Communication method and related device

Abstract

A communication method and a related device, used for implementing at least one of determination, updating, and deployment of AI models in communication networks by means of interaction between different communication apparatuses. In the method, a second communication apparatus serves as a receiver of first information, and the second communication apparatus can determine a first AI model group on the basis of the first information from a first communication apparatus and send to the first communication apparatus second information indicating a first AI model of the first AI model group. Thus, when the communication apparatuses in a communication system serve as AI participation nodes, the computing power of the communication apparatuses can be used for AI model processing, and the first information from the first communication apparatus can also be used as one basis for the second communication apparatus to determine the AI model, so that the AI model determined by the second communication apparatus can be adapted to the first communication apparatus as much as possible, thereby enhancing the processing performance of the first communication apparatus in subsequent model processing based on the AI model.

Description

A communication method and related equipment

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on December 29, 2023, with application number 202311863966.3 and application name “A Communication Method and Related Equipment”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and in particular to a communication method and related equipment. Background Art

[0003] Wireless communication can be the transmission communication between two or more communication nodes without propagating through conductors or cables. The communication nodes generally include network devices and terminal devices.

[0004] Currently, in wireless communication systems, communication nodes generally possess both signal transceiver capabilities and computing capabilities. For example, network devices with computing capabilities primarily provide computing power to support signal transceiver capabilities (e.g., processing both sending and receiving signals), enabling communication between the network device and other communication nodes.

[0005] However, in communication networks, communication nodes may have excess computing power beyond just supporting the aforementioned communication tasks. Therefore, how to utilize this computing power is a pressing technical issue. Summary of the Invention

[0006] The present application provides a communication method and related equipment for determining and deploying artificial intelligence (AI) models in a communication network through interaction between different communication devices, so that the computing power of the communication devices can be applied to the processing of AI models.

[0007] The first aspect of the present application provides a communication method, which is performed by a first communication device, which may be a communication device (such as a terminal device), or the first communication device may be a component in the communication device (such as a processor, chip or chip system, etc.), or the first 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 first communication device sends first information, and the first information is used to determine a first AI model group, and the first AI model group includes K AI models and a second AI model, where K is an integer greater than or equal to 1; wherein the input of any AI model in the K AI models includes the output of the second AI model, or the input of the second AI model includes the output of one or more AI models in the K AI models; the second AI model is deployed on the second communication device, and the K AI models are used to be deployed on M communication devices, and the M communication devices include the first communication device, and M is less than or equal to K; the first communication device receives second information, and the second information is used to determine the first AI model, and the first AI model includes one or more models in the K AI models.

[0008] Based on the above technical solution, the second communication device acts as the recipient 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 send the second information used to determine the first AI model in the first AI model group to the first communication device. 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 serve 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, thereby improving the processing performance of the subsequent model processing based on the AI ​​model by the first communication device.

[0009] 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.

[0010] It should be understood that the first AI model group includes K AI models and a second AI model. It can be understood that the functions of the first AI model group are implemented at least through model processing of the K AI models and model processing of the second AI model. In other words, after the first communication device receives the second information, the first communication device can determine the first AI model based on 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 can include one or more of model update processing, model training processing, and model inference processing.

[0011] Optionally, the M communication devices used to deploy K AI models can be referred to as a collaboration set of the second communication devices, or a collaboration set of the first AI model group, or a collaboration set of the second AI model.

[0012] Optionally, when the first AI model group is regarded as one AI model, the K AI models and the second AI model can be understood as different AI sub-models in the one AI model.

[0013] It should be understood that the second communication device may be implemented in various ways.

[0014] For example, any one of the M communication devices is a terminal device and the second communication device can be a terminal device. Accordingly, the first communication device and the second communication device can communicate on a sidelink (SL). In this case, the K AI models and the second AI model can be referred to as end-to-end models, or end-to-end collaborative models, etc. For example, taking the end-to-end collaborative model as an example, when K is equal to 1, it can be called a single-link end-to-end collaborative model; when K is greater than 1, it can be called a multi-link end-to-end collaborative model.

[0015] For another example, any of the M communication devices is a terminal device and the second communication device can be a network device (such as an access network device). Accordingly, the first communication device and the second communication device can communicate on the uplink and downlink communication links. In this case, the K AI models and the second AI model can be called edge-end models, edge-end collaborative models, end-edge models, end-edge collaborative models, etc. Exemplarily, taking the end-edge collaborative model as an example, when K is equal to 1, it can be called a single-link end-edge collaborative model; when K is greater than 1, it can be called a multi-link end-edge collaborative model.

[0016] It should be understood that deploying an AI model on a communication device (e.g., a first AI model deployed on a first communication device, a second AI model deployed on a second communication device, etc.) can be described as deploying an AI model on a communication device. In other words, after obtaining model parameters of an AI model, a communication device can obtain / generate / construct 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.

[0017] It should be understood that K AI models are used to be deployed on M communication devices, where M is less than or equal to K.

[0018] For example, when M is equal to K, different AI models among the K AI models can be deployed in different communication devices among the M communication devices. That is, the K AI models and the M communication devices can have a one-to-one correspondence. In other words, the i-th AI model among the K AI models is deployed in the i-th communication device among the M communication devices (where i ranges from 1 to K or 1 to M). Exemplarily, the first AI model deployed in the first communication device may include one of the K AI models.

[0019] For another example, when M is less than K, at least two of the K AI models can be deployed in one of the M communication devices. That is, the K AI models may not correspond one-to-one with the M communication devices. For example, a first AI model deployed in a first communication device may include at least two of the K AI models.

[0020] Optionally, the model parameters may include one or more of the model's hyperparameters, the model's dataset (including the model's input data and label data corresponding to the input data), and the model's structural parameters.

[0021] It should be understood that wireless communication signals (such as the transmission and reception of configuration information of communication resources, the transmission and reception of reference signals, etc.) can be transmitted between different communication devices (such as a first communication device and a second communication device). Optionally, the AI ​​model involved in this application (such as a first AI model, a second AI model, etc.) can be used to manage the wireless communication signal (including at least one of configuration, update, and optimization). For example, the AI ​​model may include 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 one or more AI models for replacing one or more modules in a transmitter and / or receiver. Alternatively, the AI ​​model involved in this application may also be an AI model 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.

[0022] In one possible implementation, before the first communication device receives the second information, the method also includes: the first communication device receives third information, and the third information is used to configure a mapping relationship between P dimensional information and Q indexes, where P and Q are both positive integers; the second information includes one or more indexes of the Q indexes, and the one or more indexes are used to determine one of the dimensional information in the P dimensional information.

[0023] In this application, index can be replaced by other terms, such as identification, number, etc.

[0024] Optionally, the mapping relationship of the third information configuration can be implemented through a table, a formula, etc.

[0025] Based on the above technical solution, a first communication device can receive third information for configuring a mapping relationship between P pieces of dimension information and Q indexes. Subsequently, the second information received by the first communication device may include one or more indices of the Q indexes, and the first communication device may determine one piece of dimension information from the P pieces of dimension information based on the one or more indices. Thus, by implementing the third information to configure the mapping relationship, the second information sent by the second communication device can indicate the dimension information by carrying the index, thereby reducing the indication overhead.

[0026] Optionally, the third information is layer 3 (layer 3, L3) signaling, and the second information is layer 1 (layer 1, L1) and / or layer 2 (layer 2, L2) signaling. For example, the L3 signaling may include non-access stratum (NAS) signaling and / or radio resource control (RRC) layer signaling. For another example, L1 signaling may be understood as physical layer signaling. For another example, L2 signaling may be understood as wireless network layer signaling, including at least one of medium access control (MAC) layer signaling, radio link control (RLC) signaling, packet data convergence protocol (PDCP) signaling, and service data adaptation protocol (SDAP) layer signaling.

[0027] In one possible implementation, the second information includes at least one of the following: model parameters of the first AI model, model parameters of the first AI model group, dimensional information of input data of the first AI model, and dimensional information of output data of the first AI model.

[0028] It is understood that when the second information includes dimensional information of the input data of the first AI model and / or dimensional information of the output data of the first AI model, the first communication device can update the initial model based on the dimensional information of the input data and / or the dimensional information of the output data to obtain the first AI model. Optionally, the initial model can be a model pre-configured in the first communication device or a model configured by the second communication device (such as the third AI model described below), which is not limited here.

[0029] Based on the above technical solution, the second information used to determine the first AI model may include at least one of the above items. In other words, the second communication device can deploy the first AI model on the first communication device through at least one of the above items to improve the flexibility of the solution implementation.

[0030] Optionally, the second information may be sent via one message / signaling or multiple messages / signaling, which is not limited here.

[0031] In one possible implementation, the first information includes first dimensional information or second dimensional information; when the input of the first AI model includes the output of the second AI model, the first dimensional information is used to determine the dimensional information of the input data of the first AI model or the dimensional 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 dimensional information is used to determine the dimensional information of the output data of the first AI model or the dimensional information of the input data of the second AI model.

[0032] 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. When the communication bandwidth between the first communication device and the second communication device is constant, since the dimension of the data transmitted on the communication link is related to the processing performance of the AI ​​model, this method can simplify the implementation process of the second communication device determining the first AI model group, 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.

[0033] In one possible implementation, the dimension information includes at least one of the following: an upper limit value of the dimension, a lower limit value of the dimension, the dimension expected by the first communication device, and a value range of the dimension expected by the first communication device.

[0034] Optionally, the dimensional information may include the value of at least one of the above items, or the quantized value of the value of at least one of the above items, or the index of the value of at least one of the above items, the index of the quantized value of the value of at least one of the above items, etc., or may be implemented in other ways, which are not limited here.

[0035] Based on the above technical solution, the dimensional information determined by the first dimensional information or the second dimensional information may include at least one of the above items to enhance the flexibility of the solution implementation.

[0036] For example, when the above-mentioned dimensional 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 implementation of the solution.

[0037] For example, when the above-mentioned dimensional 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 dimensional information can meet the expectations of the first communication device.

[0038] In a possible implementation, the first dimension information or the second dimension information is determined based on channel state information.

[0039] Based on the above technical solution, the first dimension information or the second dimension information contained in the first information can be determined based on the 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 AI ​​model that can be subsequently 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, 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.

[0040] Optionally, the channel state information may include channel information between the first communication device and the second communication device, and / or channel information between the second communication device and the first communication device. Where 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.

[0041] Optionally, the channel state information may be obtained based on a reference signal.

[0042] For example, in the case where 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 synchronization signal / physical broadcast channel block, sidelink SSB, SL-SSB, or S-SS / PSBCH block), a sidelink channel state information reference signal (sidelink channel state information reference signal, SL-CSI-RS), etc.

[0043] For 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.

[0044] In one possible implementation, the first information includes at least one of the following: input data of the first AI model and label data of the input data of the first AI model, local computing power status information of the first communication device, and channel status information.

[0045] Based on the above technical solution, the first information may include at least one of the above information, so that the second communication device can determine the first AI model group adapted for the first communication device based on the above at least one information.

[0046] In an implementation example, when the first information includes input data of a first AI model and label data of the input data of the first AI model, since the input data can be used as input of the first AI model, the label data can be used as one of the bases for determining the model processing performance of the first AI model. Therefore, for the second communication device, the second communication device can obtain an AI model with better performance based on these two pieces of information.

[0047] 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 sent and received by the second communication device on the wireless link (such as the input data of the second AI model or the output data of the second AI model, etc.), 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 under the premise that the wireless link data meets the bandwidth.

[0048] In another implementation example, when the first information includes local computing power status information of the first communication device, the complexity requirement of the AI ​​model's model processing 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 to provide a first AI model that meets the local computing power status, thereby improving the success rate of the first communication device's model processing based on the first AI model.

[0049] In another implementation example, when the first information includes 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, for the second communication device, the second communication device determines a first AI model group based on the channel state information to adapt to the channel characteristics, so that the transmission data of the wireless link meets the channel bandwidth requirements as much as possible, in order to improve the transmission performance of the AI ​​data corresponding to the AI ​​model.

[0050] It can be understood that when the first information includes two or more of the above-mentioned information, based on the technical gain brought by any one of the above-mentioned items, further superposition gain can be obtained through the two or more items of information.

[0051] Optionally, the first information may be sent via one message / signaling or multiple messages / signaling, which is not limited here.

[0052] In one possible implementation, the first information is used to determine a 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 X AI models and a fourth AI model, where X is an integer greater than or equal to 1; wherein the input of any AI model among the X AI models includes the output of the fourth AI model, or the input of the fourth AI model includes the output of any AI model among the X AI models; a third AI model among the X AI models is deployed on a first communication device, the third AI model including one or more AI models among the X AI models; the fourth AI model is deployed on a second communication device, and the X AI models are deployed on Y communication devices, where the Y communication devices include the first communication device, and Y is less than or equal to X.

[0053] Optionally, update can be replaced by other terms such as modification, iteration, optimization, processing, etc.

[0054] Optionally, when the second AI model group is regarded as one AI model, the X AI models and the fourth AI model can be understood as multiple AI sub-models in the one AI model.

[0055] 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 AI model update scenarios.

[0056] Optionally, the third AI model and the second AI model included in the second AI model group may be general models or dedicated models to enable updates of different types of models.

[0057] It should be understood that the general model can be called the basic model, large model or L0 model, and the specialized model can be called the small model, L1 model, L2 model, etc.

[0058] Taking large models as an example, large models can refer to machine learning models with a large number of parameters and complex structures, which can process massive data and complete various complex tasks, such as natural language processing, computer vision, speech recognition, etc.

[0059] Alternatively, large models are typically built from deep neural networks, with billions or even hundreds of billions of parameters.

[0060] Optionally, the purpose of designing a large model can be to improve the model's expressiveness and predictive performance, and to be able to handle more complex tasks and data.

[0061] Alternatively, large models can learn complex patterns and features by training on massive amounts of data, have stronger generalization capabilities, and can make accurate predictions on unprocessed data.

[0062] In contrast, a small model can refer to a model with fewer parameters and fewer layers. Generally speaking, compared to small models, large models usually have more parameters and deeper layers, and have stronger expressive power and higher accuracy, but also require more computing resources and time for training and inference. They are suitable for scenarios with large data volumes and abundant computing resources, such as cloud computing, high-performance computing, and artificial intelligence.

[0063] Alternatively, small models have the advantages of being lightweight, efficient, and easy to deploy, and are suitable for scenarios with small data volumes and limited computing resources, such as mobile applications, embedded devices, and the Internet of Things.

[0064] In one possible implementation, after the first communication device receives the second information, the method further includes: the first communication device receives fourth information, where the fourth information is used to instruct to stop processing the first AI model.

[0065] Based on the above technical solution, after the first communication device receives the second information used to determine the first AI model, the first communication device can perform model processing based on the determined first AI model. Thereafter, the first communication device can also receive fourth information for instructing to stop processing the first AI model, causing the first communication device to stop participating in the processing of the first AI model group, thereby freeing up resources of the first communication device and reducing transmission overhead of input data and / or output data corresponding to the first AI model.

[0066] In addition, when K is greater than 1, that is, the communication devices participating in the first AI model group can include other K-1 communication devices in addition to the first communication device. The first communication device can stop processing the first AI model through the instruction of the fourth information, and can implement pruning processing of some AI models (such as the first AI model) to prune inefficient devices / inefficient links and achieve the selection of a better (or optimal) collaboration set.

[0067] In one possible implementation, before the first communication device receives the fourth information, the method also includes: the first communication device sends fifth information, and the fifth information is used to determine the fourth information; wherein the fifth information includes at least one of the following: input data or output data of the first AI model, dimensional information of the input data of the first AI model or dimensional information of the output data of the first AI model, the dimension expected by the first communication device, the value range of the dimension expected by the first communication device, and the channel state information of the first communication device.

