Method for executing task in communication system, and related apparatus

Abstract

The present application relates to the field of communications, and in particular to a method for executing a task in a communication system, and a related apparatus. The method comprises: a terminal acquiring computing power information of a network side and an effective time of the computing power information; and on the basis of the computing power information and the effective time, the terminal sending a first message to a first network device, wherein the first message is used for requesting the execution of a target task. Using the solution in the present application helps to alleviate the computing load of a terminal or a server.

Description

Methods and related devices for task execution in communication systems

[0001] This application claims priority to Chinese Patent Application No. 202410452310.0, filed on April 15, 2024, entitled "Method and Related Apparatus for Task Execution in a Communication System", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to a method and related apparatus for task execution in a communication system. Background Technology

[0003] In communication systems, with the continuous development of terminals, terminals themselves have also acquired certain computing capabilities, enabling them to handle a certain amount of neural network computation. For example, terminal users use neural network models to perform artificial intelligence (AI) tasks (image recognition, speech recognition, etc.).

[0004] However, with the development of artificial intelligence, neural networks are becoming increasingly large, leading to situations where the computing power of terminals cannot meet the computational demands of executing AI tasks. For servers, when there are many terminals requesting AI tasks, it will bring a large computational load to the server, which may cause computational congestion, resulting in the inability to execute the AI ​​tasks requested by the terminals. Summary of the Invention

[0005] This application provides a method and related apparatus for task execution in a communication system. Using this application is beneficial for alleviating the computing load on terminals or servers.

[0006] Firstly, embodiments of this application provide a method for task execution in a communication system. This method should be applicable to the terminal side, such as a terminal or a communication / processing module within a terminal, or circuits or chips in the terminal responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip containing a modem core, or a system-in-package (SIP) chip), or circuits or chips in the terminal responsible for processing functions (such as a graphics processing unit (GPU)). This method should also be applicable to the server side, such as a server or a communication / processing module within a server, or circuits or chips in the server responsible for processing functions (such as a processing core, digital signal processor (DSP), microcontroller unit (MCU), application-specific integrated circuit (ASIC), central processing unit (CPU), graphics processing unit (GPU), field-programmable gate array (FPGA), AI processor, or neural processing unit (NPU)).

[0007] Taking the application of this method to a terminal as an example, in this method, the terminal obtains the computing power information of the network side and the effective time of the computing power information. Based on the computing power information and the effective time of the computing power information, the terminal sends a first message to the first network device. The first message is used to request the execution of the target task.

[0008] Optionally, the network-side computing power information can be the network-side remaining computing power information, information on the network-side's ability to still support computing demands, or network-side computing power-related information; no limitation is made here. In one example, the remaining computing power information includes the remaining computing power size and the remaining memory size.

[0009] It can be seen that by sending a message to the network side requesting the execution of a target task based on the network side's computing power information, the terminal can alleviate the terminal's computing load and fully utilize the network side's computing resources. Similarly, when the server executes the above method, it also helps alleviate the server's computing load and fully utilizes the network side's computing resources.

[0010] In one possible design, the method of this embodiment further includes: the terminal receiving a second message from a first network device, the second message including the execution result of the target task.

[0011] In one possible design, the terminal sends a first message to the first network device based on the computing power information and the effective time of the computing power information, including: the terminal determines whether the network side meets the computing power requirements for executing the target task based on the computing power information, and when it is determined that the network side meets the computing power requirements for executing the target task, the terminal sends a first message to the first network device based on the effective time of the computing power information on the network side.

[0012] It can be seen that when the terminal determines that the computing power information on the network side can meet the computing power requirements for executing the target task, it sends the first message to the first network device, which can ensure that the computing power resources on the network side are fully utilized.

[0013] In one possible design, the terminal sends a first message to the first network device based on the effective time of the network-side computing power information, including:

[0014] The terminal determines whether the effective time of the computing power information on the network side meets the time requirement for executing the target task. If the effective time of the computing power information on the network side meets the time requirement for executing the target task, the terminal sends a first message to the first network device; if the effective time of the computing power information on the network side does not meet the time requirement for executing the target task, the terminal does not send a first message to the first network device.

[0015] In one possible design, the network-side computing power information includes the computing power information of the first network device. The terminal obtains the network-side computing power information, including:

[0016] The terminal obtains the first computing power level, and based on the first computing power level, obtains the computing power information of the first network device. There is a correspondence between the first computing power level and the computing power information of the first network device.

[0017] In one possible design, the network-side computing power information includes the total computing power information of the first network device and the second network device. The terminal obtains the network-side computing power information, including:

[0018] The terminal obtains a second computing power level, and based on the second computing power level, obtains the total computing power information of the first network device and the second network device. There is a corresponding relationship between the second computing power level and the total computing power information of the first network device and the second network device.

[0019] In one possible design, the network-side computing power information includes the computing power information of a first network device and the computing power information of a second network device. The terminal obtains the network-side computing power information, including:

[0020] The terminal obtains the third computing power level, and based on the third computing power level, obtains the computing power information of the first network device and the computing power information of the second network device. There is a correspondence between the first computing power level and the computing power information of the first network device and the computing power information of the second network device.

[0021] In one possible design, the network-side computing power information includes the computing power information of the second network device. The terminal obtains the network-side computing power information, including:

[0022] The terminal obtains the fourth computing power level, and based on the fourth computing power level, obtains the computing power information of the second network device. There is a corresponding relationship between the fourth computing power level and the computing power information of the second network device.

[0023] In one possible design, the network-side computing power information includes the computing power information of the first network device. The terminal obtains the network-side computing power information, including:

[0024] The terminal obtains a first computing power identifier, and obtains the computing power information of the first network device based on the first computing power identifier. There is a corresponding relationship between the first computing power identifier and the computing power information of the first network device.

[0025] In one possible design, the network-side computing power information includes the computing power information of the second network device. The terminal obtains the network-side computing power information, including:

[0026] The terminal obtains the second computing power identifier, and obtains the computing power information of the second network device based on the second computing power identifier. There is a corresponding relationship between the second computing power identifier and the computing power information of the second network device.

[0027] In one possible design, the network-side computing power information includes the computing power information of a first network device and the computing power information of a second network device. The terminal obtains the network-side computing power information, including:

[0028] The terminal obtains a first computing power identifier and a second computing power identifier, and obtains the computing power information of the first network device based on the first computing power identifier; there is a corresponding relationship between the first computing power identifier and the computing power information of the first network device.

[0029] The computing power information of the second network device is obtained based on the second computing power identifier, and there is a corresponding relationship between the second computing power identifier and the computing power information of the second network device.

[0030] In one possible design, the network-side computing power information includes the computing power information of the first network device, and the effective time for the terminal to obtain the network-side computing power information includes:

[0031] The terminal obtains the first effective time identifier, and obtains the effective time of the computing power information of the first network device based on the first effective time identifier. There is a corresponding relationship between the first effective time identifier and the effective time of the computing power information of the first network device.

[0032] In one possible design, the network-side computing power information includes the total computing power information of the first network device and the second network device. The effective time for the terminal to obtain the network-side computing power information includes:

[0033] The terminal obtains the second effective time identifier, and obtains the effective time of the total computing power information of the first network device and the second network device based on the second effective time identifier. There is a corresponding relationship between the second effective time identifier and the effective time of the total computing power information of the first network device and the second network device.

[0034] In one possible design, the network-side computing power information includes the computing power information of the second network device, and the effective time for the terminal to obtain the network-side computing power information includes:

[0035] The terminal obtains the third effective time identifier, and obtains the effective time of the computing power information of the second network device based on the third effective time identifier. There is a corresponding relationship between the third effective time identifier and the effective time of the computing power information of the second network device.

[0036] In one possible design, the network-side computing power information includes the computing power information of the first network device and the computing power information of the second network device. The effective time for the terminal to obtain the network-side computing power information includes:

[0037] The terminal obtains a first effective time identifier and a third effective time identifier. Based on the first effective time identifier, it obtains the effective time of the computing power information of the first network device. There is a corresponding relationship between the first effective time identifier and the effective time of the computing power information of the first network device. Based on the third effective time identifier, it obtains the effective time of the computing power information of the second network device. There is a corresponding relationship between the third effective time identifier and the effective time of the computing power information of the second network device.

[0038] In one possible design, the first message indicates the target task, which includes at least one of the following:

[0039] AI application request tasks, AI model training tasks, AI model fine-tuning tasks, and AI-based data transmission tasks.

[0040] Secondly, embodiments of this application provide a method for task execution in a communication system. This method is applied to the network side, such as access network equipment, modules (e.g., circuits, chips, or chip systems) within the access network equipment, or logical nodes, logical modules, or software capable of implementing all or part of the functions of the access network equipment.

[0041] Taking the application of this method to an access network device as an example, in this method, the first network device sends network-side computing power indication information and effective time indication information to the terminal, and receives a first message from the terminal. The first message is sent by the terminal based on the effective time of the network-side computing power information when it determines that the network side can meet the computing power requirements for executing the target task based on the network-side computing power information. The network-side computing power information is determined based on the network-side computing power indication information, and the effective time of the network-side computing power information is determined based on the effective time indication information. The first message is used to request the execution of the target task.

[0042] It can be seen that the terminal or server sends a message to the network side to request the execution of the target task based on the computing power information of the network side, so that the network side can execute the target task. This helps to alleviate the computing load of the terminal or server and makes full use of the computing power resources of the network side.

[0043] In one possible design, the method of this embodiment further includes: a first network device sending a second message to a terminal based on a first message, the second message including the execution result of the target task.

[0044] In one possible design, the first network device sends a second message to the terminal based on the first message, including:

[0045] The first network device determines whether its computing power information meets the computing power requirements for executing the target task. If it is determined that the computing power information of the first network device meets the computing power requirements for executing the target task, the first network device executes the target task to obtain the execution result of the target task.

[0046] Furthermore, the first network device sends a second message to the terminal based on the execution result of the target task.

[0047] In one possible design, the method of this embodiment further includes:

[0048] When the first network device determines that its computing power information does not meet the computing power requirements for executing the target task, it sends a third message to the second network device or the server. The third message is used to request the execution of the target task.

[0049] Furthermore, the first network device receives a fourth message from the second network device, the fourth message including the execution result of the target task.

[0050] It can be seen that the first network device executes the target task only when it determines that its computing power information meets the computing power requirements for executing the target task. If the computing power information of the first network device does not meet the computing power requirements for executing the target task, the first network device sends a message to the second network device to request the execution of the target task, so that the second network device can execute the target task. This not only ensures that the target task is executed, but also makes full use of the computing power resources of the second network device.

[0051] In one possible design, the network-side computing power indication information includes a first computing power level, and the effective time indication information includes a first effective time identifier. The method in this embodiment further includes:

[0052] The first network device obtains the computing power information of the first network device and the effective time of the computing power information, obtains the first computing power level based on the computing power information of the first network device, and there is a corresponding relationship between the computing power information of the first network device and the first computing power level; and obtains the first effective time identifier based on the effective time of the computing power information of the first network device, and there is a corresponding relationship between the first effective time identifier and the effective time of the computing power information of the first network device.

[0053] In one possible design, the network-side computing power indication information includes a third computing power level, and the effective time indication information includes a first effective time identifier and a third effective time identifier. The method in this embodiment further includes:

[0054] The first network device obtains the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device.

[0055] The first network device obtains a third computing power level based on the computing power information of the first network device and the computing power information of the second network device, and there is a correspondence between the computing power information of the first network device, the computing power information of the second network device and the third computing power level; a first effective time identifier is determined based on the effective time of the computing power information of the first network device, and there is a correspondence between the effective time of the computing power information of the first network device and the first effective time identifier; a third effective time identifier is determined based on the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier.

[0056] In one possible design, the network-side computing power indication information includes a first computing power level, and the effective time indication information includes a first effective time identifier. The method in this embodiment further includes:

[0057] The first network device obtains the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device.

[0058] If the effective time of the computing power information of the first network device is earlier than the effective time of the computing power information of the second network device, a first computing power level is obtained based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power level; a first effective time identifier is obtained based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device.

[0059] In one possible design, the network-side computing power indication information includes a second computing power level, and the effective time indication information includes a second effective time identifier, wherein the second effective time identifier is the effective time of the total computing power information of the first network device and the second network device. The method of this embodiment further includes:

[0060] The first network device obtains the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device.

[0061] If the effective time of the computing power information of the first network device is the same as the effective time of the computing power information of the second network device, the total computing power information of the first network device and the second network device is determined based on the computing power information of the first network device and the second network device. The second computing power level is obtained based on the total computing power information of the first network device and the second network device, and there is a correspondence between the total computing power information of the first network device and the second computing power level. The second effective time identifier is determined based on the effective time of the computing power information of the first network device or the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the first network device or the effective time of the computing power information of the second network device and the second effective time identifier.

[0062] In one possible design, the network-side computing power indication information includes a fourth computing power level, and the effective time indication information includes a third effective time identifier. The method in this embodiment further includes:

[0063] The first network device obtains the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device.

[0064] If the computing power information of the second network device takes effect earlier than the computing power information of the first network device, the first network device obtains the fourth computing power level based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the fourth computing power level; the third effective time identifier is determined based on the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier.

[0065] In one possible design, the network-side computing power indication information includes a first computing power identifier, and the effective time indication information includes a first effective time identifier. The method in this embodiment further includes:

[0066] The first network device obtains the computing power information of the first network device, and obtains the first computing power identifier based on the computing power information of the first network device. The computing power information of the first network device and the first computing power identifier have a corresponding relationship. The first effective time identifier is obtained based on the effective time of the computing power information of the first network device. The first effective time identifier has a corresponding relationship with the effective time of the computing power information of the first network device.

[0067] In one possible design, the network-side computing power indication information includes a first computing power identifier and a second computing power identifier, and the effective time indication information includes a first effective time identifier and a third effective time identifier. The method in this embodiment further includes:

[0068] The first network device obtains the computing power information of the first network device and the computing power information of the second network device, as well as the effective time of the computing power information of the first network device and the effective time of the computing power information of the second network device.

