Communication method and related equipment

Abstract

The invention provides a communication method and related equipment, which can realize the indication of two modes, namely an artificial intelligence (AI) inference mode and an AI training mode in a communication network, so that the computing power of a communication node can be applied to the processing process of an AI task. In the method, a terminal device receives first indication information, the first indication information is used for indicating that a processing mode of K AI models is a first mode or a second mode, the K AI models correspond to a first AI task, and K is a positive integer; wherein the first mode comprises AI reasoning, and the second mode comprises AI training; and the terminal equipment processes the K AI models through the first mode or the second mode.

Description

A communication method and related equipment Technical Field

[0001] The present application relates to the field of communications, and in particular to a communication method and related equipment. Background Art

[0002] Wireless communication refers to the transmission of information between multiple communication nodes without the use of conductors or cables. Generally, network devices and terminal devices can act as different communication nodes and communicate based on wireless communication.

[0003] Currently, in wireless communication systems, communication nodes generally possess both signal transceiver and computing capabilities. For example, network devices with computing capabilities primarily provide computing power to support signal transceiver capabilities (for example, calculating the time and frequency domain resources required to carry the signal), enabling communication between the network device and other communication nodes.

[0004] 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.

[0005] Summary of the Invention

[0006] The present application provides a communication method and related equipment that can implement the indication of two modes, artificial intelligence (AI) inference mode and AI training mode, in a communication network, so that the computing power of the communication node can be applied to the processing process of AI tasks.

[0007] The first aspect of the present application provides a communication method, which is executed by a terminal device, or the method is executed by some components in the terminal device (such as a processor, chip or chip system, etc.), or the method can also be implemented by a logic module or software that can realize all or part of the terminal device functions. In the first aspect and its possible implementation, the method is described as being executed by a terminal device. In this method, the terminal device receives first indication information, and the first indication information is used to indicate that the processing mode of K AI models is a first mode or a second mode, and the K AI models correspond to a first AI task, and K is a positive integer; wherein the first mode includes AI reasoning, and the second mode includes AI training; the terminal device processes the K AI models through the first mode or the second mode.

[0008] Based on the above technical solution, the first indication information received by the terminal device is used to indicate that the processing mode of the K AI models is the first mode or the second mode. Thereafter, based on the first indication information, the terminal device can process the K AI models in the first mode or the second mode. The first mode includes AI reasoning, and the second mode includes AI training. Thus, the terminal device, as a communication node in the communication system, can perform AI reasoning or AI training on the AI ​​model based on the first indication information, so that the computing power of the communication node can be applied to the processing process of the AI ​​task, and can implement the indication of the two modes of AI reasoning (inference) mode and AI training (training) mode in the communication network.

[0009] It should be understood that an AI task corresponds to one or more AI models, and it can be understood that the execution process of an AI task includes the processing of the one or more AI models by the AI ​​node. The AI ​​node may include a terminal device. Optionally, the AI ​​node may also include other devices, such as the network device and the first device mentioned below.

[0010] It should be understood that in the above technical solution, the first AI task may correspond to P AI models, where K is less than or equal to P. In other words, the K AI models processed by the terminal device may be some of the one or more AI models corresponding to the first AI task, or the K AI models processed by the terminal device may be all of the one or more AI models corresponding to the first AI task. The K AI models corresponding to the first AI task may be indicated by the identifier of the first AI task and the identifiers of the K AI models.

[0011] Optionally, in the above technical solution, the K AI models indicated by the first indication information correspond to the same AI task (i.e., the first AI task), that is, the indication of the AI ​​model processing mode received by the terminal device can be indicated at the granularity of the AI ​​task, that is, based on the first indication information, the indication of one or more AI models contained in the same AI task can be implemented to reduce overhead and improve efficiency. In actual applications, the K AI models indicated by the first indication information can be decoupled from the AI ​​task, that is, the indication of the AI ​​model processing mode received by the terminal device can be indicated at the granularity of the AI ​​model to improve the flexibility of the solution implementation. Similarly, other information / data mentioned later (such as management information, indication information for indicating the AI ​​model, data associated with the AI ​​model, indication information for indicating the supported processing mode, etc.) can also be indicated at the granularity of the AI ​​task or at the granularity of the AI ​​model.

[0012] It should be understood that the first mode includes AI reasoning, which can be understood as the AI ​​node performing at least AI reasoning on the AI ​​model in the first mode. Among them, the AI ​​node (such as a terminal device, and a network device, a first device, etc. that may participate in an AI task) performs AI reasoning on the AI ​​model, which can include the process in which the communication device inputs input data into the AI ​​model and obtains output data corresponding to the input data through reasoning by the AI ​​model. Similarly, the second mode includes AI training, which can be understood as the AI ​​node performing at least AI training on the AI ​​model in the second mode. Among them, the AI ​​node (such as a terminal device, and a network device, a first device, etc. that may participate in an AI task) performs AI training on the AI ​​model, which can include the process in which the communication device inputs input data and label data into the AI ​​model to update the parameters of the AI ​​model.

[0013] In this application, AI model can be replaced by learning model, AI learning model, machine learning model, neural network, AI network, etc.

[0014] In a possible implementation manner of the first aspect, the method further includes: the terminal device receiving indication information indicating management information of the K AI models.

[0015] Based on the above technical solution, the terminal device can also receive indication information indicating the management information of the K AI models. The terminal device can subsequently manage the K AI models based on the indication information, thereby enabling the management of AI models in the communication network through the indication information.

[0016] Optionally, the management information includes at least one of the following: model selection, model enablement, model update, model switching, and model rollback.

[0017] In a possible implementation of the first aspect, after the terminal device processes the K AI models through the first mode or the second mode, the method further includes: the terminal device sending model performance measurement results of the K AI models.

[0018] Based on the above technical solution, after the terminal device processes the K AI models through the first mode or the second mode, the terminal device can measure the model performance of the K AI models to obtain model performance measurement results. Subsequently, the terminal device can send the model performance measurement results of the K AI models to realize the measurement of the performance of the AI ​​models deployed in the communication network.

[0019] In a possible implementation manner of the first aspect, the method further includes: the terminal device receiving indication information instructing to report the model performance measurement results of the K AI models.

[0020] Based on the above technical solution, the terminal device can also receive indication information instructing to report the model performance measurement results of the K AI models, and send the model performance measurement results of the K AI models based on the indication information to realize measurement indication of the performance of the AI ​​models deployed in the communication network.

[0021] In a possible implementation manner of the first aspect, the method further includes: the terminal device sending data associated with the K AI models.

[0022] Based on the above technical solution, the terminal device can also send data associated with the K AI models to realize data collection of AI model associated data deployed in the communication network.

[0023] Optionally, in the first mode, the data associated with the K AI models include the input data of the K AI models; and / or, in the second mode, the data associated with the K AI models include the input data and label data of the K AI models.

[0024] In a possible implementation of the first aspect, the terminal device processes the K AI models through the second mode, including: the terminal device processes the K AI models through the second mode to obtain K updated AI models; and the terminal device sends indication information indicating the K updated AI models.

[0025] Based on the above technical solution, the second mode includes AI training. Accordingly, the terminal device processes the K AI models through the second mode to obtain K updated AI models. In addition, the terminal device can also send indication information indicating the K updated AI models, so that the recipient of the indication information obtains the updated AI model, thereby realizing the training of the AI ​​model deployed in the communication network.

[0026] In a possible implementation manner of the first aspect, the method further includes: the terminal device receiving indication information indicating the K AI models.

[0027] Based on the above technical solution, the terminal device can also receive indication information indicating the K AI models, so that the terminal device determines the K AI models based on the indication information to realize the deployment of the AI ​​models in the communication network.

[0028] Optionally, the K AI models may be preconfigured or predefined.

[0029] In a possible implementation of the first aspect, the first indication information is one of N indication information, and the N indication information are respectively used to indicate a processing mode of the AI ​​model corresponding to N AI tasks, where the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer.

[0030] Based on the above technical solution, the first indication information received by the terminal device may be one of N indication information, and the N indication information may be used to indicate the processing mode of the AI ​​model corresponding to the N AI tasks respectively, so that the terminal device can determine the processing mode of the N AI tasks based on the N indication information, and then implement the indication of the processing mode of the AI ​​model with the AI ​​task as the granularity.

[0031] In a possible implementation of the first aspect, the method further includes: the terminal device sends indication information indicating a processing mode of the AI ​​model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task.

[0032] Optionally, the indication information sent by the terminal device is used to indicate the processing mode of the AI ​​model corresponding to the M AI tasks, wherein the indication information can be used to indicate the processing mode supported by the terminal device in the AI ​​model corresponding to the M AI tasks. In other words, the indication information can be capability indication information.

[0033] Based on the above technical solution, the indication information sent by the terminal device is used to indicate the processing mode of the AI ​​model corresponding to M AI tasks, and the M AI tasks include the first AI task, so that the recipient of the indication information can determine the first indication information based on the processing mode of the AI ​​model corresponding to the M AI tasks, so that the processing mode indicated by the first indication information can be adapted to the capabilities of the terminal device.

[0034] The second aspect of the present application provides a communication method, which is executed by a network device, or the method is executed by some components in the network device (such as a processor, chip or chip system, etc.), or the method can also be implemented by a logic module or software that can realize all or part of the network device functions. In the second aspect and its possible implementation, the method is described as being executed by a network device. For example, the network device may include an access network device and / or a core network device. In this method, the network device receives a first indication message, and the first indication message is used to indicate that the processing mode of K artificial intelligence AI models is a first mode or a second mode, and the K AI models correspond to a first AI task, and K is a positive integer; wherein the first mode includes AI reasoning, and the second mode includes AI training; the network device sends the first indication message.

[0035] Based on the above technical solution, the first indication information received by the network device is used to indicate that the processing mode of the K AI models is the first mode or the second mode. Thereafter, the network device can send the first indication information, and after the subsequent terminal device receives the first indication information, the terminal device can process the K AI models through the first mode or the second mode. The first mode includes AI reasoning, and the second mode includes AI training. Thus, the terminal device, as a communication node in the communication system, can perform AI reasoning or AI training on the AI ​​model based on the first indication information, and can implement the indication of both the AI ​​reasoning mode and the AI ​​training mode in the communication network, so that the computing power of the communication node can be applied to the processing of the AI ​​task.

[0036] It should be noted that the network device may include an access network device and / or a core network device, and some implementation examples will be provided below for illustration.

[0037] In one implementation example, the network device may be an access network device. In the above technical solution, the first indication information received by the access network device may come from the core network device, and accordingly, the access network device may send the first indication information to the terminal device. In other words, the communication interface through which the above network device receives the first indication information may be the communication interface between the access network device and the core network device, that is, the first device sends the first indication information to the access network device through the core network device. The communication interface through which the above network device sends the first indication information may be the communication interface between the access network device and the terminal device, that is, the access network device sends the first indication information to the terminal device.

[0038] In another implementation example, the network device may be a core network device. In the above technical solution, the first indication information received by the core network device may come from a first device (for example, the first device may be a server, a virtual machine, a container, etc.), and accordingly, the core network device may send the first indication information to the access network device, and the subsequent access network device may further send the first indication information to the terminal device. In other words, the communication interface for the above network device to receive the first indication information may be a communication interface between the core network device and the first device, that is, the first device sends the first indication information to the core network device. The communication interface for the above network device to send the first indication information may be a communication interface between the core network device and the access network device, that is, the core network device sends the first indication information to the terminal device through the access network device.

[0039] In another implementation example, the network device may include an access network device and a core network device, that is, the access network device and the core network device are collectively provided in the same device. In the above technical solution, the first indication information received by the network device may come from a first device (for example, the first device may be a server, a virtual machine, a container, etc.), and accordingly, the network device may send the first indication information to the terminal device. In other words, the communication interface through which the above network device receives the first indication information may be a communication interface between the network device and the first device, that is, the first device sends the first indication information to the network device. The communication interface through which the above network device sends the first indication information may be a communication interface between the network device and the terminal device, that is, the network device sends the first indication information to the terminal device.

[0040] In a possible implementation of the second aspect, the method further includes: the network device receiving first configuration information, where the first configuration information is used to configure management information of AI models corresponding to X AI tasks, where the X AI tasks include the first AI task, and X is a positive integer; and the network device sending indication information indicating the management information of the K AI models based on the first configuration information.

[0041] Based on the above technical solution, the network device may also receive the first configuration information, and based on the first configuration information, the network device may also send indication information indicating management information of the K AI models. After receiving the indication information, the terminal device may subsequently manage the K AI models based on the indication information. Thus, the indication information may enable management of AI models in the communication network.

[0042] Optionally, the network device that determines the management information based on the first configuration information may be a core network device, an access network device, or a device that combines a core network device and an access network device, which is not limited here.

[0043] Optionally, the first configuration information includes one or more of the following: applicable scenarios of the AI ​​models corresponding to the X AI tasks, selection conditions of the AI ​​models corresponding to the X AI tasks, enabling conditions of the AI ​​models corresponding to the X AI tasks, update conditions of the AI ​​models corresponding to the X AI tasks, switching conditions of the AI ​​models corresponding to the X AI tasks, fallback conditions of the AI ​​models corresponding to the X AI tasks, and data collection information of the AI ​​models corresponding to the X AI tasks.