[0068] Based on the above technical solution, after the first communication device receives the second information for determining the first AI model, the first communication device can perform model processing based on the determined first AI model. Thereafter, the first communication device can send fifth information to facilitate the second communication device to determine fourth information based on the at least one item of information indicated by the fifth information. Thus, the fourth information instructing the first communication device to stop model processing can be determined based on the status information of the first communication device indicated by the fifth information, allowing the second communication device to implement pruning processing based on the status information of one or more communication devices in the collaborative set.

[0069] In a possible implementation, the method further includes: the first communication device sending sixth information, where the sixth information is used to request to stop processing the first AI model.

[0070] Based on the above technical solution, after a first communication device receives second information for determining a first AI model, the first communication device may perform model processing based on the determined first AI model. Thereafter, the first communication device may send sixth information for requesting that processing of the first AI model be stopped, so that the second communication device can determine fourth information based on the sixth information. Thus, the fourth information instructing the first communication device to stop model processing may be determined based on the first communication device's request, allowing the second communication device to implement pruning based on requests from one or more communication devices in the collaborative set.

[0071] Optionally, the first communication device may trigger the determination (or transmission) of the sixth information based on multiple trigger conditions. For example, the trigger condition may include: the first communication device determines that the channel state indicated by the channel state information is lower than or equal to a threshold, the first communication device determines that the computing power indicated by its own computing power state information is lower than or equal to a threshold, and the first communication device determines that the dimension information of the input data or the dimension information of the output data of the first AI model indicates that the dimension is lower than a threshold. One or more of the following:

[0072] In a second aspect, the present application provides a communication method, which is performed by a second communication device, which may be a communication device (such as a network device or a terminal device), or a component of a communication device (such as a processor, a chip, or a chip system), or 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, the first AI model group including K AI models and a second AI model, where K is an integer greater than or equal to 1; wherein the input of any AI model in the K AI models includes the output of the second AI model, or the input of the second AI model includes the output of one or more AI models in the K AI models; the second AI model is deployed on the second communication device, and the K AI models are deployed on M communication devices, the M communication devices including the first communication device, where M is less than or equal to K; the second communication device sends second information, the second information being used to determine a first AI model, the first AI model being deployed on the first communication device, and the first AI model including one or more models in the K AI models.

[0073] Based on the above technical solution, the second communication device acts as the recipient 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 send the second information used to determine the first AI model in the first AI model group to the first communication device. 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 serve 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, thereby improving the processing performance of the subsequent model processing based on the AI ​​model by the first communication device.

[0074] In one possible implementation, before the second communication device sends the second information, the method also includes: the second communication device sends third information, and the third information is used to configure the mapping relationship between P dimensional information and Q indexes, where P and Q are both positive integers; the second information includes one or more indexes of the Q indexes, and the one or more indexes are used to determine one of the dimensional information in the P dimensional information.

[0075] Based on the above technical solution, the second communication device can send third information for configuring a mapping relationship between P pieces of dimension information and Q indexes. Thereafter, the second information sent by the second communication device can include one or more indices of the Q indexes, and the first communication device can determine one piece of dimension information from the P pieces of dimension information based on the one or more indices. Thus, by implementing the third information to configure the mapping relationship, the second information sent by the second communication device can indicate the dimension information by carrying an index, thereby reducing the indication overhead.

[0076] Optionally, the third information is layer 3 signaling, and the second information is layer 1 and / or layer 2 signaling.

[0077] In one possible implementation, the second information includes at least one of the following: model parameters of the first AI model, model parameters of the first AI model group, dimensional information of input data of the first AI model, and dimensional information of output data of the first AI model.

[0078] It is understood that when the second information includes dimensional information of the input data of the first AI model and / or dimensional information of the output data of the first AI model, the first communication device can update the initial model based on the dimensional information of the input data and / or the dimensional information of the output data to obtain the first AI model. Optionally, the initial model can be a model pre-configured in the first communication device or a model configured by the second communication device (such as the third AI model described below), which is not limited here.

[0079] Based on the above technical solution, the second information used to determine the first AI model may include at least one of the above items. In other words, the second communication device can deploy the first AI model on the first communication device through at least one of the above items to improve the flexibility of the solution implementation.

[0080] Optionally, the second information may be sent via one message / signaling or multiple messages / signaling, which is not limited here.

[0081] In one possible implementation, the first information includes first dimensional information or second dimensional information; when the input of the first AI model includes the output of the second AI model, the first dimensional information is used to determine the dimensional information of the input data of the first AI model or the dimensional 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 dimensional information is used to determine the dimensional information of the output data of the first AI model or the dimensional information of the input data of the second AI model.

[0082] 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. When the communication bandwidth between the first communication device and the second communication device is constant, since the dimension of the data transmitted on the communication link is related to the processing performance of the AI ​​model, this method can simplify the implementation process of the second communication device determining the first AI model group, 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.

[0083] In one possible implementation, the dimension information includes at least one of the following: an upper limit value of the dimension, a lower limit value of the dimension, the dimension expected by the first communication device, and a value range of the dimension expected by the first communication device.

[0084] Optionally, the dimensional information may include the value of at least one of the above items, or the quantized value of the value of at least one of the above items, or the index of the value of at least one of the above items, the index of the quantized value of the value of at least one of the above items, etc., or may be implemented in other ways, which are not limited here.

[0085] Based on the above technical solution, the dimensional information determined by the first dimensional information or the second dimensional information may include at least one of the above items to enhance the flexibility of the solution implementation.

[0086] For example, when the above-mentioned dimensional 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 implementation of the solution.

[0087] For example, when the above-mentioned dimensional 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 dimensional information can meet the expectations of the first communication device.

[0088] In a possible implementation, the first dimension information or the second dimension information is determined based on channel state information.

[0089] Based on the above technical solution, the first dimension information or the second dimension information contained in the first information can be determined based on the 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 AI ​​model that can be subsequently 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, 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.

[0090] In one possible implementation, the first information includes at least one of the following: input data of the first AI model and label data of the input data of the first AI model, local computing power status information of the first communication device, and channel status information.

[0091] Based on the above technical solution, the first information may include at least one of the above information, so that the second communication device can determine the first AI model group adapted for the first communication device based on the at least one of the above information. The specific possible implementation of the first information can refer to the relevant content of the first aspect and will not be repeated here.

[0092] In one possible implementation, after the second communication device sends the second information, the method further includes: the second communication device sends fourth information, where the fourth information is used to instruct to stop processing the first AI model.

[0093] Based on the above technical solution, after the first communication device receives the second information used to determine the first AI model, the first communication device can perform model processing based on the determined first AI model. Thereafter, the second communication device can also send fourth information to instruct the first communication device to stop processing the first AI model, causing the first communication device to stop participating in the processing of the first AI model group, thereby freeing up resources of the first communication device and reducing the transmission overhead of the input data and / or output data corresponding to the first AI model.

[0094] In addition, when K is greater than 1, that is, the communication devices participating in the first AI model group can include other K-1 communication devices in addition to the first communication device. The first communication device can stop processing the first AI model through the instruction of the fourth information, and can implement pruning processing of some AI models (such as the first AI model) to prune inefficient devices / inefficient links and achieve the selection of a better (or optimal) collaboration set.

[0095] In one possible implementation, before the second communication device sends the fourth information, the method also includes: the second communication device receives fifth information, and the fifth information is used to determine the fourth information; wherein the fifth information includes at least one of the following: input data or output data of the first AI model, dimensional information of the input data of the first AI model or dimensional information of the output data of the first AI model, the dimension expected by the first communication device, the value range of the dimension expected by the first communication device, and the channel state information of the first communication device.

[0096] Based on the above technical solution, after the first communication device receives the second information for determining the first AI model, the first communication device can perform model processing based on the determined first AI model. Thereafter, the second communication device can receive fifth information so that the second communication device can determine fourth information based on the at least one item of information indicated by the fifth information. Thus, the fourth information instructing the first communication device to stop model processing can be determined based on the status information of the first communication device indicated by the fifth information, so that the second communication device can implement pruning processing based on the status information of one or more communication devices in the collaborative set.

[0097] In one possible implementation, the method further includes: the second communication device receiving sixth information, where the sixth information is used to request to stop processing the first AI model.

[0098] Based on the above technical solution, after a first communication device receives second information for determining a first AI model, the first communication device may perform model processing based on the determined first AI model. Thereafter, the second communication device may receive sixth information for requesting that processing of the first AI model be stopped, so that the second communication device can determine fourth information based on the sixth information. Thus, the fourth information instructing the first communication device to stop model processing may be determined based on the first communication device's request, allowing the second communication device to implement pruning based on requests from one or more communication devices in the collaborative set.

[0099] The third aspect of the present application provides a communication method, which is performed by a first communication device, which may be a communication device (such as a terminal device), or the first communication device may be a partial component in the communication device (such as a processor, a chip or a chip system, etc.), or the first communication device may also be a logic module or software that can realize all or part of the functions of the communication device. In this method, the first communication device performs model processing based on a first AI model, and the first AI model and the second AI model are included in a first AI model group; wherein 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; the first communication device receives fourth information, and the fourth information is used to instruct to stop the processing of the first AI model.

[0100] Based on the above technical solution, during the process of the first communication device performing model processing based on the first AI model, the first communication device can receive fourth information for instructing to stop processing the first AI model, so that the first communication device stops participating in the processing of the first AI model group, thereby releasing the resources of the first communication device and saving the transmission overhead of the input data and / or output data corresponding to the first AI model.

[0101] In one possible implementation, the first AI model group also includes Z AI models, where Z is a positive integer, and the input of any AI model among the Z AI models includes the output of the second AI model, or the input of the second AI model includes the output of any one or more AI models among the Z AI models.

[0102] Based on the above technical solution, in addition to the first AI model deployed on the first communication device and the second AI model deployed on the second communication device, the first AI model group may also include Z AI models deployed on other communication devices. In other words, the communication devices participating in the first AI model group may include other communication devices in addition to the first communication device. The fourth information may be used to instruct the first communication device to stop processing the first AI model, thereby enabling pruning of some AI models (such as the first AI model) to remove inefficient devices / inefficient links and select a better (or optimal) collaboration set.

[0103] In one possible implementation, before the first communication device receives the fourth information, the method also includes: the first communication device sends fifth information, and the fifth information is used to determine the fourth information; wherein the fifth information includes at least one of the following: input data or output data of the first AI model, dimensional information of the input data of the first AI model or dimensional information of the output data of the first AI model, the dimension expected by the first communication device, the value range of the dimension expected by the first communication device, and the channel state information of the first communication device.

[0104] Based on the above technical solution, the first communication device can send fifth information so that the second communication device can determine fourth information based on the at least one item of information indicated by the fifth information. Thus, the fourth information instructing the first communication device to stop model processing can be determined based on the status information of the first communication device indicated by the fifth information, allowing the second communication device to implement pruning based on the status information of one or more communication devices in the cooperative set.

[0105] In a possible implementation, the method further includes: the first communication device sending sixth information, where the sixth information is used to request to stop processing the first AI model.

[0106] Based on the above technical solution, the first communication device can send sixth information requesting the suspension of processing of the first AI model, so that the second communication device can determine the fourth information based on the sixth information. Thus, the fourth information instructing the first communication device to suspend model processing can be determined based on the first communication device's request, allowing the second communication device to implement pruning based on the request of one or more communication devices in the collaborative set.

[0107] Optionally, the first communication device may trigger the determination (or transmission) of the sixth information based on multiple trigger conditions. For example, the trigger condition may include: the first communication device determines that the channel state indicated by the channel state information is lower than or equal to a threshold, the first communication device determines that the computing power indicated by its own computing power state information is lower than or equal to a threshold, and the first communication device determines that the dimension information of the input data or the dimension information of the output data of the first AI model indicates that the dimension is lower than a threshold. One or more of the following:

[0108] The fourth aspect of the present application provides a communication method, which is performed by a second communication device, which may be a communication device (such as a network device or a terminal device), or the second communication device may be a partial component 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 realize all or part of the functions of the communication device. In this method, the second communication device determines fourth information, and the fourth information is used to indicate to stop processing the first AI model, and the first AI model and the second AI model are included in the first AI model group; wherein 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; the second communication device sends the fourth information.

[0109] Based on the above technical solution, when the first communication device is performing model processing based on the first AI model, the second communication device can send fourth information for instructing to stop processing the first AI model, so that the first communication device stops participating in the processing of the first AI model group, thereby releasing the resources of the first communication device and saving the transmission overhead of the input data and / or output data corresponding to the first AI model.

[0110] In a possible implementation of the fourth aspect, the first AI model group also includes Z AI models, and the input of any AI model among the Z AI models includes the output of the second AI model, or the input of the second AI model includes the output of any one or more AI models among the Z AI models.

[0111] Based on the above technical solution, in addition to the first AI model deployed on the first communication device and the second AI model deployed on the second communication device, the first AI model group may also include Z AI models deployed on other communication devices. In other words, the communication devices participating in the first AI model group may include other communication devices in addition to the first communication device. The fourth information may be used to instruct the first communication device to stop processing the first AI model, thereby enabling pruning of some AI models (such as the first AI model) to remove inefficient devices / inefficient links and select a better (or optimal) collaboration set.

[0112] In a possible implementation of the fourth aspect, before the second communication device sends the fourth information, the method also includes: the second communication device receives fifth information, and the fifth information is used to determine the fourth information; wherein the fifth information includes at least one of the following: input data or output data of the first AI model, dimensional information of the input data of the first AI model or dimensional information of the output data of the first AI model, the dimension expected by the first communication device, the value range of the dimension expected by the first communication device, and the channel state information of the first communication device.

[0113] Based on the above technical solution, the second communication device can receive the fifth information, so that the second communication device can determine the fourth information based on the at least one item of information indicated by the fifth information. Thus, the fourth information instructing the first communication device to stop model processing can be determined based on the status information of the first communication device indicated by the fifth information, allowing the second communication device to implement pruning based on the status information of one or more communication devices in the cooperative set.

[0114] In a possible implementation manner of the fourth aspect, the method further includes: the second communication device receiving sixth information, where the sixth information is used to request to stop processing the first AI model.

[0115] Based on the above technical solution, the second communication device can receive sixth information requesting the first AI model to stop processing, so that the second communication device can determine fourth information based on the sixth information. Thus, the fourth information instructing the first communication device to stop model processing can be determined based on the first communication device's request, allowing the second communication device to implement pruning based on the request of one or more communication devices in the collaborative set.

[0116] In a fifth aspect, the present application provides a communication device, which is a first communication device and includes a transceiver unit and a processing unit; the processing unit is used to determine first information; the transceiver unit is used to send the first information, the first information is used to determine a first AI model group, the first AI model group includes K AI models and a second AI model, K is an integer greater than or equal to 1; wherein the input of any AI model in the K AI models includes the output of the second AI model, or the input of the second AI model includes the output of one or more AI models in the K AI models; the second AI model is deployed in a second communication device, the K AI models are used to be deployed in M ​​communication devices, the M communication devices include the first communication device, M is less than or equal to K; the transceiver unit is also used to receive second information, the second information is used to determine the first AI model, the first AI model includes one or more models in the K AI models.

[0117] In the fifth aspect of this application, the constituent modules of the communication device can also be used to execute the steps performed in each possible implementation method of the first aspect and achieve corresponding technical effects. For details, please refer to the first aspect and will not be repeated here.