[0069] A first computing power identifier is obtained based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power identifier; a second computing power identifier is obtained based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the second computing power identifier; a first effective time identifier is determined based on the effective time of the computing power information of the first network device, and there is a correspondence between the effective time of the computing power information of the first network device and the first effective time identifier; a third effective time identifier is determined based on the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier.

[0070] In one possible design, the network-side computing power indication information includes a first computing power identifier, and the effective time indication information includes a first effective time identifier. The method in this embodiment further includes:

[0071] The first network device obtains the computing power information of the first network device and the computing power information of the second network device, as well as the effective time of the computing power information of the first network device and the effective time of the computing power information of the second network device.

[0072] If the effective time of the computing power information of the first network device is earlier than the effective time of the computing power information of the second network device, then the first computing power identifier is obtained based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power identifier; the first effective time identifier is obtained based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device.

[0073] In one possible design, the network-side computing power indication information includes a second computing power identifier, and the effective time indication information includes a third effective time identifier. The method in this embodiment further includes:

[0074] The first network device obtains the computing power information of the first network device and the computing power information of the second network device, as well as the effective time of the computing power information of the first network device and the effective time of the computing power information of the second network device.

[0075] If the effective time of the computing power information of the second network device is earlier than the effective time of the computing power information of the first network device, then a second computing power identifier is obtained based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the second computing power identifier; a third effective time identifier is obtained based on the effective time of the computing power information of the second network device, and there is a correspondence between the third effective time identifier and the effective time of the computing power information of the second network device.

[0076] In one possible design, the first message indicates the target task, which includes at least one of the following:

[0077] AI application request tasks, AI model training tasks, AI model fine-tuning tasks, and AI-based data transmission tasks.

[0078] Thirdly, embodiments of this application provide a method for task execution in a communication system, including:

[0079] The first network device sends network-side computing power indication information and computing power effective time indication information to the terminal;

[0080] The terminal obtains the computing power information of the network side based on the computing power indication information of the network side, and obtains the effective time of the computing power information of the network side based on the computing power effective time indication information;

[0081] The terminal sends a first message to the first network device based on the computing power information on the network side and the effective time of the computing power information. The first message is used to instruct the target model to execute the target task.

[0082] In one possible design, the method of this embodiment further includes: a first network device sending a second message to a terminal based on a first message, the second message including the execution result of the target task.

[0083] In one possible design, the network-side computing power indication information includes a first computing power level, and the effective time indication information includes a first effective time identifier. The method in this embodiment further includes:

[0084] The first network device obtains the computing power information of the first network device and the effective time of the computing power information, obtains the first computing power level based on the computing power information of the first network device, and there is a corresponding relationship between the computing power information of the first network device and the first computing power level; and obtains the first effective time identifier based on the effective time of the computing power information of the first network device, and there is a corresponding relationship between the first effective time identifier and the effective time of the computing power information of the first network device.

[0085] In one possible design, the network-side computing power indication information includes a third computing power level, and the effective time indication information includes a first effective time identifier and a third effective time identifier. The method in this embodiment further includes:

[0086] The first network device obtains the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device.

[0087] The first network device obtains a third computing power level based on the computing power information of the first network device and the computing power information of the second network device, and there is a correspondence between the computing power information of the first network device, the computing power information of the second network device and the third computing power level; a first effective time identifier is determined based on the effective time of the computing power information of the first network device, and there is a correspondence between the effective time of the computing power information of the first network device and the first effective time identifier; a third effective time identifier is determined based on the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier.

[0088] In one possible design, the network-side computing power indication information includes a first computing power level, and the effective time indication information includes a first effective time identifier. The method in this embodiment further includes:

[0089] The first network device obtains the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device.

[0090] If the effective time of the computing power information of the first network device is earlier than the effective time of the computing power information of the second network device, a first computing power level is obtained based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power level; a first effective time identifier is obtained based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device.

[0091] In one possible design, the network-side computing power indication information includes a second computing power level, and the effective time indication information includes a second effective time identifier, wherein the second effective time identifier is the effective time of the total computing power information of the first network device and the second network device. The method of this embodiment further includes:

[0092] The first network device obtains the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device.

[0093] If the effective time of the computing power information of the first network device is the same as the effective time of the computing power information of the second network device, the total computing power information of the first network device and the second network device is determined based on the computing power information of the first network device and the second network device. The second computing power level is obtained based on the total computing power information of the first network device and the second network device, and there is a correspondence between the total computing power information of the first network device and the second computing power level. The third effective time identifier is determined based on the effective time of the computing power information of the first network device or the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the first network device or the effective time of the computing power information of the second network device and the third effective time identifier.

[0094] In one possible design, the network-side computing power indication information includes a fourth computing power level, and the effective time indication information includes a third effective time identifier. The method in this embodiment further includes:

[0095] The first network device obtains the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device.

[0096] If the computing power information of the second network device takes effect earlier than the computing power information of the first network device, the first network device obtains the fourth computing power level based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the fourth computing power level; the third effective time identifier is determined based on the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier.

[0097] In one possible design, the network-side computing power indication information includes a first computing power identifier, and the effective time indication information includes a first effective time identifier. The method in this embodiment further includes:

[0098] The first network device obtains the computing power information of the first network device, and obtains the first computing power identifier based on the computing power information of the first network device. The computing power information of the first network device and the first computing power identifier have a corresponding relationship. The first effective time identifier is obtained based on the effective time of the computing power information of the first network device. The first effective time identifier has a corresponding relationship with the effective time of the computing power information of the first network device.

[0099] In one possible design, the network-side computing power indication information includes a first computing power identifier and a second computing power identifier, and the effective time indication information includes a first effective time identifier and a third effective time identifier. The method in this embodiment further includes:

[0100] The first network device obtains the computing power information of the first network device and the computing power information of the second network device, as well as the effective time of the computing power information of the first network device and the effective time of the computing power information of the second network device.

[0101] A first computing power identifier is obtained based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power identifier; a second computing power identifier is obtained based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the second computing power identifier; a first effective time identifier is determined based on the effective time of the computing power information of the first network device, and there is a correspondence between the effective time of the computing power information of the first network device and the first effective time identifier; a third effective time identifier is determined based on the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier.

[0102] In one possible design, the network-side computing power indication information includes a first computing power identifier, and the effective time indication information includes a first effective time identifier. The method in this embodiment further includes:

[0103] The first network device obtains the computing power information of the first network device and the computing power information of the second network device, as well as the effective time of the computing power information of the first network device and the effective time of the computing power information of the second network device.

[0104] If the effective time of the computing power information of the first network device is earlier than the effective time of the computing power information of the second network device, then the first computing power identifier is obtained based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power identifier; the first effective time identifier is obtained based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device.

[0105] In one possible design, the network-side computing power indication information includes a second computing power identifier, and the effective time indication information includes a third effective time identifier. The method in this embodiment further includes:

[0106] The first network device obtains the computing power information of the first network device and the computing power information of the second network device, as well as the effective time of the computing power information of the first network device and the effective time of the computing power information of the second network device.

[0107] If the effective time of the computing power information of the second network device is earlier than the effective time of the computing power information of the first network device, then a second computing power identifier is obtained based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the second computing power identifier; a third effective time identifier is obtained based on the effective time of the computing power information of the second network device, and there is a correspondence between the third effective time identifier and the effective time of the computing power information of the second network device.

[0108] In one possible design, the network-side computing power indication information includes a first computing power level, and the network-side computing power information includes the computing power information of a first network device. The terminal obtains the network-side computing power information based on the network-side computing power indication information, including:

[0109] The terminal obtains the computing power information of the first network device based on the first computing power level, and there is a corresponding relationship between the first computing power level and the computing power information of the first network device.

[0110] In one possible design, the network-side computing power indication information includes a second computing power level, and the network-side computing power information includes the total computing power information of the first network device and the second network device. The terminal obtains the network-side computing power information based on the network-side computing power indication information, including:

[0111] The terminal obtains the total computing power information of the first network device and the second network device based on the second computing power level, and there is a corresponding relationship between the second computing power level and the total computing power information of the first network device and the second network device.

[0112] In one possible design, the network-side computing power indication information includes a third computing power level, and the network-side computing power information includes the computing power information of the first network device and the computing power information of the second network device. The terminal obtains the network-side computing power information based on the network-side computing power indication information, including:

[0113] The terminal obtains the computing power information of the first network device and the second network device based on the third computing power level. There is a correspondence between the first computing power level and the computing power information of the first network device and the second network device.

[0114] In one possible design, the network-side computing power information includes the computing power information of the second network device. The terminal obtains the network-side computing power information based on the network-side computing power indication information, including:

[0115] The computing power information of the second network device is obtained based on the fourth computing power level, and there is a corresponding relationship between the fourth computing power level and the computing power information of the second network device.

[0116] In one possible design, the network-side computing power indication information includes a first computing power identifier, and the network-side computing power information includes the computing power information of a first network device. The terminal obtains the network-side computing power information based on the network-side computing power indication information, including:

[0117] The terminal obtains the computing power information of the first network device based on the first computing power identifier, and there is a corresponding relationship between the first computing power identifier and the computing power information of the first network device.

[0118] In one possible design, the network-side computing power indication information includes a second computing power identifier, and the network-side computing power information includes the computing power information of a second network device. The terminal obtains the network-side computing power information based on the network-side computing power indication information, including:

[0119] The terminal obtains the second computing power identifier, and obtains the computing power information of the second network device based on the second computing power identifier. There is a corresponding relationship between the second computing power identifier and the computing power information of the second network device.

[0120] In one possible design, the network-side computing power indication information includes a first computing power identifier and a second computing power identifier. The network-side computing power information includes the computing power information of a first network device and the computing power information of a second network device. The terminal obtains the network-side computing power information based on the network-side computing power indication information, including:

[0121] The terminal obtains the computing power information of the first network device based on the first computing power identifier; there is a correspondence between the first computing power identifier and the computing power information of the first network device; the terminal obtains the computing power information of the second network device based on the second computing power identifier; there is a correspondence between the second computing power identifier and the computing power information of the second network device.

[0122] In one possible design, the network-side computing power information includes the computing power information of the first network device, and the computing power activation time indication information includes a first activation time identifier. The terminal obtains the activation time of the network-side computing power information based on the computing power activation time indication information, including:

[0123] The terminal obtains the effective time of the computing power information of the first network device based on the first effective time identifier, and there is a corresponding relationship between the first effective time identifier and the effective time of the computing power information of the first network device.

[0124] In one possible design, the network-side computing power information includes the total computing power information of the first network device and the second network device, and the computing power activation time indication information includes a second activation time identifier. The terminal obtains the activation time of the network-side computing power information based on the computing power activation time indication information, including:

[0125] The terminal obtains the effective time of the total computing power information of the first network device and the second network device based on the second effective time identifier, and there is a corresponding relationship between the second effective time identifier and the effective time of the total computing power information of the first network device and the second network device.

[0126] In one possible design, the network-side computing power information includes the computing power information of the second network device, and the computing power activation time indication information includes a third activation time identifier. The terminal obtains the activation time of the network-side computing power information based on the computing power activation time indication information, including:

[0127] The terminal obtains the effective time of the computing power information of the second network device based on the third effective time identifier, and there is a corresponding relationship between the third effective time identifier and the effective time of the computing power information of the second network device.

[0128] In one possible design, the network-side computing power information includes the computing power information of a first network device and the computing power information of a second network device. The computing power activation time indication information includes a first activation time identifier and a third activation time identifier. The terminal obtains the activation time of the network-side computing power information based on the computing power activation time indication information, including:

[0129] The terminal obtains the effective time of the computing power information of the first network device based on the first effective time identifier, and there is a corresponding relationship between the first effective time identifier and the effective time of the computing power information of the first network device; it obtains the effective time of the computing power information of the second network device based on the third effective time identifier, and there is a corresponding relationship between the third effective time identifier and the effective time of the computing power information of the second network device.

[0130] In one possible design, the terminal sends a first message to the first network device based on the network-side computing power information and the effective time of the computing power information, including:

[0131] The terminal determines whether the network side meets the computing power requirements for executing the target task based on the computing power information on the network side. When it is determined that the network side meets the computing power requirements for executing the target task, the terminal sends a first message to the first network device based on the effective time of the computing power information on the network side.

[0132] In one possible design, the terminal sends a first message to the first network device based on the effective time of the network-side computing power information, including:

[0133] The terminal determines whether the effective time of the computing power information on the network side meets the time requirement for executing the target task. If the effective time of the computing power information on the network side meets the time requirement for executing the target task, the terminal sends a first message to the first network device; if the effective time of the computing power information on the network side does not meet the time requirement for executing the target task, the terminal does not send a first message to the first network device.

[0134] In one possible design, the first network device sends a second message to the terminal based on the first message, including:

[0135] The first network device determines whether its computing power information meets the computing power requirements for executing the target task. If it is determined that the computing power information of the first network device meets the computing power requirements for executing the target task, the first network device executes the target task to obtain the execution result of the target task.

[0136] Furthermore, the first network device sends a second message to the terminal based on the execution result of the target task.

[0137] In one possible design, the method of this embodiment further includes:

[0138] When the first network device determines that its computing power information does not meet the computing power requirements for executing the target task, it sends a third message to the second network device. The third message is used to request the execution of the target task.

[0139] Furthermore, the first network device receives a fourth message from the second network device, the fourth message including the execution result of the target task.

[0140] Fourthly, embodiments of this application provide a communication device that has the functions of the first aspect described above. For example, the communication device includes modules, units, or means corresponding to the operations involved in the first aspect. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0141] Fifthly, embodiments of this application provide a communication device that has the functions to implement the second aspect described above. For example, the communication device includes modules, units, or means corresponding to the operations involved in the second aspect described above. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0142] Sixthly, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the necessary computer program or instructions for implementing the functions described in the first aspect above. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the first aspect above. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0143] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0144] In one possible design, the communication device may also include the memory.