[0044] Optionally, the data collection information of the AI ​​model corresponding to the X AI tasks includes one or more of the following: data type, collection time, collection frequency, collection location, and collection quantity.

[0045] In a possible implementation manner of the second aspect, the method further includes: the network device receiving indication information indicating management information of the K AI models; and the network device sending indication information indicating management information of the K AI models.

[0046] Based on the above technical solution, the network device can receive and send indication information indicating the management information of the K AI models, so that the network device can act as a transparent communication role and send the indication information to the terminal device. Thus, the indication information can be used to manage the AI ​​model in the communication network.

[0047] Optionally, the device that determines the management information based on the first configuration information may be a core network device. Accordingly, the core network device may send indication information indicating the management information of the K AI models to the access network device, and the access network device may subsequently perform transparent transmission processing on the indication information, that is, the network device that plays the role of transparent transmission communication in the above technical solution may be an access network device.

[0048] Optionally, the management information includes at least one of the following: model selection, model enablement, model update, model switching, and model rollback.

[0049] In a possible implementation manner of the second aspect, the method further includes: the network device receiving indication information indicating model performance measurement results of the K AI models.

[0050] Based on the above technical solution, the network device can also receive indication information indicating the model performance measurement results of the K AI models to realize the measurement of the performance of the AI ​​models deployed in the communication network.

[0051] In a possible implementation of the second aspect, before the network device receives indication information indicating the model performance measurement results of the K AI models, the method also includes: the network device receives second configuration information, where the second configuration information is used to configure measurement information of the AI ​​models corresponding to Y AI tasks, where the Y AI tasks include the first AI task; and the network device sends indication information indicating reporting of the model performance measurement results of the K AI models based on the second configuration information.

[0052] Based on the above technical solution, the network device may also receive second configuration information and, based on the second configuration information, send instruction information instructing the reporting of the model performance measurement results of the K AI models. Thus, the terminal device sends the model performance measurement results of the K AI models based on the instruction information, thereby implementing measurement instructions for the performance of the AI ​​models deployed on the communication network.

[0053] Optionally, the network device that determines the indication information for reporting the model performance measurement results of the K AI models based on the second configuration information can be a core network device, an access network device, or a device that is a combination of a core network device and an access network device, which is not limited here.

[0054] Optionally, the second configuration information includes one or more of the following: a measurement object, a measurement period, a measurement triggering condition, and a reporting method of a measurement result.

[0055] In a possible implementation of the second aspect, before the network device receives indication information indicating the model performance measurement results of the K AI models, the method also includes: the network device receives indication information instructing to report the model performance measurement results of the K AI models; and the network device sends indication information instructing to report the model performance measurement results of the K AI models.

[0056] Based on the above technical solution, the network device can also receive and send indication information to instruct the reporting of the model performance measurement results of the K AI models, so that the network device acts as a transparent communication role and sends the indication information to the terminal device to realize the measurement indication of the performance of the AI ​​model deployed in the communication network.

[0057] Optionally, the device that determines the indication information for reporting the model performance measurement results of the K AI models based on the second configuration information can be a core network device. Accordingly, the core network device can send the indication information to the access network device, and the access network device can subsequently perform transparent transmission processing on the indication information, that is, the network device that plays the role of transparent transmission communication in the above technical solution can be an access network device.

[0058] In a possible implementation of the second aspect, the method further includes: the network device receiving data associated with the K AI models.

[0059] Based on the above technical solution, the network device can also receive data associated with the K AI models to realize data collection of AI model associated data deployed in the communication network.

[0060] In a possible implementation manner of the second aspect, the method further includes: the network device sends first data, where the first data is processed based on data associated with the K AI models.

[0061] Optionally, the first data is obtained by performing one or more processes such as data integration, preprocessing, and redundancy removal on the data associated with the K AI models.

[0062] Based on the above technical solution, after the network device receives data associated with K AI models, the network device can process the data associated with the K AI models to obtain first data, and send the first data, so that the recipient of the first data can obtain the first data.

[0063] Optionally, the network device that processes the data associated with the K AI models to obtain the first data can be a core network device, an access network device, or a device that is a combination of a core network device and an access network device, which is not limited here.

[0064] In a possible implementation manner of the second aspect, the method further includes: the network device sending data associated with the K AI models.

[0065] Based on the above technical solution, after the network device receives the data associated with K AI models, the network device can act as a transparent communication role and send the data associated with the K AI models, so that the recipient of the data associated with the K AI models can further obtain other data (for example, the first data) to realize data collection.

[0066] Optionally, the network device that transparently transmits the data associated with the K AI models may be an access network device, and the subsequent core network device may obtain other data (eg, first data) based on the data associated with the K AI models.

[0067] Optionally, in the first mode, the data associated with the K AI models include the input data of the K AI models; and / or, in the second mode, the data associated with the K AI models include the input data and label data of the K AI models.

[0068] In a possible implementation manner of the second aspect, the method further includes: the network device receiving indication information indicating the K updated AI models, where the K updated AI models are obtained by processing the K AI models through the second mode.

[0069] Based on the above technical solution, the second mode includes AI training. Accordingly, the terminal device processes the K AI models through the second mode to obtain K updated AI models. In addition, the terminal device can also send indication information indicating the K updated AI models, so that the network device obtains the updated AI model, thereby realizing the training of the AI ​​model deployed in the communication network.

[0070] In a possible implementation manner of the second aspect, the method further includes: the network device performs a fusion process on the K updated AI models to obtain a fusion result; and the network device sends indication information indicating the fusion result.

[0071] Based on the above technical solution, after receiving the indication information indicating the K updated AI models, the network device can also perform fusion processing on the K updated AI models to obtain a fusion result, and send indication information indicating the fusion result to enable model fusion in the AI ​​training scenario.

[0072] Optionally, the network device that performs the fusion processing on the K updated AI models to obtain the fusion result can be a core network device, an access network device, or a device that is a combination of a core network device and an access network device, which is not limited here.

[0073] In a possible implementation manner of the second aspect, the method further includes: the network device sending indication information indicating the K updated AI models.

[0074] Based on the above technical solution, after the network device receives the indication information indicating the K updated AI models, the network device can, as a transparent communication role, send indication information indicating the K updated AI models, so that the recipient of the indication information can further realize model fusion.

[0075] Optionally, the network device that transparently transmits the indication information indicating the K updated AI models may be an access network device, and subsequent core network devices may perform model fusion based on the indication information.

[0076] In a possible implementation manner of the second aspect, the method further includes: the network device sending indication information indicating the K AI models.

[0077] Based on the above technical solution, the network device can also send indication information indicating the K AI models to the terminal device to realize the deployment of the AI ​​model in the communication network.

[0078] Optionally, the K AI models may be preconfigured or predefined.

[0079] In a possible implementation of the second aspect, the method further includes: the network device receiving third configuration information, where the third configuration information is used to configure P AI models, where the P AI models correspond to the first AI task, and P is greater than or equal to K.

[0080] Optionally, the third configuration information includes at least one of the following: task type information of the first AI task, AI model type information of P AI models, model scale information of the P AI models, and model performance requirement information of the P AI models.

[0081] Based on the above technical solution, the network device can receive the third configuration information for configuring P AI models, and then send indication information indicating the K AI models to the terminal device, that is, the network device can screen / select the required K AI models from the P AI models, and then deploy the K AI models to the terminal device.

[0082] Optionally, the network device that determines K AI models based on P AI models can be a core network device, an access network device, or a device that is a combination of a core network device and an access network device, and there is no limitation here.

[0083] In a possible implementation manner of the second aspect, the method further includes: the network device receiving indication information indicating K AI models.

[0084] Based on the above technical solution, the network device acts as a transparent communication role, and the network device can send indication information indicating the K AI models to the terminal device to realize the deployment of the AI ​​model in the communication network.

[0085] In a possible implementation of the second aspect, the first indication information is one of N indication information, and the N indication information are respectively used to indicate the processing mode of the AI ​​model corresponding to N AI tasks, where the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer.

[0086] Based on the above technical solution, the first indication information sent by the network device can be one of N indication information, and the N indication information can be used to indicate the processing mode of the AI ​​model corresponding to the N AI tasks respectively, so that the terminal device can determine the processing mode of the N AI tasks based on the N indication information, and then implement the indication of the processing mode of the AI ​​model with AI tasks as the granularity.

[0087] In a possible implementation of the second aspect, the method further includes: the network device receives indication information indicating a processing mode of the AI ​​model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task.

[0088] Optionally, the indication information received by the network device is used to indicate the processing mode of the AI ​​model corresponding to the M AI tasks, wherein the indication information can be used to indicate the processing mode supported by the terminal device in the AI ​​model corresponding to the M AI tasks. In other words, the indication information can be capability indication information.

[0089] Based on the above technical solution, the indication information received by the network device is used to indicate the processing mode of the AI ​​model corresponding to M AI tasks, and the M AI tasks include the first AI task, so that the network device can determine the first indication information based on the processing mode of the AI ​​model corresponding to the M AI tasks, so that the processing mode indicated by the first indication information can be adapted to the capabilities of the terminal device.

[0090] In a possible implementation manner of the second aspect, the method further includes: the network device sending indication information indicating a processing mode of the AI ​​model corresponding to the M AI tasks.

[0091] Based on the above technical solution, after the network device indicates the processing mode of the AI ​​model corresponding to the M AI tasks, the network device can also send the indication information as a communication role of transparent forwarding to realize the transmission of the capability information of the terminal device.

[0092] The third aspect of the present application provides a communication method, which is executed by a first device, or the method is executed by some components in the first device (such as a processor, chip or chip system, etc.), or the method can also be implemented by a logic module or software that can realize all or part of the functions of the first device. In the third aspect and its possible implementation, the method is described as being executed by the first device. For example, the first device can be a device that provides application services (for example, the device is an over-the-top (OTT) manufacturer device), including a server, a virtual machine, a container, etc. In this method, the first device determines first indication information, and the first indication information is used to indicate that the processing mode of K artificial intelligence AI models is the first mode or the second mode, and the K AI models correspond to the first AI task, and K is a positive integer; wherein the first mode includes AI reasoning, and the second mode includes AI training; the first device sends the first indication information.

[0093] Based on the above technical solution, the first indication information sent by the first device is used to indicate that the processing mode of the K AI models is the first mode or the second mode. After the subsequent terminal device receives the first indication information, the terminal device can process the K AI models in the first mode or the second mode. The first mode includes AI reasoning, and the second mode includes AI training. Thus, the terminal device, as a communication node in the communication system, can perform AI reasoning or AI training on the AI ​​model based on the first indication information, and can implement the indication of both AI reasoning mode and AI training mode in the communication network, so that the computing power of the communication node can be applied to the processing process of the AI ​​task.

[0094] It should be noted that the first device may send the first indication information to a network device, and the network device may include a core network device and / or an access network device.

[0095] In a possible implementation of the third aspect, the method further includes: the first device sending first configuration information, where the first configuration information is used to configure management information of AI models corresponding to X AI tasks, where the X AI tasks include the first AI task, and X is a positive integer.

[0096] Based on the above technical solution, the first device can also send first configuration information for configuring management information of the AI ​​models corresponding to X AI tasks, so that the network device can subsequently send indication information indicating the management information of the K AI models based on the first configuration information. After receiving the indication information, the terminal device can subsequently manage the K AI models based on the indication information. Thus, the indication information can be used to implement AI model management in the communication network.

[0097] Optionally, the first configuration information includes one or more of the following: applicable scenarios of the AI ​​models corresponding to the X AI tasks, selection conditions of the AI ​​models corresponding to the X AI tasks, enabling conditions of the AI ​​models corresponding to the X AI tasks, update conditions of the AI ​​models corresponding to the X AI tasks, switching conditions of the AI ​​models corresponding to the X AI tasks, fallback conditions of the AI ​​models corresponding to the X AI tasks, and data collection information of the AI ​​models corresponding to the X AI tasks.

[0098] Optionally, the data collection information of the AI ​​model corresponding to the X AI tasks includes one or more of the following: data type, collection time, collection frequency, collection location, and collection quantity.

[0099] Optionally, the first configuration information is used to determine management information of the K AI models, and the management information includes at least one of the following: model selection, model enablement, model update, model switching, and model rollback.

[0100] In a possible implementation manner of the third aspect, the method further includes: the first device receiving indication information indicating model performance measurement results of the K AI models.

[0101] Based on the above technical solution, the first device can also receive indication information indicating the model performance measurement results of the K AI models to realize the measurement of the performance of the AI ​​models deployed in the communication network.

[0102] In a possible implementation of the third aspect, before the first device receives indication information indicating the model performance measurement results of the K AI models, the method further includes: the first device sends second configuration information, where the second configuration information is used to configure measurement information of the AI ​​models corresponding to Y AI tasks, where the Y AI tasks include the first AI task.

[0103] Based on the above technical solution, the first device may further send second configuration information, so that after the network device receives the second configuration information, the network device can send, based on the second configuration information, instruction information instructing the reporting of the model performance measurement results of the K AI models. Thus, the terminal device sends the model performance measurement results of the K AI models based on the instruction information, thereby implementing measurement instructions for the performance of the AI ​​models deployed on the communication network.

