment does not limit this. The antenna 1015 is connected to the transceiver 1013. The network interface 1014 is used to enable the communication device to communicate with other communication devices through a communication link. For example, the network interface 1014 can include a network interface between the communication device and a core network device, such as an S1 interface, and the network interface can include a network interface between the communication device and other communication devices (such as other network devices or core network devices), such as an X2 or Xn interface.

[0366] Among them, Figure 7 the transceiver unit 702 shown can be a communication interface, and this communication interface can beFigure 10 The network interface 1014 therein, which may include an input interface and an output interface. Alternatively, the network interface 1014 may also be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0367] The processor 1011 is mainly used to process communication protocols and communication data, and to control the entire communication device, execute software programs, and process the data of software programs. For example, it is used to support the communication device to perform the actions described in the embodiments. The communication device may include a baseband processor and a central processor. The baseband processor is mainly used to process communication protocols and communication data, and the central processor is mainly used to control the entire terminal device, execute software programs, and process the data of software programs. Figure 10 The processor 1011 therein may integrate the functions of the baseband processor and the central processor. Those skilled in the art can understand that the baseband processor and the central processor may also be independent processors, interconnected through technologies such as a bus. Those skilled in the art can understand that the terminal device may include multiple baseband processors to adapt to different network modes, and the terminal device may include multiple central processors to enhance its processing ability. Each component of the terminal device may be connected through various buses. The baseband processor may also be referred to as a baseband processing circuit or a baseband processing chip. The central processor may also be referred to as a central processing circuit or a central processing chip. The function of processing communication protocols and communication data may be built into the processor or stored in the memory in the form of a software program, and the processor executes the software program to implement the baseband processing function.

[0368] The memory is mainly used to store software programs and data. The memory 1012 may exist independently and be connected to the processor 1011. Optionally, the memory 1012 may be integrated with the processor 1011, for example, integrated within a single chip. Among them, the memory 1012 can store the program code for implementing the technical solution of the embodiments of the present application and be controlled by the processor 1011 to execute. Various types of computer program codes being executed can also be regarded as the driver programs of the processor 1011.

[0369] Figure 10 Only one memory and one processor are shown. In an actual terminal device, there may be multiple processors and multiple memories. The memory may also be referred to as a storage medium or a storage device, etc. The memory may be a storage element on the same chip as the processor, that is, an on-chip storage element, or an independent storage element. The embodiments of the present application do not make any limitations in this regard.

[0370] The transceiver 1013 can be used to support the reception or transmission of radio frequency signals between a communication device and a terminal. The transceiver 1013 can be connected to the antenna 1015. The transceiver 1013 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 1015 can receive radio frequency signals. The receiver Rx of the transceiver 1013 is used to receive the radio frequency signals from the antenna, convert the radio frequency signals into digital baseband signals or digital intermediate frequency signals, and provide the digital baseband signals or digital intermediate frequency signals to the processor 1011 so that the processor 1011 can further process the digital baseband signals or digital intermediate frequency signals, such as demodulation processing and decoding processing. In addition, the transmitter Tx in the transceiver 1013 is also used to receive the modulated digital baseband signals or digital intermediate frequency signals from the processor 1011, convert the modulated digital baseband signals or digital intermediate frequency signals into radio frequency signals, and transmit the radio frequency signals through one or more antennas 1015. Specifically, the receiver Rx can selectively perform one-stage or multi-stage down-conversion processing and analog-to-digital conversion processing on the radio frequency signals to obtain digital baseband signals or digital intermediate frequency signals, and the order of the down-conversion processing and the analog-to-digital conversion processing can be adjusted. The transmitter Tx can selectively perform one-stage or multi-stage up-conversion processing and digital-to-analog conversion processing on the modulated digital baseband signals or digital intermediate frequency signals to obtain radio frequency signals, and the order of the up-conversion processing and the digital-to-analog conversion processing can be adjusted. Digital baseband signals and digital intermediate frequency signals can be collectively referred to as digital signals.

[0371] The transceiver 1013 can also be referred to as a transceiver unit, a transceiver, a transceiver device, etc. Optionally, the devices used to implement the receiving function in the transceiver unit can be regarded as a receiving unit, and the devices used to implement the transmitting function in the transceiver unit can be regarded as a transmitting unit. That is, the transceiver unit includes a receiving unit and a transmitting unit. The receiving unit can also be referred to as a receiver, an input port, a receiving circuit, etc., and the transmitting unit can be referred to as a transmitter, a transmitter, or a transmitting circuit, etc.