[0145] The aforementioned communication device may be a terminal, or a communication / processing module in the terminal, or a chip in the terminal responsible for communication functions such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a circuit or chip in the terminal responsible for processing functions (such as a GPU).

[0146] In a seventh aspect, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the necessary computer program or instructions for implementing the functions described in the second aspect above. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the second aspect above. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0147] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0148] In one possible design, the communication device may also include the memory.

[0149] The aforementioned communication device may be a terminal, or a communication / processing module in the terminal, or a chip in the terminal responsible for communication functions such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a circuit or chip in the terminal responsible for processing functions (such as a GPU).

[0150] Eighthly, embodiments of this application provide a communication system, including a terminal and a first network device.

[0151] The first network device is used to send network-side computing power indication information and computing power effective time indication information to the terminal;

[0152] The terminal is used to obtain network-side computing power information based on network-side computing power indication information.

[0153] The terminal is also used to obtain the effective time of computing power information on the network side based on the computing power effective time indication information;

[0154] The terminal is also used to send a first message to the first network device based on the computing power information on the network side and the effective time of the computing power information. The first message is used to instruct the target model to execute the target task.

[0155] In one possible design, the first network device is also used to send a second message to the terminal based on the first message, the second message including the execution result of the target task.

[0156] In one possible design, the network-side computing power indication information includes a first computing power level, and the effective time indication information includes a first effective time identifier.

[0157] The first network device is further configured to obtain computing power information of the first network device and the effective time of the computing power information, obtain a first computing power level based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power level; and obtain a first effective time identifier based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device.

[0158] In one possible design, the network-side computing power indication information includes a third computing power level, and the effective time indication information includes a first effective time identifier and a third effective time identifier.

[0159] The first network device is further configured to acquire computing power information of the first network device, the effective time of the computing power information of the first network device, computing power information of the second network device, and the effective time of the computing power information of the second network device; acquire a third computing power level based on the computing power information of the first network device and the computing power information of the second network device, wherein there is a correspondence between the computing power information of the first network device, the computing power information of the second network device, and the third computing power level; determine a first effective time identifier based on the effective time of the computing power information of the first network device, wherein there is a correspondence between the effective time of the computing power information of the first network device and the first effective time identifier; and determine a third effective time identifier based on the effective time of the computing power information of the second network device, wherein there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier.

[0160] In one possible design, the network-side computing power indication information includes a first computing power level, and the effective time indication information includes a first effective time identifier.

[0161] The first network device is further configured to acquire computing power information of the first network device, the effective time of the computing power information of the first network device, computing power information of the second network device, and the effective time of the computing power information of the second network device; if the effective time of the computing power information of the first network device is earlier than the effective time of the computing power information of the second network device, a first computing power level is acquired based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power level; a first effective time identifier is acquired based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device.

[0162] In one possible design, the network-side computing power indication information includes a second computing power level, and the effective time indication information includes a second effective time identifier, which is the effective time of the total computing power information of the first network device and the second network device.

[0163] The first network device is further configured to acquire computing power information of the first network device, the effective time of the computing power information of the first network device, computing power information of the second network device, and the effective time of the computing power information of the second network device; if the effective time of the computing power information of the first network device is the same as the effective time of the computing power information of the second network device, the total computing power information of the first network device and the second network device is determined based on the computing power information of the first network device and the computing power information of the second network device, and a second computing power level is acquired based on the total computing power information of the first network device and the second network device, and there is a correspondence between the total computing power information of the first network device and the second network device and the second computing power level; a second effective time identifier is determined based on the effective time of the computing power information of the first network device or the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the first network device or the effective time of the computing power information of the second network device and the second effective time identifier.

[0164] In one possible design, the network-side computing power indication information includes a fourth computing power level, and the effective time indication information includes a third effective time identifier.

[0165] The first network device is further configured to acquire computing power information of the first network device, the effective time of the computing power information of the first network device, computing power information of the second network device, and the effective time of the computing power information of the second network device; if the effective time of the computing power information of the second network device is earlier than the effective time of the computing power information of the first network device, a fourth computing power level is acquired based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the fourth computing power level; a third effective time identifier is determined based on the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier.

[0166] In one possible design, the network-side computing power indication information includes a first computing power identifier, and the effective time indication information includes a first effective time identifier.

[0167] The first network device is also used to obtain computing power information of the first network device, obtain a first computing power identifier based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power identifier; and obtain a first effective time identifier based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device.

[0168] In one possible design, the network-side computing power indication information includes a first computing power identifier and a second computing power identifier, and the effective time indication information includes a first effective time identifier and a third effective time identifier.

[0169] The first network device is further configured to acquire computing power information of the first network device and computing power information of the second network device, as well as acquire the effective time of the computing power information of the first network device and the effective time of the computing power information of the second network device; acquire a first computing power identifier based on the computing power information of the first network device, wherein there is a correspondence between the computing power information of the first network device and the first computing power identifier; acquire a second computing power identifier based on the computing power information of the second network device, wherein there is a correspondence between the computing power information of the second network device and the second computing power identifier; determine a first effective time identifier based on the effective time of the computing power information of the first network device, wherein there is a correspondence between the effective time of the computing power information of the first network device and the first effective time identifier; and determine a third effective time identifier based on the effective time of the computing power information of the second network device, wherein there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier.

[0170] In one possible design, the network-side computing power indication information includes a first computing power identifier, and the effective time indication information includes a first effective time identifier.

[0171] The first network device is further configured to acquire computing power information of the first network device and computing power information of the second network device, and to acquire the effective time of the computing power information of the first network device and the effective time of the computing power information of the second network device; if the effective time of the computing power information of the first network device is earlier than the effective time of the computing power information of the second network device, then a first computing power identifier is acquired based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power identifier; a first effective time identifier is acquired based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device.

[0172] In one possible design, the network-side computing power indication information includes a second computing power identifier, and the effective time indication information includes a third effective time identifier.

[0173] The first network device is further configured to acquire computing power information of the first network device and computing power information of the second network device, as well as acquire the effective time of the computing power information of the first network device and the effective time of the computing power information of the second network device; if the effective time of the computing power information of the second network device is earlier than the effective time of the computing power information of the first network device, then a second computing power identifier is acquired based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the second computing power identifier; a third effective time identifier is acquired based on the effective time of the computing power information of the second network device, and there is a correspondence between the third effective time identifier and the effective time of the computing power information of the second network device.

[0174] In one possible design, the network-side computing power indication information includes a first computing power level, and the network-side computing power information includes the computing power information of a first network device. The terminal is used to obtain the network-side computing power information based on the network-side computing power indication information, including:

[0175] The terminal is used to obtain the computing power information of the first network device based on the first computing power level, and there is a corresponding relationship between the first computing power level and the computing power information of the first network device.

[0176] In one possible design, the network-side computing power indication information includes a second computing power level, and the network-side computing power information includes the total computing power information of the first network device and the second network device. The terminal is used to obtain the network-side computing power information based on the network-side computing power indication information, including:

[0177] The terminal is used to obtain the total computing power information of the first network device and the second network device based on the second computing power level, and there is a corresponding relationship between the second computing power level and the total computing power information of the first network device and the second network device.

[0178] In one possible design, the network-side computing power indication information includes a third computing power level, and the network-side computing power information includes the computing power information of a first network device and the computing power information of a second network device. The terminal is used to obtain the network-side computing power information based on the network-side computing power indication information, including:

[0179] The terminal is used to obtain the computing power information of the first network device and the second network device based on the third computing power level. There is a correspondence between the first computing power level and the computing power information of the first network device and the second network device.

[0180] In one possible design, the network-side computing power information includes the computing power information of the second network device. The terminal is used to obtain the network-side computing power information based on the network-side computing power indication information, including:

[0181] The terminal is used to obtain the computing power information of the second network device based on the fourth computing power level, and there is a corresponding relationship between the fourth computing power level and the computing power information of the second network device.

[0182] In one possible design, the network-side computing power indication information includes a first computing power identifier, and the network-side computing power information includes the computing power information of a first network device. The terminal is used to obtain the network-side computing power information based on the network-side computing power indication information, including:

[0183] The terminal is used to obtain the computing power information of the first network device based on the first computing power identifier, and there is a corresponding relationship between the first computing power identifier and the computing power information of the first network device.

[0184] In one possible design, the network-side computing power indication information includes a second computing power identifier, and the network-side computing power information includes the computing power information of a second network device. The terminal is used to obtain the network-side computing power information based on the network-side computing power indication information, including:

[0185] The terminal is used to obtain the second computing power identifier and obtain the computing power information of the second network device based on the second computing power identifier. There is a corresponding relationship between the second computing power identifier and the computing power information of the second network device.

[0186] In one possible design, the network-side computing power indication information includes a first computing power identifier and a second computing power identifier. The network-side computing power information includes the computing power information of a first network device and the computing power information of a second network device. The terminal is used to obtain the network-side computing power information based on the network-side computing power indication information, including:

[0187] The terminal is used to obtain computing power information of a first network device based on a first computing power identifier; the first computing power identifier corresponds to the computing power information of the first network device; and to obtain computing power information of a second network device based on a second computing power identifier, the second computing power identifier corresponding to the computing power information of the second network device.

[0188] In one possible design, the network-side computing power information includes the computing power information of the first network device, and the computing power effective time indication information includes a first effective time identifier. The terminal is also used to obtain the effective time of the network-side computing power information based on the computing power effective time indication information, including:

[0189] The terminal is also used to obtain the effective time of the computing power information of the first network device based on the first effective time identifier, and there is a corresponding relationship between the first effective time identifier and the effective time of the computing power information of the first network device.

[0190] In one possible design, the network-side computing power information includes the total computing power information of the first network device and the second network device, and the computing power effective time indication information includes a second effective time identifier. The terminal is also used to obtain the effective time of the network-side computing power information based on the computing power effective time indication information, including:

[0191] The terminal is also used to obtain the effective time of the total computing power information of the first network device and the second network device based on the second effective time identifier, and there is a corresponding relationship between the second effective time identifier and the effective time of the total computing power information of the first network device and the second network device.

[0192] In one possible design, the network-side computing power information includes the computing power information of the second network device, and the computing power effective time indication information includes a third effective time identifier. The terminal is also used to obtain the effective time of the network-side computing power information based on the computing power effective time indication information, including:

[0193] The terminal is also used to obtain the effective time of the computing power information of the second network device based on the third effective time identifier, and there is a corresponding relationship between the third effective time identifier and the effective time of the computing power information of the second network device.

[0194] In one possible design, the network-side computing power information includes the computing power information of a first network device and the computing power information of a second network device. The computing power activation time indication information includes a first activation time identifier and a third activation time identifier. The terminal is also used to obtain the activation time of the network-side computing power information based on the computing power activation time indication information, including:

[0195] The terminal is also used to obtain the effective time of the computing power information of the first network device based on the first effective time identifier, and there is a corresponding relationship between the first effective time identifier and the effective time of the computing power information of the first network device; and to obtain the effective time of the computing power information of the second network device based on the third effective time identifier, and there is a corresponding relationship between the third effective time identifier and the effective time of the computing power information of the second network device.

[0196] In one possible design, the terminal is also used to send a first message to the first network device based on network-side computing power information and the effective time of the computing power information, including:

[0197] The terminal is also used to determine whether the network side meets the computing power requirements for executing the target task based on the computing power information on the network side. When it is determined that the network side meets the computing power requirements for executing the target task, the terminal is used to send a first message to the first network device based on the effective time of the computing power information on the network side.

[0198] In one possible design, the terminal sends a first message to the first network device based on the effective time of the network-side computing power information, including:

[0199] The terminal is used to determine whether the effective time of the computing power information on the network side meets the terminal's execution time requirements for the target task. If the effective time of the computing power information on the network side meets the time requirements for executing the target task, the terminal sends a first message to the first network device; if the effective time of the computing power information on the network side does not meet the time requirements for executing the target task, the terminal does not send a first message to the first network device.

[0200] In one possible design, the first network device is further configured to send a second message to the terminal based on the first message, including:

[0201] The first network device is further configured to determine the computing power information of the first network device, and based on whether the computing power information of the first network device meets the computing power requirements for executing the target task, execute the target task when it is determined that the computing power information of the first network device meets the computing power requirements for executing the target task, so as to obtain the execution result of the target task.

[0202] Furthermore, the first network device is also used to send a second message to the terminal based on the execution result of the target task, the second message including the execution result of the target task.

[0203] In one possible design, the first network device is also configured to send a third message to the second network device when it is determined that the computing power information of the first network device does not meet the computing power requirements for executing the target task. The third message is used to request the execution of the target task.

[0204] Furthermore, the first network device is also used to receive a fourth message from the second network device, the fourth message including the execution result of the target task.

[0205] Ninthly, this application provides a computer-readable storage medium storing computer-readable instructions that, when read and executed by a computer, cause the computer to perform any of the possible designs in the first to second aspects described above.

[0206] In a tenth aspect, this application provides a computer program product that, when read and executed by a computer, causes the computer to perform any of the possible designs in the first to second aspects described above.

[0207] It is understood that the beneficial effects of the embodiments described in the third to tenth aspects can be referred to the beneficial effects of the methods described in the first to second aspects, and will not be repeated here. Attached Figure Description

[0208] Figure 1a is a schematic diagram illustrating one possible, non-limiting system;

[0209] Figures 1b and 1c are schematic diagrams of possible application frameworks in a communication system;

[0210] Figures 2 and 3 are schematic flowcharts of a task execution method in a communication system provided in an embodiment of this application;

[0211] Figure 4 is an interactive flowchart illustrating the task execution method in the communication system provided in an embodiment of this application;

[0212] Figures 5-7 are schematic diagrams of the communication system provided in the embodiments of this application;

[0213] Figure 8 shows a possible exemplary block diagram of the communication device involved in the embodiments of this application;

[0214] Figure 9 is a schematic diagram of the structure of a communication device provided in an embodiment of this application. Detailed Implementation

[0215] The embodiments of this application will now be described with reference to the accompanying drawings.