[0118] In a sixth aspect, the present application provides a communication device, which is a second communication device and includes a transceiver and a processing unit. The transceiver receives first information; the processing unit is used to determine a first AI model group based on the first information, the first AI model group including K AI models and a second AI model, where K is an integer greater than or equal to 1; wherein the input of any AI model in the K AI models includes the output of the second AI model, or the input of the second AI model includes the output of one or more AI models in the K AI models; the second AI model is deployed in the second communication device, and the K AI models are deployed in M ​​communication devices, where the M communication devices include the first communication device, and M is less than or equal to K; the transceiver is also used to send second information, where the second information is used to determine the first AI model, the first AI model is deployed in the first communication device, and the first AI model includes one or more models in the K AI models.

[0119] In the sixth aspect of this application, the constituent modules of the communication device can also be used to execute the steps performed in each possible implementation method of the second aspect and achieve corresponding technical effects. For details, please refer to the second aspect and will not be repeated here.

[0120] In a seventh aspect, the present application provides a communication device, which is a first communication device and includes a transceiver unit and a processing unit; the processing unit is used to perform model processing based on a first AI model, and the first AI model and the second AI model are included in a first AI model group; wherein 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; the transceiver unit is used to receive fourth information, and the fourth information is used to instruct to stop processing of the first AI model.

[0121] The constituent modules of the communication device can also be used to execute the steps performed in each possible implementation method of the third aspect and achieve corresponding technical effects. For details, please refer to the third aspect and will not be repeated here.

[0122] In an eighth aspect, the present application provides a communication device, which is a second communication device, and includes a transceiver unit and a processing unit. The processing unit is used to determine fourth information, and the fourth information is used to instruct to stop processing of the first AI model. The first AI model and the second AI model are included in the first AI model group; wherein 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; the transceiver unit is used to send the fourth information.

[0123] The constituent modules of the communication device can also be used to execute the steps performed in each possible implementation method of the fourth aspect and achieve corresponding technical effects. For details, please refer to the fourth aspect and will not be repeated here.

[0124] In a ninth aspect, the present application provides a communication device, comprising at least one processor coupled to a memory; the memory is used to store programs or instructions; the at least one processor is used to execute the program or instructions so that the device implements the method described in any possible implementation method of any one of the first to fourth aspects.

[0125] In a possible implementation, the communication device further includes a memory. Optionally, the processor and the memory are integrated together.

[0126] In a tenth aspect, the present application provides a communication device comprising at least one logic circuit and an input / output interface; the logic circuit is used to execute the method described in any possible implementation of any one of the first to fourth aspects.

[0127] In an eleventh aspect, the present application provides a communication system, which includes the above-mentioned first communication device and second communication device.

[0128] A 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 possible implementation of any aspect of the first to fourth aspects above.

[0129] The thirteenth aspect of the present 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 possible implementation of any one of the first to fourth aspects above.

[0130] A fourteenth aspect of the present application provides a chip system, which includes at least one processor for supporting a communication device to implement the method described in any possible implementation of any one of the first to fourth aspects above.

[0131] In one possible design, the chip system may further include a memory for storing program instructions and data necessary for the communication device. The chip system may be composed of a chip or may include a chip and other discrete components. Optionally, the chip system may further include an interface circuit for providing program instructions and / or data to the at least one processor.

[0132] Among them, the technical effects brought about by any design method in the fifth to fourteenth aspects can refer to the technical effects brought about by the different design methods in the above-mentioned first to fourth aspects, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0133] Figures 1a and 1b are schematic diagrams of a communication system provided by this application;

[0134] Figures 2a to 2g are schematic diagrams of the AI ​​processing process involved in this application;

[0135] Figures 3 to 6 are interactive schematic diagrams of the communication method provided by this application;

[0136] 7 to 11 are schematic diagrams of the communication device provided in this application. DETAILED DESCRIPTION

[0137] First, some of the terms used in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0138] (1) Terminal device: It can be a wireless terminal device that can receive network device scheduling and instruction information. The wireless terminal device can be a device that provides voice and / or data connectivity to the user, or a handheld device with wireless connection function, or other processing device connected to a wireless modem.

[0139] Terminal devices can communicate with one or more core networks or the Internet via a radio access network (RAN). Terminal devices can be mobile terminal devices, such as mobile phones (also known as "cellular" phones, mobile phones), computers, and data cards. For example, they can be portable, pocket-sized, handheld, computer-built-in, or vehicle-mounted mobile devices that exchange voice and / or data with the radio access network. Examples include personal communication service (PCS) phones, cordless phones, Session Initiation Protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), tablet computers, and computers with wireless transceiver capabilities. Wireless terminal equipment can also be called system, subscriber unit, subscriber station, mobile station, mobile station (MS), remote station, access point (AP), remote terminal equipment (remote terminal), access terminal equipment (access terminal), user terminal equipment (user terminal), user agent, subscriber station (SS), customer premises equipment (CPE), terminal, user equipment (UE), mobile terminal (MT), etc.

[0140] As an example and not a limitation, in the embodiments of the present application, the terminal device may also be a wearable device. Wearable devices may also be referred to as wearable smart devices or smart wearable devices, etc., which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, etc., as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets, smart helmets, and smart jewelry for vital sign monitoring.

[0141] The terminal can also be a drone, a robot, a terminal in device-to-device communication (D2D), a terminal in vehicle to everything (V2X), 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 a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc.

[0142] In addition, the terminal device may also be a terminal device in a communication system that has evolved after the fifth generation (5G) communication system (e.g., a sixth generation (6G) communication system) or a terminal device in a future public land mobile network (PLMN). For example, 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 (with integrated satellite terminal functions), drones, and Internet of Things (IoT) devices.

[0143] In an embodiment of the present application, the terminal device may also obtain AI services provided by the network device. Optionally, the terminal device may also have AI processing capabilities.

[0144] (2) Network equipment: It can be a device in a wireless network. For example, the network equipment can be a RAN node (or device) that connects a terminal device to a wireless network, which can also be called a base station. Currently, some examples of RAN equipment include: 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. In addition, in a network structure, the network equipment can include a centralized unit (CU) node, a distributed unit (DU) node, or a RAN device including a CU node and a DU node.

[0145] Optionally, the RAN node can be a macro base station, micro base station, indoor base station, relay node, donor node, or a wireless controller in a cloud radio access network (CRAN) scenario. A RAN node can also be a server, wearable device, vehicle, or vehicle-mounted device. For example, the access network device in V2X technology can be a road side unit (RSU).

[0146] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, and different RAN nodes respectively implement part of the functions of the base station. For example, the RAN node can be a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). The CU and DU can be set separately, or they can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0147] In different systems, 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 radio access network (O-RAN or ORAN) system, CU may also be called O-CU (open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. For the convenience of description, this application takes CU, CU-CP, CU-UP, DU and RU as examples for description. Any unit of 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.

[0148] Communication between access network equipment and terminal devices follows a specific protocol layer structure. This 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: RRC layer, PDCP layer, RLC layer, MAC layer, or physical layer. The user plane protocol layer may include at least one of the following: SDAP layer, PDCP layer, RLC layer, MAC layer, or physical layer.

[0149] For the correspondence between network elements in the ORAN system and their achievable protocol layer functions, please refer to Table 1 below.

[0150] Table 1

[0151] The network device may be any other device that provides wireless communication functionality to the terminal device. The embodiments of this application do not limit the specific technology and device form used by the network device. For ease of description, the embodiments of this application do not limit this.

[0152] The network equipment may also include core network equipment, which may include, for example, 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 fourth generation (4G) network; and 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 equipment may also include other core network equipment in a 5G network and a next generation network of a 5G network.

[0153] In an embodiment of the present application, the above-mentioned network device may also have 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 on the network side (access network or core network), a computing power node, a RAN node with AI capabilities, a core network element with AI capabilities, etc.

[0154] In the embodiments of the present application, the apparatus for implementing the function of the network device may be the network device, or may be a device capable of supporting the network device in implementing the function, such as a chip system, which may be installed in the network device. In the technical solutions provided in the embodiments of the present application, the technical solutions provided in the embodiments of the present application are described by taking the network device as an example.

[0155] (3) Configuration and pre-configuration: In this application, configuration and pre-configuration are used simultaneously. Configuration refers to the network device / server sending some parameter configuration information or parameter values ​​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 can be parameter information or parameter values ​​pre-negotiated between the network device / server and the terminal device, or parameter information or parameter values ​​used by the base station / network device or terminal device as specified in the standard protocol, or parameter information or parameter values ​​pre-stored in the base station / server or terminal device. This application does not limit this.

[0156] Furthermore, these values ​​and parameters can be changed or updated.

[0157] (4) The terms "system" and "network" in the embodiments of the present application can be used interchangeably. "Multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. In addition, 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, timing, priority or importance of multiple objects.

[0158] (5) “Sending” and “receiving” in the embodiments of the present application indicate the direction of signal transmission. For example, “sending information to XX” can be understood as the destination of the information being XX, which can include direct sending through the air interface, as well as indirect sending through the air interface by other units or modules. “Receiving information from YY” can be understood as the source of the information being YY, which can include direct receiving from YY through the air interface, as well as indirect receiving from YY through the air interface from 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.

[0159] In other words, sending and receiving can be performed between devices, for example, between a network device and a terminal device, or can be performed within a device, for example, sending or receiving between components, modules, chips, software modules or hardware modules within the device through a bus, wiring or interface.

[0160] It is understandable that information may be processed between the source and destination of information transmission, such as coding, modulation, etc., but the destination can understand the valid information from the source. Similar expressions in this application can be understood similarly and will not be repeated.

[0161] (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. The information indicated by a certain information (such as the indication information described below) is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, directly indicating the information to be indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated may also be indirectly indicated by indicating other information, wherein the other information is associated with the information to be indicated; or only a part of the information to be indicated may be indicated, while the other part of the information to be indicated is known or agreed in advance. For example, the indication of specific information may be achieved by means of the arrangement order of each information agreed in advance (such as predefined by the protocol), thereby reducing the indication overhead to a certain extent. The present application does not limit the specific method of indication. It is understandable 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.

[0162] In this application, unless otherwise specified, the same or similar parts between the various embodiments can refer to each other. In the various embodiments of this application, and the various methods / designs / implementations in each embodiment, if there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments and the various methods / designs / implementations in each embodiment are consistent and can be referenced to each other. The technical features in different embodiments and the various methods / designs / implementations in each embodiment can be combined to form new embodiments, methods, or implementations according to their inherent logical relationships. The following description of the implementation methods of this application does not constitute a limitation on the scope of protection of this application.

[0163] 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.). The communication system includes at least one network device and / or at least one terminal device.

[0164] Please refer to Figure 1a, which is a schematic diagram of the architecture of a communication system 1000 used in an embodiment of the present application. As shown in Figure 1a, the communication system includes a RAN 100 and a core network 200. Optionally, the communication system 1000 may also include the Internet 300. The RAN 100 includes at least one RAN node (such as 110a and 110b in Figure 1a, collectively referred to as 110) and may also include at least one terminal (such as 120a-120j in Figure 1a, collectively referred to as 120). The RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1a). The terminal 120 is wirelessly connected to the RAN node 110, and the RAN node 110 is wirelessly or wiredly connected to the core network 200. The core network devices in the core network 200 and the RAN node 110 in the RAN 100 may be independent and different physical devices, or they may be the same physical device that integrates the logical functions of the core network devices and the logical functions of the RAN nodes. Terminals and RAN nodes may be connected to each other via wired or wireless means.

[0165] The RAN 100 may be an evolved universal terrestrial radio access (E-UTRA) system, a NR system, or a future radio access system defined in the 3rd Generation Partnership Project (3GPP). The RAN 100 may also include two or more of the aforementioned different radio access systems. The RAN 100 may also be an open RAN (O-RAN).

[0166] For ease of description, a base station is taken as an example of a RAN node for description below.

[0167] Base stations and terminals can be fixed or mobile. They can be deployed on land, indoors or outdoors, handheld or vehicle-mounted; on water; or on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of base stations and terminals.

[0168] The roles of base stations and terminals can be relative. For example, the helicopter or drone 120i in Figure 1a can be configured as a mobile base station. To terminals 120j accessing the wireless access network 100 via 120i, terminal 120i is a base station. However, to base station 110a, 120i is a terminal, meaning that communication between 110a and 120i occurs via a wireless air interface protocol. Of course, communication between 110a and 120i can also occur via a base station-to-base station interface protocol. In this case, 120i is also a base station relative to 110a. Therefore, base stations and terminals can be collectively referred to as communication devices. 110a and 110b in Figure 1a can be referred to as communication devices with base station functionality, while 120a-120j in Figure 1a can be referred to as communication devices with terminal functionality.

[0169] Communication between base stations and terminals, between base stations, and between terminals can be carried out through authorized spectrum, unauthorized spectrum, or both; communication can be carried out through spectrum below 6 gigahertz (GHz), spectrum above 6 GHz, or spectrum below 6 GHz and spectrum above 6 GHz. The embodiments of the present application do not limit the spectrum resources used for wireless communication.

[0170] In the embodiments of the present application, the functions of the base station may also be performed by a module (such as a chip) in the base station, or by a control subsystem that includes the base station functions. The control subsystem that includes the base station functions here may be a control center in the above-mentioned application scenarios such as smart grid, industrial control, smart transportation, and smart city. The functions of the terminal may also be performed by a module (such as a chip or modem) in the terminal, or by a device that includes the terminal functions.

[0171] Figure 1b is another schematic diagram of a communication system provided by an embodiment of the present application. In Figure 1b, the network device is a base station as an example for illustration, and device 1 and device 2 are both terminal devices. As shown in Figure 1b, the communication link between device 1 and device 2 can be called a sidelink (SL), and the communication link between device 1 (or device 2) and the base station can be called an uplink and a downlink, including an uplink and a downlink. It can be seen that a sidelink is a communication mechanism that allows different terminal devices to communicate directly without going through a network device.

[0172] Optionally, in SL, generally speaking, the transmitting device and the receiving device can be terminal devices or network devices of the same type, or they can be RSU and terminal devices, where RSU is a roadside station or roadside unit from a physical entity perspective, and can be a terminal device or a network device from a functional perspective, and this application does not impose any restrictions on 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 terminal device; or, the transmitting device is a terminal device and the receiving device is also a roadside station. In addition, the sidelink can also be a base station device of the same type or different types. In this case, the function of the sidelink is similar to that of the relay link, but the air interface technology used can be the same or different.

[0173] Exemplarily, the sidelink supports broadcast, unicast, and multicast.

[0174] When a terminal device (eg, device 1 ) communicates directly with another terminal device (eg, device 2 ) without going through a network device, the two terminal devices may communicate based on a proximity-based services communication 5 (PC5) port.

[0175] A typical application of sidelink is V2X communication, which utilizes and enhances current cellular network functions and elements to achieve low-latency and high-reliability communication between 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.

[0176] The technical solution provided in this application can be applied to a wireless communication system (e.g., the system shown in FIG. 1a or FIG. 1b ). For example, an AI network element can be introduced into the communication system provided in this application to implement some or all 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 a network element built into 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 (OAM) to implement AI-related functions. The OAM can be a network management device for a core network device and / or a network management device for an access network device. Alternatively, the AI ​​network element can also be an independently set network element in the communication system. Optionally, the terminal or the chip built into the terminal can also include an AI entity to implement AI-related functions.

[0177] The following is a brief introduction to artificial intelligence (AI) that may be involved in this application.