[0104] Optionally, the second configuration information includes one or more of the following: a measurement object, a measurement period, a measurement triggering condition, and a reporting method of a measurement result.

[0105] In a possible implementation of the third aspect, the method further includes: the first device receiving data associated with the K AI models, or first data, where the first data is processed based on the data associated with the K AI models.

[0106] Based on the above technical solution, the first device can also receive data associated with the K AI models to realize data collection of AI model associated data deployed in the communication network.

[0107] Optionally, in the first mode, the data associated with the K AI models include the input data of the K AI models; and / or, in the second mode, the data associated with the K AI models include the input data and label data of the K AI models.

[0108] In a possible implementation of the third aspect, the method further includes: the first device receiving indication information indicating the K updated AI models, where the K updated AI models are obtained by processing the K AI models through the second mode; or, the first device receiving indication information indicating a fusion result, where the fusion result is obtained based on fusion processing of the K updated AI models.

[0109] Based on the above technical solution, the second mode includes AI training. Accordingly, the terminal device processes the K AI models through the second mode to obtain K updated AI models. In addition, the terminal device can also send indication information indicating the K updated AI models, so that the first device obtains the updated AI model, thereby realizing the training of the AI ​​model deployed in the communication network.

[0110] In a possible implementation of the third aspect, the method further includes: the first device sending third configuration information, where the third configuration information is used to configure P AI models, where the P AI models correspond to the first AI task, and P is greater than or equal to K.

[0111] Optionally, the third configuration information includes at least one of the following: task type information of the first AI task, AI model type information of P AI models, model scale information of the P AI models, and model performance requirement information of the P AI models.

[0112] Based on the above technical solution, the first device can send third configuration information for configuring P AI models, so that the network device can send indication information indicating the K AI models to the terminal device based on the P AI models, that is, the network device can screen / select the required K AI models from the P AI models and then deploy the K AI models to the terminal device.

[0113] In a possible implementation of the third aspect, the first indication information is one of N indication information, and the N indication information are respectively used to indicate the processing mode of the AI ​​model corresponding to N AI tasks, where the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer.

[0114] Based on the above technical solution, the first indication information sent by the first device can be one of N indication information, and the N indication information can be used to indicate the processing mode of the AI ​​model corresponding to the N AI tasks respectively, so that the terminal device can determine the processing mode of the N AI tasks based on the N indication information, and then implement the indication of the processing mode of the AI ​​model with AI tasks as the granularity.

[0115] In a possible implementation of the third aspect, the method further includes: the first device receiving indication information indicating a processing mode of the AI ​​model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task.

[0116] Based on the above technical solution, the indication information received by the first device is used to indicate the indication information of the processing mode of the AI ​​model corresponding to M AI tasks, and the M AI tasks include the first AI task, so that the first device can determine the first indication information based on the processing mode of the AI ​​model corresponding to the M AI tasks, so that the processing mode indicated by the first indication information can be adapted to the capabilities of the terminal device.

[0117] In a fourth aspect, the present application provides a communication device, which is a terminal device, or a component of a terminal device (such as a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the terminal device's functions. In the fourth aspect and its possible implementations, the communication device is described as an example of a terminal device.

[0118] The device includes a processing unit and a transceiver unit; the transceiver unit is used to receive first indication information, where the first indication information is used to indicate that the processing mode of K artificial intelligence (AI) models is a first mode or a second mode, where the K AI models correspond to a first AI task, and K is a positive integer; wherein the first mode includes AI reasoning and the second mode includes AI training; the processing unit is used to process the K AI models through the first mode or the second mode.

[0119] In a possible implementation manner of the fourth aspect, the transceiver unit is further used to receive indication information indicating management information of the K AI models.

[0120] In a possible implementation manner of the fourth aspect, the management information includes at least one of the following: model selection, model enablement, model update, model switching, and model rollback.

[0121] In a possible implementation of the fourth aspect, the transceiver unit is further used to send model performance measurement results of the K AI models.

[0122] In a possible implementation of the fourth aspect, the transceiver unit is further used to receive indication information instructing to report the model performance measurement results of the K AI models.

[0123] In a possible implementation of the fourth aspect, the transceiver unit is further used to send data associated with the K AI models.

[0124] In a possible implementation of the fourth aspect, in the first mode, the data associated with the K AI models include the input data of the K AI models; and / or, in the second mode, the data associated with the K AI models include the input data and label data of the K AI models.

[0125] In a possible implementation of the fourth aspect, the processing unit is configured to process the K AI models through the second mode, including: processing the K AI models through the second mode to obtain K updated AI models; and sending indication information indicating the K updated AI models.

[0126] In a possible implementation manner of the fourth aspect, the transceiver unit is further used to receive indication information indicating the K AI models.

[0127] In a possible implementation of the fourth aspect, the first indication information is one of N indication information, and the N indication information are respectively used to indicate the processing mode of the AI ​​model corresponding to N AI tasks, where the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer.

[0128] In a possible implementation of the fourth aspect, the transceiver unit is further used to send indication information indicating a processing mode of the AI ​​model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task.

[0129] In a fifth aspect, the present application provides a communication device, which is a network device, or a component of a network device (such as a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the network device functions. In the fifth aspect and its possible implementations, the communication device is described as a network device.

[0130] The device includes a transceiver unit; the transceiver unit is used to receive first indication information, where the first indication information is used to indicate that the processing mode of K artificial intelligence (AI) models is a first mode or a second mode, where the K AI models correspond to a first AI task, and K is a positive integer; wherein the first mode includes AI reasoning and the second mode includes AI training; the transceiver unit is also used to send the first indication information.

[0131] In a possible implementation of the fifth aspect, the transceiver unit is further used to receive first configuration information, where the first configuration information is used to configure management information of AI models corresponding to X AI tasks, where the X AI tasks include the first AI task, and X is a positive integer; the transceiver unit is further used to send indication information indicating the management information of the K AI models based on the first configuration information.

[0132] In a possible implementation of the fifth aspect, the first configuration information includes one or more of the following: applicable scenarios of the AI ​​models corresponding to the X AI tasks, selection conditions of the AI ​​models corresponding to the X AI tasks, enabling conditions of the AI ​​models corresponding to the X AI tasks, update conditions of the AI ​​models corresponding to the X AI tasks, switching conditions of the AI ​​models corresponding to the X AI tasks, fallback conditions of the AI ​​models corresponding to the X AI tasks, and data collection information of the AI ​​models corresponding to the X AI tasks.

[0133] In a possible implementation of the fifth aspect, the data collection information of the AI ​​model corresponding to the X AI tasks includes one or more of the following: data type, collection time, collection frequency, collection location, and collection quantity.

[0134] In a possible implementation of the fifth aspect, the transceiver unit is further used to receive indication information indicating management information of the K AI models; the transceiver unit is further used to send indication information indicating management information of the K AI models.

[0135] In a possible implementation manner of the fifth aspect, the management information includes at least one of the following: model selection, model enablement, model update, model switching, and model rollback.

[0136] In a possible implementation of the fifth aspect, the transceiver unit is further used to receive indication information indicating the model performance measurement results of the K AI models.

[0137] In a possible implementation of the fifth aspect, the transceiver unit is further used to receive second configuration information, where the second configuration information is used to configure measurement information of AI models corresponding to Y AI tasks, where the Y AI tasks include the first AI task; the transceiver unit is further used to send indication information indicating reporting of model performance measurement results of the K AI models based on the second configuration information.

[0138] In a possible implementation manner of the fifth aspect, the second configuration information includes one or more of the following: a measurement object, a measurement period, a measurement triggering condition, and a reporting method of a measurement result.

[0139] In a possible implementation of the fifth aspect, the transceiver unit is further used to receive indication information instructing to report the model performance measurement results of the K AI models; the transceiver unit is further used to send indication information instructing to report the model performance measurement results of the K AI models.

[0140] In a possible implementation of the fifth aspect, the transceiver unit is further used to receive data associated with the K AI models.

[0141] In a possible implementation of the fifth aspect, the transceiver unit is further used to send first data, where the first data is obtained by processing data associated with the K AI models.

[0142] In a possible implementation of the fifth aspect, the transceiver unit is further used to send data associated with the K AI models.

[0143] In a possible implementation of the fifth aspect, in the first mode, the data associated with the K AI models include the input data of the K AI models; and / or, in the second mode, the data associated with the K AI models include the input data and label data of the K AI models.

[0144] In a possible implementation manner of the fifth aspect, the transceiver unit is further used to receive indication information indicating the K updated AI models, where the K updated AI models are obtained by processing the K AI models through the second mode.

[0145] In a possible implementation of the fifth aspect, the communication device also includes a processing unit, which is used to perform fusion processing on the K updated AI models to obtain a fusion result; the transceiver unit is also used to send indication information indicating the fusion result.

[0146] In a possible implementation manner of the fifth aspect, the transceiver unit is further used to send indication information indicating the K updated AI models.

[0147] In a possible implementation of the fifth aspect, the transceiver unit is further used to send indication information indicating the K AI models.

[0148] In a possible implementation of the fifth aspect, the transceiver unit is further used to receive third configuration information, where the third configuration information is used to configure P AI models, where the P AI models correspond to the first AI task, and P is greater than or equal to K.

[0149] In a possible implementation manner of the fifth aspect, the transceiver unit is further used to receive indication information indicating K AI models.

[0150] In a possible implementation of the fifth aspect, the first indication information is one of N indication information, and the N indication information are respectively used to indicate the processing mode of the AI ​​model corresponding to the N AI tasks, where the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer.

[0151] In a possible implementation of the fifth aspect, the transceiver unit is further used to receive indication information indicating a processing mode of the AI ​​model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task.

[0152] In a possible implementation of the fifth aspect, the transceiver unit is further used to send indication information indicating a processing mode of the AI ​​model corresponding to the M AI tasks.

[0153] In a sixth aspect of the present application, a communication device is provided, which is a first device, or a component of the first device (such as a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the first device. In the sixth aspect and its possible implementations, the communication device is described as a first device, and the first device can be a terminal device or a network device.

[0154] The device includes a processing unit and a transceiver unit; the processing unit is used to determine first indication information, where the first indication information is used to indicate that the processing mode of K artificial intelligence (AI) models is a first mode or a second mode, and the K AI models correspond to a first AI task, where K is a positive integer; wherein the first mode includes AI reasoning and the second mode includes AI training; the transceiver unit is used to send the first indication information.

[0155] In a possible implementation of the sixth aspect, the transceiver unit is further used to send first configuration information, where the first configuration information is used to configure management information of the AI ​​model corresponding to X AI tasks, where the X AI tasks include the first AI task, and X is a positive integer.

[0156] In a possible implementation of the sixth aspect, the first configuration information includes one or more of the following: applicable scenarios of the AI ​​models corresponding to the X AI tasks, selection conditions of the AI ​​models corresponding to the X AI tasks, enabling conditions of the AI ​​models corresponding to the X AI tasks, update conditions of the AI ​​models corresponding to the X AI tasks, switching conditions of the AI ​​models corresponding to the X AI tasks, fallback conditions of the AI ​​models corresponding to the X AI tasks, and data collection information of the AI ​​models corresponding to the X AI tasks.

[0157] In a possible implementation of the sixth aspect, the data collection information of the AI ​​model corresponding to the X AI tasks includes one or more of the following: data type, collection time, collection frequency, collection location, and collection quantity.

[0158] In a possible implementation of the sixth aspect, the first configuration information is used to determine management information of the K AI models, and the management information includes at least one of the following: model selection, model enablement, model update, model switching, and model rollback.

[0159] In a possible implementation of the sixth aspect, the transceiver unit is further used to receive indication information indicating the model performance measurement results of the K AI models.

[0160] In a possible implementation of the sixth aspect, the transceiver unit is further used to send second configuration information, where the second configuration information is used to configure measurement information of the AI ​​model corresponding to Y AI tasks, where the Y AI tasks include the first AI task.

[0161] In a possible implementation manner of the sixth aspect, the second configuration information includes one or more of the following: a measurement object, a measurement period, a measurement triggering condition, and a reporting method of a measurement result.

[0162] In a possible implementation of the sixth aspect, the transceiver unit is further used to receive data associated with the K AI models, or first data, where the first data is processed based on the data associated with the K AI models.

[0163] In a possible implementation of the sixth aspect, in the first mode, the data associated with the K AI models include the input data of the K AI models; and / or, in the second mode, the data associated with the K AI models include the input data and label data of the K AI models.

[0164] In a possible implementation of the sixth aspect, the transceiver unit is further used to receive indication information indicating the K updated AI models, where the K updated AI models are obtained by processing the K AI models through the second mode; or, the transceiver unit is further used to receive indication information indicating a fusion result, where the fusion result is obtained based on fusion processing of the K updated AI models.

[0165] In a possible implementation of the sixth aspect, the transceiver unit is further used to send third configuration information, where the third configuration information is used to configure P AI models, where the P AI models correspond to the first AI task, and P is greater than or equal to K.

[0166] In a possible implementation of the sixth aspect, the first indication information is one of N indication information, and the N indication information are respectively used to indicate the processing mode of the AI ​​model corresponding to the N AI tasks, where the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer.

[0167] In a possible implementation of the sixth aspect, the transceiver unit is further used to receive indication information indicating a processing mode of the AI ​​model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task.