[0216] Figure 1a is a schematic diagram illustrating one possible, non-limiting system. As shown in Figure 1a, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. RAN 100 includes at least one RAN node (110a and 110b in Figure 1a, collectively referred to as 110) and at least one terminal (120a-120j in Figure 1a, collectively referred to as 120). RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1a). Terminal 120 is wirelessly connected to RAN node 110. RAN node 110 is wirelessly or wired connected to core network 200. The core network equipment in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0217] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or future-oriented evolution systems (such as 6G mobile communication systems). RAN 100 can also be an open access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0218] RAN node 110, sometimes referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and assists terminals in achieving wireless access. Multiple RAN nodes 110 in communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative. For example, network element 120i in Figure 1a can be a helicopter or drone, which can be configured as a mobile base station. For terminals 120j accessing RAN 100 through network element 120i, network element 120i is a base station; however, for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes both referred to as communication devices. For example, network elements 110a and 110b in Figure 1a can be understood as communication devices with base station functions, and network elements 120a-120j can be understood as communication devices with terminal functions.

[0219] In one possible scenario, the RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a next-generation base station in a 6th-generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. The RAN node can be a macro base station (as shown in Figure 1a, 110a), a micro base station or indoor station (as shown in Figure 1a, 110b), a relay node or donor node, or a radio controller in a CRAN scenario. Optionally, the RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). All or part of the functions of the RAN node in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). The RAN node may also include communication modules, circuits, or chips that perform corresponding communication functions. The RAN node may also be configured with program instructions for performing these functions, as well as corresponding program instructions. The RAN node in this application may also be a logic node, logic module, or software capable of implementing all or part of the RAN node's functions.

[0220] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with each RAN node performing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be separate entities or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0221] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0222] A terminal can be a device or module that accesses the aforementioned communication system and has corresponding communication functions. A terminal can also be called a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, etc. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, smart home devices, transportation vehicles with wireless communication capabilities, communication modules, etc. The embodiments of this application do not limit the device form of the terminal. A terminal typically contains a communication module, circuit, or chip that performs the corresponding communication function. The terminal can also be configured with program instructions for performing the corresponding communication function.

[0223] To support artificial intelligence (AI) technology in wireless networks, AI nodes may also be introduced into the network.

[0224] AI nodes can be deployed in one or more of the following locations within the communication system: access network nodes (RAN nodes), terminal devices, or core network devices. Alternatively, AI nodes can be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an over-the-top (OTT) system. AI nodes can communicate with other devices in the communication system, which can be one or more of the following: network devices, terminal devices, or core network elements.

[0225] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0226] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0227] AI nodes can be AI network elements or AI modules.

[0228] Figure 1b is a schematic diagram of a possible application framework in a communication system. As shown in Figure 1b, network elements in the communication system are connected through interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in operations administration and maintenance (OAM), are equipped with one or more AI modules (only one is shown in Figure 1b for clarity). Access network nodes can be single RAN nodes or can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be equipped with one or more AI modules. The CU can also be split into CU-CP and CU-UP, and one or more AI modules are installed in the CU-CP and / or CU-UP.

[0229] AI modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. The models of AI modules can achieve different functions depending on the parameter configurations. The models of AI modules can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the biases of the neural network.

[0230] In one example, the neural network mentioned above can be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), or a generative adversarial network (GAN).

[0231] Deep Neural Networks (DNNs) are artificial neural network architectures with multiple layers of nonlinear transformation units stacked in a hierarchical structure to form deep computational models. Compared to shallow neural networks, deep neural networks have more hidden layers, allowing the network model to capture more complex data structures and higher-level abstract features.

[0232] A CNN is a deep neural network with a convolutional structure. A CNN contains a feature extractor consisting of convolutional layers and subsampling layers. This feature extractor can be viewed as a filter, and the convolution process can be seen as performing convolution between a trainable filter and an input image or a convolutional feature map.

[0233] RNN is a type of recursive neural network that takes sequence data as input, recursively moves along the direction of sequence evolution, and connects all nodes (recurrent units) in a chain-like manner.

[0234] GAN is a deep learning model. It consists of a generator and a discriminator, and is trained through adversarial learning. Its purpose is to estimate the potential distribution of data samples and generate new data samples.

[0235] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0236] Figure 1c illustrates a possible application framework in a communication system. As shown in Figure 1c, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​module shown in Figure 1b, used to implement AI-related functions. RICs include near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0237] Near real-time (NRT) RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. NRT RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data. NRT RICs can deliver inference results to RAN nodes and / or terminals. Inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, a NRT RIC delivers an inference result to a DU, which then forwards it to an RU.

[0238] Non-real-time RICs are also used for model training and inference. For example, they are used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to RAN nodes and / or terminals. Inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, a non-real-time RIC delivers inference results to a DU, which then forwards them to an RU.

[0239] Near real-time RICs and non-real-time RICs can also be configured as separate network elements. Near real-time RICs and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be set in RAN nodes (e.g., CU, DU), while non-real-time RICs can be set in OAM, cloud servers, core network devices, or other network devices.

[0240] In this application, "sending information" can be understood as one device sending information to another device, or it can also be understood as one logical module within a device sending information to another logical module. For example, "access network device sending information" can be understood as the access network device sending information to another device (such as a terminal), or it can be understood as logical module 1 in the access network device sending information to logical module 2 in the access network device.

[0241] In this application, "receiving information" can be understood as one device receiving information from another device, or it can also be understood as a logical module within a device receiving information from another logical module. For example, "access network device receiving information" can be understood as the access network device receiving information from another device (such as a terminal), or it can be understood as logical module 1 in the access network device receiving information from logical module 2 in the access network device.

[0242] In this application, phrases such as "sending information to... (e.g., a terminal)" or related illustrations in the accompanying drawings can be understood as indicating that the destination of the information is a terminal. This can include sending information directly or indirectly to a terminal. Similarly, phrases such as "receiving information from... (e.g., a terminal)," "receiving information from... (e.g., a terminal)," or "receiving information sent by (e.g., a terminal)," or related illustrations in the accompanying drawings, can be understood as indicating that the source of the information is a terminal. This can include receiving information directly or indirectly from a terminal. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be interpreted similarly and will not be elaborated further here.

[0243] Referring to Figure 2, which is a flowchart illustrating a task execution method in a communication system according to an embodiment of this application, this method can be applied to the terminal shown in Figures 1a, 1b, or 1c, or it can be implemented by a communication / processing module in the terminal or by circuits or chips (such as a modem chip (also known as a baseband chip), a SoC chip containing a modem core, a SIP chip, or a GPU) responsible for communication / processing functions in the terminal. This method can also be applied to a server, or it can be implemented by a communication / processing module in the server or by circuits or chips (such as a computing core, MCU, ASIC, FPGA, AI processor, CPU, GPU, or NPU) responsible for communication / processing functions in the server.

[0244] Taking the terminal implementation of this method as an example, as shown in Figure 2, the method includes:

[0245] S201. The terminal obtains the computing power information from the network side and the effective time of the computing power information.

[0246] The effective time of network device computing power information refers to the effective time of the network device's computing power status. For example, if the network-side computing power information is the first computing power information, the corresponding effective time is the first time period. That is to say, during the first time period, the network-side computing power information is the first computing power information.

[0247] In one example, the effective time of computing power information can be represented solely by the start time of its effectiveness. This indicates that the computing power information takes effect from the start time of its effectiveness, and the duration of effectiveness is not limited. In another example, the effective time of computing power information can be represented by both the start time of its effectiveness and the duration of effectiveness.

[0248] Optionally, the network-side computing power information can be the remaining computing power information on the network side, or information about the computing needs that the network side can support, or information related to computing power on the network side; these are not limited here. In one example, the remaining computing power information includes the remaining computing power size and the remaining memory size.

[0249] It should be noted that the "network side" here refers to the network connecting the terminal and another device, and the computing power information on the network side refers to the computing power information of the network devices in that network. The other device can be a terminal or a server. This network includes one or more network devices, such as access network devices, core network devices, fixed network devices, and WiFi devices.

[0250] In one possible design, the network-side computing power information includes the computing power information of a first network device. The terminal obtains a first computing power level and, based on this first computing power level, obtains the computing power information of the first network device. There is a correspondence between the first computing power level and the computing power information of the first network device. In other words, the terminal pre-stores the correspondence between computing power levels and the computing power information of network devices, and determines the computing power information of the first network device corresponding to the first computing power level based on this correspondence.

[0251] In one example, Table 1 below illustrates the correspondence between computing power levels and the remaining computing power information of network devices, where the remaining computing power information includes remaining computing power and remaining memory.

[0252] Table 1

[0253] It should be noted that TOPS represents the number of operations performed per second (1 trillion). The unit of computing power can also be FLOPS, where 1 TFLOPS represents the number of floating-point operations performed per second (1 trillion).

[0254] In one possible design, the network side includes a first network device and a second network device. The computing power information on the network side includes the total computing power information of the first and second network devices. The terminal obtains a second computing power level and, based on the second computing power level, obtains the total computing power information of the first and second network devices. There is a correspondence between the first computing power level and the total computing power information of the first and second network devices. In other words, the terminal pre-stores the correspondence between computing power levels and the total computing power information of network devices, and determines the total computing power information of the first and second network devices corresponding to the second computing power level based on this correspondence.

[0255] In one possible design, the network side includes a first network device and a second network device. The computing power information on the network side includes the computing power information of the first network device and the second network device. The terminal obtains a third computing power level, and based on the third computing power level, obtains the computing power information of the first network device and the second network device. There is a correspondence between the first computing power level and the computing power information of the first and second network devices. In other words, the terminal pre-stores the correspondence between the computing power level and the computing power information of the first and second network devices, and determines the computing power information of the first and second network devices corresponding to the third computing power level based on this correspondence.

[0256] In one example, Table 2 below illustrates the correspondence between computing power level and the remaining computing power information of the first network device and the remaining computing power information of the second network device. The remaining computing power information includes the remaining computing power and the remaining memory.

[0257] Table 2

[0258] In one possible design, the network-side computing power information includes the computing power information of the second network device. The terminal obtains a fourth computing power level and, based on this fourth computing power level, obtains the computing power information of the second network device. There is a correspondence between the fourth computing power level and the computing power information of the second network device. In other words, the terminal pre-stores the correspondence between computing power levels and the computing power information of network devices, and determines the computing power information of the second network device corresponding to the fourth computing power level based on this correspondence.

[0259] In one possible design, the network-side computing power information includes the computing power information of a first network device. The terminal obtains a first computing power identifier and, based on the first computing power identifier, obtains the computing power information of the first network device. There is a correspondence between the first computing power identifier and the computing power information of the first network device. In other words, the terminal pre-stores the correspondence between computing power identifiers and the computing power information of network devices, and the terminal determines the computing power information of the first network device corresponding to the first computing power identifier based on the correspondence between the computing power identifier and the computing power information of network devices.

[0260] In one example, the computing power information mentioned above refers to remaining computing power information, which includes remaining computing power and remaining memory. The first computing power identifier includes a first remaining computing power identifier and a first remaining memory identifier.

[0261] In one possible design, the network-side computing power information includes the computing power information of the second network device. The terminal obtains a fourth computing power identifier and, based on this identifier, retrieves the computing power information of the second network device. There is a correspondence between the fourth computing power identifier and the computing power information of the second network device. In other words, the terminal pre-stores the correspondence between computing power identifiers and the computing power information of network devices, and determines the computing power information of the second network device corresponding to the fourth computing power identifier based on this correspondence.

[0262] In one possible design, the network-side computing power information includes the computing power information of a first network device and a second network device. The terminal obtains a first computing power identifier and a second computing power identifier, and obtains the computing power information of the first network device based on the first computing power identifier; there is a correspondence between the first computing power identifier and the computing power information of the first network device. Similarly, the terminal obtains the computing power information of the second network device based on the second computing power identifier, and there is a correspondence between the second computing power identifier and the computing power information of the second network device. In other words, the terminal pre-stores the correspondence between computing power identifiers and the computing power information of network devices, and determines the computing power information of the first network device corresponding to the first computing power identifier and the computing power information of the second network device corresponding to the second computing power identifier based on this correspondence.

[0263] In one possible design, the network-side computing power information includes the computing power information of a first network device. The terminal obtains a first effective time identifier and, based on this identifier, determines the effective time of the computing power information of the first network device. There is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device. In other words, the terminal pre-stores the correspondence between the effective time identifier and the effective time of the computing power information of the network device, and determines the effective time of the computing power information of the first network device corresponding to the first effective time identifier based on this correspondence.

[0264] In one example, Table 3 below illustrates the correspondence between the effective time identifier and the effective time of the computing power information of the network device.

[0265] Table 3

[0266] It should be noted that the above effective time is after the current moment, meaning that the computing power information is valid from the current moment onwards; the above effective time is 30 minutes later, meaning that the computing power information is valid 30 minutes after the current moment; similarly, the above effective time is 1 hour later, meaning that the computing power information is valid 1 hour after the current moment; and the above effective time is 4 hours later, meaning that the computing power information is valid 4 hours after the current moment.

[0267] In one possible design, the network-side computing power information includes the computing power information of a second network device. The terminal obtains a third effective time identifier and, based on this identifier, determines the effective time of the second network device's computing power information. There is a correspondence between the third effective time identifier and the effective time of the second network device's computing power information. In other words, the terminal pre-stores the correspondence between effective time identifiers and the effective times of network device computing power information, and determines the effective time of the second network device's computing power information corresponding to the third effective time identifier based on this correspondence.