[0178] AI can imbue machines with human intelligence, for example, by enabling them to simulate certain intelligent human behaviors using computer hardware and software. Machine learning methods can be used to achieve AI. In machine learning, a machine uses training data to learn (or train) a model. This model represents the mapping from input to output. The learned model can be used for inference (or prediction), meaning it can be used to predict the output corresponding to a given input. This output can also be called an inference result (or prediction result).

[0179] Machine learning can include supervised learning, unsupervised learning, and reinforcement learning. Among them, unsupervised learning can also be called unsupervised learning.

[0180] Supervised learning uses machine learning algorithms to learn the mapping relationship between sample values ​​and sample labels based on collected sample values ​​and sample labels, and then expresses this learned mapping relationship using an AI model. The process of training a machine learning model is the process of learning this mapping relationship. During training, sample values ​​are input into the model to obtain the model's predicted values. The model parameters are optimized by calculating the error between the model's predicted values ​​and the sample labels (ideal values). Once the mapping relationship is learned, the learned mapping can be used to predict new sample labels. The mapping relationship learned by supervised learning can include linear mappings or nonlinear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0181] Unsupervised learning uses algorithms to discover inherent patterns in collected sample values. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals, meaning the model learns the mapping from one sample to another. This is called self-supervised learning. During training, the model parameters are optimized by calculating the error between the model's predictions and the samples themselves. Self-supervised learning can be used in signal compression and decompression recovery applications. Common algorithms include autoencoders and generative adversarial networks.

[0182] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems lack explicit label data for "correct" actions. Instead, the algorithm must interact with the environment to obtain reward signals from the environment, and then adjust its decision-making actions to maximize the reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmit power of each user based on the overall system throughput fed back by the wireless network, hoping to achieve higher system throughput. The goal of reinforcement learning is also to learn the mapping between environmental states and optimal (e.g., optimal) decision-making actions. However, because the labels for "correct actions" cannot be obtained in advance, network optimization cannot be achieved by calculating the error between actions and "correct actions." Reinforcement learning training is achieved through iterative interaction with the environment.

[0183] A neural network (NN) is a specific model in machine learning technology. According to the universal approximation theorem, NNs can theoretically approximate any continuous function, enabling them to learn arbitrary mappings. Traditional communication systems require extensive expert knowledge to design communication modules. However, deep learning communication systems based on neural networks can automatically discover implicit patterns in massive data sets and establish mapping relationships between data, achieving performance superior to traditional modeling methods.

[0184] The idea of ​​a neural network is derived from the neuronal structure of the brain. For example, each neuron performs a weighted sum operation on its input values ​​and outputs the result through an activation function.

[0185] As shown in Figure 2a, it is a schematic diagram of the neuron structure. Assume that the input of the neuron is x = [x0, x1, ..., x n ], and the weights corresponding to each input are w=[w,w1,…,w n ], where n is a positive integer, w i and x i It can be a decimal, an integer (such as 0, a positive integer or a negative integer, etc.), or a complex number. i As x i The weight of x iWeighted. The bias of the weighted sum of the input values ​​according to the weight is, for example, b. The activation function can take many forms. Assuming that the activation function of a neuron is: y = f(z) = max(0,z), then the output of the neuron is: For another example, if the activation function of a neuron is: y = f(z) = z, then the output of the neuron is: b can be a decimal, an integer (eg, 0, a positive integer, or a negative integer), or a complex number, etc. The activation functions of different neurons in a neural network can be the same or different.

[0186] Furthermore, neural networks generally include multiple layers, each of which may include one or more neurons. Increasing the depth and / or width of a neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can refer to the number of layers it comprises, and the number of neurons in each layer can be referred to as the width of that layer. In one implementation, a neural network includes an input layer and an output layer. The input layer processes the input information received by the neural network through neurons, passing the processing results to the output layer, which then obtains the output of the neural network. In another implementation, a neural network includes an input layer, a hidden layer, and an output layer. The input layer processes the input information received by the neural network through neurons, passing the processing results to an intermediate hidden layer. The hidden layer performs calculations on the received processing results to obtain a calculation result, which is then passed to the output layer or the next adjacent hidden layer, which ultimately obtains the output of the neural network. A neural network can include one hidden layer or multiple hidden layers connected in sequence, without limitation.

[0187] A neural network is, for example, a deep neural network (DNN). Depending on how the network is constructed, a DNN can include a feedforward neural network (FNN), a convolutional neural network (CNN), and a recurrent neural network (RNN).

[0188] Figure 2b is a schematic diagram of an FNN network. A characteristic of FNN networks is that neurons in adjacent layers are fully connected. This characteristic typically requires a large amount of storage space and results in high computational complexity.

[0189] CNN is a neural network specifically designed to process data with a grid-like structure. For example, time series data (discrete sampling along the time axis) and image data (discrete sampling along two dimensions) can both be considered grid-like data. CNNs do not utilize all input information at once for computation. Instead, they use a fixed-size window to intercept a portion of the information for convolution operations, significantly reducing the computational complexity of model parameters. Furthermore, depending on the type of information intercepted by the window (e.g., people and objects in an image represent different types of information), each window can use a different convolution kernel, enabling CNNs to better extract features from the input data.

[0190] RNNs are a type of DNN that utilizes feedback time series information. Their input consists of a new input value at the current moment and their own output value at the previous moment. RNNs are suitable for capturing temporally correlated sequence features and are particularly well-suited for applications such as speech recognition and channel coding.

[0191] During the machine learning model training process, a loss function can be defined. This function describes the gap or discrepancy between the model's output and the ideal target value. Loss functions can be expressed in various forms, and there are no restrictions on their specific form. The model training process can be viewed as adjusting some or all of the model's parameters to keep the loss function below a threshold or meet the target.

[0192] A model may also be referred to as an AI model, rule, or other name. An AI model can be considered a specific method for implementing an AI function. An AI model represents a mapping relationship or function between the input and output of a model. AI functions may include one or more of the following: data collection, model training (or model learning), model information release, model inference (or model reasoning, inference, or prediction, etc.), model monitoring or model verification, or inference result release, etc. AI functions may also be referred to as AI (related) operations, or AI-related functions.

[0193] The following is an exemplary description of the implementation process of the neural network with reference to the accompanying drawings.

[0194] 1. Fully connected neural network, also known as multilayer perceptron (MLP).

[0195] As shown in Figure 2c, an MLP consists of an input layer (left), an output layer (right), and multiple hidden layers (center). Each layer of the MLP contains several nodes, called neurons. Neurons in adjacent layers are connected to each other.

[0196] Optionally, considering neurons in two adjacent layers, the output h of a neuron in the next layer is the weighted sum of all neurons x connected to it in the previous layer and passes through an activation function, which can be expressed as: h=f(wx+b).

[0197] Among them, w is the weight matrix, b is the bias vector, and f is the activation function.

[0198] Alternatively, the output of the neural network can be recursively expressed as: y = f n (w n f n-1 (…)+b n ).

[0199] Where n is the index of the neural network layer, 1<=n<=N, where N is the total number of neural network layers.

[0200] In other words, a neural network can be understood as a mapping from an input data set to an output data set. Neural networks are typically initialized randomly, and the process of obtaining this mapping from random w and b using existing data is called neural network training.

[0201] Optionally, a specific training method is to use a loss function to evaluate the output results of the neural network.

[0202] As shown in Figure 2d, the error can be backpropagated, and the neural network parameters (including w and b) can be iteratively optimized using gradient descent until the loss function reaches a minimum, which is the "better point (e.g., optimal point)" in Figure 2d. It is understood that the neural network parameters corresponding to the "better point (e.g., optimal point)" in Figure 2d can be used as the neural network parameters in the trained AI model information.

[0203] Alternatively, the gradient descent process can be expressed as:

[0204] Among them, θ is the parameter to be optimized (including w and b), L is the loss function, and η is the learning rate, which controls the step size of gradient descent. represents the derivative operation, represents the derivative of θ with respect to L.

[0205] Optionally, the backpropagation process utilizes the chain rule for partial derivatives.

[0206] As shown in Figure 2e, the gradient of the previous layer parameters can be recursively calculated from the gradient of the next layer parameters, which can be expressed as:

[0207] Among them, w ij is the weight of node j connecting to node i, si is the weighted sum of the inputs to node i.

[0208] 2. Federated Learning (FL)

[0209] The concept of federated learning effectively solves the current difficulties faced by the development of artificial intelligence. On the premise of fully protecting user data privacy and security, it efficiently completes the model learning task by promoting the collaboration between various edge devices and central servers.

[0210] As shown in Figure 2f, the FL architecture is a training architecture currently used in the FL field. For example, the FedAvg algorithm is the basic algorithm of FL, and its algorithm flow is roughly as follows:

[0211] (1) The center initializes the model to be trained And broadcast it to all client devices.

[0212] (2) In the round t∈[1,T], client k∈[1,K] based on the local dataset For the received global model Perform E epochs of training to obtain local training results Report it to the central node.

[0213] (3) The central node aggregates and collects the local training results from all (or some) clients. Assume that the client set that uploads the local model in round t is The center will use the number of samples of the corresponding client as the weight to perform weighted averaging to obtain a new global model. The specific update rule is: The center then sends the latest version of the global model Broadcast to all client devices for a new round of training.

[0214] (4) Repeat steps (2) and (3) until the model finally converges or the number of training rounds reaches the upper limit.

[0215] In addition to reporting local models You can also use the local gradient of training After reporting, the central node averages the local gradients and updates the global model according to the direction of the average gradient.

[0216] As you can see, in the FL framework, datasets exist on distributed nodes. Distributed nodes collect local datasets, perform local training, and report the local training results (models or gradients) to the central node. The central node itself does not have a dataset; it is only responsible for fusing the training results of distributed nodes to obtain a global model and send it to the distributed nodes.

[0217] 3. Decentralized learning: Different from federated learning, decentralized learning is another distributed learning architecture.

[0218] As shown in Figure 2g, consider a fully distributed system without a central node. The design goal f(x) of a decentralized learning system is generally the goal f of each node. i The mean of (x), that is Where n is the number of distributed nodes, x is the parameter to be optimized. In machine learning, x is the parameter of the machine learning (such as neural network) model. Each node uses local data and local target f i (x) Calculate local gradient Then it is sent to the neighboring nodes that can be communicated with. After any node receives the gradient information sent by its neighbor, it can update the parameter x of the local model according to the following formula:

[0219] in, represents the parameters of the local model after the k+1th (k is a natural number) update in the i-th node, Represents the parameters of the local model after the kth update in the i-th node (if k is 0, it means is the parameter of the local model of the i-th node that does not participate in the update), α k Represents the tuning coefficient, N i is the set of neighbor nodes of node i, |N i | represents the number of elements in the neighbor node set of node i, that is, the number of neighbor nodes of node i. Through information interaction between nodes, the decentralized learning system will eventually learn a unified model.

[0220] The technical solutions provided in this application can be applied to wireless communication systems (e.g., the systems shown in Figures 1a and 1b). In wireless communication systems, communication nodes generally have both signal transceiver capabilities and computing capabilities. For example, network devices with computing capabilities primarily provide computing power to support signal transceiver capabilities (e.g., performing signal transmission and reception processing) to enable communication between the network device and other communication nodes.

[0221] In communication networks, communication nodes may have excess computing power beyond supporting the aforementioned communication tasks. Therefore, how to utilize this computing power is a pressing technical issue.

[0222] In one possible implementation, a communication node can act as a participating node in an AI learning system, applying its computing power to a specific component of the 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 transformers (GPT), can accomplish increasingly complex tasks and achieve superior performance. However, for large models, even the inference process is limited by device capacity, so large models are typically stored on central cloud servers. Furthermore, each device in the network generates a massive amount of raw data daily, which requires multiple inference calls on the large model. Typically, a device (such as a communication node) sends data to a central server, which then performs inference using the data and returns the inference results to the device. This process consumes significant communication resources for data transmission and also risks the privacy of device data.

[0223] To better reduce communication overhead and protect user data privacy, one possible implementation is to use distributed inference technology for deep neural networks. Specifically, this involves distributing models to devices and leveraging their local computing power to infer the models, thereby reducing communication overhead and ensuring data privacy. However, in communication systems, there is currently no solution for determining the AI ​​models used by communication nodes (for example, how they are generated and updated).

[0224] Please refer to FIG3 , which is a schematic diagram of an implementation of the communication method provided in this application. The method includes the following steps.

[0225] It should be noted that, in Figure 3 (and / or Figure 6 below), the method is illustrated by taking the first communication device and the second communication device as the execution subjects of the interaction diagram as an example, but the present application does not limit the execution subjects of the interaction diagram. For example, in Figure 3 (and / or Figure 6 below), 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. In Figure 3 (and / or Figure 6 below), the first communication device can be a network device and the second communication device can be a terminal device, or the first communication device and the second communication device are both terminal devices (for example, the method can be applied to the communication process of different terminal devices in a side link communication scenario).

[0226] S301. A first communication device sends first information, and a second communication device receives the first information accordingly. The first information is used to determine a first AI model group, where the first AI model group includes K AI models and a second AI model, where K is an integer greater than or equal to 1; the input of any AI model in the K AI models includes the output of the second AI model, or the input of the second AI model includes the output of one or more AI models in the K AI models; the second AI model is deployed on the second communication device, and the K AI models are deployed on M communication devices, where the M communication devices include the first communication device, and M is less than or equal to K.

[0227] S302. The second communication device sends second information, and the first communication device receives the second information accordingly. The second information is used to determine a first AI model, which includes one or more models among the K AI models.

[0228] 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.

[0229] 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. The first AI model group includes K AI models and a second AI model. It can be understood that the function of the first AI model group is implemented at least through the model processing of the K AI models 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 determine the first AI model through 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.

[0230] It should be understood that wireless communication signals (such as the transmission and reception of configuration information of communication resources, the transmission and reception of reference signals, etc.) can be transmitted between different communication devices (such as the first communication device and the second communication device).

[0231] Optionally, the AI ​​model involved in this application (such as the first AI model, the second AI model, etc.) can be used to manage the wireless communication signal (including at least one of configuration, update, and optimization). For example, the AI ​​model may include 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, or one or more AI models for replacing one or more modules in a transmitter and / or receiver. Alternatively, the AI ​​model involved in this application may also be an AI model 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.

[0232] Optionally, when the first AI model group is regarded as one AI model, the K AI models and the second AI model can be understood as different AI sub-models in the one AI model.

[0233] It should be understood that an AI model deployed on a communication device (for example, a first AI model deployed on a first communication device, a second AI model deployed on a second communication device, etc.) can be expressed as an AI model for deployment on a communication device. In other words, after a communication device obtains the model parameters of an AI model, it can obtain / generate / construct 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. Optionally, the model parameters may include one or more of the model's hyperparameters, the model's data set (including the model's input data and label data corresponding to the input data), and the model's structural parameters.

[0234] In one possible implementation, the second communication device is a functional entity that determines an AI model group list based on the first information, and the AI ​​model group list 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 (e.g., 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, and subsequently the second communication device can deploy the AI ​​model on one or more first communication devices.

[0235] 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 mentioned 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. To this end, 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.

[0236] Optionally, list can be replaced with other terms such as set, dictionary, combination, space, etc.

[0237] Optionally, the second communication device is a functional entity that determines the AI ​​model group list based on the first information, including: 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 in the AI ​​model group list. Specifically, after the second communication device determines the AI ​​model group list based on the first information, the function implemented by the second communication device may also include selecting some or all of the AI ​​model groups used by the first communication device in the AI ​​model group list. 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 an AI model that is compatible with the one or more first communication devices in one or more first communication devices.