[0168] A seventh aspect of an embodiment of the present application provides a communication device, comprising at least one processor, which is used to execute programs or instructions in a memory so that the device implements the method described in the first aspect or any possible implementation method of the first aspect.

[0169] In an eighth aspect, an embodiment of the present application provides a communication device, comprising at least one processor, which is used to execute programs or instructions in a memory so that the device implements the method described in the second aspect or any possible implementation method of the second aspect.

[0170] A ninth aspect of an embodiment of the present application provides a communication device, comprising at least one processor, which is used to execute programs or instructions in a memory so that the device implements the method described in the third aspect or any possible implementation method of the third aspect.

[0171] In a tenth aspect, an embodiment of 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 the first aspect or any possible implementation of the first aspect.

[0172] In an eleventh aspect of an embodiment of the present application, a communication device is provided, comprising at least one logic circuit and an input / output interface; the logic circuit is used to execute the method described in the second aspect or any possible implementation of the second aspect.

[0173] A twelfth aspect of an embodiment of 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 the third aspect or any possible implementation of the third aspect.

[0174] Among them, the communication device provided in aspects 7 to 12 may be a device (such as a terminal device or a network device or a first device), or the communication device may be a partial component (such as a processor, a chip or a chip system, etc.) in a device (such as a terminal device or a network device or a first device), or the communication device may also be a logic module or software that can realize all or part of the functions of a device (such as a terminal device or a network device or a first device).

[0175] A thirteenth aspect of an embodiment 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 one of the first to third aspects above.

[0176] A fourteenth aspect of an embodiment of the present application provides a computer program product (or computer program). When 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 third aspects above.

[0177] A fifteenth aspect of an embodiment of the present application provides a chip system (or chip), which includes at least one processor for supporting a communication device to implement the functions involved in any possible implementation method of any aspect of the first to third aspects mentioned above.

[0178] 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.

[0179] A sixteenth aspect of an embodiment of the present application provides a communication system, which includes the communication device of the fourth aspect, the communication device of the fifth aspect, and the communication device of the sixth aspect; or, the communication system includes the communication device of the seventh aspect, the communication device of the eighth aspect, and the communication device of the ninth aspect; or, the communication system includes the communication device of the tenth aspect, the communication device of the eleventh aspect, and the communication device of the twelfth aspect.

[0180] Among them, the technical effects brought about by any design method in the fourth to sixteenth aspects can refer to the technical effects brought about by the different design methods in the above-mentioned first to third aspects, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0181] FIG1a is a schematic diagram of a communication system provided by the present application;

[0182] FIG1b is another schematic diagram of the communication system provided by the present application;

[0183] FIG1c is another schematic diagram of the communication system provided by the present application;

[0184] FIG2 is an interactive schematic diagram of the communication method provided by this application;

[0185] FIG3 is another interactive schematic diagram of the communication method provided by this application;

[0186] FIG4 is another interactive schematic diagram of the communication method provided by this application;

[0187] FIG5 is another interactive schematic diagram of the communication method provided by this application;

[0188] FIG6 is a schematic diagram of an implementation of the communication method involved in this application;

[0189] FIG7 is another schematic diagram of an implementation of the communication method involved in this application;

[0190] FIG8 is a schematic diagram of a communication device provided by the present application;

[0191] FIG9 is another schematic diagram of a communication device provided by the present application;

[0192] FIG10 is another schematic diagram of the communication device provided by the present application;

[0193] FIG11 is another schematic diagram of a communication device provided by the present application;

[0194] FIG12 is another schematic diagram of the communication device provided in this application. DETAILED DESCRIPTION

[0195] First, some of the terms used in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0196] (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.

[0197] 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.

[0198] 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.

[0199] The terminal may also be a drone, a robot, a terminal in device-to-device (D2D) communication, 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 smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc.

[0200] 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.

[0201] 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.

[0202] (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.

[0203] Alternatively, a 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 vehicle-to-everything (V2X) technology can be a roadside unit (RSU).

[0204] 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).

[0205] 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 access network (open RAN, 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.

[0206] The communication between the access network device and the terminal device follows a certain protocol layer structure. The protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, a media access control (MAC) layer, or a physical (PHY) layer. The user plane protocol layer may include at least one of the following: a service data adaptation protocol (SDAP) layer, a PDCP layer, an RLC layer, a MAC layer, or a physical layer.

[0207] For the correspondence between network elements in the ORAN system and their achievable protocol layer functions, please refer to Table 1 below.

[0208] Table 1

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] (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.

[0214] Furthermore, these values ​​and parameters can be changed or updated.

[0215] (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.

[0216] (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.

[0217] 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.

[0218] 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.

[0219] (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.

[0220] 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.

[0221] 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.

[0222] Please refer to Figure 1a, which is a schematic diagram of a communication system in this application. Figure 1a exemplarily illustrates a network device and six terminal devices, namely terminal device 1, terminal device 2, terminal device 3, terminal device 4, terminal device 5, and terminal device 6. In the example shown in Figure 1a, terminal device 1 is a smart teacup, terminal device 2 is a smart air conditioner, terminal device 3 is a smart gas pump, terminal device 4 is a vehicle, terminal device 5 is a mobile phone, and terminal device 6 is a printer.

[0223] As shown in Figure 1a, the entity sending AI-related information (such as the first indication information mentioned later, the indication information indicating the management information of the K AI models, etc.) can be a network device. The entity receiving AI-related information can be terminal devices 1-terminal devices 6. In this case, the network device and terminal devices 1-terminal devices 6 form a communication system. In this communication system, terminal devices 1-terminal devices 6 can send AI-related data (such as the model performance measurement results of the K AI models mentioned later, data associated with the K AI models, etc.) to the network device, and the network device can receive the AI-related data sent by terminal devices 1-terminal devices 6.

[0224] For example, in Figure 1a, terminal devices 4 and 6 can also form a communication system. Terminal device 5 serves as a network device, i.e., the entity that sends AI-related information; terminal devices 4 and 6 serve as terminal devices, i.e., the entities that receive AI-related information. For example, in a connected vehicle system, terminal device 5 sends AI-related information to terminal devices 4 and 6, respectively, and receives AI-related data from terminal devices 4 and 6. Correspondingly, terminal devices 4 and 6 receive AI-related information from terminal device 5 and send AI-related data to terminal device 5.

[0225] Taking the communication system shown in Figure 1a as an example, in addition to performing communication-related services, different devices (including between network devices and network devices, between network devices and terminal devices, and / or between terminal devices) may also perform AI-related services. For example, as shown in Figure 1b, taking the network device as a base station as an example, the base station can perform communication-related services and AI-related services with one or more terminal devices, and different terminal devices can also perform communication-related services and AI-related services. For another example, as shown in Figure 1c, taking the terminal devices including a TV and a mobile phone as an example, communication-related services and AI-related services can also be performed between the TV and the mobile phone.

[0226] The technical solution provided in this application can be applied to a wireless communication system (e.g., the system shown in FIG. 1a , FIG. 1b , or FIG. 1c ). 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: 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.

[0227] Currently, in wireless communication systems (such as those shown in Figures 1a, 1b, or 1c), communication nodes typically possess both signal transceiver capabilities and computing capabilities. For example, network devices with computing capabilities primarily provide computing power to support signal transceiver capabilities (for example, calculating the time and frequency domain resources required to carry the signal), enabling communication between the network device and other communication nodes.

[0228] 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.

[0229] As an example, to meet the vision of intelligent and inclusive future, intelligence is likely to evolve further at the wireless network architecture level. In future communication systems, AI will likely be further integrated with wireless networks, enabling inherent network intelligence and terminal intelligence. For example, the integration of AI and wireless networks can be applied to the following new demands and scenarios: For example, more flexible and intelligent terminal connectivity, including but not limited to diverse terminal types, the Super Internet of Things (Supper IoT) (e.g., Supper IoT can include IoT, connected vehicles, industrial, and medical), massive connectivity, more flexible terminal connectivity, and terminals with inherent AI capabilities. Another example is inherent network intelligence: in addition to traditional communication connectivity services, the network will also provide computing and AI services to better support inclusive, real-time, and highly secure AI services. These new demands and scenarios will bring about changes in wireless network architecture and communication models.

[0230] Taking the 5G communication network as an example, AI capabilities can be introduced into the communication network by adding a network data analytics function (NWDAF) network element. The main functions of the NWDAF network element include: supporting data collection from other network functions (NF) and application functions (AF), supporting data collection from operation, administration, and maintenance (OAM) systems, and providing metadata exposure services and data analysis services to NF / AF. The main goal of introducing the NWDAF network element is to automate and intelligentize network operation and maintenance, optimize network performance and service experience, and provide end-to-end guarantees. The AI ​​model trained by the NWDAF network element can be applied to network areas such as mobility management, session management, and network automation, using AI methods to replace the numerical formula-based methods in the original network functions. However, the NWDAF network element is deployed in the core network and is a newly added external AI unit. It is not designed to be strongly coupled with the communication network, and its performance is limited.

[0231] In order to solve the above problems, the present application provides a communication method and related equipment, which can implement the indication of two modes: AI inference mode and AI training mode in the communication network, so that the computing power of the communication node can be applied to the processing process of AI tasks.

[0232] Please refer to FIG2 , which is a schematic diagram of an implementation of the communication method provided in this application. The method includes the following steps.

[0233] It should be noted that, in FIG2 , the method is illustrated by taking the terminal device, the network device and the first device as the execution subjects of the interaction diagram as examples, but the present application does not limit the execution subjects of the interaction diagram. For example, the execution subject of S201 in FIG2 and the corresponding implementation is the first device, and the execution subject may also be a chip, a chip system, or a processor that supports the first device to implement the method, or a logic module or software that can implement all or part of the terminal device functions. The network device in S201-S202 in FIG2 and the corresponding implementation may also be replaced by a chip, a chip system, or a processor that supports the network device to implement the method, or may also be replaced by a logic module or software that can implement all or part of the network device functions. The terminal device in S202-S203 in FIG2 and the corresponding implementation may also be replaced by a chip, a chip system, or a processor that supports the terminal device to implement the method, or may also be replaced by a logic module or software that can implement all or part of the terminal device functions.

[0234] S201. A first device sends first indication information, and a network device receives the first indication information. The first indication information is used to indicate whether a processing mode of K AI models is a first mode or a second mode, where the K AI models correspond to a first AI task, and K is a positive integer; the first mode includes AI reasoning, and the second mode includes AI training.

[0235] It should be noted that the first device may be a device that provides application services (for example, the device is an over-the-top (OTT) manufacturer's device), including a server, a virtual machine, a container, etc.

[0236] S202. The network device sends first indication information, and correspondingly, the terminal device receives the first indication information.

[0237] It should be noted that the network device may include an access network device and / or a core network device, and some implementation examples will be provided below for illustration.

[0238] In an implementation example, the network device may be an access network device. In step S201, the first indication information received by the access network device may come from the core network device, and accordingly, the access network device may send the first indication information to the terminal device. In other words, the communication interface through which the above-mentioned network device receives the first indication information may be the communication interface between the access network device and the core network device, that is, the first device sends the first indication information to the access network device through the core network device in step S201. The communication interface through which the above-mentioned network device sends the first indication information may be the communication interface between the access network device and the terminal device, that is, the access network device sends the first indication information to the terminal device in step S202.

[0239] In another implementation example, the network device may be a core network device. In the above technical solution, the first indication information received by the core network device may come from a first device (for example, the first device may be a server, a virtual machine, a container, etc.), and accordingly, the core network device may send the first indication information to the access network device, and the subsequent access network device may further send the first indication information to the terminal device. In other words, the communication interface for the above network device to receive the first indication information may be a communication interface between the core network device and the first device, that is, the first device sends the first indication information to the core network device in step S201. The communication interface for the above network device to send the first indication information may be a communication interface between the core network device and the access network device, that is, the core network device sends the first indication information to the terminal device through the access network device in step S202.

[0240] In another implementation example, the network device may include an access network device and a core network device, that is, the access network device and the core network device are collectively provided in the same device. In the above technical solution, the first indication information received by the network device may come from the first device (for example, the first device may be a server, a virtual machine, a container, etc.), and accordingly, the network device may send the first indication information to the terminal device. In other words, the communication interface through which the above network device receives the first indication information may be the communication interface between the network device and the first device, that is, the first device sends the first indication information to the network device in step S201. The communication interface through which the above network device sends the first indication information may be the communication interface between the network device and the terminal device, that is, the network device sends the first indication information to the terminal device in step S202.

[0241] It is understandable that the first indication information may be carried by different messages on different communication interfaces.

[0242] For example, in step S201, if the first indication information is sent by the first device to the core network device, the first indication information is transmitted through the communication interface between the first device and the core network device (for example, the N6 interface between the user plane function (UPF) network element in the data center and the core network network element).

[0243] For example, in step S201, if the first indication information is sent by the first device to the access network device, the first indication information is transmitted through the communication interface between the first device and the access network device (such as the N6 interface between the data center and the UPF network element in the core network network element, and the N3 interface between the UPF network element in the core network network element and the access network device).

[0244] For example, in step S202, if the first indication information is sent by the network device to the access network device, the first indication information is transmitted through the communication interface (such as the NG interface) between the core network device and the access network device.