[0268] In one possible design, the network-side computing power information includes the computing power information of a first network device and a second network device. The terminal obtains a first effective time identifier and a third effective time identifier. Based on the first effective time identifier, it obtains the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device. Based on the third effective time identifier, it obtains the effective time of the computing power information of the second network device, and there is a correspondence between the third effective time identifier and the effective time of the computing power information of the second network device. In other words, the terminal pre-stores the correspondence between effective time identifiers and the effective times of computing power information of network devices. The terminal determines the effective time of the computing power information of the first network device corresponding to the first effective time identifier based on the correspondence between the effective time identifiers and the effective times of the computing power information of network devices. The terminal also determines the effective time of the computing power information of the second network device corresponding to the third effective time identifier based on the correspondence between the effective time identifiers and the effective times of the computing power information of network devices.

[0269] In one possible design, the network-side computing power information includes the total computing power information of a first network device and a second network device. The terminal obtains a second effective time identifier and, based on this identifier, determines the effective time of the total computing power information of the first and second network devices. There is a correspondence between the second effective time identifier and the effective time of the total computing power information of the first and second network devices. In other words, the terminal pre-stores the correspondence between the effective time identifier and the effective time of the total computing power information of the network devices, and determines the effective time of the total computing power information of the first and second network devices corresponding to the second effective time identifier based on this correspondence.

[0270] In one example, the computing power information mentioned above refers to remaining computing power information, which includes remaining computing power and remaining memory. The first computing power identifier includes a first remaining computing power identifier and a first remaining memory identifier, and the second computing power identifier includes a second remaining computing power identifier and a second remaining memory identifier.

[0271] In one possible design, the aforementioned computing power level (including the first, second, and third computing power levels), computing power identifier (including the first and second computing power identifiers), or effective time identifier (including the first, second, and third effective time identifiers) originates from the first network device. The first network device periodically sends messages carrying the aforementioned computing power level or computing power identifier to the terminal, or sends such messages to the terminal upon receiving a computing power request from the terminal. The messages carrying the aforementioned computing power level, computing power identifier, or effective time identifier can be downlink control information (DCI) signaling, media access control (MAC)-control element (CE) signaling, or radio resource control (RRC) signaling.

[0272] In one example, the aforementioned computing power identifier or effective time identifier is carried in an existing or newly added field in DCI signaling, MAC-CE signaling, or RRC signaling.

[0273] S202. The terminal sends a first message to the first network device based on the computing power information on the network side and the effective time of the computing power information. The first message is used to request the execution of the target task.

[0274] The target tasks include at least one of the following: AI application request task, AI model training task, AI model fine-tuning task, and AI-based data transmission task.

[0275] In one example, an AI application request task could be a text generation request, an image generation request, a video generation request, an object detection request, an object recognition request, or an object statistics request, etc. For each AI application request task, the network device needs to return the corresponding execution result to the terminal.

[0276] An AI model training task is a task used to train an AI model. This task includes at least one of the following parameters: training samples, AI model identifiers, training epochs, or training duration. For an AI model training task, the network device needs to return the corresponding execution result (i.e., the parameters of the trained model) to the terminal.

[0277] AI model fine-tuning tasks are used to fine-tune the architecture and / or parameters of AI models. An AI model fine-tuning task includes at least one of the following parameters: training samples, AI model identifier, initial parameters, adjusted model architecture, training epochs, or training duration. For AI model fine-tuning tasks, the network device needs to return the corresponding execution result (i.e., the parameters of the fine-tuned model) to the terminal.

[0278] AI-based data transmission tasks refer to tasks that process the transmitted data, such as super-resolution of low-resolution images / videos, interference removal / preprocessing of data samples, and semantic data restoration. For AI-based data transmission tasks, there is no need to send the execution result back to the terminal; it is only necessary to transmit the execution result to the designated recipient.

[0279] In one possible design, the terminal determines whether the network side meets the computing power requirements for executing the target task based on the computing power information. If the network side meets the computing power requirements, the terminal determines whether the effective time of the computing power information on the network side meets the time requirements for executing the target task. If the effective time of the computing power information on the network side meets the time requirements for executing the target task, the terminal sends a first message to the first network device. If the effective time of the computing power information on the network side does not meet the time requirements for executing the target task, the terminal does not send the first message to the first network device. If the computing power information on the network side determines that the network side cannot meet the computing power requirements for executing the target task, the terminal does not perform subsequent actions, i.e., S202 and S203.

[0280] Specifically, the terminal acquires the target task, which can be determined based on user instructions. For example, if the user instruction detected by the terminal is an object detection instruction, the target task is an object detection task; if the user instruction detected by the terminal is an object classification instruction, the target task is a classification task. The terminal pre-stores a correspondence between target tasks and target models, and can determine the target model based on the target task. For example, the object detection task corresponds to the ResNet-34 model, the classification task corresponds to the ResNet-50 model, the content generation task corresponds to the Stable-Diffsion-V2 model, and the prediction task corresponds to the VGG-16 model.

[0281] Different models are used to execute different tasks, and the computing power requirements vary. After determining the target model to be called to execute the target task, the terminal determines the computing power information required to execute the target task using the target model. If the computing power information on the network side is determined to meet the computing power requirements for executing the target task based on the computing power information required to execute the target task, then it is determined whether the effective time of the computing power information on the network side meets the time requirements for executing the target task. If it is determined that the effective time of the computing power information on the network side meets the time requirements for executing the target task, the terminal sends a first message to the first network device; if it is determined that the effective time of the computing power information on the network side does not meet the time requirements for executing the target task, the terminal does not send a first message to the first network device.

[0282] For example, if a terminal needs to execute a target task 20 minutes from the current time, and the network-side computing power information becomes effective after the current time, it means that the effective time of the network-side computing power information meets the time requirement for executing the target task. In this case, the terminal sends a first message to the first network device to request the network side to execute the target task. If the network-side computing power information becomes effective 30 minutes from the current time, it means that the effective time of the network-side computing power information does not meet the time requirement for executing the target task. In this case, the terminal does not send a first message to the first network device, that is, it does not request the network side to execute the target task.

[0283] It should be noted that when the terminal sends the first message to the first network device based on the effective time of the computing power information on the network side, it means that the terminal sends the first message to the first network device before the computing power information on the network side becomes effective, or the terminal sends the first message to the first network device while the computing power information on the network side is in effect.

[0284] S203, The terminal receives a second message from the first network device, the second message including the execution result of the target task.

[0285] It should be noted that S203 is optional. The results of some tasks need to be returned to the terminal, while the results of others do not. For example, the results of object detection tasks need to be returned to the terminal, while the results of AI-based data transmission tasks do not need to be returned to the terminal.

[0286] As can be seen, in this embodiment, the terminal sends a message to the network side requesting the execution of a target task based on the network side's computing power information. This helps alleviate the terminal's computing load and ensures full utilization of the network side's computing resources. Furthermore, the terminal only sends the first message requesting the execution of the target task to the first network device after determining that the network side's computing power information can meet the computing power requirements for executing the target task. This ensures that the target task is executed smoothly.

[0287] Referring to Figure 3, Figure 3 is a flowchart illustrating a task execution method in a communication system according to an embodiment of this application. This method is applied to a first network device, which can be the RAN node or core network device in Figure 1a, or the access network node or core network device in Figure 1b, or the access network node in Figure 1c. This method can also be implemented by modules (e.g., circuits, chips, or chip systems) in the first network device, or by logic nodes, logic modules, or software capable of implementing all or part of the functions of the first network device. Taking the implementation of this method by the first network device as an example, as shown in Figure 3, the method includes:

[0288] S301. The first network device sends network-side computing power indication information and effective time indication information to the terminal.

[0289] Among them, the network-side computing power indication information is used to indicate the computing power information on the network side, and the effective time indication information is used to indicate the effective time of the computing power information on the network side.

[0290] In one example, the effective time of computing power information can be represented solely by the start time of its effectiveness. This indicates that the computing power information takes effect from the start time of its effectiveness, with no limit on the duration of effectiveness. In this case, the effective time indication information is the indication of the start time of effectiveness. In another example, the effective time of computing power information can be represented by both the start time of its effectiveness and the duration of effectiveness. In this case, the effective time indication information includes both the indication of the start time of effectiveness and the indication of the duration of effectiveness.

[0291] Specifically, the first network device obtains the computing power indication information and the effective time indication information from the network side, including the following methods:

[0292] Method 1: When the network side includes a first network device, the first network device obtains its own computing power information and the effective time of that computing power information. Based on the computing power information, it obtains a first computing power level, and there is a correspondence between the computing power information and the first computing power level. The first network device obtains a first effective time identifier based on the effective time of its own computing power information, and there is a correspondence between the first effective time identifier and the effective time of its own computing power information. In other words, the first network device pre-stores the correspondence between computing power level and network device computing power information, as well as the correspondence between effective time and effective time identifier. Based on the correspondence between computing power level and network device computing power information, it determines the first computing power level corresponding to the first network device's computing power information. Based on the correspondence between effective time and effective time identifier, it determines the first effective time identifier corresponding to the effective time of the first network device's computing power information. The computing power indication information on the network side includes the first computing power level; the effective time indication information includes the first effective time identifier.

[0293] Method 2: When the network side includes a first network device and a second network device, the first network device obtains the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device.

[0294] The first network device obtains a third computing power level based on the computing power information of the first network device and the computing power information of the second network device, and there is a correspondence between the computing power information of the first network device, the computing power information of the second network device, and the third computing power level; a first effective time identifier is determined based on the effective time of the computing power information of the first network device, and there is a correspondence between the effective time of the computing power information of the first network device and the first effective time identifier; a third effective time identifier is determined based on the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier; in other words, the first network device stores the computing power level and the computing power information of the first network device and the second network device. The network device's computing power information correspondence relationship; the first network device obtains the computing power information of the first network device and the third computing power level corresponding to the computing power information of the second network device based on the correspondence relationship between the computing power level and the computing power information of the first network device and the computing power information of the second network device; the first network device stores the correspondence relationship between the effective time and the effective time identifier, and the first network device obtains the first effective time corresponding to the computing power information of the first network device and the third effective time corresponding to the computing power information of the second network device based on the correspondence relationship between the effective time and the effective time identifier; the computing power indication information on the network side includes the third computing power level, and the effective time indication information includes the first effective time identifier and the third effective time identifier.

[0295] Method 3: When the network side includes a first network device and a second network device, the first network device obtains its own computing power information, the effective time of its computing power information, the computing power information of the second network device, and the effective time of the computing power information of the second network device. If the effective time of the computing power information of the first network device is earlier than that of the computing power information of the second network device, a first computing power level is obtained based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power level. A first effective time identifier is obtained based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device. In other words, the first network device pre-stores the correspondence between computing power level and computing power information of the network device, and the correspondence between effective time and effective time identifier. Based on the correspondence between computing power level and computing power information of the network device, the first computing power level corresponding to the computing power information of the first network device is determined. Based on the correspondence between effective time and effective time identifier, the first effective time identifier corresponding to the effective time of the computing power information of the first network device is determined. The computing power indication information on the network side includes the first computing power level; the effective time indication information includes the first effective time identifier.

[0296] Method 4: When the network side includes a first network device and a second network device, the first network device obtains the computing power information of both the first and second network devices, as well as the effective time of the computing power information of the first and second network devices. If the effective time of the computing power information of the first and second network devices is the same, the first network device determines the total computing power information of the first and second network devices based on the computing power information of the first and second network devices. Based on the total computing power information of the first and second network devices, a second computing power level is obtained, and there is a correspondence between the total computing power information of the first and second network devices and the second computing power level. A second effective time identifier is determined based on the effective time of the computing power information of the first or second network device, and there is a correspondence between the effective time of the computing power information of the first or second network device and the second computing power level. In other words, the first network device pre-stores the correspondence between computing power level and total computing power information of the network device, as well as the correspondence between effective time and effective time identifier. Based on the correspondence between computing power identifier and computing power information of the network device, the second computing power level corresponding to the total computing power information of the first and second network devices is determined. Based on the correspondence between effective time and effective time identifier, the effective time of computing power information of the first network device or the effective time of computing power information of the second network device corresponding to the second effective time identifier is obtained. The computing power indication information on the network side includes the second computing power level, and the effective time indication information includes the second effective time identifier.

[0297] It should be noted that the effective time of the computing power information of the first network device or the effective time of the computing power information of the second network device can be regarded as the effective time of the total computing power information of the first network device and the second network device.

[0298] Method 5: When the network side includes a first network device and a second network device, the first network device obtains its own computing power information, the effective time of its own computing power information, the computing power information of the second network device, and the effective time of the second network device's computing power information. If the effective time of the second network device's computing power information is earlier than that of the first network device, a fourth computing power level is obtained based on the second network device's computing power information, and there is a correspondence between the second network device's computing power information and the fourth computing power level. A third effective time identifier is obtained based on the effective time of the second network device's computing power information, and there is a correspondence between the third effective time identifier and the effective time of the second network device's computing power information. In other words, the first network device pre-stores the correspondence between computing power levels and the network device's computing power information, as well as the correspondence between effective time and effective time identifier. Based on the correspondence between computing power levels and the network device's computing power information, the fourth computing power level corresponding to the second network device's computing power information is determined. Based on the correspondence between effective time and effective time identifier, the third effective time identifier corresponding to the effective time of the second network device's computing power information is determined. The computing power indication information on the network side includes the fourth computing power level; the effective time indication information includes the third effective time identifier.

[0299] Method Six: When the network side includes a first network device, the first network device obtains its own computing power information and the effective time of that computing power information. Based on the computing power information, it obtains a first computing power identifier, and there is a correspondence between the computing power information and the first computing power identifier. The first network device obtains a first effective time identifier based on the effective time of its own computing power information, and there is a correspondence between the first effective time identifier and the effective time of its own computing power information. In other words, the first network device pre-stores the correspondence between the computing power identifier and the network device's computing power information, as well as the correspondence between the effective time and the effective time identifier. Based on the correspondence between the computing power identifier and the network device's computing power information, it determines the first computing power identifier corresponding to the first network device's computing power information. Based on the correspondence between the effective time and the effective time identifier, it determines the first effective time identifier corresponding to the effective time of the first network device's computing power information. The computing power indication information on the network side includes the first computing power identifier; the effective time indication information includes the first effective time identifier.