[0372] It should be noted that Figure 10 The illustrated communication device 1000 can specifically be used to implement the steps implemented by the network device in the foregoing method embodiments and achieve the corresponding technical effects of the network device. Figure 10 For the specific implementation manners of the illustrated communication device 1000, reference can be made to the descriptions in the foregoing method embodiments, and details are not described herein one by one.

[0373] Please refer to Figure 11 , which is a schematic structural diagram of the communication device involved in the foregoing embodiments provided in the embodiments of the present application.

[0374] It can be understood that the communication device 110 includes, for example, modules, units, components, circuits, or interfaces, etc., which are appropriately configured together to execute the technical solutions provided in this application. The communication device 110 can be the terminal device or network device described above, or a component (such as a chip) in these devices, for implementing the methods described in the following method embodiments. The communication device 110 includes one or more processors 111. The processor 111 can be a general-purpose processor or a dedicated processor, etc. For example, it can be a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control the communication device (such as a RAN node, terminal, or chip, etc.), execute software programs, and process the data of software programs.

[0375] Optionally, in one design, the processor 111 can include a program 113 (sometimes also referred to as code or instructions), and the program 113 can be run on the processor 111, so that the communication device 110 executes the methods described in the following embodiments. In another possible design, the communication device 110 includes a circuit ( Figure 11 not shown).

[0376] Optionally, the communication device 110 can include one or more memories 112, on which there is a program 114 (sometimes also referred to as code or instructions), and the program 114 can be run on the processor 111, so that the communication device 110 executes the methods described in the above method embodiments.

[0377] Optionally, the processor 111 and / or the memory 112 can include AI modules 117, 118, and the AI modules are used to implement AI-related functions. The AI modules can be implemented in a software, hardware, or software-hardware combination manner. For example, the AI module can include a radio intelligence control (RIC) module. For example, the AI module can be a near-real-time RIC or a non-real-time RIC.

[0378] Optionally, data can also be stored in the processor 111 and / or the memory 112. The processor and the memory can be set separately or integrated together.

[0379] Optionally, the communication device 110 can further include a transceiver 115 and / or an antenna 116. The processor 111 is sometimes also referred to as a processing unit, which controls the communication device (such as a RAN node or a terminal). The transceiver 115 is sometimes also referred to as a transceiver unit, transceiver, transceiver circuit, or transceiver, etc., and is used to implement the transceiver function of the communication device through the antenna 116.

[0380] Among them, Figure 7 the processing unit 701 shown may be the processor 111. Figure 7 the transceiver unit 702 shown may be a communication interface, and this communication interface may be Figure 11 the transceiver 115 in, and this transceiver 115 may include an input interface and an output interface. Alternatively, this transceiver 115 may also be a transceiver circuit, and this transceiver circuit may include an input interface circuit and an output interface circuit.

[0381] The embodiments of the present application also provide a computer-readable storage medium, which is used to store one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method described in the possible implementation manners of the first communication device or the second communication device in the foregoing embodiments.

[0382] The embodiments of the present application also provide a computer program product (or computer program). When the computer program product is executed by the processor, the processor executes the method of the possible implementation manners of the foregoing first communication device or second communication device.

[0383] The embodiments of the present application also provide a chip system, which includes at least one processor and is used to support a communication device to implement the functions involved in the possible implementation manners of the foregoing communication device. Optionally, the chip system further includes an interface circuit, and the interface circuit provides program instructions and / or data for the at least one processor. In a possible design, the chip system may further include a memory, which is used to store the necessary program instructions and data of the communication device. The chip system may be composed of chips or may include chips and other discrete devices, where the communication device may specifically be the first communication device or the second communication device in the foregoing method embodiments.

[0384] The embodiments of the present application also provide a communication system, and the network system architecture includes the first communication device and the second communication device in any of the foregoing embodiments.

[0385] In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point, the displayed or discussed couplings or direct couplings or communication connections to each other may be through some interfaces, and the indirect couplings or communication connections of devices or units may be in electrical, mechanical, or other forms.

[0386] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0387] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that makes a contribution, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

Claims

1. A communication method, characterized in that, the method is applied to a first communication device, and the method includes: sending first information, where the first information is used to determine a first artificial intelligence (AI) model group, and the first AI model group includes the first AI model and the second AI model; wherein, the first AI model is deployed on the first communication device, and the second AI model is deployed on a second communication device; the input of the first AI model includes the output of the second AI model, or the input of the second AI model includes the output of the first AI model; receiving second information from the second communication device, where the second information includes the model parameters of the first AI model group or the model parameters of the first AI model.