[0245] For example, in step S202, if the interface through which the network device sends the first indication information is the communication interface between the access network device and the terminal device, the first indication information can be carried in an RRC message or a system information block (SIB).

[0246] S203. The terminal device processes K AI models through the first mode or the second mode.

[0247] It should be understood that an AI task corresponds to one or more AI models, and it can be understood that the execution process of an AI task includes the processing of the one or more AI models by the AI ​​node. The AI ​​node may include a terminal device. Optionally, the AI ​​node may also include other devices, such as a network device, a first device, etc.

[0248] It should be understood that in the above technical solution, the first AI task may correspond to P AI models, where K is less than or equal to P. In other words, in step S203, the K AI models processed by the terminal device may be some of the one or more AI models corresponding to the first AI task, or the K AI models processed by the terminal device may be all of the one or more AI models corresponding to the first AI task. The K AI models corresponding to the first AI task may be indicated by the identifier of the first AI task and the identifiers of the K AI models.

[0249] Optionally, in the above technical solution, the K AI models indicated by the first indication information correspond to the same AI task (i.e., the first AI task), that is, the indication of the AI ​​model processing mode received by the terminal device can be indicated at the granularity of the AI ​​task, that is, based on the first indication information, the indication of one or more AI models contained in the same AI task can be implemented to reduce overhead and improve efficiency. In actual applications, the K AI models indicated by the first indication information can be decoupled from the AI ​​task, that is, the indication of the AI ​​model processing mode received by the terminal device can be indicated at the granularity of the AI ​​model to improve the flexibility of the solution implementation. Similarly, other information / data mentioned later (such as management information, indication information for indicating the AI ​​model, data associated with the AI ​​model, indication information for indicating the supported processing mode, etc.) can also be indicated at the granularity of the AI ​​task or at the granularity of the AI ​​model.

[0250] It should be understood that the first mode includes AI reasoning, which can be understood as the first mode in which the AI ​​node performs at least AI reasoning on the AI ​​model. Among them, the AI ​​node (such as a terminal device, and a network device, a first device, etc. that may participate in an AI task) performs AI reasoning on the AI ​​model, which can include the process in which the communication device inputs input data into the AI ​​model, and obtains output data corresponding to the input data through reasoning by the AI ​​model. Similarly, the second mode includes AI training, which can be understood as the second mode in which the AI ​​node performs at least AI training on the AI ​​model. Among them, the AI ​​node (such as a terminal device, and a network device, a first device, etc. that may participate in an AI task) performs AI training on the AI ​​model, which can include the process in which the communication device inputs input data and label data into the AI ​​model to update the parameters of the AI ​​model.

[0251] In this application, AI model can be replaced by learning model, AI learning model, machine learning model, neural network, AI network, etc.

[0252] In one possible implementation, the first indication information sent by the network device in step S202 is one of N indication information, where the N indication information are respectively used to indicate the processing mode of the AI ​​model corresponding to the N AI tasks, where the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer. Specifically, the first indication information sent by the network device may be one of the N indication information, and the N indication information may be respectively used to indicate the processing mode of the AI ​​model corresponding to the N AI tasks, so that the terminal device can determine the processing mode for the N AI tasks based on the N indication information, thereby implementing the indication of the processing mode of the AI ​​model at the AI ​​task granularity.

[0253] As an implementation example, N indication information can be carried in the system information block (SIB) sent by the network device to the terminal device, which will be described below in conjunction with the implementation example shown in Figure 3. For example, in step S301 shown in Figure 3, the network device can send N indication information to the terminal device through a periodic SIB (denoted as SIB (periodic) in the figure). For another example, in steps S302 and S303 shown in Figure 3, the network device can receive request information from the terminal device (the request information is used to request N configuration information) and send a SIB based on the request information (on request). Thus, by sending N indication information through the SIB, one or more terminal devices can obtain N indication information through the SIB, which can save overhead.

[0254] As another implementation example, N indication information can be carried in a radio resource control (RRC) message sent by the network device to the terminal device, which will be described below in conjunction with the implementation example shown in Figure 4. For example, the terminal device can send an RRC re-establishment request (RRCReEstablishmenRequest) message (the message is used to request N indication information) in step S401. Thereafter, the network device can send an RRC re-establishment message (RRCReEstablishmenRequest) or an RRC configuration (RRCSetup) message carrying N indication information based on the RRCReEstablishmenRequest message in step S402. Thus, by sending N indication information through an RRC message, the terminal device can obtain N indication information based on the RRC connection between the terminal device and the network device, thereby providing a more flexible implementation method.

[0255] Exemplarily, the SIB sent by the network device in step S301 or step S303 (or the RRC message sent by the network device in step S402) may add one or more AI task information (AITaskInfo) information elements (IE). The one or more AITaskInfo information elements are respectively used to carry the N indication information. Optionally, one or more AITaskInfo information elements may be included in the AI ​​task information list (AITaskInfoList) information element. The following will provide an exemplary description of each information element in conjunction with some information element formats.

[0256] Table 2

[0257] It should be understood that in Table 2, the SIB is recorded as SIBx (x is a positive integer, such as 1, 2, 3...16, 17, 18, etc.) as an example. As shown in Table 2, the SIB can carry an AITaskInfoList information element for carrying the list of the N indication information. Moreover, the AITaskInfoList information element can carry one or more AITaskInfo information elements for respectively carrying the N indication information. In addition, each AITaskInfo information element can carry one indication information (such as the first indication information) among the N indication information, wherein the one indication information can carry the identifier (AITaskID) information element of the AI ​​task and the learning mode (learn mode, LM) information element to implement the indication of the AI ​​training mode or the AI ​​reasoning mode. For example, the LM information element value is 1, indicating the AI ​​training mode and the LM information element value is 2, indicating the AI ​​reasoning mode, or the LM information element value is 2, indicating the AI ​​training mode and the LM information element value is 1, indicating the AI ​​reasoning mode.

[0258] In addition, in Table 2, in the "aitaskInfoList AITaskInfoList" information element, the "aitaskInfoList" information element refers to the name of the signaling field as AI task information list (that is, the instance of the class of the signaling field is AI task information list), and the "AITaskInfoList" information element refers to the class of the signaling field as AI task information list (that is, the class of the signaling field is AI task information list).

[0259] Table 3

[0260] Table 4

[0261] Table 5

[0262] As shown in Table 3, the RRCReEstablishmentRequest message sent by the terminal device can be used to request the learning mode of one or more AI tasks. The subsequent network device can send N indication information to the terminal device through the RRCReEstablishment message shown in Table 4 or the RRCSetup message shown in Table 5. Similarly, in the RRCReEstablishmentRequest message shown in Table 3, the RRCReEstablishment message shown in Table 4, and the RRCSetup message shown in Table 5, the implementation of each information element can refer to the definition of each information element in the aforementioned Table 2.

[0263] In one possible implementation, in the method shown in FIG2 , the method further includes: the network device receiving indication information indicating the processing mode of the AI ​​model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task. Specifically, the indication information received by the network device is used to indicate the processing mode of the AI ​​model corresponding to the M AI tasks, and the M AI tasks include the first AI task, so that the network device can determine the first indication information based on the processing mode of the AI ​​model corresponding to the M AI tasks, so that the processing mode indicated by the first indication information can be adapted to the capabilities of the terminal device.

[0264] In one possible implementation, after the network device receives the indication information indicating the processing mode of the AI ​​model corresponding to the M AI tasks, the method further includes: the network device sends the indication information indicating the processing mode of the AI ​​model corresponding to the M AI tasks. Specifically, after the network device sends the indication information indicating the processing mode of the AI ​​model corresponding to the M AI tasks, the network device, as a communication role of transparent forwarding, can also send the indication information (for example, the network device sends the indication information to the first device; for example, when the network device is an access network device, the access network device sends the indication information to the core network device or the first device) to realize the transmission of the capability information of the terminal device. Subsequently, the first device can determine the processing mode of the K AI models in the first AI task executed by the terminal device based on the capability information of the terminal device, and trigger the configuration and transmission of the first indication information.

[0265] Optionally, the indication information received by the network device is used to indicate the processing mode of the AI ​​model corresponding to the M AI tasks, wherein the indication information can be used to indicate the processing mode supported by the terminal device in the AI ​​model corresponding to the M AI tasks. In other words, the indication information can be capability indication information.

[0266] As an implementation example, the indication information of the processing mode of the AI ​​model corresponding to the M AI tasks sent by the terminal device can be carried in the capability information sent by the terminal device. The following will be described in conjunction with the implementation example shown in Figure 5. As shown in Figure 5, the network device can send a capability query message in step S501, so that the terminal device can send capability information in step S502 based on the capability query message, so that the network device can know the processing mode of the AI ​​model corresponding to the M AI tasks supported by the terminal device based on the capability information. Exemplarily, in step S501, the capability query message can be a user equipment learning capability query (UELearnCapobilityEnquiry) message, and accordingly, in step S502, the capability information can be a user equipment learning capability information (UELearnCapobilityInformation). Exemplarily, the UELearnCapobilityInformation sent by the terminal device can include the information elements shown in Table 6 below.

[0267] Table 6

[0268] In Table 6, UELearnCapabilityInformation may carry a user equipment learning capability container list (ue-Learn-Capability-ContainerList) information element, which may carry one or more user equipment learning capability container (UE-Learn-Capability-Container) information elements, and the one or more UE-Learn-Capability-Container information elements are respectively used to indicate the processing mode of the AI ​​model corresponding to the M AI tasks. For example, each UE-Learn-Capability-Container information element may carry an LM information element, which is used to indicate that the processing mode of the AI ​​model corresponding to one of the M AI tasks is AI training mode or AI inference mode.

[0269] In addition, in Table 6, in the "ue-Learn-Capability-ContainerList UE-Learn-Capability-ContainerList" information element, the "ue-Learn-Capability-ContainerList" information element refers to the name of the signaling field as UE learning capability container list (that is, the instance of the class of the signaling field is the UE learning capability container list), and the "UE-Learn-Capability-ContainerList" information element refers to the class of the signaling field as UE learning capability container list (that is, the class of the signaling field is UE learning capability container list).

[0270] Based on the technical solution shown in Figure 2, the first indication information received by the terminal device in step S202 is used to indicate that the processing mode of the K AI models is the first mode or the second mode. Thereafter, based on the first indication information, the terminal device can process the K AI models in the first mode or the second mode in step S203. The first mode includes AI reasoning, and the second mode includes AI training. Thus, the terminal device, as a communication node in the communication system, can perform AI reasoning or AI training on the AI ​​model based on the first indication information, and can implement the indication of both the AI ​​reasoning mode and the AI ​​training mode in the communication network, so that the computing power of the communication node can be applied to the processing of the AI ​​task.

[0271] In one possible implementation, in the method shown in Figure 2, in addition to indicating the processing modes of the K AI models through the first indication information, management information can also be used to manage the AI ​​models. For example, the management information includes at least one of the following: model selection, model enablement, model update, model switching, and model rollback. The following describes the implementation process of management information through some implementation examples.

[0272] In implementation example A, the method shown in Figure 2 also includes: the network device receives first configuration information, where the first configuration information is used to configure management information of AI models corresponding to X AI tasks, where the X AI tasks include the first AI task, and X is a positive integer; thereafter, the network device sends indication information indicating the management information of the K AI models based on the first configuration information.

[0273] In implementation example A, the network device may also receive first configuration information and, based on the first configuration information, send indication information indicating management information for the K AI models. Subsequently, after receiving the indication information, the terminal device may manage the K AI models based on the indication information. Thus, the indication information enables management of AI models in the communication network.

[0274] It should be understood that in implementation example A, the network device that determines the management information based on the first configuration information can be a core network device (that is, the core network device can send the management information to the terminal device through the access network device), or it can be an access network device, or it can be a device that is a combination of a core network device and an access network device, which is not limited here.

[0275] Optionally, the first configuration information includes one or more of the following: applicable scenarios of the AI ​​models corresponding to the X AI tasks, selection conditions of the AI ​​models corresponding to the X AI tasks, enabling conditions of the AI ​​models corresponding to the X AI tasks, update conditions of the AI ​​models corresponding to the X AI tasks, switching conditions of the AI ​​models corresponding to the X AI tasks, fallback conditions of the AI ​​models corresponding to the X AI tasks, and data collection information of the AI ​​models corresponding to the X AI tasks. The data collection information of the AI ​​models corresponding to the X AI tasks includes one or more of the following: data type, collection time, collection frequency, collection location, and collection quantity.

[0276] Implementation Example B, the method shown in Figure 2 also includes: In a possible implementation, the method also includes: the network device receives indication information indicating the management information of the K AI models; the network device sends indication information indicating the management information of the K AI models.

[0277] In implementation example B, the network device can receive and send indication information indicating the management information of the K AI models, so that the network device, as a transparent communication role, sends the indication information to the terminal device. Thus, the indication information can be used to manage the AI ​​models in the communication network.

[0278] It should be understood that in implementation example B, the device that determines the management information based on the first configuration information can be a core network device. Accordingly, the core network device can send indication information indicating the management information of the K AI models to the access network device, and the access network device can subsequently perform transparent transmission processing on the indication information, that is, the network device that plays the role of transparent transmission communication in the above technical solution can be an access network device.