[0238] It should be understood that K AI models are deployed on M communication devices, where M is less than or equal to K. When the values ​​of M and K are different, the K AI models may be implemented in different ways, which will be introduced below.

[0239] For example, when M is equal to K, different AI models among the K AI models can be deployed in different communication devices among the M communication devices. That is, the K AI models and the M communication devices can have a one-to-one correspondence. In other words, the i-th AI model among the K AI models can be deployed in the i-th communication device among the M communication devices (the value of i ranges from 1 to K or 1 to M). Exemplarily, the first AI model deployed in the first communication device may include one of the K AI models.

[0240] For another example, when M is less than K, at least two of the K AI models can be deployed in one of the M communication devices. That is, the K AI models may not correspond one-to-one with the M communication devices. For example, a first AI model deployed in a first communication device may include at least two of the K AI models.

[0241] Optionally, the M communication devices used to deploy K AI models can be referred to as a collaboration set of the second communication devices, or a collaboration set of the first AI model group, or a collaboration set of the second AI model.

[0242] For ease of understanding, the following will take the case where M is equal to K and K is greater than 1 (that is, M communication devices can be described as K communication devices) as an example to describe the AI ​​model deployed by K communication devices and the second communication device.

[0243] As shown in the example of FIG4 , the K communication devices may be the communication device 1, ..., communication device K in the figure, and the K AI models may be the AI ​​model 1, ..., AI model K in the figure. It should be understood that the first communication device may be one of the K communication devices, and the first AI model deployed on the first communication device may be one of the K AI models. In FIG4 , the input of the K AI models deployed on the K communication devices includes the output of the second AI model. For example, taking the input data of the second AI model as X as an example, after processing by the second AI model, the second communication device can obtain and send data Z1, ..., Z to the K communication devices respectively. K ; After transmission through the wireless channel, the data received by K communication devices are expressed as (It is understandable that due to the transmission loss and noise interference on the wireless channel, It may not be the same as Z1,..., With Z K Probably not the same, but The data dimension is generally the same as that of Z1,..., With Z K The data dimensions are generally the same; among them, It can be understood as an estimate of Z1 or a measurement of Z1,..., It can be understood as Z K Estimate or Z K After that, the K communication devices can use the data received by each of them as the input of the AI ​​model, and the data is processed by the AI ​​model to obtain the data. That is, the communication device 1 can obtain ,..., the communication device K can obtain

[0244] Optionally, in the example shown in FIG4 , the second AI model sends data Z1, ..., Z to K communication devices respectively. K In the example, these K data may be partially or completely the same, or different from each other.

[0245] As shown in the example of FIG5 , the K communication devices may be communication device 1, ..., communication device K in the figure, and the K AI models may be AI model 1, ..., AI model K in the figure. It should be understood that the first communication device may be one of the K communication devices, and the first AI model deployed in the first communication device may be one of the K AI models. In FIG5 , the input of the second AI model includes the output of the K AI models deployed in the K communication devices. Exemplarily, the inputs of the K AI models may be represented as X1, ..., X K , Z1,...,Z can be obtained after being processed by K AI models respectively K After transmission through the wireless channel, the data received by the second communication device is represented as (It is understandable that due to the transmission loss and noise interference on the wireless channel, It may not be the same as Z1,..., With Z K may not be the same; however, The data dimension is generally the same as that of Z1,..., With Z K The data dimensions are generally the same; among them, It can be understood as an estimate of Z1 or a measurement of Z1,..., It can be understood as Z K Estimate or Z K Thereafter, the second communication device may receive K data (i.e. ) and the second AI model performs one or more AI model processings, wherein each AI model processing may include one or more data among the K data. In addition, the processing results after the one or more AI model processings can be expressed as

[0246] It can be understood that the first communication device and the second communication device can be implemented in many ways.

[0247] For example, any one of the M communication devices is a terminal device and the second communication device can be a terminal device. Accordingly, the first communication device and the second communication device can communicate on a sidelink (SL). In this case, the K AI models and the second AI model can be referred to as end-to-end models, or end-to-end collaborative models, etc. For example, taking the end-to-end collaborative model as an example, when K is equal to 1, it can be called a single-link end-to-end collaborative model; when K is greater than 1, it can be called a multi-link end-to-end collaborative model.

[0248] For another example, any one of the M communication devices is a terminal device and the second communication device can be a network device (such as an access network device). Accordingly, the first communication device and the second communication device can communicate on the uplink and downlink communication links. In this case, the K AI models and the second AI model can be called edge models, edge-end collaboration models, end-edge models, end-edge collaboration models, etc. Exemplarily, taking the end-edge collaboration model as an example, when K is equal to 1, it can be called a single-link end-edge collaboration model; when K is greater than 1, it can be called a multi-link end-edge collaboration model.

[0249] It should be noted that in Figures 4 and 5, the data Y, Y1, ..., Y K They can be the input data X, X1,...,X of the model respectively. K The corresponding label data, the label data and the processing results of the AI ​​model (for example The association relationship between the K AI models and the second AI model can be used to detect or determine the processing performance of the K AI models and the second AI model. For example, the association relationship can be determined by gradient information, loss function, etc.

[0250] Optionally, for K AI models, the label data Y1,...,Y K They can be the same or different, and there is no limitation here.

[0251] As can be seen from the implementation process shown in Figure 3, for the second communication device, after receiving the first information in step S301, the second communication device can generate (or determine) a model based on the first information to obtain a first AI model group. The following is an exemplary description of the process by which the second communication device determines the first AI model group based on the first information.

[0252] First, the theoretical basis for the generation of the AI ​​model is described through the implementation process of the following method A.

[0253] Generally, in traditional connection or session-oriented networks, the design goal between different communication devices (i.e., transceivers) is to ensure that the receiver accurately and correctly responds to all data sent by the transmitter, that is, to pursue lossless data transmission. However, in future intelligent networks, due to the existence of massive amounts of data and the different purposes of different AI tasks, it may no longer be necessary to transmit all data, but rather data that is valuable to the AI ​​task. Therefore, the network may be able to optimize the performance of the AI ​​model (for example, maximize the accuracy of the AI ​​model) by transmitting the minimum amount of wireless data.

[0254] To achieve this goal, in the examples shown in Figures 4 and 5, the performance of the AI ​​model can be characterized based on the mutual information between different data. As an implementation example, the implementation of mutual information will be explained below using the scenario shown in Figure 5 as an example. It should be understood that in the scenario shown in Figure 4, the reverse transmission can be implemented by referring to the following example.

[0255] In Figure 5, the input data of the kth AI model (k is any one of 1 to K) among the K AI models can be expressed as X k , the input data X k Corresponding label data Y k and data received by the second communication device Satisfaction method A:

[0256] Where I(a;b) represents the mutual information between variables a and b.

[0257] express A collection of .

[0258] Represents data transmitted over a wireless channel The mutual information between the label data Y (label data Y can be understood as the correct result / expected result of the AI ​​task) and the label data Y (label data Y can be understood as the correct result / expected result of the AI ​​task). The larger the value of the mutual information, the better the data transmitted through the wireless channel. The more information of the label data Y contained in , the higher the accuracy of the AI ​​model can be understood as, that is, the better the model performance of the AI ​​model.

[0259] Represents the original input data X k Wireless link data The smaller the mutual information, the less data is transmitted in the wireless link, that is, the smaller the wireless communication overhead. represents the sum of data transmitted by K wireless links, The smaller it is, the smaller the total wireless communication overhead of K links is.

[0260] β k (e.g. β k The value range can be [0, 1]) and can control the ratio between the two mutual information, which is used to balance the accuracy of the AI ​​processing result of the kth link and the wireless communication overhead. k Can be the same or different.

[0261] Therefore, minimizing the above formula This means: while ensuring that wireless communication overhead is as low as possible, ensure that the correctness of the AI ​​model's processing results is maximized. The subscript "IB" in stands for information bottleneck (IB) theory (or distributed information bottleneck, deterministic information bottleneck, other information theories, etc.). In other words, Other symbols can be used instead. This is just an implementation example.

[0262] Exemplarily, based on the implementation of method A, in the AI ​​model generation process, the generation basis of the model may include one or more of the following data A to data C, that is, based on the following data A to data C, an AI model group can be generated (for example, the second communication device can generate the first AI model group). The data A to data C are described exemplarily below. Data AM for data and label As input data (where M is the batch size, x m,k Represents the input data of the mth pair of data, y m,k represents the label data of the mth pair of data).

[0263] Optionally, the different label data can be the same, i.e. m,1 ,...y m,K can be expressed as y m In other words, the input of multi-link data (i.e. x m,1 ,...x m,K ) can be used to collaboratively reason about the same result y m , that is, the above data A can be expressed as

[0264] Optionally, the number "M" of M pairs of data and labels serving as input data is defined differently from the number "M" of M communication devices mentioned above. Here, only the same letters are used to represent the number, and the values ​​of the two may be the same or different.

[0265] Data B. Dimensions of data transmitted in wireless links (e.g., or Z kDimensions). Exemplarily, the dimension of the data can be expressed as the number of tokens / words / tags (hereinafter uniformly expressed as tokens), or the dimension of the data can be expressed as the dimension of the embedding vector. It can be understood that Token: a concept similar to "word", can be understood as the basic unit for splitting intermediate transmission volume; Embedding: a vector representation of intermediate transmission volume. A token can be understood as each component unit in the Embedding vector, that is, the number of components in the Embedding can be the dimension of the token.

[0266] Data C. Channel state information (such as Gaussian white noise modeling, etc.).

[0267] Optionally, the process of generating an AI model group based on one or more items 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 items of data A to data C, and after processing by the neural network, the model parameters of an AI model group (the AI ​​model group includes K AI models and a second AI model) are obtained.

[0268] As an implementation example, the loss function of the neural network can be expressed as method B:

[0269] As another implementation example, in order to reduce To solve the complexity of , we can introduce variational processing to calculate the mutual information. For example, the loss function of the neural network can be expressed as C:

[0270] The subscript “VDIB” stands for variational distributed information bottleneck (VDIB);

[0271] K: number of user devices / number of links in a multi-link scenario;

[0272] θ k : neural network or model parameters configured by user k (e.g., the first communication device);

[0273] ψ: neural network or model parameters arranged on the base station side (e.g., the second communication device);

[0274] β k : Lagrange multiplier, used to balance the accuracy of AI processing results of the kth link and the wireless communication overhead;

[0275] For user k, according to the parameter θk A neural network, given input data x k In the case of The conditional probability density of ; On the base station side, according to the neural network with parameter φ, the receiving vector is given Then, we get the inference variable Cross entropy with the target variable y;

[0276] Using variational distribution Approximate z k distribution of

[0277] Represents a known probability density function p(x k ,y), find the expected / mean value of the part in {·};

[0278] Represents a known probability density function Under the premise of , find the expectation / mean of the part in {·};

[0279] represents the conditional probability distribution with parameter φ;

[0280] Represents an approximate probability distribution The variational distribution form of ;

[0281] Represents a probability distribution and probability distribution The Coulomb-Leibler (KL) divergence between .

[0282] As another implementation example, under the premise of constraining the tokens / embedding dimension according to the wireless link bandwidth, the loss function of the neural network can be expressed as form D:

[0283] in, The constraints are Th1 k Indicates the maximum bandwidth threshold of the kth wireless link, the constraint condition The physical meaning of D is that the amount of data transmitted over the wireless link satisfies the air interface bandwidth constraint. In other words, using method D, we can maximize the accuracy of AI tasks while ensuring that information transmitted over the wireless channel satisfies the bandwidth constraint.

[0284] As another implementation example, under the premise of constraining the tokens / embedding dimension according to the wireless link bandwidth, the loss function of the neural network can be expressed as E:

[0285] in, The constraints are Th2 represents the minimum threshold value of AI task accuracy, and the constraint condition The physical meaning of is that the accuracy of the AI ​​task is greater than the minimum threshold. In other words, through this method E, the amount of information transmitted by the wireless channel can be minimized under the premise that the accuracy of the AI ​​task is greater than the minimum threshold.

[0286] Based on the above implementation process, under the premise of bandwidth constraints on the tokens / embedding dimension, the AI ​​model inference accuracy is relatively high. For example, based on different data sets, the simulation results of the above method C are as follows:

[0287] Canadian Institute for Advanced Research (CIFAR) dataset test: K number of devices = 4, epochs = 320, intermediate dim = 64, accuracy = 87.44%.

[0288] Test on the Mixed National Institute of Standards and Technology (MNIST) dataset: the number of devices = 4, number of epochs = 320, intermediate dim = 64, accuracy = 98.44%.

[0289] Among them, the intermediate output latitude is the above or Z k The dimension is the precision of the AI ​​task.

[0290] Optionally, taking the K communication devices as K terminals and the second communication device as a base station as an example, the model generation process involved in any of the above-mentioned methods A to E can be summarized into the following steps.

[0291] Step 1. Based on the reparameterization technique and Monte Carlo sampling, we can obtain an unbiased estimate of the VDIB gradient and use stochastic gradient descent to optimize the objective function. Given a small batch of data and randomly sampling each group of data, we can obtain an empirical estimate of VDIB that satisfies the formula F:

[0292] Compared with method C, the meaning of the new parameters in method F is:

[0293] M: batch size, that is, the size / dimension of the input data during each training.

[0294] L: The number of sampling times of the wireless channel environment during each training.

[0295] y m : Target vector for the mth group of data.

[0296] The mth group of data is received at the base station under the lth channel sampling.

[0297] Step 2. Based on method F (i.e., Lagrangian expression of VDIB), the base station updates the model parameter ψ and converts the gradient parameter Back propagation to the terminal side supports the update of the terminal side model;

[0298] Step 3. The terminal uses the gradient parameters of the base station back propagation Update local model parameters

[0299] After multiple iterations of the above three steps, the optimal deep neural network parameters Device DNN for K terminals can be obtained. Optimal deep neural network parameters BS DNN ψ on the base station side * ; and the optimal tokens dimension of the wireless link corresponding to the highest task accuracy

[0300] Next, we will introduce in detail how to implement the back propagation of gradients during model training. The base station side updates ψ, and the terminal side updates θ k ,k=1,…,K, the specific process is as follows:

[0301] First, the base station calculates the gradient of the local model parameter ψ according to the following method G and updates the local neural network parameters. Method G satisfies:

[0302] Secondly, the base station side calculates the gradient parameter φ provided to the terminal side k,k=1,…,K, satisfying method H:

[0303] And φ k ,k=1,…,K are transmitted to the kth terminal respectively. So the back propagation parameter is

[0304] Finally, the kth terminal receives the gradient parameter φ k The gradient of the local model is obtained as follows, and the local neural network parameters θ are updated accordingly K Method I satisfies:

[0305] In the above implementation, the parameters involved are as follows.

[0306] 1. Input information includes:

[0307] The number of links (or terminals) participating in the collaboration, K;

[0308] The number of iterations T (or: number of epochs);

[0309] Channel state information for each link: channel noise power Channel sampling times L;

[0310] The number of samples for model training: batch size (batch size / batch size / batch size), which indicates the specific number of samples in a group of samples input into the model at a time during training.

[0311] 2. Output information includes:

[0312] Optimal deep neural network parameters for K terminals Device DNN

[0313] Optimal deep neural network parameters BS DNN ψ on the base station side * ;

[0314] The task completion accuracy (Accuracy) corresponding to each tokens dimension N;

[0315] By traversing N, we can get the accuracy corresponding to each N value, so we can output the optimal tokens dimension of the wireless link corresponding to the maximum task accuracy.