[0300] Method 7: When the network side includes a first network device and a second network device, the first network device obtains the computing power information of both the first and second network devices, as well as the effective time of the computing power information of the first and second network devices; the first network device obtains a first computing power identifier based on its computing power information, and there is a correspondence between the computing power information of the first network device and the first computing power identifier; the first network device obtains a second computing power identifier based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the second computing power identifier; a first effective time identifier is determined based on the effective time of the computing power information of the first network device, and there is a correspondence between the effective time of the computing power information of the first network device and the first effective time identifier; a third effective time identifier is determined based on the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier. In other words, the first network device pre-stores the correspondence between computing power identifiers and computing power information of the network device. Based on the correspondence between computing power identifiers and computing power information of the network device, the first computing power identifier corresponding to the computing power information of the first network device and the second computing power identifier corresponding to the computing power information of the second network device are determined. The first network device obtains the first effective time corresponding to the computing power information of the first network device and the third effective time corresponding to the computing power information of the second network device based on the correspondence between the effective time and the effective time identifier. The computing power indication information on the network side includes the third computing power level, and the effective time indication information includes the first effective time identifier and the third effective time identifier. The computing power indication information on the network side includes the first computing power identifier and the second computing power identifier, and the effective time indication information includes the first effective time identifier and the third effective time identifier.

[0301] Method 8: When the network side includes a first network device and a second network device, the first network device obtains the computing power information of both the first and second network devices, as well as the effective time of the computing power information of the first and second network devices. If the effective time of the computing power information of the first network device is earlier than that of the computing power information of the second network device, a first computing power identifier is obtained based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power identifier. A first effective time identifier is obtained based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device. In other words, the first network device pre-stores the correspondence between computing power level and computing power information of the network device, and the correspondence between effective time and effective time identifier. Based on the correspondence between computing power level and computing power information of the network device, the first computing power level corresponding to the computing power information of the first network device is determined, and based on the correspondence between effective time and effective time identifier, the first effective time identifier corresponding to the effective time of the computing power information of the first network device is determined. The computing power indication information on the network side includes the first computing power identifier, and the effective time indication information includes the first effective time identifier.

[0302] Method Nine: When the network side includes a first network device and a second network device, the first network device obtains the computing power information of both the first and second network devices, as well as the effective time of the computing power information of both the first and second network devices. If the effective time of the computing power information of the second network device is earlier than that of the first network device, a second computing power identifier is obtained based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the second computing power identifier. A third effective time identifier is obtained based on the effective time of the computing power information of the second network device, and there is a correspondence between the third effective time identifier and the effective time of the computing power information of the second network device. In other words, the first network device pre-stores the correspondence between the computing power identifier and the computing power information of the network device, and the correspondence between the effective time and the effective time identifier. Based on the correspondence between the computing power level and the computing power information of the network device, the second computing power identifier corresponding to the computing power information of the second network device is determined. Based on the correspondence between the effective time and the effective time identifier, the third effective time identifier corresponding to the effective time of the computing power information of the second network device is determined. The computing power indication information on the network side includes the second computing power identifier, and the effective time indication information includes the third effective time identifier.

[0303] For the first network device, the computing power information of the second network device and the effective time of the computing power information can be obtained in the following way:

[0304] A first network device receives computing power indication information or computing power information from a second network device. The computing power indication information of the second network device includes the computing power level or computing power identifier of the second network device. The first network device determines the computing power information of the second network device based on the computing power level or computing power identifier of the second network device, and there is a correspondence between the computing power level or computing power identifier of the second network device and the computing power information of the second network device. In other words, the first network device pre-stores the correspondence between computing power level and computing power information of the network device, or pre-stores the correspondence between computing power identifier and computing power information of the network device. The first network device determines the computing power information of the second network device corresponding to the computing power level of the second network device based on the correspondence between computing power level and computing power information of the network device, or the first network device determines the computing power information of the second network device corresponding to the computing power identifier of the second network device based on the correspondence between computing power identifier and computing power information of the network device.

[0305] The first network device receives the effective time of computing power information from the second network device, or a third effective time identifier; the first network device obtains the effective time of the computing power information of the second network device based on the third effective time identifier; there is a correspondence between the third effective time identifier and the effective time of the computing power information of the second network device; in other words, the first network device stores the correspondence between the effective time and the effective time identifier, and the first network device obtains the effective time of the computing power information of the second network device corresponding to the third effective time identifier based on the correspondence between the effective time and the effective time identifier.

[0306] In one example, when the first network device and the second network device are respectively an access network device and a core network device, the first network device and the second network device interact through Non-access stratum (NAS) signaling. The computing power indication information and effective time indication information of the second network device are carried on existing fields or newly added fields of the NAS signaling. The first network device and the terminal interact through access stratum (AS) signaling. The computing power indication information and effective time indication information on the network side are carried on existing fields or newly added fields of the AS signaling.

[0307] S302, The first network device receives the first message from the terminal.

[0308] The first message is sent by the terminal when it determines that the network side can meet the computing power requirements for executing the target task based on the computing power information of the network side. The computing power information of the network side is determined based on the computing power indication information of the network side, and the effective time of the computing power information of the network side is determined based on the effective time indication information. The first message is used to request the execution of the target task.

[0309] It should be noted that the specific description of the first message can be found in the relevant description of S202, and will not be repeated here.

[0310] After receiving the first message, the first network device acquires its computing power information and the effective time of that information. The first network device then determines whether its computing power information meets the computing power requirements for executing the target task. If it determines that the computing power information does not meet the requirements, the first network device sends the first message to the second network device. If it determines that the computing power information meets the requirements, the first network device determines whether the effective time of the computing power information meets the time requirements. If it determines that the effective time of the computing power information meets the time requirements, the first network device executes the target task. If it determines that the effective time of the computing power information does not meet the time requirements, the first network device sends the first message to the second network device, requesting the second network device to execute the target task.

[0311] The first network device sends the first message to the second network device before or during the effective time of the computing power information on the network side.

[0312] The first message indicates the target task, which includes at least one of the following:

[0313] AI application request tasks, AI model training tasks, AI model fine-tuning tasks, and AI-based data transmission tasks.

[0314] It should be noted that the specific description of the target task can be found in the relevant description in S202, and will not be repeated here.

[0315] S303, The first network device sends a second message to the terminal based on the first message, the second message including the execution result of the target task.

[0316] S303 is optional.

[0317] It should be noted that for some target tasks, the execution results need to be fed back to the terminal, while others do not. For example, for AI request tasks used for image recognition, the first network device needs to feed back the image recognition results to the terminal; however, for target tasks used for video super-resolution, the first network device does not need to feed back the video super-resolution results to the terminal, but only needs to transmit the video super-resolution results to the recipient of the video data.

[0318] In one possible design, after receiving the first message, the second network device obtains its own computing power information and the effective time of that information. The second network device then determines whether the first network device's computing power information meets the computing power requirements for executing the target task. If the second network device's computing power information does not meet the requirements, it sends the first message to the server to request the server to execute the target task. If the second network device's computing power information meets the requirements, it then determines whether the effective time of that information meets the time requirements. If the effective time meets the time requirements, the second network device executes the target task. If the effective time does not meet the time requirements, the second network device sends the first message to the server to request the server to execute the target task.

[0319] The second network device sends the first message to the server before or during the effective time of the computing power information on the network side.

[0320] It should be noted that the execution order of the above two operations—determining whether the computing power information on the network side meets the computing power requirements for executing the target task and determining whether the effective time of the computing power information on the network side meets the time requirements for executing the target task—is not limited. The former can be executed first and the latter second; the latter can be executed first and the former second; or both can be executed simultaneously.

[0321] As can be seen, in this embodiment, sending a message requesting the execution of a target task to the network side based on the network-side computing power information helps alleviate the terminal's computing load and ensures full utilization of the network-side computing resources. Furthermore, the first network device executes the target task only when its computing power information meets the requirements for executing the target task. If the first network device's computing power information does not meet the requirements, the first network device sends a message requesting the execution of the target task to the second network device, thus requesting the second network device to execute the target task. This not only ensures the target task is executed but also ensures full utilization of the second network device's computing resources.

[0322] Referring to Figure 4, which is an interactive schematic diagram of a task execution method in a communication system provided by an embodiment of this application, the task execution method in the communication system shown in Figure 4 can be applied to the communication system shown in Figure 5. When the first communication device is a terminal and the second communication device is a server, the first network device is an access network, and the second network device is a core network device (such as a UPF network element) and a data network device; when the first communication device is a server and the second communication device is a terminal, the first network device is a core network device (such as a UPF network element) and a data network device, and the second network device is an access network. The task execution method in the communication system shown in Figure 4 can be applied to the communication system shown in Figure 6. The first communication device is a first terminal, the second communication device is a second terminal, the first network device is an access network device, and the second network device includes a core network device (such as a UPF network element) and an access network device. The task execution method in the communication system shown in Figure 4 can be applied to the communication system shown in Figure 7. The first communication device is a terminal, and correspondingly, the second communication device is a server; the first network device is a WiFi device, and the second network device is a fixed-line device; the first communication device is a server, and correspondingly, the second communication device is a terminal, the second network device is a WiFi device, and the first network device is a fixed-line device.

[0323] It should be noted that the content executed by the terminal in the above scheme description can also be executed by the communication / processing module in the terminal or the circuit or chip in the terminal responsible for communication / processing functions (such as a modem chip (also known as a baseband chip), or a SoC chip containing a modem core, or a SIP chip, or a GPU).

[0324] The content executed by the server in the above scheme description can also be executed by the communication / processing module in the server or the circuit or chip (such as computing core, MCU, ASIC, FPGA, AI processor, CPU, GPU or NPU) in the server responsible for communication / processing functions.

[0325] The content described above, which is executed by the access network device, can also be executed by modules (such as circuits, chips, or chip systems) in the access network device, or by logical nodes, logical modules, or software that can implement all or part of the functions of the access network device.

[0326] The content performed by the core network equipment in the above scheme description can also be performed by modules (such as circuits, chips or chip systems) in the core network equipment, or by logical nodes, logical modules or software that can realize all or part of the functions of the core network equipment.

[0327] The content performed by the data network device in the above scheme description can also be performed by modules (such as circuits, chips or chip systems) in the data network device, or by logical nodes, logical modules or software that can realize all or part of the functions of the data network device.

[0328] The content performed by the fixed-line equipment in the above scheme description can also be performed by modules (such as circuits, chips or chip systems) in the fixed-line equipment, or by logical nodes, logical modules or software that can realize all or part of the functions of the fixed-line equipment.

[0329] The content performed by the WiFi device in the above scheme description can also be performed by modules (such as circuits, chips or chip systems) in the WiFi device, or by logical nodes, logical modules or software that can realize all or part of the functions of the WiFi device.

[0330] As shown in Figure 4, the method includes:

[0331] S401, The first network device sends network-side computing power indication information and effective time indication information to the first communication device.

[0332] S402, the first communication device determines the computing power information on the network side based on the computing power indication information on the network side, and determines the effective time of the computing power information on the network side based on the effective time indication information.

[0333] S403. The first communication device determines whether the network side meets the computing power requirements for executing the target task based on the network side computing power information.

[0334] Specifically, when the first communication device determines that the network side meets the computing power requirements for executing the target task, it executes S404; when the first communication device determines that the network side does not meet the computing power requirements for executing the target task, it does not execute subsequent operations.

[0335] S404. The first communication device determines whether the effective time of the computing power information on the network side meets the time requirements for executing the target task.

[0336] Specifically, when the first communication device determines that the effective time of the computing power information on the network side meets the time requirement for executing the target task, S405 is executed; when the first communication device determines that the effective time of the computing power information on the network side does not meet the time requirement for executing the target task, subsequent operations are not executed.

[0337] S405, The first communication device sends a first message to the first network device.

[0338] S406. The first network device determines whether its computing power information meets the computing power requirements for executing the target task.

[0339] Specifically, when the first network device determines that its computing power information meets the computing power requirements for executing the target task, it executes S407 or S408-S409; when the first network device determines that its computing power information does not meet the computing power requirements for executing the target task, it executes S410.

[0340] S407. The first network device determines whether the effective time of the computing power information of the first network device meets the time requirements for executing the target task.

[0341] S407 is optional.

[0342] Specifically, when the first network device determines that the effective time of the computing power information of the first network device meets the computing power requirements for executing the target task, it executes S408-S409; when the first network device determines that the effective time of the computing power information of the first network device does not meet the computing power requirements for executing the target task, it executes S410.

[0343] S408. The first network device executes the target task to obtain the execution result of the target task.

[0344] S409. The first network device sends a second message (including the execution result of the target task) to the first communication device.

[0345] S409 is optional.

[0346] S410, The first network device sends a first message to the second network device.

[0347] S411. The second network device determines whether its computing power information meets the computing power requirements for executing the target task.

[0348] Specifically, when the second network device determines that its computing power information meets the computing power requirements for executing the target task, it executes S412 or S413-S414; when the second network device determines that its computing power information does not meet the computing power requirements for executing the target task, it executes S415-S417.

[0349] S412. The second network device determines whether the effective time of the computing power information of the second network device meets the time requirements for executing the target task.

[0350] Specifically, when the second network device determines that the effective time of the computing power information of the second network device meets the time requirement for executing the target task, S413-S414 are executed; when the second network device determines that the effective time of the computing power information of the second network device does not meet the time requirement for executing the target task, S415-S417 are executed.

[0351] S413. The second network device executes the target task to obtain the execution result of the target model.

[0352] S414. The second network device sends a second message (including the execution result of the target task) to the first communication device through the first network device.

[0353] It should be noted that the specific descriptions of S401-S414 can be found in the relevant descriptions in Figures 2 and 3, and will not be repeated here.