[0279] In one possible implementation, in the method shown in FIG2 , in addition to indicating the processing modes of the K AI models through the first indication information, the performance of the AI ​​model can also be measured through other information. In other words, in the method shown in FIG2 , the method further includes: the network device receives indication information indicating the model performance measurement results of the K AI models from the terminal device, so as to measure the performance of the AI ​​model deployed on the communication network. The following will exemplarily describe the measurement indication of AI model performance through some possible implementation methods.

[0280] Implementation example C, before the network device receives indication information indicating the model performance measurement results of the K AI models, the method also includes: the network device receives second configuration information, the second configuration information is used to configure the measurement information of the AI ​​models corresponding to Y AI tasks, the Y AI tasks including the first AI task; thereafter, the network device sends indication information indicating reporting of the model performance measurement results of the K AI models based on the second configuration information.

[0281] In implementation example C, the network device may also receive second configuration information and, based on the second configuration information, send instruction information instructing the reporting of the model performance measurement results of the K AI models. Thus, the terminal device sends the model performance measurement results of the K AI models based on the instruction information, thereby implementing measurement instructions for the performance of the AI ​​models deployed on the communication network.

[0282] Optionally, in implementation example C, the network device that determines the indication information for reporting the model performance measurement results of the K AI models based on the second configuration information can be a core network device, an access network device, or a device that is a combination of a core network device and an access network device, which is not limited here.

[0283] Optionally, the second configuration information includes one or more of the following: a measurement object, a measurement period, a measurement triggering condition, and a reporting method of a measurement result.

[0284] Implementation example D, before the network device receives indication information indicating the model performance measurement results of the K AI models, the method also includes: the network device receives indication information indicating reporting of the model performance measurement results of the K AI models; the network device sends indication information indicating reporting of the model performance measurement results of the K AI models.

[0285] In implementation example D, the network device can also receive and send indication information indicating the reporting of the model performance measurement results of the K AI models, so that the network device acts as a transparent communication role and sends the indication information to the terminal device to realize the measurement indication of the performance of the AI ​​model deployed in the communication network.

[0286] Optionally, in implementation example D, the device that determines the indication information for reporting the model performance measurement results of the K AI models based on the second configuration information can be a core network device. Accordingly, the core network device can send the indication information to the access network device, and the access network device can subsequently perform transparent transmission processing on the indication information, that is, the network device that plays the role of transparent transmission communication in the above technical solution can be an access network device.

[0287] In one possible implementation, in the method shown in FIG2 , in addition to indicating the processing modes of the K AI models through the first indication information, data collection (or data reporting, etc.) of the AI ​​models can also be implemented through other information. In other words, in the method shown in FIG2 , the method further includes: the network device receives data associated with the K AI models from the terminal device to implement data collection of data associated with the AI ​​models deployed on the communication network. The following will exemplarily describe the data collection process of the AI ​​model through some possible implementation methods.

[0288] In implementation example E, after the network device receives the data associated with the K AI models from the terminal device, the method further includes: the network device sending first data, where the first data is obtained by processing based on the data associated with the K AI models. Specifically, after the network device receives the data associated with the K AI models, the network device can obtain the first data based on the data associated with the K AI models, and send the first data, so that the recipient of the first data (e.g., the core network device or the first device) can obtain the first data.

[0289] Optionally, the first data is obtained by performing one or more processes such as data integration, preprocessing, and redundancy removal on the data associated with the K AI models.

[0290] Optionally, in implementation example E, the network device that processes the data associated with the K AI models to obtain the first data can be a core network device, an access network device, or a device that is a combination of a core network device and an access network device, which is not limited here.

[0291] In implementation example F, after the network device receives the K AI model-associated data from the terminal device, the method further includes: the network device sending the K AI model-associated data. Specifically, after receiving the K AI model-associated data, the network device, as a transparent communication role, can send the K AI model-associated data, so that the recipient of the K AI model-associated data can further obtain other data (e.g., the first data) to achieve data collection.

[0292] Optionally, in implementation example F, the network device that transparently transmits the data associated with K AI models may be an access network device, and the subsequent core network device may obtain other data (e.g., the first data) based on the data associated with the K AI models.

[0293] It should be understood that in implementation example E and implementation example F, in the first mode, the data associated with the K AI models include the input data of the K AI models; and / or, in the second mode, the data associated with the K AI models include the input data and label data of the K AI models.

[0294] In one possible implementation, in the method shown in FIG2 , in addition to indicating the processing mode of the K AI models through the first indication information, the update of the AI ​​model can also be achieved through other information. In other words, in the method shown in FIG2 , the method further includes: the network device receives indication information indicating the K updated AI models, and the K updated AI models are obtained by processing the K AI models through the second mode. Among them, the second mode includes AI training, and accordingly, the terminal device processes the K AI models through the second mode to obtain K updated AI models, and the terminal device can also send indication information indicating the K updated AI models, so that the network device obtains the updated AI model, thereby realizing the training of the AI ​​model deployed on the communication network. The following is an illustrative description of the update process of the AI ​​model through some possible implementation methods.

[0295] In implementation example G, after the network device receives indication information indicating the K updated AI models, the method further includes: the network device fusing the K updated AI models to obtain a fusion result; and the network device sending indication information indicating the fusion result. Specifically, after receiving the indication information indicating the K updated AI models, the network device may further fusing the K updated AI models to obtain a fusion result, and sending indication information indicating the fusion result, thereby enabling model fusion in the AI ​​training scenario.

[0296] Optionally, in implementation example G, the network device that performs fusion processing on the K updated AI models to obtain the fusion result can be a core network device, an access network device, or a device that combines a core network device and an access network device, which is not limited here.

[0297] In implementation example H, after the network device receives indication information indicating the K updated AI models, the method further includes: the network device sending indication information indicating the K updated AI models. Specifically, after receiving the indication information indicating the K updated AI models, the network device, acting as a transparent communication role, may send indication information indicating the K updated AI models, so that a recipient of the indication information can further achieve model fusion.

[0298] Optionally, in implementation example H, the network device that transparently transmits the indication information indicating the K updated AI models may be an access network device, and the subsequent core network device (or the first device) may perform model fusion based on the indication information.

[0299] In one possible implementation, in the method shown in FIG2 , in addition to indicating the processing modes of the K AI models via the first indication information, the deployment of the AI ​​models may also be achieved via other information. In other words, the method shown in FIG2 further includes: the network device sending indication information indicating the K AI models to achieve deployment of the AI ​​models in the communication network.

[0300] Optionally, the K AI models may be preconfigured or predefined.

[0301] Optionally, the K AI models may be configured. The following describes an exemplary configuration process for AI model deployment through some possible implementations.

[0302] In implementation example 1, before the network device sends indication information indicating the K AI models, the method further includes: the network device receiving third configuration information, where the third configuration information is used to configure P AI models, where the P AI models correspond to the first AI task, and P is greater than or equal to K. Specifically, after receiving the third configuration information for configuring the P AI models, the network device may send indication information indicating the K AI models to the terminal device. That is, the network device may screen / select the K AI models required from the P AI models and then deploy the K AI models to the terminal device.

[0303] Optionally, the third configuration information includes at least one of the following: task type information of the first AI task, AI model type information of P AI models, model scale information of the P AI models, and model performance requirement information of the P AI models.

[0304] Optionally, in implementation example I, the network device that determines K AI models based on P AI models can be a core network device, an access network device, or a device that combines a core network device and an access network device, which is not limited here.

[0305] In implementation example J, before the network device sends indication information indicating the K AI models, the method further includes: the network device receiving indication information indicating the K AI models. Specifically, the network device acts as a transparent communication role, and the network device can send indication information indicating the K AI models to the terminal device to implement deployment of the AI ​​models in the communication network.

[0306] To facilitate understanding of the above implementation scheme, the following will introduce the reasoning and training of the AI ​​model respectively in combination with the implementation examples shown in Figures 6 and 7.

[0307] Please refer to Figure 6, which is a schematic diagram of an implementation of the reasoning process of the AI ​​model.

[0308] As shown in Figure 6, the first device, as an AI service provider, can maintain a training data set and a machine learning model (or model library). That is, the machine learning model is trained based on the training data set at the OTT vendor. The machine learning model can be trained using common training methods such as model fusion and model distillation. At the same time, the OTT vendor sets management indicators and measurement indicators for a certain AI service and configures them to the core network through management configuration and measurement configuration signaling, including but not limited to:

[0309] Management configuration (see Implementation Example A and Implementation Example B above), which is used to configure the type of AI service, applicable scenarios of the machine learning model used for the AI ​​service, enabling conditions, update conditions, switching conditions, fallback conditions, data collection configuration (data type, collection time, collection frequency, collection location, collection quantity, etc.);

[0310] The measurement configuration (see Implementation Example C and Implementation Example D above) is used to configure the measurement object, period, trigger conditions, and measurement result reporting method.

[0311] The core network device shown in Figure 6 can enable the model management function (AIMMF) and performance measurement function (AIPMF) based on the management and measurement configurations. These configurations are then sent to the base station (BS). The model container and data container are maintained. The model container is used by OTT vendors to deploy their machine learning models, while the data container is used to collect data (see Implementation Examples E and F above).

[0312] The access network device, as shown in Figure 6, can receive management and measurement configurations, measure model performance according to the measurement configurations, and manage the model lifecycle based on the management configurations, including but not limited to model selection, model enablement, model updates, model switching, and model rollback. The access network device manages resources related to model inference (such as computing resources, communication resources, and storage resources). The access network device downloads the model required for the region from the core network model container. The access network device collects data (locally or from associated terminals).

[0313] The terminal device shown in Figure 6 can download the required machine learning model from its associated access network device (see Implementation Examples I and J above), collect data, and perform model inference. The collected data is reported to the access network device. The model performance is measured and the measurement results are reported to the access network device.

[0314] Please refer to Figure 7, which is a schematic diagram of an implementation of the AI ​​model training process.

[0315] As shown in Figure 7, the first device can act as an AI service provider, define and describe the AI ​​service tasks according to its needs, and provide task configuration to the core network. At the same time, the OTT manufacturer sets management indicators and measurement indicators for a certain AI service and configures them to the core network through management configuration and measurement configuration signaling, including but not limited to:

[0316] Management configuration (see Implementation Example A and Implementation Example B above), which is used to configure the type of AI service, applicable scenarios of the machine learning model used for the AI ​​service, enabling conditions, update conditions, switching conditions, fallback conditions, data collection configuration (data type, collection time, collection frequency, collection location, collection quantity, etc.);

[0317] Measurement configuration (see Implementation Example C and Implementation Example D above), used to configure the measurement object, period, trigger conditions, measurement result reporting method, etc.

[0318] Task configuration (see Implementation Example I and Implementation Example J above), including task type, model type, model scale, performance requirements, etc.

[0319] As shown in Figure 7, the core network equipment can activate the AI ​​Service Function (AISF), Model Management Function (AIMMF), and Performance Measurement Function (AIPMF) based on the task description, management configuration, and measurement configuration provided by the OTT vendor. It also issues task, management, and measurement configurations to the base station (BS). It maintains a model container to store trained machine learning models for network elements such as core network, access network equipment, and terminals, and provides model purchasing services to OTT vendors.

[0320] The access network device shown in Figure 7 can receive task configuration, management configuration and measurement configuration, and determine the machine learning model (i.e., model construction) according to the task configuration. Model construction can build a complete model based on a small model, or it can be implemented by adding a branch model to the trunk model. The access network device measures the performance of the model according to the measurement configuration, and manages the life cycle of the model based on the management configuration, including but not limited to model selection, model enablement, model update, model switching, model rollback, etc. The access network device manages resources related to model training (such as computing resources, communication resources, and storage resources). The access network device downloads the model required for this area from the core network model container, and reports the trained model to the core network model container. The access network device collects data (locally or from associated terminals), builds a regional data set (refer to the previous implementation example E and implementation example F), and performs model training.

[0321] The terminal device shown in Figure 7 can download the required machine learning model from its associated access network device, collect data, and perform model training. The terminal device can report the collected data to the access network device. The terminal device can measure the model performance and report the measurement results to the access network device. The terminal device can send the trained AI model (i.e., the updated AI model) (see Implementation Example G and Implementation Example H above).

[0322] Referring to Figure 8 , an embodiment of the present application provides a communication device 800. This communication device 800 can implement the functions of the communication device in the above-described method embodiment, and thus can also achieve the beneficial effects of the above-described method embodiment. In the embodiment of the present application, the communication device 800 can be a terminal device, a network device, or a first device, or can be an integrated circuit or component, such as a chip, within the terminal device, network device, or first device. The following embodiments are described using the communication device 800 as an example, wherein the terminal device, network device, or first device is used.

[0323] It should be noted that the transceiver unit 802 may include a sending unit and a receiving unit, which are respectively used to perform sending and receiving.

[0324] In one possible implementation, when the device 800 is used to execute the method executed by the terminal device in the previous embodiment, the device 800 includes a processing unit 801 and a transceiver unit 802; the transceiver unit 802 is used to receive first indication information, and the first indication information is used to indicate that the processing mode of K artificial intelligence AI models is the first mode or the second mode, and the K AI models correspond to the first AI task, and K is a positive integer; wherein the first mode includes AI reasoning, and the second mode includes AI training; the processing unit 801 is used to process the K AI models through the first mode or the second mode.