[0316] 3. Key interactions during model training:

[0317] For any given initial model, after one round of iteration (including T epochs), the final base station side and terminal side model parameters are obtained. The intermediate interactive information mainly includes: back propagation gradient parameters That is, the back propagation parameters of each interaction can satisfy method H.

[0318] In one possible implementation, the second information sent by the second communication device in step S302 includes at least one of the following: model parameters of the first AI model, model parameters of the first AI model group, dimensional information of the input data of the first AI model, and dimensional information of the output data of the first AI model. In other words, the second communication device can deploy the first AI model on the first communication device using at least one of the above items, thereby increasing the flexibility of solution implementation.

[0319] It can be understood that when the second information includes the model parameters of the first AI model and / or the model parameters of the first AI model group, the first communication device can locally construct / generate the first AI model based on the model parameters contained in the second information, and obtain the first AI model in this way.

[0320] It is understood that when the second information includes dimensional information of the input data of the first AI model and / or dimensional information of the output data of the first AI model, the first communication device can update the initial model based on the dimensional information of the input data and / or the dimensional information of the output data to obtain the first AI model. Optionally, the initial model can be a model pre-configured in the first communication device or a model configured by the second communication device (such as the third AI model described below), which is not limited here.

[0321] Furthermore, when the second information includes dimensional information of the input data of the first AI model and / or dimensional information of the output data of the first AI model, the second information can be implemented in various ways. For example, the second information can include specific values ​​of the dimensional information or index values ​​of the dimensional information.

[0322] For ease of understanding, the following description will be made by taking the implementation process of the second information including the index value of the dimension information as an example.

[0323] In one possible implementation, before the first communication device receives the second information, the method further includes: the first communication device receives third information, the third information is used to configure a mapping relationship between P dimensional information and Q indexes, where P and Q are both positive integers; the second information includes one or more indexes of the Q indexes, and the one or more indexes are used to determine one of the dimensional information in the P dimensional information. In other words, the first communication device can receive third information for configuring a mapping relationship between P dimensional information and Q indexes. Thereafter, the second information received by the first communication device in step S302 may include one or more indexes of the Q indexes, and the first communication device can determine one of the dimensional information in the P dimensional information based on the one or more indexes. Thus, by configuring the mapping relationship through the third information, the second information sent by the second communication device can indicate the dimensional information by carrying the index, which can reduce the overhead of the indication.

[0324] In this application, index can be replaced by other terms, such as representation, number, etc.

[0325] Optionally, the third information is layer 3 (L3) signaling, and the second information is layer 1 (L1) and / or layer 2 (L2) signaling. For example, the L3 signaling may include NAS signaling and / or RRC layer signaling. In another example, L1 signaling may be understood as physical layer signaling. In another example, L2 signaling may be understood as radio network layer signaling, including at least one of MAC layer signaling, RLC signaling, PDCP signaling, and SDAP layer signaling.

[0326] Optionally, the mapping relationship configured by the third information may be implemented through a table, a formula, etc. The following is an example description of the implementation process of configuring the mapping relationship by the third information through a table.

[0327] Table 2 shows an example of implementing the third information by configuring a mapping relationship through a table.

[0328] Table 2

[0329] In Table 2, there may be a one-to-one correspondence between the P dimensional information and the Q indexes, that is, the values ​​of P and Q may be equal.

[0330] For example, in the example shown in Table 2, if the second communication device indicates that the dimension value is "8," the second information sent by the second communication device in step S302 may include an index value of "3." If the second communication device indicates that the dimension value is "32," the second information sent by the second communication device in step S302 may include an index value of "5." This shows that when the dimension value is large, including the index value in the second information can reduce indication overhead.

[0331] Optionally, in the example shown in Table 2, when the second communication device indicates that the dimension value does not appear in the table, the second communication device can be implemented by rounding up, rounding down, or sending multiple index values. For example, when the second communication device indicates that the dimension value is "6", by rounding up, the second information sent by the second communication device in step S302 may include the index value "3", that is, the dimension value is "8"; by rounding down, the second information sent by the second communication device in step S302 may include the index value "2", that is, the dimension value is "8"; by sending multiple index values, the second information sent by the second communication device in step S302 may include the index values ​​"1" and "2", that is, the dimension value is "2+4=6", or the second information sent by the second communication device in step S302 may include the index values ​​"3" and "1", that is, the dimension value is "8-1=6".

[0332] Optionally, in the example shown in Table 2, different dimension values ​​can be expressed by formulas. For example, the dimension value N satisfies: N=2 I ;

[0333] Here, I represents the index.

[0334] Table 3 shows an example of implementing the third information by configuring a mapping relationship through a table.

[0335] Table 3

[0336] In Table 3, there may be a one-to-many relationship between the P dimensional information and the Q indexes, that is, the value of P is smaller than the value of Q.

[0337] For example, in the example shown in Table 3, there are some indexes that can indicate two or more dimension values ​​through a single index value. For example, if the second communication device determines that the performance of dimension values ​​"2" and "4" is the same or similar based on any of the above methods A to E, the second information sent by the second communication device in step S302 may include an index value of "1", so that the first communication device can locally decide to use one of the dimension values ​​"2" or "4" to determine the first AI model.

[0338] Tables 4 to 6 show another implementation example of configuring a mapping relationship of the third information through a table.

[0339] Table 4

[0340] Table 5

[0341] Table 6

[0342] In the implementations shown in Tables 4 to 6, there may be a one-to-many relationship between the P pieces of dimensional information and the Q indexes, that is, the value of P is smaller than the value of Q.

[0343] For example, in the examples shown in Tables 4 to 6, the Q indexes contained in the second information sent by the second communication device in step S302 can be two indexes, one index is used to indicate the category of the AI ​​model (denoted as index 1), and the other index is used to indicate the dimension value in the category of the AI ​​model (denoted as index 2).

[0344] For example, when the second communication device indicates that the category of the AI ​​model is X and the dimension value is "16", the second information sent by the second communication device in step S302 may include index values ​​(1, 4), that is, the value of index 1 is 1 and the value of index 2 is 4. In this way, the first communication device can determine Table 5 based on the value of index 1 being 1, and determine "the dimension value corresponding to the category of the AI ​​model being X is 16" in Table 5 based on the value of index 2 being 4.

[0345] For another example, when the second communication device indicates that the category of the AI ​​model is Y and the dimension value is "50", the second information sent by the second communication device in step S302 may include an index value (2, 5), that is, the value of index 1 is 2 and the value of index 2 is 5. In this way, the first communication device can determine Table 6 based on the value of index 1 being 2, and determine "the dimension value corresponding to the category of the AI ​​model being X is 50" in Table 6 based on the value of index 2 being 5.

[0346] Optionally, in any of the above implementations, the one or more tables configured by the third information may be delivered via one message / signaling, or via multiple messages / signaling, which is not limited here.

[0347] Optionally, in the examples shown in Tables 4 to 6, "category of AI model" can be replaced by other implementations, such as the identifier of the AI ​​model, the functional identifier of the AI ​​model, the task category corresponding to the AI ​​model, the data category corresponding to the AI ​​model, the size category of the AI ​​model, the functional category of the AI ​​model, the morphological category of the AI ​​model, and the category of AI model deployment.

[0348] As can be seen from the foregoing 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-mentioned methods A to E, the first information may include one or more of the following information A to 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 E contained in the following first information, and generate the first AI model group according to one of the methods A to E.

[0349] Information A. First dimensional information. When the input of the first AI model includes the output of the second AI model, the first dimensional information is used to determine the dimensional information of the input data of the first AI model or the dimensional information of the output data of the second AI model.

[0350] Information B. Second dimensional information. When the input of the second AI model includes the output of the first AI model, the second dimensional information is used to determine the dimensional information of the output data of the first AI model or the dimensional information of the input data of the second AI model.

[0351] Information C: input data of the first AI model and label data of the input data of the first AI model.

[0352] Information D: local computing power status information of the first communication device.

[0353] Information E. Channel state information.

[0354] For information A or information B, the second communication device can determine the dimensional information of the data transmitted on the communication link through the first 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 constant, since the dimension of the data transmitted on the communication link is related to the processing performance of the AI ​​model, this method can simplify the implementation process of the second communication device determining the first AI model group, 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.

[0355] Optionally, the dimension information includes at least one of the following items: an upper limit value of the dimension, a 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 a 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).

[0356] For example, when the above-mentioned dimensional 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 implementation of the solution.

[0357] For example, when the above-mentioned dimensional 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 dimensional information can meet the expectations of the first communication device.

[0358] Optionally, in information A or information B, the first dimension information or the second dimension information is determined based on channel state information (CSI). Specifically, the first dimension information or the second dimension information contained in the first information can be determined based on the 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 AI ​​model that can be subsequently 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, 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.

[0359] Optionally, the channel state information may include channel information between the first communication device and the second communication device, and / or channel information between the second communication device and the first communication device. Where 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.

[0360] Optionally, the channel state information may be obtained based on a reference signal.

[0361] For example, in the case where 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 synchronization signal / physical broadcast channel block, sidelink SSB, SL-SSB, or S-SS / PSBCH block), a sidelink channel state information reference signal (sidelink channel state information reference signal, SL-CSI-RS), etc.

[0362] For 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.

[0363] 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, the label data can be used as one of the bases for determining the model processing performance of the first AI model. Therefore, for the second communication device, the second communication device can obtain an AI model with better performance based on these two pieces of information.

[0364] 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 sent and received by the second communication device on the wireless link (such as the input data of the second AI model or the output data of the second AI model, etc.), 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 under the premise that the wireless link data meets the bandwidth.

[0365] With respect to information D, when the first information includes the local computing power status information of the first communication device, since the complexity requirement of the model processing of the AI ​​model may be related to the local computing power status of the first communication device, for this reason, 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 to provide a first AI model that satisfies the local computing power status, thereby improving the success rate of the model processing performed by the first communication device based on the first AI model.

[0366] For information E, when the first information includes 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, for this reason, the second communication device determines a first AI model group based on the channel state information to adapt to the channel characteristics, so that the transmission data of the wireless link meets the channel bandwidth requirements as much as possible, in order to improve the transmission performance of the AI ​​data corresponding to the AI ​​model.

[0367] It can be understood that when the first information includes two or more of the above-mentioned information A to information E, based on the technical gain brought by any one of the above-mentioned items, further superposition gain can be obtained through the two or more items of information.

[0368] Optionally, the first information may be sent via one message / signaling or multiple messages / signaling, which is not limited here.

[0369] In one possible implementation, the first information sent by the first communications device in step S301 is used to determine a 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 X AI models and a fourth AI model, where X is an integer greater than or equal to 1; wherein the input of any AI model among the X AI models includes the output of the fourth AI model, or the input of the fourth AI model includes the output of any AI model among the X AI models; a third AI model among the X AI models is deployed on the first communications device, the third AI model including one or more AI models among the X AI models; and the fourth AI model is deployed on the second communications device, the X AI models being deployed on Y communications devices, the Y communications devices including the first communications device, where Y is less than or equal to X. In other words, after receiving the first information, the second communications device may 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, so that the solution can be applicable to AI model update scenarios.

[0370] Optionally, update can be replaced by other terms such as modification, iteration, optimization, processing, etc.

[0371] Optionally, when the second AI model group is regarded as one AI model, the X AI models and the fourth AI model can be understood as multiple AI sub-models in the one AI model.

[0372] Optionally, the third AI model and the fourth AI model included in the second AI model group may be general models or dedicated models to enable updates of different types of models.

[0373] It should be understood that the general model can be called the basic model, large model or L0 model, and the specialized model can be called the small model, L1 model, L2 model, etc.

[0374] Taking large models as an example, large models can refer to machine learning models with a large number of parameters and complex structures, which can process massive data and complete various complex tasks, such as natural language processing, computer vision, speech recognition, etc.

[0375] Alternatively, large models are typically built from deep neural networks, with billions or even hundreds of billions of parameters.

[0376] Optionally, the purpose of designing a large model can be to improve the model's expressiveness and predictive performance, and to be able to handle more complex tasks and data.

[0377] Alternatively, large models can learn complex patterns and features by training on massive amounts of data, have stronger generalization capabilities, and can make accurate predictions on unprocessed data.

[0378] In contrast, a small model can refer to a model with fewer parameters and fewer layers. Generally speaking, compared to small models, large models usually have more parameters and deeper layers, and have stronger expressive power and higher accuracy, but also require more computing resources and time for training and inference. They are suitable for scenarios with large data volumes and abundant computing resources, such as cloud computing, high-performance computing, and artificial intelligence.

[0379] Alternatively, small models have the advantages of being lightweight, efficient, and easy to deploy, and are suitable for scenarios with small data volumes and limited computing resources, such as mobile applications, embedded devices, and the Internet of Things.

[0380] In one possible implementation, the first information sent by the first communication device in step S301 is periodically sent information, and / or the second information sent by the second communication device in step S302 is periodically sent information. Specifically, the first information may be one of the bases for determining the AI ​​model, and the second information may be used to deploy the AI ​​model. The periodic transmission of the first information and / or the second information between the first communication device and the second communication device enables periodic determination and / or periodic deployment of the AI ​​model, thereby enabling multiple iterative updates of the AI ​​model through a periodic process.

[0381] In one possible implementation, the first information sent by the first communication device in step S301 is used to determine the first AI model group, and the AI ​​model of the first AI model group is a dedicated model. Specifically, the first communication device can be a terminal device, and for this purpose, 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 power, different channel characteristics, etc.), by deploying a dedicated model in the terminal device, 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.

[0382] Based on the technical solution shown in Figure 3, the second communication device acts as the recipient 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 send second information used to determine the first AI model in the first AI model group to the first communication device. 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 serve 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, thereby improving the processing performance of the subsequent model processing based on the AI ​​model by the first communication device.

[0383] In one possible implementation of the method shown in FIG3 , after the first communication device receives the second information in step S302, the method further includes: the first communication device receiving fourth information, the fourth information being used to instruct the first AI model to stop processing. Specifically, the first communication device may also receive fourth information instructing the first AI model to stop processing, so that the first communication device stops participating in the processing of the first AI model group, thereby freeing up resources of the first communication device and reducing transmission overhead of input data and / or output data corresponding to the first AI model.

[0384] In addition, when K is greater than 1, that is, the communication devices participating in the first AI model group can include other K-1 communication devices in addition to the first communication device. The first communication device can stop processing the first AI model through the instruction of the fourth information, and can implement pruning processing of some AI models (such as the first AI model) to prune inefficient devices / inefficient links and achieve the selection of a better (or optimal) collaboration set.

[0385] In a possible implementation, the second communication device may send (or determine / generate, etc.) the fourth information based on multiple methods, which will be described below with reference to some implementation examples.

[0386] As an implementation example, the second communication device may obtain the effective information volume ratio of M links between the second communication device and M communication devices, and send the fourth information to the communication device on a link whose effective information volume ratio is lower than the threshold. For example, the predefined or preconfigured single link effective information volume ratio threshold is Th ratio ; The ratio of the effective information content of the kth link among the M links k satisfy:

[0387] The definition of each parameter can refer to the previous description.

[0388] By the above method, the second communication device can send a message to the user whose effective information ratio is lower than the threshold value Th. ratio The communication device on a certain link sends the fourth information. The instruction of the fourth information can enable some communication devices (for example, the first communication device) to stop processing the first AI model, so as to implement pruning processing of some AI models (for example, the first AI model) to prune inefficient devices / inefficient links and achieve the selection of a better (or optimal) collaboration set.