[0354] S415, The second network device sends a first message to the second communication device.

[0355] S416. The second communication device executes the target task to obtain the execution result of the target task.

[0356] After acquiring the target task, the second communication device can obtain the AI ​​model required to execute the target task from the target task, or determine the AI ​​model corresponding to the target task based on the correspondence between the task and the model; the second communication device then executes the target task based on the AI ​​model.

[0357] It should be noted that the specific implementation process of S416 can be found in the relevant description of the first network device performing the target task, and will not be described here.

[0358] S417. The second communication device sends a second message (including the execution result of the target task) to the first communication device through the second network device and the first network device.

[0359] It can be seen that when the computing power information or effective time of the second network device cannot meet the requirements of the target task, the second network device sends a message to the second communication device requesting the second communication device to execute the target task, which helps to ensure that the target task is executed completely. It should be noted that the beneficial effects of the embodiment shown in Figure 4 can also be found in the relevant descriptions of Figures 2 and 3, and will not be repeated here.

[0360] It should be noted that if the first communication device is a server and the second communication device is a terminal, the server executes the steps shown in Figure 4 after obtaining the target task. The target task can be a user instruction detected by the terminal, determined based on the instruction, and sent to the server. The server can also obtain the task through other means, which are not limited here.

[0361] Figure 8 illustrates a possible exemplary block diagram of the communication device involved in the embodiments of this application. As shown in Figure 8, the communication device 800 may include modules or units for implementing the methods described above. In one possible design, the communication device 800 includes a processing unit 802 and a communication unit 803. Optionally, the communication device 800 may further include a storage unit 801 for storing device program code and / or data.

[0362] The communication device 800 can be a terminal-side device as described in the above embodiments, such as a terminal or a communication module in a terminal, or a circuit or chip in a terminal responsible for communication functions. The communication device 800 can also be a server as described in the above embodiments, such as a communication module in a server, or a circuit or chip in a server responsible for communication functions.

[0363] For example, in one embodiment, the processing unit 802 is used to: obtain computing power information on the network side and the effective time of the computing power information, and control the communication device 800 to send a first message to the first network device based on the computing power information on the network side and the effective time of the computing power information, the first message being used to request the execution of the target task.

[0364] In one possible design, the communication unit 803 is used to receive a second message from the first network device, the second message including the execution result of the target task.

[0365] In one possible design, the processing unit 802 is used to control the communication device 800 to send a first message to the first network device based on computing power information, including:

[0366] In the processing unit 802, when it is determined that the network side meets the computing power requirements for executing the target task based on the computing power information on the network side, the communication unit 803 sends a first message to the first network device based on the effective time of the computing power information on the network side.

[0367] In one possible design, the processing unit 802 controls the communication unit 803 to send a first message to the first network device based on the effective time of the computing power information on the network side, including:

[0368] The processing unit 802 is used to determine whether the effective time of the computing power information on the network side meets the time requirement for executing the target task. If the effective time of the computing power information on the network side meets the time requirement for executing the target task, the processing unit 802 controls the communication unit 803 to send a first message to the first network device. If the effective time of the computing power information on the network side does not meet the time requirement for executing the target task, the processing unit 802 does not control the communication unit 803 to send a first message to the first network device.

[0369] In one possible design, the network-side computing power information includes the computing power information of the first network device, and the processing unit 802 is used to acquire the network-side computing power information, including:

[0370] The processing unit 802 is used to obtain a first computing power level and to obtain computing power information of a first network device based on the first computing power level; there is a correspondence between the first computing power level and the computing power information of the first network device.

[0371] In one possible design, the network-side computing power information includes the total computing power information of the first network device and the second network device. The processing unit 802 is used to obtain the network-side computing power information, including:

[0372] Processing unit 802 is used to obtain the second computing power level and for...

[0373] The total computing power information of the first network device and the second network device is obtained based on the second computing power level; there is a corresponding relationship between the second computing power level and the total computing power information of the first network device and the second network device.

[0374] In one possible design, the network-side computing power information includes the computing power information of a first network device and the computing power information of a second network device. The processing unit 802 is used to acquire the network-side computing power information, including:

[0375] Processing unit 802 is used to obtain the third computing power level and for...

[0376] The computing power information of the first network device and the second network device are obtained based on the third computing power level; there is a correspondence between the third computing power level and the computing power information of the first network device and the second network device.

[0377] In one possible design, the network-side computing power information includes the computing power information of the second network device. The processing unit 802 is used to acquire the network-side computing power information, including:

[0378] The processing unit 802 is used to obtain the fourth computing power level and to obtain the computing power information of the second network device based on the fourth computing power level; there is a correspondence between the fourth computing power level and the computing power information of the second network device.

[0379] In one possible design, the network-side computing power information includes the computing power information of the first network device, and the processing unit 802 is used to acquire the network-side computing power information, including:

[0380] Processing unit 802 is used to obtain the first computing power identifier and to...

[0381] The computing power information of the first network device is obtained based on the first computing power identifier, and there is a corresponding relationship between the first computing power identifier and the computing power information of the first network device.

[0382] In one possible design, the network-side computing power information includes the computing power information of the second network device. The processing unit 802 is used to acquire the network-side computing power information, including:

[0383] The processing unit 802 is used to obtain a second computing power identifier and to obtain computing power information of a second network device based on the second computing power identifier. There is a correspondence between the second computing power identifier and the computing power information of the second network device.

[0384] In one possible design, the network-side computing power information includes the computing power information of a first network device and the computing power information of a second network device. The processing unit 802 is used to acquire the network-side computing power information, including:

[0385] The processing unit 802 is used to obtain a first computing power identifier and a second computing power identifier, and to obtain computing power information of a first network device based on the first computing power identifier; there is a correspondence between the first computing power identifier and the computing power information of the first network device;

[0386] The processing unit 802 is also used to obtain the computing power information of the second network device based on the second computing power identifier, and there is a corresponding relationship between the second computing power identifier and the computing power information of the second network device.

[0387] In one possible design, the network-side computing power information includes the computing power information of the first network device. The processing unit 802 is used to obtain the effective time of the network-side computing power information, including:

[0388] The processing unit 802 is used to obtain a first effective time identifier and to obtain the effective time of the computing power information of the first network device based on the first effective time identifier. There is a corresponding relationship between the first effective time identifier and the effective time of the computing power information of the first network device.

[0389] In one possible design, the network-side computing power information includes the total computing power information of the first network device and the second network device. The processing unit 802 is used to obtain the effective time of the network-side computing power information, including:

[0390] The processing unit 802 is used to obtain a second effective time identifier and obtain the effective time of the total computing power information of the first network device and the second network device based on the second effective time identifier. There is a corresponding relationship between the second effective time identifier and the effective time of the total computing power information of the first network device and the second network device.

[0391] In one possible design, the network-side computing power information includes the computing power information of the second network device. The processing unit 802 is used to obtain the effective time of the network-side computing power information, including:

[0392] The processing unit 802 is used to obtain the third effective time identifier and to obtain the effective time of the computing power information of the second network device based on the third effective time identifier. There is a corresponding relationship between the third effective time identifier and the effective time of the computing power information of the second network device.

[0393] In one possible design, the network-side computing power information includes the computing power information of a first network device and the computing power information of a second network device. The processing unit 802 is used to obtain the effective time of the network-side computing power information, including:

[0394] The processing unit 802 is used to obtain a first effective time identifier and a third effective time identifier, and to obtain the effective time of the computing power information of the first network device based on the first effective time identifier, wherein there is a corresponding relationship between the first effective time identifier and the effective time of the computing power information of the first network device; it is also used to obtain the effective time of the computing power information of the second network device based on the third effective time identifier, wherein there is a corresponding relationship between the third effective time identifier and the effective time of the computing power information of the second network device.

[0395] In one possible design, the first message indicates the target task, which includes at least one of the following:

[0396] AI application request tasks, AI model training tasks, AI model fine-tuning tasks, and AI-based data transmission tasks.

[0397] In one possible design, when the communication device 800 is a terminal or a communication module within a terminal, the function of the processing unit 802 can be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system-on-a-chip (SoC) chip or a SIP chip containing a modem core. The function of the communication unit 803 can be implemented by transceiver circuitry.

[0398] In one possible design, when the communication device 800 is a circuit or chip in a terminal responsible for communication functions, such as a modem chip or a system-on-a-chip (SoC) or SIP chip containing a modem core, the function of the processing unit 802 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the communication unit 803 can be implemented by an interface circuit or data transceiver circuit on the aforementioned chip.

[0399] In one possible design, when the communication device 800 is a terminal or a processing module within a terminal, the functionality of the processing unit 802 can be implemented by one or more processors. Specifically, the processor may include a GPU, or a system-on-a-chip (SoC) or SIP chip containing a GPU. The functionality of the communication unit 803 can be implemented by transceiver circuitry.

[0400] In one possible design, when the communication device 800 is a circuit or chip in the terminal responsible for processing functions, such as a GPU or a system-on-a-chip (SoC) or SIP chip containing a GPU, the function of the processing unit 802 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the communication unit 803 can be implemented by interface circuitry or data transceiver circuitry on the aforementioned chip.

[0401] The communication device 800 can be a network-side device as described in the above embodiments. For example, it can be an access network device or a communication module in an access network device, or a circuit or chip in an access network device that is responsible for communication functions; or it can be a core network device or a communication module in a core network device, or a circuit or chip in a core network device that is responsible for communication functions.

[0402] For example, in one embodiment, the communication unit 803 is used to send network-side computing power indication information and effective time indication information to the terminal, and receive a first message from the terminal. The first message is sent by the terminal based on the effective time of the network-side computing power information when it determines that the network side can meet the computing power requirements for executing the target task based on the network-side computing power information. The effective time of the network-side computing power information is determined based on the effective time indication information, and the network-side computing power information is determined based on the network-side computing power indication information. The first message is used to request the execution of the target task.

[0403] In one possible design, the processing unit 802 is used to control the communication device 800 to send a second message to the terminal based on the first message, the second message including the execution result of the target task.

[0404] In one possible design, the processing unit 802 is used to control the communication device 800 to send a second message to the terminal based on the first message, including:

[0405] The processing unit 802 is used to: determine whether the computing power information of the first network device meets the computing power requirements for executing the target task; and when it is determined that the computing power information of the first network device meets the computing power requirements for executing the target task, use the target task to execute the target task to obtain the execution result of the target task.

[0406] In one possible design, the processing unit 802 controls the communication device 800 to send a second message to the terminal based on the execution result of the target task. The second message includes the execution result of the target task.

[0407] In one possible design, the processing unit 802 is further configured to: when it is determined that the computing power information of the first network device does not meet the computing power requirements for executing the target task, control the communication device 800 to send a third message to the second network device or server, the third message being used to request the execution of the target task.

[0408] In one possible design, the communication unit 803 is also used to receive a fourth message from the second network device, the fourth message including the execution result of the target task.

[0409] In one possible design, the network-side computing power indication information includes a first computing power level, the effective time indication information includes a first effective time identifier, and the processing unit 802 is further used for:

[0410] Obtain the computing power information of the first network device and the effective time of the computing power information; obtain the first computing power level based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power level; obtain the first effective time identifier based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device.

[0411] In one possible design, the network-side computing power indication information includes a third computing power level, and the effective time indication information includes a first effective time identifier and a third effective time identifier. The processing unit 802 is also used for:

[0412] Acquire the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device;

[0413] A third computing power level is obtained based on the computing power information of the first network device and the computing power information of the second network device, and there is a correspondence between the computing power information of the first network device, the computing power information of the second network device and the third computing power level; a first effective time identifier is determined based on the effective time of the computing power information of the first network device, and there is a correspondence between the effective time of the computing power information of the first network device and the first effective time identifier; a third effective time identifier is determined based on the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier.

[0414] In one possible design, the network-side computing power indication information includes a first computing power level, the effective time indication information includes a first effective time identifier, and the processing unit 802 is further used for:

[0415] Acquire the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device;

[0416] If the effective time of the computing power information of the first network device is earlier than the effective time of the computing power information of the second network device, a first computing power level is obtained based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power level; a first effective time identifier is obtained based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device.

[0417] In one possible design, the network-side computing power indication information includes a second computing power level, and the effective time indication information includes a second effective time identifier, wherein the second effective time identifier is the effective time of the total computing power information of the first network device and the second network device. The processing unit 802 is further configured to:

[0418] Obtain the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device; if the effective time of the computing power information of the first network device is the same as the effective time of the computing power information of the second network device; determine the total computing power information of the first network device and the second network device based on the computing power information of the first network device and the computing power information of the second network device; obtain the second computing power level based on the total computing power information of the first network device and the second network device, and there is a correspondence between the total computing power information of the first network device and the second computing power level; determine the second effective time identifier based on the effective time of the computing power information of the first network device or the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the first network device or the effective time of the computing power information of the second network device and the first effective time identifier.

[0419] In one possible design, the network-side computing power indication information includes a fourth computing power level, the effective time indication information includes a third effective time identifier, and the processing unit 802 is further used for:

[0420] Acquire the computing power information of the first network device, the effective time of the computing power information of the first network device, the computing power information of the second network device, and the effective time of the computing power information of the second network device;

[0421] If the computing power information of the second network device takes effect earlier than the computing power information of the first network device, a fourth computing power level is obtained based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the fourth computing power level; a third effective time identifier is determined based on the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier.

[0422] In one possible design, the network-side computing power indication information includes a first computing power identifier, the effective time indication information includes a first effective time identifier, and the processing unit 802 is further used for:

[0423] Obtain the computing power information of the first network device, obtain the first computing power identifier based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power identifier; obtain the first effective time identifier based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device.