[0325] In a possible implementation, the transceiver unit 802 is further configured to receive indication information indicating management information of the K AI models.

[0326] In a possible implementation manner, the management information includes at least one of the following: model selection, model enabling, model updating, model switching, and model rollback.

[0327] In one possible implementation, the transceiver unit 802 is further configured to send model performance measurement results of the K AI models.

[0328] In a possible implementation, the transceiver unit 802 is further configured to receive instruction information instructing to report the model performance measurement results of the K AI models.

[0329] In one possible implementation, the transceiver unit 802 is further used to send data associated with the K AI models.

[0330] In one possible implementation, in the first mode, the data associated with the K AI models include the input data of the K AI models; and / or, in the second mode, the data associated with the K AI models include the input data and label data of the K AI models.

[0331] In one possible implementation, the processing unit 801 is configured to process the K AI models through the second mode, including: processing the K AI models through the second mode to obtain K updated AI models; and sending indication information indicating the K updated AI models.

[0332] In a possible implementation, the transceiver unit 802 is further configured to receive indication information indicating the K AI models.

[0333] In one possible implementation, the first indication information is one of N indication information, and the N indication information are respectively used to indicate the processing mode of the AI ​​model corresponding to N AI tasks, the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer.

[0334] In one possible implementation, the transceiver unit 802 is further used to send indication information indicating the processing mode of the AI ​​model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task.

[0335] In one possible implementation, when the device 800 is used to execute the method executed by the network device in the previous embodiment, the device 800 includes a processing unit 801 and a transceiver unit 802; the transceiver unit 802 is used to receive first indication information, and the first indication information is used to indicate that the processing mode of K artificial intelligence AI models is the first mode or the second mode, and the K AI models correspond to the first AI task, and K is a positive integer; wherein the first mode includes AI reasoning, and the second mode includes AI training; the transceiver unit 802 is also used to send the first indication information.

[0336] In one possible implementation, the transceiver unit 802 is further used to receive first configuration information, where the first configuration information is used to configure management information of AI models corresponding to X AI tasks, where the X AI tasks include the first AI task, and X is a positive integer; the transceiver unit 802 is further used to send indication information indicating the management information of the K AI models based on the first configuration information.

[0337] In one possible implementation, the first configuration information includes one or more of the following: applicable scenarios of the AI ​​models corresponding to the X AI tasks, selection conditions of the AI ​​models corresponding to the X AI tasks, enabling conditions of the AI ​​models corresponding to the X AI tasks, update conditions of the AI ​​models corresponding to the X AI tasks, switching conditions of the AI ​​models corresponding to the X AI tasks, fallback conditions of the AI ​​models corresponding to the X AI tasks, and data collection information of the AI ​​models corresponding to the X AI tasks.

[0338] In one possible implementation, the data collection information of the AI ​​model corresponding to the X AI tasks includes one or more of the following: data type, collection time, collection frequency, collection location, and collection quantity.

[0339] In a possible implementation, the transceiver unit 802 is further used to receive indication information indicating management information of the K AI models; the transceiver unit 802 is further used to send indication information indicating management information of the K AI models.

[0340] In a possible implementation manner, the management information includes at least one of the following: model selection, model enabling, model updating, model switching, and model rollback.

[0341] In a possible implementation, the transceiver unit 802 is further configured to receive indication information indicating model performance measurement results of the K AI models.

[0342] In one possible implementation, the transceiver unit 802 is further used to receive second configuration information, where the second configuration information is used to configure measurement information of the AI ​​models corresponding to Y AI tasks, where the Y AI tasks include the first AI task; the transceiver unit 802 is further used to send indication information indicating reporting of model performance measurement results of the K AI models based on the second configuration information.

[0343] In a possible implementation manner, the second configuration information includes one or more of the following: a measurement object, a measurement period, a measurement triggering condition, and a reporting method of a measurement result.

[0344] In one possible implementation, the transceiver unit 802 is further used to receive indication information indicating reporting of the model performance measurement results of the K AI models; the transceiver unit 802 is further used to send indication information indicating reporting of the model performance measurement results of the K AI models.

[0345] In one possible implementation, the transceiver unit 802 is further used to receive data associated with the K AI models.

[0346] In a possible implementation, the transceiver unit 802 is further used to send first data, where the first data is processed based on the data associated with the K AI models.

[0347] In one possible implementation, the transceiver unit 802 is further used to send data associated with the K AI models.

[0348] In one possible implementation, in the first mode, the data associated with the K AI models include the input data of the K AI models; and / or, in the second mode, the data associated with the K AI models include the input data and label data of the K AI models.

[0349] In a possible implementation, the transceiver unit 802 is further configured to receive indication information indicating the K updated AI models, where the K updated AI models are obtained by processing the K AI models using the second mode.

[0350] In one possible implementation, the communication device further includes a processing unit 801, which is used to perform fusion processing on the K updated AI models to obtain a fusion result; the transceiver unit 802 is also used to send indication information indicating the fusion result.

[0351] In a possible implementation, the transceiver unit 802 is further configured to send indication information indicating the K updated AI models.

[0352] In a possible implementation, the transceiver unit 802 is further configured to send indication information indicating the K AI models.

[0353] In a possible implementation, the transceiver unit 802 is further configured to receive third configuration information, where the third configuration information is used to configure P AI models, where the P AI models correspond to the first AI task, and P is greater than or equal to K.

[0354] In a possible implementation, the transceiver unit 802 is further configured to receive indication information indicating K AI models.

[0355] In one possible implementation, the first indication information is one of N indication information, and the N indication information are respectively used to indicate the processing mode of the AI ​​model corresponding to N AI tasks, the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer.

[0356] In one possible implementation, the transceiver unit 802 is further used to receive indication information indicating a processing mode of the AI ​​model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task.

[0357] In a possible implementation, the transceiver unit 802 is further configured to send indication information indicating a processing mode of the AI ​​model corresponding to the M AI tasks.

[0358] In one possible implementation, when the device 800 is used to execute the method executed by the first device in the previous embodiment, the device 800 includes a processing unit 801 and a transceiver unit 802; the processing unit 801 is used to determine first indication information, and the first indication information is used to indicate that the processing mode of K artificial intelligence AI models is the first mode or the second mode, and the K AI models correspond to the first AI task, and K is a positive integer; wherein the first mode includes AI reasoning, and the second mode includes AI training; the transceiver unit 802 is used to send the first indication information.

[0359] In one possible implementation, the transceiver unit 802 is further used to send first configuration information, where the first configuration information is used to configure management information of the AI ​​model corresponding to X AI tasks, where the X AI tasks include the first AI task, and X is a positive integer.

[0360] In one possible implementation, the first configuration information includes one or more of the following: applicable scenarios of the AI ​​models corresponding to the X AI tasks, selection conditions of the AI ​​models corresponding to the X AI tasks, enabling conditions of the AI ​​models corresponding to the X AI tasks, update conditions of the AI ​​models corresponding to the X AI tasks, switching conditions of the AI ​​models corresponding to the X AI tasks, fallback conditions of the AI ​​models corresponding to the X AI tasks, and data collection information of the AI ​​models corresponding to the X AI tasks.

[0361] In one possible implementation, the data collection information of the AI ​​model corresponding to the X AI tasks includes one or more of the following: data type, collection time, collection frequency, collection location, and collection quantity.

[0362] In one possible implementation, the first configuration information is used to determine management information of the K AI models, and the management information includes at least one of the following: model selection, model enablement, model update, model switching, and model rollback.

[0363] In a possible implementation, the transceiver unit 802 is further configured to receive indication information indicating model performance measurement results of the K AI models.

[0364] In a possible implementation, the transceiver unit 802 is further configured to send second configuration information, where the second configuration information is used to configure measurement information of the AI ​​model corresponding to Y AI tasks, where the Y AI tasks include the first AI task.

[0365] In a possible implementation manner, the second configuration information includes one or more of the following: a measurement object, a measurement period, a measurement triggering condition, and a reporting method of a measurement result.

[0366] In one possible implementation, the transceiver unit 802 is further used to receive data associated with the K AI models, or first data, where the first data is processed based on the data associated with the K AI models.

[0367] In one possible implementation, in the first mode, the data associated with the K AI models include the input data of the K AI models; and / or, in the second mode, the data associated with the K AI models include the input data and label data of the K AI models.

[0368] In one possible implementation, the transceiver unit 802 is further used to receive indication information indicating the K updated AI models, where the K updated AI models are obtained by processing the K AI models through the second mode; or, the transceiver unit 802 is further used to receive indication information indicating a fusion result, where the fusion result is obtained based on the fusion processing of the K updated AI models.

[0369] In a possible implementation, the transceiver unit 802 is further configured to send third configuration information, where the third configuration information is used to configure P AI models, where the P AI models correspond to the first AI task, and P is greater than or equal to K.

[0370] In one possible implementation, the first indication information is one of N indication information, and the N indication information are respectively used to indicate the processing mode of the AI ​​model corresponding to N AI tasks, the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer.

[0371] In one possible implementation, the transceiver unit 802 is further used to receive indication information indicating a processing mode of the AI ​​model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task.

[0372] It should be noted that, for details on the information execution process of the units of the above-mentioned communication device 800, please refer to the description in the method embodiment shown above in this application, and no further details will be given here.

[0373] Please refer to Figure 9, which is another schematic structural diagram of a communication device 900 provided in this application. The communication device 900 includes a logic circuit 901 and an input / output interface 902. The communication device 900 may be a chip or an integrated circuit.

[0374] The transceiver unit 802 shown in FIG8 may be a communication interface, which may be the input / output interface 902 in FIG9 , 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.

[0375] Optionally, the input-output interface 902 is used to receive first indication information, where the first indication information is used to indicate that the processing mode of K artificial intelligence AI models is a first mode or a second mode, where the K AI models correspond to a first AI task, and K is a positive integer; wherein the first mode includes AI reasoning, and the second mode includes AI training; and the logic circuit 901 is used to process the K AI models through the first mode or the second mode.

[0376] Optionally, the input-output interface 902 is used to receive first indication information, where the first indication information is used to indicate that the processing mode of K artificial intelligence AI models is the first mode or the second mode, where the K AI models correspond to a first AI task, and K is a positive integer; wherein the first mode includes AI reasoning, and the second mode includes AI training; the input-output interface 902 is also used to send the first indication information.

[0377] Optionally, the logic circuit 901 is used to determine first indication information, where the first indication information is used to indicate that the processing mode of K artificial intelligence AI models is the first mode or the second mode, where the K AI models correspond to a first AI task, and K is a positive integer; wherein the first mode includes AI reasoning, and the second mode includes AI training; and the input-output interface 902 is used to send the first indication information.

[0378] Among them, the logic circuit 901 and the input and output interface 902 can also execute other steps executed by the terminal device, network device or first device in any embodiment and achieve corresponding beneficial effects, which will not be repeated here.

[0379] In a possible implementation, the processing unit 801 shown in FIG. 8 may be the logic circuit 901 in FIG. 9 .

[0380] Optionally, the logic circuit 901 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] Please refer to Figure 10, which shows 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 serving as a terminal device in the above-mentioned embodiments. The example shown in Figure 10 is that the terminal device is implemented through the terminal device (or a component in the terminal device).

[0385] Herein, a possible logical structure diagram of the communication device 1000 is shown. The communication device 1000 may include but is not limited to at least one processor 1001 and a communication port 1002 .

[0386] The transceiver unit 802 shown in FIG8 may be a communication interface, which may be the communication port 1002 in FIG10 , which may include an input interface and an output interface. Alternatively, the communication port 1002 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0387] Further optionally, the device may also include at least one of a memory 1003 and a bus 1004. In an embodiment of the present application, the at least one processor 1001 is used to control and process the actions of the communication device 1000.

[0388] In addition, the processor 1001 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.

[0389] It should be noted that the communication device 1000 shown in Figure 10 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 10 can refer to the description in the aforementioned method embodiment and will not be repeated here.

[0390] Please refer to Figure 11, which is a structural diagram of the communication device 1100 involved in the above-mentioned embodiments provided in an embodiment of the present application. The communication device 1100 can specifically be a communication device as a network device in the above-mentioned embodiments. The example shown in Figure 11 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 11.

[0391] The communication device 1100 includes at least one processor 1111 and at least one network interface 1114. Further optionally, the communication device also includes at least one memory 1112, at least one transceiver 1113 and one or more antennas 1115. The processor 1111, the memory 1112, the transceiver 1113 and the network interface 1114 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 1115 is connected to the transceiver 1113. The network interface 1114 is used to enable the communication device to communicate with other communication devices through a communication link. For example, the network interface 1114 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.

[0392] The transceiver unit 802 shown in FIG8 may be a communication interface, which may be the network interface 1114 in FIG11 , which may include an input interface and an output interface. Alternatively, the network interface 1114 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0393] Processor 1111 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 1111 in Figure 11 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.

[0394] The memory is primarily used to store software programs and data. Memory 1112 can exist independently and be connected to processor 1111. Alternatively, memory 1112 can be integrated with processor 1111, for example, within a single chip. Memory 1112 can store program code for executing the technical solutions of the embodiments of the present application, and execution is controlled by processor 1111. The various computer program codes executed can also be considered drivers for processor 1111.

[0395] Figure 11 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.