[0389] Optionally, in addition to the effective information ratio of the M links and the effective information ratio threshold, the basis for determining the above-mentioned fourth information can also be achieved through other parameters, such as the effective information of some or all of the links in the M links and the effective information threshold, the mutual information of some or all of the links in the M links and the mutual information threshold, the dimension of the input data of some or all of the links in the M links and the dimension threshold of the input data, the dimension of the output data of some or all of the links in the M links and the output dimension threshold, etc.

[0390] Optionally, any of the above thresholds may be determined by the second communication device based on various methods, such as the local computing power status of the second communication device, the number of AI tasks processed by the second communication device, etc. Alternatively, any of the thresholds may be preconfigured.

[0391] In one possible implementation, the second communication device may obtain some parameters in the basis for determining the fourth information based on the information sent by the M communication devices (e.g., the effective information volume of the M links, the mutual information volume of some or all of the M links, the dimension of the input data of some or all of the M links, the dimension of the output data of some or all of the M links, etc.). For example, before the first communication device receives the fourth information, the method further includes: the first communication device sends fifth information to the second communication device, and the fifth information is used to determine the fourth information; wherein the fifth information includes at least one of the following: input data or output data of the first AI model, dimension information of the input data of the first AI model or dimension information of the output data of the first AI model, the dimension expected by the first communication device, the value range of the dimension expected by the first communication device, and the channel state information of the first communication device. Specifically, after the first communication device receives the second information for determining the first AI model in step S302, the first communication device may perform model processing based on the determined first AI model. Thereafter, the first communication device may send the fifth information so that the second communication device can determine the fourth information based on the at least one information indicated by the fifth information. Therefore, the fourth information instructing the first communication device to stop the model processing may be determined based on the status information of the first communication device indicated by the fifth information, so that the second communication device can implement pruning processing based on the status information of one or more communication devices in the cooperation set.

[0392] As another implementation example, the second communication device may also trigger the sending of fourth information to the first communication device based on other methods. For example, the method also includes: the first communication device sends sixth information to the second communication device, and the sixth information is used to request to stop the processing of the first AI model. Specifically, after the first communication device receives the second information for determining the first AI model in step S302, the first communication device may perform model processing based on the determined first AI model. Thereafter, the first communication device may send sixth information for requesting to stop the processing of the first AI model, so that the second communication device determines the fourth information based on the sixth information. Thus, the fourth information instructing the first communication device to stop model processing may be determined based on the request of the first communication device, so that the second communication device can implement pruning processing based on the request of one or more communication devices in the collaborative set.

[0393] Optionally, the first communication device may trigger the determination (or transmission) of the sixth information based on multiple trigger conditions. For example, the trigger condition may include: the first communication device determines that the channel state indicated by the channel state information is lower than or equal to a threshold, the first communication device determines that the computing power indicated by its own computing power state information is lower than or equal to a threshold, and the first communication device determines that the dimension information of the input data or the dimension information of the output data of the first AI model indicates that the dimension is lower than a threshold. One or more of the following:

[0394] Please refer to FIG6 , which is a schematic diagram of an implementation of the communication method provided in this application. The method includes the following steps.

[0395] S601. The first communication device performs model processing based on the first AI model, and the first AI model and the second AI model are included in the first AI model group; wherein, 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.

[0396] S602: The second communication device sends fourth information, and the first communication device receives the fourth information accordingly, wherein the fourth information is used to instruct to stop processing of the first AI model.

[0397] In one possible implementation, the first AI model group also includes Z AI models, and the input of any AI model in the Z AI models includes the output of the second AI model, or the input of the second AI model includes the output of any one or more AI models in the Z AI models. Specifically, in addition to the first AI model deployed on the first communication device and the second AI model deployed on the second communication device, the first AI model group may also include Z AI models deployed on other communication devices. In other words, the communication devices participating in the first AI model group may include other communication devices in addition to the first communication device. The instruction of the fourth information can enable the first communication device to stop processing the first AI model, and can implement pruning processing of some AI models (such as the first AI model) to prune inefficient devices / inefficient links and achieve the selection of a better (or optimal) collaboration set.

[0398] In one possible implementation, before the first communication device receives the fourth information, the method further includes: the first communication device sends fifth information, and the fifth information is used to determine the fourth information; wherein the fifth information includes at least one of the following: input data or output data of the first AI model, dimension information of the input data of the first AI model or dimension information of the output data of the first AI model, the dimension expected by the first communication device, the value range of the dimension expected by the first communication device, and the channel state information of the first communication device. Specifically, the first communication device can send the fifth information so that the second communication device can determine the fourth information based on the at least one information indicated by the fifth information. Thus, the fourth information indicating to the first communication device to stop model processing can be determined based on the state information of the first communication device indicated by the fifth information, so that the second communication device can implement pruning processing based on the state information of one or more communication devices in the collaborative set.

[0399] In one possible implementation, the method further includes: the first communication device sending sixth information requesting that processing of the first AI model be stopped. Specifically, the first communication device may send the sixth information requesting that processing of the first AI model be stopped, so that the second communication device determines the fourth information based on the sixth information. Thus, the fourth information instructing the first communication device to stop model processing may be determined based on the request of the first communication device, allowing the second communication device to implement pruning processing based on the request of one or more communication devices in the collaborative set.

[0400] Optionally, the first communication device may trigger the determination (or transmission) of the sixth information based on multiple trigger conditions. For example, the trigger condition may include: the first communication device determines that the channel state indicated by the channel state information is lower than or equal to a threshold, the first communication device determines that the computing power indicated by its own computing power state information is lower than or equal to a threshold, and the first communication device determines that the dimension information of the input data or the dimension information of the output data of the first AI model indicates that the dimension is lower than a threshold. One or more of the following:

[0401] It should be noted that, in the implementation shown in FIG6 , the fourth information / fifth information / sixth information can also refer to the previous description and achieve corresponding technical effects, which will not be elaborated here.

[0402] Based on the technical solution shown in Figure 6, during the process of the first communication device performing model processing based on the first AI model, the first communication device can receive fourth information for instructing to stop processing the first AI model, so that the first communication device stops participating in the processing of the first AI model group, thereby releasing the resources of the first communication device and saving the transmission overhead of the input data and / or output data corresponding to the first AI model.

[0403] Referring to Figure 7, an embodiment of the present application provides a communication device 700. This communication device 700 can implement the functions of the second communication device or the first communication device in the above-mentioned method embodiment, thereby also achieving the beneficial effects of the above-mentioned method embodiment. In this embodiment of the present application, the communication device 700 can be the first communication device (or the second communication device), or it can be an integrated circuit or component, such as a chip, within the first communication device (or the second communication device).

[0404] 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.

[0405] In one possible implementation, when the device 700 is used to execute the method executed by the first communication device in the aforementioned embodiment, the device 700 includes a processing unit 701 and a transceiver unit 702; the processing unit 701 is used to determine first information; the transceiver unit 702 is used to send the first information, where the first information is used to determine a first AI model group, where the first AI model group includes K AI models and a second AI model, where K is an integer greater than or equal to 1; wherein the input of any AI model in the K AI models includes the output of the second AI model, or the input of the second AI model includes the output of one or more AI models in the K AI models; the second AI model is deployed in a second communication device, where the K AI models are used to be deployed in M ​​communication devices, where the M communication devices include the first communication device, and M is less than or equal to K; the transceiver unit 702 is further used to receive second information, where the second information is used to determine the first AI model, where the first AI model includes one or more models in the K AI models.

[0406] In one possible implementation, when the device 700 is used to execute the method executed by the second communication device in the aforementioned embodiment, 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 used to determine a first AI model group based on the first information, where the first AI model group includes K AI models and a second AI model, where K is an integer greater than or equal to 1; wherein the input of any AI model in the K AI models includes the output of the second AI model, or the input of the second AI model includes the output of one or more AI models in the K AI models; the second AI model is deployed in the second communication device, and the K AI models are deployed in M ​​communication devices, where the M communication devices include the first communication device, and M is less than or equal to K; the transceiver unit 702 is further used to send second information, where the second information is used to determine a first AI model, where the first AI model is deployed in the first communication device, and the first AI model includes one or more models in the K AI models.

[0407] In one possible implementation, when the device 700 is used to execute the method executed by the first communication device in the aforementioned embodiment, the device 700 includes a processing unit 701 and a transceiver unit 702; the processing unit 701 is used to perform model processing based on a first AI model, and the first AI model and the second AI model are included in a first AI model group; wherein 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; the transceiver unit 702 is used to receive fourth information, and the fourth information is used to instruct to stop processing of the first AI model.

[0408] In one possible implementation, when the device 700 is used to execute the method executed by the second communication device in the aforementioned embodiment, the device 700 includes a processing unit 701 and a transceiver unit 702; the processing unit 701 is used to determine fourth information, and the fourth information is used to indicate to stop processing of the first AI model, and the first AI model and the second AI model are included in the first AI model group; wherein 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; the transceiver unit 702 is used to send the fourth information.

[0409] It should be noted that, for details on the information execution process of the units of the above-mentioned communication device 700, please refer to the description in the method embodiment shown above in this application, and no further details will be given here.

[0410] Please refer to Fig. 8, which is another schematic structural diagram of a communication device 800 provided in this application. The communication device 800 includes a logic circuit 801 and an input / output interface 802. The communication device 800 may be a chip or an integrated circuit.

[0411] The transceiver unit 702 shown in FIG7 may be a communication interface, which may be the input / output interface 802 in FIG8 , which may include an input interface and an output interface. Alternatively, the communication interface may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0412] Optionally, the logic circuit 801 is used to determine first information; the input-output interface 802 is used to send first information, the first information is used to determine a first AI model group, the first AI model group includes K AI models and a second AI model, K is an integer greater than or equal to 1; wherein, the input of any AI model in the K AI models includes the output of the second AI model, or, the input of the second AI model includes the output of one or more AI models in the K AI models; the second AI model is deployed in a second communication device, the K AI models are used to be deployed in M ​​communication devices, the M communication devices include the first communication device, M is less than or equal to K; the input-output interface 802 is also used to receive second information, the second information is used to determine the first AI model, the first AI model includes one or more models in the K AI models.

[0413] Optionally, the input-output interface 802 receives first information; the logic circuit 801 is used to determine a first AI model group based on the first information, the first AI model group including K AI models and a second AI model, where K is an integer greater than or equal to 1; wherein the input of any AI model among the K AI models includes the output of the second AI model, or the input of the second AI model includes the output of one or more AI models among the K AI models; the second AI model is deployed on a second communication device, and the K AI models are deployed on M communication devices, the M communication devices including the first communication device, M being less than or equal to K; the input-output interface 802 is also used to send second information, the second information being used to determine a first AI model, the first AI model being deployed on the first communication device, and the first AI model including one or more models among the K AI models.

[0414] Optionally, the logic circuit 801 is used to perform model processing based on a first AI model, and the first AI model and the second AI model are included in a first AI model group; wherein, 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; the input-output interface 802 is used to receive fourth information, and the fourth information is used to instruct to stop processing of the first AI model.

[0415] Optionally, the logic circuit 801 is used to determine fourth information, which is used to instruct to stop processing of the first AI model, and the first AI model and the second AI model are included in the first AI model group; wherein 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; the input-output interface 802 is used to send the fourth information.

[0416] The logic circuit 801 and the input / output interface 802 may also execute other steps executed by the first communication device or the second communication device in any embodiment and achieve corresponding beneficial effects, which will not be described in detail here.

[0417] In a possible implementation, the processing unit 701 shown in FIG. 7 may be the logic circuit 801 in FIG. 8 .

[0418] Optionally, the logic circuit 801 may be a processing device, and the functions of the processing device may be partially or entirely implemented by software. The functions of the processing device may be partially or entirely implemented by software.

[0419] Optionally, the processing device may include a memory and a processor, wherein 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 one of the method embodiments.

[0420] Alternatively, the processing device may include only a processor. A memory for storing the computer program is located outside the processing device, and the processor is connected to the memory via circuits / wires to read and execute the computer program stored in the memory. The memory and processor may be integrated or physically separate.

[0421] 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 processors (DSPs), microcontroller units (MCUs), programmable logic devices (PLDs), or other integrated chips, or any combination of the above chips or processors.

[0422] Please refer to Figure 9, which shows a communication device 900 involved in the above-mentioned embodiments provided in an embodiment of the present application. The communication device 900 can specifically be a communication device serving as a terminal device in the above-mentioned embodiments. The example shown in Figure 9 is that the terminal device is implemented through the terminal device (or a component in the terminal device).

[0423] Herein, a possible logical structure diagram 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 .

[0424] The transceiver unit 702 shown in FIG7 may be a communication interface, which may be the communication port 902 in FIG9 , which may include an input interface and an output interface. Alternatively, the communication port 902 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0425] Further optionally, the device may also include at least one of a memory 903 and a bus 904. In an embodiment of the present application, the at least one processor 901 is used to control and process the actions of the communication device 900.

[0426] 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, a transistor logic device, a hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction 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 will 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 aforementioned method embodiments and will not be repeated here.

[0427] It should be noted that the communication device 900 shown in Figure 9 can be specifically used to implement the steps implemented by the terminal device in the aforementioned method embodiment and achieve the corresponding technical effects of the terminal device. The specific implementation methods of the communication device shown in Figure 9 can refer to the description in the aforementioned method embodiment and will not be repeated here.

[0428] Please refer to Figure 10, which is a structural diagram of the communication device 1000 involved in the above-mentioned embodiments provided in an embodiment of the present application. The communication device 1000 can specifically be a communication device as a network device in the above-mentioned embodiments. The example shown in Figure 10 is that the network device is implemented through the network device (or a component in the network device), wherein the structure of the communication device can refer to the structure shown in Figure 10.

[0429] The communication device 1000 includes at least one processor 1011 and at least one network interface 1014. Further optionally, the communication device also 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, via a bus. In an embodiment of the present application, the connection may include various interfaces, transmission lines or buses, etc., which are not limited in this embodiment. 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 may include a network interface between the communication device and the core network device, such as an S1 interface, and the network interface may 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.

[0430] The transceiver unit 702 shown in FIG7 may be a communication interface, which may be the network interface 1014 in FIG10 , which may include an input interface and an output interface. Alternatively, the network interface 1014 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0431] Processor 1011 is primarily used to process communication protocols and communication data, control the entire communication device, execute software programs, and process software program data, for example, to support the communication device in performing the actions described in the embodiments. The communication device may include a baseband processor and a central processing unit. The baseband processor is primarily used to process communication protocols and communication data, while the central processing unit is primarily used to control the entire terminal device, execute software programs, and process software program data. Processor 1011 in Figure 10 may integrate the functions of both a baseband processor and a central processing unit. Those skilled in the art will appreciate that the baseband processor and the central processing unit may also be independent processors interconnected via a bus or other technology. Those skilled in the art will appreciate that a terminal device may include multiple baseband processors to accommodate different network standards, multiple central processing units to enhance its processing capabilities, and various components of the terminal device may be connected via various buses. The baseband processor may also be referred to as a baseband processing circuit or a baseband processing chip. The central processing unit may also be referred to as a central processing circuit or a central processing chip. The functionality for processing communication protocols and communication data may be built into the processor or stored in memory as a software program, which is executed by the processor to implement the baseband processing functionality.

[0432] The memory is primarily used to store software programs and data. Memory 1012 can exist independently and be connected to processor 1011. Alternatively, memory 1012 and processor 1011 can be integrated together, for example, within a single chip. Memory 1012 can store program code for executing the technical solutions of the embodiments of the present application, and execution is controlled by processor 1011. The various computer program codes executed can also be considered drivers for processor 1011.

[0433] Figure 10 shows only one memory and one processor. 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. The memory may be a storage element on the same chip as the processor, i.e., an on-chip storage element, or an independent storage element, which is not limited in the present embodiment.