[0424] In one possible design, the network-side computing power indication information includes a first computing power identifier and a second computing power identifier, and the effective time indication information includes a first effective time identifier and a third effective time identifier. The processing unit 802 is further used for:

[0425] Obtain computing power information of the first network device and computing power information of the second network device, and obtain the effective time of the computing power information of the first network device and the effective time of the computing power information of the second network device;

[0426] A first computing power identifier is obtained based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power identifier; a second computing power identifier is obtained based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the second computing power identifier; a first effective time identifier is determined based on the effective time of the computing power information of the first network device, and there is a correspondence between the effective time of the computing power information of the first network device and the first effective time identifier; a third effective time identifier is determined based on the effective time of the computing power information of the second network device, and there is a correspondence between the effective time of the computing power information of the second network device and the third effective time identifier.

[0427] In one possible design, the network-side computing power indication information includes a first computing power identifier, the effective time indication information includes a first effective time identifier, and the processing unit 802 is further used for:

[0428] Obtain computing power information of the first network device and computing power information of the second network device, and obtain the effective time of the computing power information of the first network device and the effective time of the computing power information of the second network device;

[0429] If the effective time of the computing power information of the first network device is earlier than the effective time of the computing power information of the second network device, then the first computing power identifier is obtained based on the computing power information of the first network device, and there is a correspondence between the computing power information of the first network device and the first computing power identifier; the first effective time identifier is obtained based on the effective time of the computing power information of the first network device, and there is a correspondence between the first effective time identifier and the effective time of the computing power information of the first network device.

[0430] In one possible design, the network-side computing power indication information includes a second computing power identifier, and the effective time indication information includes a third effective time identifier. The processing unit 802 is also used in the method of this embodiment, which further includes:

[0431] Obtain computing power information of the first network device and computing power information of the second network device, and obtain the effective time of the computing power information of the first network device and the effective time of the computing power information of the second network device;

[0432] If the effective time of the computing power information of the second network device is earlier than the effective time of the computing power information of the first network device, then a second computing power identifier is obtained based on the computing power information of the second network device, and there is a correspondence between the computing power information of the second network device and the second computing power identifier; a third effective time identifier is obtained based on the effective time of the computing power information of the second network device, and there is a correspondence between the third effective time identifier and the effective time of the computing power information of the second network device.

[0433] In one possible design, the first message indicates the target task, which includes at least one of the following:

[0434] AI application request tasks, AI model training tasks, AI model fine-tuning tasks, and AI-based data transmission tasks.

[0435] It is understood that the division of units in the above-described device is merely a logical functional division. One function can correspond to one functional unit, or two or more functions can be integrated into one functional unit. In actual implementation, all or some units can be integrated onto a single physical entity, or distributed across different physical entities. Furthermore, the aforementioned functional units can be implemented in hardware, software, or a combination of both. Whether a function is executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for specific applications, but such implementations should not be considered beyond the scope of this application.

[0436] In one example, the functional unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as: one or more application-specific integrated circuits (ASICs), or one or more central processing units (CPUs), one or more microcontroller units (MCUs), one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0437] In one example, storage unit 801 may include random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory and / or registers, etc.

[0438] Referring to Figure 9, which is a schematic diagram of a communication device provided in an embodiment of this application, the communication device 900 can correspond to the terminal, access network node, server, or core network device shown in Figure 1a, or the terminal, access network device, core network device, or OAM shown in Figure 1b, or the access network node or terminal shown in Figure 1c, or the terminal, server, access network device, core network device, or data network device in Figure 5, the first terminal, second terminal, access network device, or core network device in Figure 6, or the terminal, server, fixed network device, or WiFi device shown in Figure 7, and is used to implement the operation of the terminal in the above embodiments. As shown in Figure 9, the communication device 900 includes: one or more antennas 910, a radio frequency processing system 920, and a processor system 930.

[0439] In the downlink or sidelink direction, the RF processing system 920 receives RF signals through the antenna 910 and sends the RF-processed signals to the processor system 930 for further processing. In the uplink or sidelink direction, the processor system 930 processes the information from the communication device side and sends it to the RF processing system 920, which then processes the signal and transmits it through the antenna 910.

[0440] In one example, the radio frequency (RF) processing system 920 serves as the communication interface for external communication of the communication device and may include an RF front end (RFFE) 921 and an RF transceiver 922. The RFFE 921 is primarily used for one or more processing operations, such as shaping, passband selection, or gain adjustment, on the RF signals received by the antenna or those to be transmitted through the antenna. It may include one or more components such as RF switches, duplexers, filters, power amplifiers, antenna tuners, and low-noise amplifiers. The RFFE 921 can be a circuit system composed of multiple discrete components or integrated into one or more chips. The RF transceiver 922 processes the RF signals received by the RFFE into baseband / IF signals for further processing by the processor system 930, and processes the baseband / IF signals provided by the processor system 930 into RF signals for transmission to the RFFE 921. The baseband / IF signals transmitted between the RF transceiver 922 and the processor system 930 can be digital or analog signals. The RF transceiver 922 can be implemented by one or more chips, which are commonly referred to as RF ICs.

[0441] In one example, the processor system 930 may include one or more processors for processing signals and executing one or more communication protocols. Optionally, the processor system 930 may also include a memory 936. In one example, the one or more processors include at least one baseband processor 931 (also known as a modem processor). The memory 936 is used to store data and / or computer program instructions. Optionally, the processor system 930 may also include one or more application processors 932 for implementing processing of the communication device's operating system and application layer. The application processor 932 may include, for example, a GPU. Optionally, the processor system 930 may also include one or more of a voice subsystem 933, a multimedia subsystem 934, or an interface circuit 935. The voice subsystem 933 is used to process voice signals, the multimedia subsystem 934 is used to handle multimedia-related operations, such as video encoding / decoding, image processing, etc., and the interface circuit 935 is used to enable communication with other communication device components, such as a display 940, an input device 950, a memory 960, etc. The above-mentioned components in the processor system 930 can communicate with each other via a bus or communication interface circuit.

[0442] In one example, the processor system 930 can be packaged as a single processor chip, such as a SoC chip or a SIP chip. In another example, the processor system 930 can be a system composed of multiple chips; for example, the baseband processor 931 can be packaged as a single chip, or packaged with part or all of the circuitry of the radio frequency processing system into a single chip.

[0443] In one example, memory 936 can be on-chip memory, i.e., located on the system-on-a-chip (SoC) 930. In another example, memory 960 can be off-chip memory, i.e., located outside the SoC 930.

[0444] In one example, the baseband processor 931 may include one or more processor cores 9311 and interface circuitry 9314. The one or more processor cores 9311 are used to process signals and execute one or more communication protocols. Optionally, the baseband processor 931 may also include a memory 9312 for storing at least a portion of the corresponding computer program instructions and / or data. In one example, the one or more processor cores 9311 implement the relevant operations in the above method embodiments (as shown in Figure 2 or Figure 3) by executing the computer program instructions stored in the memory 9312. In this disclosure, the memory 9312 is used to store corresponding computer program instructions and / or data. This can mean that the memory 9312 stores all corresponding computer program instructions and / or data for execution by the processor core 9311; or it can mean that the memory 9312 stores a portion of the corresponding computer program instructions and / or data, including the computer program instructions and / or data currently required to be executed by the processor core 9311. The memory 9312 can store different portions of computer program instructions and / or data multiple times for execution by the processor core 9311 to implement the relevant operations in the above method embodiments. The interface circuit 9314 serves as a communication interface for communication with other components, such as transmitting signals with the radio frequency processing system 920, communicating with other subsystems and related components of the processor system 930 via a bus, such as transmitting data control signals with the application processor 932, and transmitting data or computer program instructions with the memory 936 or memory 960. Optionally, in order to reduce the load on the processor core, a baseband signal processing circuit 9313 can be set to perform at least some baseband signal processing, including one or more of signal demodulation, modulation, encoding or decoding.

[0445] In one example, the communication device provided in this application may be a communication device 900, including a communication module comprising a processor system 930 and a radio frequency processing system 920, or a baseband processor 931.

[0446] The processor, processor system, application processor, baseband processor, processor circuit, or processor core mentioned above can be collectively referred to as a processor. The processor may include one or more of the following: central processing unit (CPU), digital signal processor (DSP), microprocessor unit (MPU), microcontroller unit (MCU), graphics processing unit (GPU), field programmable gate array (FPGA), artificial intelligence processor (AI processor), or neural processing unit (NPU).

[0447] The aforementioned memory may include one or more of the following storage media: random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), phase-change memory (PCM), resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), cache, register, read-only memory (ROM), flash memory, erasable programmable read-only memory (EPROM), hard disk, etc. In one example, computer program instructions for executing the above embodiments may be stored on non-volatile memory, such as at least a portion of the aforementioned memory 960 (e.g., one or more of ROM, flash memory, EPROM, or hard disk). When the communication device is running, the corresponding computer program instructions may be partially or wholly loaded onto a memory with a faster transmission speed than the processor, such as at least a portion of the memory 936 and / or memory 9312 (e.g., one or more of RAM, SRAM, DRAM, PCM, RERAM, MRAM, FRAM, cache, or register), for the processor to execute in order to implement the steps in the above method embodiments.

[0448] In one example, the RF transceiver 922 and the RF front-end 921 can also be packaged in a single chip. In another example, the RF transceiver 922, the RF front-end 921, and the baseband processor 931 can also be packaged in a single chip.

[0449] The terms "system" and "network" in this application embodiment are used interchangeably. "At least one" refers to one or more, and "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B, or C" includes A, B, C, AB, AC, BC, or ABC; "at least one of A, B, and C" can also be understood as including A, B, C, AB, AC, BC, or ABC. Furthermore, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in this application embodiment are used to distinguish multiple objects and are not used to limit the order, sequence, priority, or importance of multiple objects.

[0450] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, etc.) containing computer-usable program code.

[0451] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0452] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0453] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0454] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A task execution method, characterized in that, include: Obtain the computing power information from the network side and the effective time of the computing power information; Based on the computing power information and the effective time, a first message is sent to the first network device, the first message being used to request the execution of the target task.

2. The method according to claim 1, characterized in that, The method further includes: Receive a second message from the first network device, the second message including the execution result of the target task.

3. The method according to claim 1 or 2, characterized in that, Sending the first message to the first network device based on the computing power information and the effective time includes: Based on the computing power information, it is determined that the network side meets the computing power requirements for executing the target task, and the first message is sent to the first network device based on the effective time.

4. The method according to any one of claims 1-3, characterized in that, The network-side computing power information includes the computing power information of the first network device, and obtaining the network-side computing power information includes: Obtain the first computing power level; The computing power information of the first network device is obtained based on the first computing power level; there is a correspondence between the first computing power level and the computing power information of the first network device.

5. The method according to any one of claims 1-3, characterized in that, The network-side computing power information includes the total computing power information of the first network device and the second network device. Obtaining the network-side computing power information includes: Obtain the second computing power level; The total computing power information of the first network device and the second network device is obtained based on the second computing power level; there is a corresponding relationship between the second computing power level and the total computing power information of the first network device and the second network device.

6. The method according to any one of claims 1-3, characterized in that, The network-side computing power information includes the computing power information of the first network device and the computing power information of the second network device. Obtaining the network-side computing power information includes: Obtain the third computing power level; The computing power information of the first network device and the computing power information of the second network device are obtained based on the third computing power level; the third computing power level has a corresponding relationship with the computing power information of the first network device and the computing power information of the second network device.

7. The method according to any one of claims 1-6, characterized in that, The first message indicates the target task, which includes at least one of the following: Artificial intelligence (AI) application request tasks, AI model training tasks, AI model fine-tuning tasks, and AI-based data transmission tasks.

8. A communication device, characterized in that, include: The processing unit is used to obtain the computing power information on the network side and the effective time of the computing power information; The processing unit is further configured to control the communication device to send a first message to the first network device based on the computing power information and the effective time, the first message being used to request the execution of a target task.

9. The communication device according to claim 8, characterized in that, The communication device further includes: A communication unit is configured to receive a second message from the first network device, the second message including the execution result of the target task.

10. The communication device according to claim 8 or 9, characterized in that, The processing unit is used to control the communication device to send a first message to the first network device based on the computing power information and the effective time, including: When the processing unit determines, based on the computing power information, that the network side meets the computing power requirements for executing the target task, the communication unit is used to send the first message to the first network device based on the effective time.

11. The communication device according to any one of claims 8-10, characterized in that, The network-side computing power information includes the computing power information of the first network device. The processing unit is used to acquire the network-side computing power information, including: The processing unit is used to obtain the first computing power level and is used for The computing power information of the first network device is obtained based on the first computing power level; there is a correspondence between the first computing power level and the computing power information of the first network device.

12. The communication device according to any one of claims 8-10, characterized in that, The network-side computing power information includes the total computing power information of the first network device and the second network device. The processing unit is used to obtain the network-side computing power information, including: The processing unit is used to obtain the second computing power level and is used for The total computing power information of the first network device and the second network device is obtained based on the second computing power level; there is a corresponding relationship between the second computing power level and the total computing power information of the first network device and the second network device.

13. The communication device according to any one of claims 8-10, characterized in that, The network-side computing power information includes the computing power information of the first network device and the computing power information of the second network device. The processing unit is used to obtain the network-side computing power information, including: The processing unit is used to obtain the third computing power level and is used for The computing power information of the first network device and the computing power information of the second network device are obtained based on the third computing power level; the third computing power level has a corresponding relationship with the computing power information of the first network device and the computing power information of the second network device.

14. The communication device according to any one of claims 8-13, characterized in that, The first message indicates the target task, which includes at least one of the following: Artificial intelligence (AI) service requests, AI model training tasks, AI model fine-tuning tasks, and AI-based data transmission tasks.

15. A communication device, characterized in that, The method includes at least one processor, wherein the at least one processor is coupled to a memory for storing program code, and the at least one processor is configured to execute the program code to implement the method of any one of claims 1 to 7.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

17. A computer program product that, when run on a computer, causes the computer to perform the method as described in any one of claims 1-7.

18. A communication device, characterized in that, Includes a unit for performing the method as described in any one of claims 1-7.

Images