[0396] The transceiver 1113 can be used to support the reception or transmission of radio frequency signals between the communication device and the terminal. The transceiver 1113 can be connected to the antenna 1115. The transceiver 1113 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 1115 can receive radio frequency signals. The receiver Rx of the transceiver 1113 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 1111 so that the processor 1111 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 1113 is also used to receive a modulated digital baseband signal or digital intermediate frequency signal from the processor 1111, 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 1115. 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.

[0397] The transceiver 1113 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.

[0398] It should be noted that the communication device 1100 shown in Figure 11 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 1100 shown in Figure 11 can refer to the description in the aforementioned method embodiment, and will not be repeated here one by one.

[0399] Please refer to FIG12 , which is a schematic structural diagram of the communication device involved in the above-mentioned embodiment provided in an embodiment of the present application.

[0400] It can be understood that the communication device 120 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 120 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 120 includes one or more processors 121. The processor 121 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.

[0401] Optionally, in one design, the processor 121 may include a program 123 (sometimes also referred to as code or instructions), which may be executed on the processor 121 to cause the communication device 120 to perform the methods described in the following embodiments. In yet another possible design, the communication device 120 includes circuitry (not shown in FIG12 ).

[0402] Optionally, the communication device 120 may include one or more memories 122 on which a program 124 (sometimes also referred to as code or instructions) is stored. The program 124 can be run on the processor 121, so that the communication device 120 executes the method described in the above method embodiment.

[0403] Optionally, the processor 121 and / or the memory 122 may include an AI module 127, 128, which is used to implement AI-related functions. The AI ​​module may 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.

[0404] Optionally, data may be stored in the processor 121 and / or the memory 122. The processor and the memory may be provided separately or integrated together.

[0405] Optionally, the communication device 120 may further include a transceiver 125 and / or an antenna 126. The processor 121 may also be sometimes referred to as a processing unit, and controls the communication device (e.g., a RAN node or terminal). The transceiver 125 may also be sometimes 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 126.

[0406] The transceiver unit 802 shown in FIG8 may be a communication interface, which may be the transceiver 125 in FIG12 . The transceiver 125 may include an input interface and an output interface. Alternatively, the transceiver 125 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0407] An embodiment of the present application also 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 terminal device, network device or first device in the above embodiments.

[0408] An embodiment of the present application also provides a computer program product (or computer program). When the computer program product is executed by the processor, the processor executes the method of the possible implementation mode of the above-mentioned terminal device, network device or first device.

[0409] 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 a terminal device, a network device or a first device in the aforementioned method embodiment.

[0410] An embodiment of the present application also provides a communication system, which includes at least two devices among the terminal device, network device or first device in any of the above embodiments.

[0411] 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.

[0412] 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.

[0413] 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: include: Receive first indication information, where the first indication information is used to indicate that a processing mode of K artificial intelligence (AI) models is a first mode or a second mode, where the K AI models correspond to a first AI task, and K is a positive integer; wherein the first mode includes AI reasoning, and the second mode includes AI training; The K AI models are processed by the first mode or the second mode.

2. The method according to claim 1, characterized in that The method further comprises: Receive indication information indicating management information of the K AI models.

3. The method according to claim 2, wherein the management information comprises at least one of the following: Model selection, model enabling, model updating, model switching, and model rollback.

4. The method according to any one of claims 1 to 3, characterized in that: After processing the K AI models by the first mode or the second mode, the method further includes: Send the model performance measurement results of the K AI models.

5. The method according to claim 4, characterized in that The method further comprises: Receive indication information instructing to report the model performance measurement results of the K AI models.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Send data associated with the K AI models.

7. The method according to claim 6, characterized in that In the first mode, the data associated with the K AI models include input data of the K AI models; and / or, In the second mode, the data associated with the K AI models include input data and label data of the K AI models.

8. The method according to any one of claims 1 to 7, characterized in that: Processing the K AI models by the second mode includes: Processing the K AI models by using the second mode to obtain K updated AI models; Send indication information indicating the K updated AI models.

9. The method according to any one of claims 1 to 8, characterized in that: The method further comprises: Receive indication information indicating the K AI models.

10. The method according to any one of claims 1 to 9, characterized in that: The first indication information is one of N indication information, and the N indication information are respectively used to indicate the processing mode of the AI ​​model corresponding to the N AI tasks, the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer.

11. The method according to any one of claims 1 to 10, characterized in that: The method further comprises: Send indication information indicating a processing mode of an AI model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task.

12. A communication method, characterized in that: include: Receive first indication information, where the first indication information is used to indicate that the processing mode of K artificial intelligence AI models is a first mode or a second mode, where the K AI models correspond to a first AI task, and K is a positive integer; wherein the first mode includes AI reasoning, and the second mode includes AI reasoning. The formula includes AI training; Send the first indication information.

13. The method according to claim 12, characterized in that The method further comprises: Receive first configuration information, where the first configuration information is used to configure management information of an AI model corresponding to X AI tasks, where the X AI tasks include the first AI task, and X is a positive integer; Based on the first configuration information, indication information indicating management information of the K AI models is sent.

14. The method according to claim 13, characterized in that The first configuration information includes one or more of the following: Applicable scenarios of the AI ​​models corresponding to the X AI tasks, selection conditions of the AI ​​models corresponding to the X AI tasks, enabling conditions of the AI ​​models corresponding to the X AI tasks, update conditions of the AI ​​models corresponding to the X AI tasks, switching conditions of the AI ​​models corresponding to the X AI tasks, fallback conditions of the AI ​​models corresponding to the X AI tasks, and data collection information of the AI ​​models corresponding to the X AI tasks.

15. The method according to claim 14, characterized in that The data collection information of the AI ​​models corresponding to the X AI tasks includes one or more of the following: Data type, collection time, collection frequency, collection location, and collection quantity.

16. The method according to claim 12, characterized in that The method further comprises: receiving indication information indicating management information of the K AI models; Send indication information indicating management information of the K AI models.

17. The method according to any one of claims 13 to 16, characterized in that The management information includes at least one of the following: Model selection, model enabling, model updating, model switching, and model rollback.

18. The method according to any one of claims 12 to 16, characterized in that The method further comprises: Receive indication information indicating model performance measurement results of the K AI models.

19. The method according to claim 18, characterized in that Before receiving indication information indicating the model performance measurement results of the K AI models, the method further includes: receiving second configuration information, where the second configuration information is used to configure measurement information of an AI model corresponding to Y AI tasks, where the Y AI tasks include the first AI task; Based on the second configuration information, indication information is sent to instruct reporting the model performance measurement results of the K AI models.

20. The method according to claim 19, characterized in that The second configuration information includes one or more of the following: Measurement object, measurement cycle, measurement trigger conditions, and reporting method of measurement results.

21. The method according to claim 18, characterized in that Before receiving indication information indicating the model performance measurement results of the K AI models, the method further includes: Receiving instruction information for instructing to report the model performance measurement results of the K AI models; Send indication information for instructing to report the model performance measurement results of the K AI models.

22. The method according to any one of claims 12 to 21, characterized in that The method further comprises: Receive data associated with the K AI models.

23. The method according to claim 22, characterized in that The method further comprises: Send first data, where the first data is processed based on data associated with the K AI models.

24. The method according to claim 22, characterized in that The method further comprises: Send data associated with the K AI models.

25. The method according to any one of claims 22 to 24, characterized in that In the first mode, the data associated with the K AI models include input data of the K AI models; and / or, In the second mode, the data associated with the K AI models include input data and label data of the K AI models.

26. The method according to any one of claims 12 to 25, characterized in that The method further comprises: Indication information indicating the K updated AI models is received, where the K updated AI models are obtained by processing the K AI models by the second mode.

27. The method according to claim 26, characterized in that The method further comprises: Performing fusion processing on the K updated AI models to obtain a fusion result; Sending indication information indicating the fusion result.

28. The method according to claim 26, characterized in that The method further comprises: Send indication information indicating the K updated AI models.

29. The method according to any one of claims 12 to 28, characterized in that The method further comprises: Send indication information indicating the K AI models.

30. The method according to claim 29, characterized in that The method further comprises: Receive third configuration information, where the third configuration information is used to configure P AI models, where the P AI models correspond to the first AI task, and P is greater than or equal to K.

31. The method according to claim 30, characterized in that The third configuration information includes at least one of the following: The task type information of the first AI task, the AI ​​model type information of the P AI models, the model scale information of the P AI models, and the model performance requirement information of the P AI models.

32. The method according to claim 29, characterized in that The method further comprises: Receive indication information indicating K AI models.

33. The method according to any one of claims 12 to 32, characterized in that The first indication information is one of N indication information, and the N indication information are respectively used to indicate the processing mode of the AI ​​model corresponding to the N AI tasks, the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer.

34. The method according to any one of claims 12 to 33, characterized in that The method further comprises: Receive indication information indicating a processing mode of an AI model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task.

35. The method according to claim 34, characterized in that The method further comprises: Send indication information indicating the processing mode of the AI ​​model corresponding to the M AI tasks.

36. A communication method, characterized in that: include: Determine first indication information, where the first indication information is used to indicate that a processing mode of K artificial intelligence AI models is a first mode or a second mode, where the K AI models correspond to a first AI task, and K is a positive integer; wherein the first mode includes AI reasoning, and the second mode includes AI training; Send the first indication information.

37. The method according to claim 36, characterized in that The method further comprises: Send first configuration information, where the first configuration information is used to configure management information of the AI ​​model corresponding to X AI tasks, where the X AI tasks include the first AI task, and X is a positive integer.

38. The method according to claim 37, characterized in that The first configuration information includes one or more of the following: Applicable scenarios of the AI ​​models corresponding to the X AI tasks, selection conditions of the AI ​​models corresponding to the X AI tasks, enabling conditions of the AI ​​models corresponding to the X AI tasks, update conditions of the AI ​​models corresponding to the X AI tasks, switching conditions of the AI ​​models corresponding to the X AI tasks, fallback conditions of the AI ​​models corresponding to the X AI tasks, and data collection information of the AI ​​models corresponding to the X AI tasks.

39. The method according to claim 38, characterized in that The data collection information of the AI ​​models corresponding to the X AI tasks includes one or more of the following: Data type, collection time, collection frequency, collection location, and collection quantity.

40. The method according to any one of claims 37 to 39, characterized in that The first configuration information is used to determine management information of the K AI models, and the management information includes at least one of the following: Model selection, model enabling, model updating, model switching, and model rollback.

41. The method according to any one of claims 36 to 40, characterized in that The method further comprises: Receive indication information indicating model performance measurement results of the K AI models.

42. The method according to claim 41, characterized in that Before receiving indication information indicating the model performance measurement results of the K AI models, the method further includes: Send second configuration information, where the second configuration information is used to configure measurement information of the AI ​​model corresponding to Y AI tasks, where the Y AI tasks include the first AI task.

43. The method according to claim 42, characterized in that The second configuration information includes one or more of the following: Measurement object, measurement cycle, measurement trigger conditions, and reporting method of measurement results.

44. The method according to any one of claims 36 to 43, characterized in that The method further comprises: Receive data associated with the K AI models, or first data, where the first data is processed based on the data associated with the K AI models.

45. The method according to claim 44, characterized in that In the first mode, the data associated with the K AI models include input data of the K AI models; and / or, In the second mode, the data associated with the K AI models include input data and label data of the K AI models.

46. ​​The method according to any one of claims 36 to 45, characterized in that The method further comprises: receiving indication information indicating the K updated AI models, where the K updated AI models are obtained by processing the K AI models by the second mode; or, Receive indication information indicating a fusion result, where the fusion result is obtained by fusion processing based on the K updated AI models.

47. The method according to any one of claims 36 to 46, characterized in that The method further comprises: Send third configuration information, where the third configuration information is used to configure P AI models, where the P AI models correspond to the first AI task, and P is greater than or equal to K.

48. The method according to claim 47, characterized in that The third configuration information includes at least one of the following: The task type information of the first AI task, the AI ​​model type information of the P AI models, the model scale information of the P AI models, and the model performance requirement information of the P AI models.

49. The method according to any one of claims 36 to 48, characterized in that The first indication information is one of N indication information, and the N indication information are respectively used to indicate the processing mode of the AI ​​model corresponding to the N AI tasks, the processing mode includes the first mode or the second mode, the N AI tasks include the first AI task, and N is a positive integer.

50. The method according to any one of claims 36 to 49, characterized in that The method further comprises: Receive indication information indicating a processing mode of an AI model corresponding to M AI tasks, where M is a positive integer; wherein the processing mode includes the first mode or the second mode, and the M AI tasks include the first AI task.

51. A communication device, characterized in that: Comprising modules for executing the method according to any one of claims 1 to 50.

52. A communication device, characterized in that: The method comprises at least one processor coupled to a memory; the at least one processor is configured to execute the method according to any one of claims 1 to 50.

53. The communication device according to claim 52, characterized in that The communication device is a chip or a chip system.

54. A readable storage medium, characterized in that The storage medium stores a computer program or instruction, and when the computer program or instruction is executed by the communication device, the method as claimed in any one of claims 1 to 50 is implemented.

55. A computer program product, characterized in that The method comprises instructions which, when executed on a computer, cause the computer to perform the method according to any one of claims 1 to 50.

Images