[0434] The transceiver 1013 can be used to support the reception or transmission of radio frequency signals between the communication device and the 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 signal from the antenna, convert the radio frequency signal into a digital baseband signal or a digital intermediate frequency signal, and provide the digital baseband signal or digital intermediate frequency signal to the processor 1011 so that the processor 1011 can further process the digital baseband signal or digital intermediate frequency signal, such as demodulation and decoding. In addition, the transmitter Tx in the transceiver 1013 is also used to receive a modulated digital baseband signal or digital intermediate frequency signal from the processor 1011, convert the modulated digital baseband signal or digital intermediate frequency signal into a radio frequency signal, and transmit the radio frequency signal through one or more antennas 1015. Specifically, the receiver Rx can selectively perform one or more stages of down-mixing and analog-to-digital conversion on the RF signal to obtain a digital baseband signal or a digital intermediate frequency signal. The order of the down-mixing and analog-to-digital conversion processes is adjustable. The transmitter Tx can selectively perform one or more stages of up-mixing and digital-to-analog conversion on the modulated digital baseband signal or digital intermediate frequency signal to obtain a RF signal. The order of the up-mixing and digital-to-analog conversion processes is adjustable. The digital baseband signal and the digital intermediate frequency signal may be collectively referred to as digital signals.

[0435] The transceiver 1013 may also be referred to as a transceiver unit, a transceiver, a transceiver device, etc. Optionally, a device in the transceiver unit that implements a receiving function may be referred to as a receiving unit, and a device in the transceiver unit that implements a transmitting function may be referred to as a transmitting unit. That is, the transceiver unit includes a receiving unit and a transmitting unit. The receiving unit may also be referred to as a receiver, an input port, a receiving circuit, etc., and the transmitting unit may be referred to as a transmitter, a transmitter, or a transmitting circuit, etc.

[0436] It should be noted that the communication device 1000 shown in Figure 10 can be specifically used to implement the steps implemented by the network device in the aforementioned method embodiment, and to achieve the corresponding technical effects of the network device. The specific implementation methods of the communication device 1000 shown in Figure 10 can refer to the description in the aforementioned method embodiment, and will not be repeated here one by one.

[0437] Please refer to FIG11 , which is a schematic structural diagram of the communication device involved in the above-mentioned embodiment provided in an embodiment of the present application.

[0438] It can be understood that the communication device 110 includes, for example, modules, units, elements, circuits, or interfaces, which are appropriately configured together to implement 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, used to implement the method described in the following method embodiment. The communication device 110 includes one or more processors 111. The processor 111 can be a general-purpose processor or a dedicated processor. 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 data of software programs.

[0439] Optionally, in one design, the processor 111 may include a program 113 (sometimes also referred to as code or instructions), which may be executed on the processor 111 to cause the communication device 110 to perform the methods described in the following embodiments. In yet another possible design, the communication device 110 includes circuitry (not shown in FIG11 ).

[0440] Optionally, the communication device 110 may include one or more memories 112 on which a program 114 (sometimes also referred to as code or instructions) is stored. The program 114 can be run on the processor 111, so that the communication device 110 executes the method described in the above method embodiment.

[0441] Optionally, the processor 111 and / or the memory 112 may include AI modules 117 and 118, which are used to implement AI-related functions. The AI ​​module can be implemented through software, hardware, or a combination of software and hardware. For example, the AI ​​module may include a wireless intelligent control (RIC) module. For example, the AI ​​module may be a near real-time RIC or a non-real-time RIC.

[0442] Optionally, data may be stored in the processor 111 and / or the memory 112. The processor and the memory may be provided separately or integrated together.

[0443] Optionally, the communication device 110 may further include a transceiver 115 and / or an antenna 116. The processor 111 may also be referred to as a processing unit, and controls the communication device (e.g., a RAN node or terminal). The transceiver 115 may also be referred to as a transceiver unit, a transceiver, a transceiver circuit, or a transceiver, and is configured to implement the transceiver functions of the communication device through the antenna 116.

[0444] The processing unit 701 shown in FIG7 may be the processor 111. The transceiver unit 702 shown in FIG7 may be a communication interface, which may be the transceiver 115 shown in FIG11 . The transceiver 115 may include an input interface and an output interface. Alternatively, the transceiver 115 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0445] An embodiment of the present application further 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 the possible implementation methods of the first communication device or the second communication device in the aforementioned embodiment.

[0446] An embodiment of the present application also provides a computer program product (or computer program) containing a program or instructions. When the computer program product is executed by the processor, the processor executes the method that may be implemented by the above-mentioned first communication device or second communication device.

[0447] An embodiment of the present application also provides a chip system, which includes at least one processor for supporting a communication device to implement the functions involved in the possible implementation methods of the above-mentioned communication device. Optionally, the chip system also includes an interface circuit, which provides program instructions and / or data to the at least one processor. In one possible design, the chip system may also include a memory, which is used to store the necessary program instructions and data for the communication device. The chip system can be composed of chips, or it can include chips and other discrete devices, wherein the communication device can specifically be the first communication device or the second communication device in the aforementioned method embodiment.

[0448] An embodiment of the present application further provides a communication system, wherein the network system architecture includes the first communication device and the second communication device in any of the above embodiments.

[0449] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0450] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0451] In addition, the functional units in the various embodiments of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into 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 this understanding, the technical solution of the present application is essentially or the contributing part or all or part of the technical solution can be embodied in the form of a software product, which 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 method described in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

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. The first AI model group includes K AI models and a second AI model, and K is an integer greater than or equal to 1. Among the K AI models, the input of any one of the K AI models includes the output of the second AI model, or the input of the second AI model includes the output of one or more of the K AI models. The second AI model is deployed in a second communication device, and the K AI models are used to be deployed in M communication devices, where the M communication devices include the first communication device, and M is less than or equal to K. Receiving second information, where the second information is used to determine a first AI model, and the first AI model includes one or more of the K AI models.

2. The method according to claim 1, wherein Before receiving the second information, the method further includes: Receiving third information, where the third information is used to configure the mapping relationship between P dimension information and Q indexes, and both P and Q are positive integers. The second information includes one or more of the Q indexes, and the one or more indexes are used to determine one of the P dimension information.

3. The method according to claim 2, wherein The third information is a layer 3 signaling, and the second information is a layer 1 and / or layer 2 signaling.

4. The method according to any one of claims 1 to 3, characterized in that The second information includes at least one of the following: The model parameters of the first AI model, the model parameters of the first AI model group, the dimension information of the input data of the first AI model, the dimension information of the output data of the first AI model.

5. The method according to any one of claims 1 to 4, 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.

6. The method according to claim 5, 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, the value range of the dimension expected by the first communication device.

7. The method according to claim 5 or 6, characterized in that, The first dimension information or the second dimension information is determined based on the channel state information.

8. The method according to any one of claims 1 to 7, 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, the channel state information.

9. The method according to any one of claims 1 to 8, characterized in that, 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 X AI models and a fourth AI model, where X is an integer greater than or equal to 1; among them, the input of any one of the X AI models includes the output of the fourth AI model, or the input of the fourth AI model includes the output of any one of the X AI models; the third AI model among the X AI models is deployed on the first communication device, and the third AI model includes one or more of the X AI models; the fourth AI model is deployed on the second communication device, and the X AI models are deployed on Y communication devices, and the Y communication devices include the first communication device, and Y is less than or equal to X.

10. The method according to any one of claims 1 to 9, characterized in that, After receiving the second information, the method further includes: Receiving fourth information, where the fourth information is used to indicate to stop the processing of the first AI model.

11. The method according to claim 10, characterized in that, Before receiving the fourth information, the method further includes: Sending fifth information, where the fifth information is used to determine the fourth information; among them, the fifth information includes at least one of the following: The input data or output data of the first AI model, the dimension information of the input data of the first AI model or the dimension information of the output data of the first AI model, the dimension expected by the first communication device, the value range of the dimension expected by the first communication device, the channel state information of the first communication device.

12. The method according to claim 10 or 11, characterized in that The method further includes: Sending sixth information, where the sixth information is used to request to stop the processing of the first AI model.

13. A communication method, characterized in that, Including: Receiving the first information; Determining a first artificial intelligence (AI) model group based on the first information, where the first AI model group includes K AI models and a second AI model, and K is an integer greater than or equal to 1; among them, the input of any one of the K AI models includes the output of the second AI model, or the input of the second AI model includes the output of one or more of the K AI models; the second AI model is deployed on the second communication device, and the K AI models are deployed on M communication devices, and the M communication devices include the first communication device, and M is less than or equal to K; Sending second information, where the second information is used to determine the first AI model, and the first AI model is deployed on the first communication device, and the first AI model includes one or more of the K AI models.

14. The method according to claim 13, wherein Before sending the second information, the method further includes: Sending third information, where the third information is used to configure the mapping relationship between P dimension information and Q indexes, and both P and Q are positive integers; the second information includes one or more of the Q indexes, and the one or more indexes are used to determine one of the P dimension information.

15. The method according to claim 14, characterized in that, The third information is a layer 3 signaling, and the second information is a layer 1 and / or layer 2 signaling.

16. The method according to any one of claims 13 to 15, characterized in that, The second information includes at least one of the following: The model parameters of the first AI model, the model parameters of the first AI model group, the dimension information of the input data of the first AI model, and the dimension information of the output data of the first AI model.

17. The method according to any one of claims 13 to 16, 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.

18. The method according to claim 17, 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.

19. The method according to claim 17 or 18, characterized in that The first dimension information or the second dimension information is determined based on the channel state information.

20. The method according to any one of claims 13 to 19, 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 the channel state information.

21. The method according to any one of claims 13 to 20, characterized in that, 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 X AI models and a fourth AI model, where X is an integer greater than or equal to 1; among them, the input of any one of the X AI models includes the output of the fourth AI model, or the input of the fourth AI model includes the output of any one of the X AI models; the third AI model among the X AI models is deployed on the first communication device, and the third AI model includes one or more AI models among the X AI models; the fourth AI model is deployed on a second communication device, and the X AI models are deployed on Y communication devices, and the Y communication devices include the first communication device, and Y is less than or equal to X.

22. The method according to any one of claims 13 to 21, characterized in that, After sending the second information, the method further includes: Sending fourth information, where the fourth information is used to indicate to stop the processing of the first AI model.

23. The method according to claim 22, wherein Before sending the fourth information, the method further includes: Receiving fifth information, where the fifth information is used to determine the fourth information; among them, the fifth information includes at least one of the following: The input data or output data of the first AI model, the dimension information of the input data of the first AI model or the dimension information of the output data of the first AI model, the dimension expected by the first communication device, the value range of the dimension expected by the first communication device, and the channel state information of the first communication device.

24. The method according to claim 22 or 23, characterized in that, The method further includes: Receiving sixth information, where the sixth information is used to request to stop the processing of the first AI model.

25. A communication method, characterized in that, The method is applied to a first communication device and includes: Perform model processing based on a first AI model, where the first AI model and a second AI model are included in a first group of AI models; 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; Receive fourth information, where the fourth information is used to indicate the termination of the processing of the first AI model.

26. The method according to claim 25, wherein The first group of AI models includes Z AI models, where Z is a positive integer; the input of any one of the Z AI models includes the output of the second AI model, or, the input of the second AI model includes the output of any one or more of the Z AI models.

27. The method according to claim 25 or 26, characterized in that, Before receiving the fourth information, the method further includes: Send fifth information, where the fifth information is used to determine the fourth information; wherein, the fifth information includes at least one of the following: the input data or output data of the first AI model, the dimensionality information of the input data of the first AI model or the dimensionality information of the output data of the first AI model, the dimension expected by the first communication device, the value range of the dimension expected by the first communication device, the channel state information of the first communication device.

28. The method according to any one of claims 25 to 27, characterized in that, The method further includes: Send sixth information, where the sixth information is used to request the termination of the processing of the first AI model.

29. A communication method, characterized in that, The method is applied to a second communication device, and the method includes: Determine fourth information, where the fourth information is used to indicate the termination of the processing of a first AI model, and the first AI model and a second AI model are included in a first group of AI models; wherein, the first AI model is deployed on a 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; Send the fourth information.

30. The method according to claim 29, characterized in that, The first group of AI models includes Z AI models, and the input of any one of the Z AI models includes the output of the second AI model, or, the input of the second AI model includes the output of any one or more of the Z AI models.

31. The method according to claim 29 or 30, characterized in that, Before sending the fourth information, the method further includes: Receive fifth information, where the fifth information is used to determine the fourth information; wherein, the fifth information includes at least one of the following: the input data or output data of the first AI model, the dimensionality information of the input data of the first AI model or the dimensionality information of the output data of the first AI model, the dimension expected by the first communication device, the value range of the dimension expected by the first communication device, the channel state information of the first communication device.

32. The method according to any one of claims 29 to 31, characterized in that, The method further includes: Receive sixth information, where the sixth information is used to request the termination of the processing of the first AI model.

33. A first communication device, characterized in that, Includes a module for performing the method according to any one of claims 1 to 12 or 25 to 28.

34. A second communication device, characterized in that, Comprises a module for performing the method according to any one of claims 13 to 24 or 29 to 32.

35. A first communication device, characterized in that, Comprises at least one processor, the at least one processor being coupled to a memory; the at least one processor is configured to execute a program or instructions stored in the memory such that the communication device performs the method according to any one of claims 1 to 12 or 25 to 28.

36. The first communication device according to claim 35, characterized in that, The first communication device is a chip or a chip system.

37. A second communication device, characterized in that, Comprises at least one processor, the at least one processor being coupled to a memory; the at least one processor is configured to execute a program or instructions stored in the memory such that the second communication device performs the method according to any one of claims 13 to 24 or 29 to 32.

38. The second communication device according to claim 37, wherein The second communication device is a chip or a chip system.

39. A first communication device, characterized in that, Comprises at least one logic circuit and an input-output interface; the logic circuit is configured to execute the method according to any one of claims 1 to 12 or 25 to 28.

40. A second communication device, characterized in that, Comprises at least one logic circuit and an input-output interface; the logic circuit is configured to execute the method according to any one of claims 13 to 24 or 29 to 32.

41. A communication system, characterized in that, Comprises a first communication device according to any one of claims 33, 35 or 39 and a second communication device according to any one of claims 34, 37 or 40.

42. A chip system, characterized in that, The chip system comprises at least one processor for supporting the first communication device to implement the method according to any one of claims 1 to 12 or 25 to 28, or for supporting the second communication device to implement the method according to any one of claims 13 to 24 or 29 to 32.

43. The chip system according to claim 42, characterized in that, The chip system further comprises a memory; the memory is used for storing program instructions and data of the first communication device; or the memory is used for storing program instructions and data of the second communication device.

44. The chip system according to claim 42 or 43, characterized in that, The chip system is composed of chips, or the chip system includes chips and other discrete devices.

45. The chip system according to any one of claims 42 to 44, characterized in that, The chip system further comprises an interface circuit, and the interface circuit provides program instructions and / or data for the at least one processor.

46. A readable storage medium, characterized in that, The computer program or instructions are stored in the storage medium, and when the computer program or instructions are executed by the communication device, the method according to any one of claims 1 to 12 or 25 to 28 is implemented; or the method according to any one of claims 13 to 24 or 29 to 32 is implemented.

47. A computer program product, characterized in that, Comprises computer instructions, and when the instructions run on a processor, the method according to any one of claims 1 to 12 or 25 to 28 is executed; or the method according to any one of claims 13 to 24 or 29 to 32 is executed.

Images