2. The method according to claim 1, characterized in that, the first information includes first dimension information or second dimension information; when the input of the first AI model includes the output of the second AI model, the first dimension information is used to determine the dimension information of the input data of the first AI model or the dimension information of the output data of the second AI model; when the input of the second AI model includes the output of the first AI model, the second dimension information is used to determine the dimension information of the output data of the first AI model or the dimension information of the input data of the second AI model.

3. The method according to claim 2, characterized in that, the dimension information includes at least one of the following: the upper limit value of the dimension, the lower limit value of the dimension, the dimension expected by the first communication device, and the value range of the dimension expected by the first communication device.

4. The method according to claim 2 or 3, characterized in that, the first dimension information or the second dimension information is determined based on channel state information.

5. The method according to any one of claims 1 to 4, characterized in that, the first information includes at least one of the following: the input data of the first AI model and the label data of the input data of the first AI model, the local computing power state information of the first communication device, and channel state information.

6. The method according to any one of claims 1 to 5, characterized in that, the first information is used to determine the first AI model group, including: the first information is used to update a second AI model group to obtain the first AI model group; the second AI model group includes a third AI model and a fourth AI model, the third AI model is deployed on the first communication device, the fourth AI model is deployed on the second communication device, the input of the third AI model includes the output of the fourth AI model, or the input of the fourth AI model includes the output of the third AI model.

7. The method according to any one of claims 1 to 6, further characterized in that the first information is information sent periodically, and / or the second information is information sent periodically.

8. The method according to any one of claims 1 to 7, characterized in that, the AI models in the first AI model group are dedicated models.

9. A communication method, characterized in that, Applied to a second communication device, the method includes: Receiving first information; Determining a first AI model group based on the first information, the first AI model group including the first AI model and a second AI model; wherein, the first AI model is deployed on a first communication device, the second AI model is deployed on the second communication device, the input of the first AI model includes the output of the second AI model, or, the input of the second AI includes the output of the first AI model; Sending second information, the second information including the model parameters of the first AI model group or the model parameters of the first AI model.

10. The method according to claim 9, wherein, The second communication device is a functional entity for determining a list of AI model groups based on the first information, the list of AI model groups including one or more AI model groups, and the one or more AI model groups including the first AI model group.

11. The method according to claim 10, wherein, The second communication device is a functional entity for determining a list of AI model groups based on the first information, and for selecting some or all of the AI model groups used by the first communication device from the list of AI model groups.

12. The method according to any one of claims 9 to 11, wherein, The first information includes first dimension information or second dimension information; In the case where the input of the first AI model includes the output of the second AI model, the first dimension information is used to determine the dimension information of the input data of the first AI model or the dimension information of the output data of the second AI model; In the case where the input of the second AI model includes the output of the first AI model, the second dimension information is used to determine the dimension information of the output data of the first AI model or the dimension information of the input data of the second AI model.

13. The method according to claim 12, wherein, The dimension information includes at least one of the following: The upper limit value of the dimension, the lower limit value of the dimension, the dimension expected by the first communication device, and the value range of the dimension expected by the first communication device.

14. The method according to claim 12 or 13, wherein, The first dimension information or the second dimension information is determined based on channel state information.

15. The method according to any one of claims 11 to 14, wherein, The first information includes at least one of the following: The input data of the first AI model and the label data of the input data of the first AI model, the local computing power status information of the first communication device, and channel state information.

16. The method according to any one of claims 11 to 15, wherein, The determining the first AI model group based on the first information includes: Update the second AI model group based on the first information to obtain the first AI model group; wherein, the second AI model group includes a third AI model and a fourth AI model, the third AI model is deployed on the first communication device, and the fourth AI model is deployed on the second communication device; the input of the third AI model includes the output of the fourth AI model, or the input of the fourth AI includes the output of the third AI model.

17. The method according to any one of claims 11 to 16, further characterized in that the first information is information sent periodically, and / or the second information is information sent periodically.

18. The method according to any one of claims 11 to 17, characterized in that the AI models of the first AI model group are dedicated models.

19. A communication device, characterized in that it includes a module for executing the method according to any one of claims 1 to 18.

20. A communication device, characterized in that it includes at least one processor, and the at least one processor is coupled to a memory; the at least one processor is configured to execute the method according to any one of claims 1 to 18.

21. The communication device according to claim 20, characterized in that the communication device is a chip or a chip system.

22. A readable storage medium, characterized in that the storage medium stores a computer program or instruction, and when the computer program or instruction is executed by a communication device, the method according to any one of claims 1 to 18 is implemented.

Images