Communication method and communication apparatus

By introducing data-driven decision-making, dynamic management tool invocation, and updates into the first planning and execution functions of the wireless AI system, the problems of task execution efficiency and success rate in the lifecycle management of the wireless AI system are solved, and system performance is optimized and power consumption is reduced.

WO2026233261A1PCT designated stage Publication Date: 2026-11-12HUAWEI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2026/094527
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-09
Filing Date
2026-04-30
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

How to optimize the lifecycle management of agent-based wireless AI systems to improve the success rate and efficiency of task execution.

Method used

The first planning function acquires task-related data and instructs the execution function to call appropriate tools or tool combinations to perform the task, including AI models or non-AI algorithm tools. It combines data interaction with memory, perception and other planning functions to dynamically manage the activation and updating of tools to adapt to different task requirements.

Benefits of technology

It improved the success rate and efficiency of task execution, optimized system performance, and saved power consumption of unnecessary tools.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2026094527_12112026_PF_FP_ABST
    Figure CN2026094527_12112026_PF_FP_ABST
Patent Text Reader

Abstract

Provided in the present application are a communication method and a communication apparatus. The method comprises: a first planning function acquiring first data related to a first task; on the basis of the first data, the first planning function sending a first instruction to an execution function, wherein the first instruction is used for instructing the invoking of at least one first tool, so as to execute the first task; the execution function acquiring second data used for executing the first task and the at least one first tool; and on the basis of the second data and the at least one first tool, the execution function executing the first task. On the basis of the present application, provided is a lifecycle management system applicable to an agent-based wireless AI system, the lifecycle management system comprising a first planning function and an execution function. On the basis of the lifecycle management system provided in the present application, it is beneficial to optimize the system performance.
Need to check novelty before this filing date? Find Prior Art

Description

Communication methods and communication devices

[0001] This application claims priority to Chinese Patent Application No. 202510601621.3, filed on May 9, 2025, entitled "Communication Method and Communication Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of wireless communication, and more particularly to a communication method and a communication device. Background Technology

[0003] With the continuous development of artificial intelligence (AI) technology, AI models are being applied to mobile communication networks. For example, agents in mobile communication networks can use AI models to process tasks and realize the intentions of terminal devices. The basic characteristics of an agent are: the ability to react to changes in the environment and then automatically adjust its behavior and state; different agents can also interact with other agents according to their respective intentions.

[0004] With the deployment and application of intelligent agents, how to perform life cycle management (LCM) on intelligent agents to optimize the performance of communication systems has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a communication method and a communication device, with the aim of providing a lifecycle management system suitable for agent-based wireless AI systems.

[0006] In a first aspect, a communication method is provided, the method comprising: a first planning function acquiring first data related to a first task; the first planning function sending a first instruction to an execution function based on the first data, the first instruction being used to instruct the invocation of at least one first tool to execute the first task; the execution function acquiring second data for executing the first task and at least one first tool; and the execution function executing the first task based on the second data and at least one first tool.

[0007] The first planning function can be replaced by equipment on the terminal side, network side, or core network side. The execution function can be replaced by equipment on the terminal side or network side.

[0008] The terminal-side equipment may include terminal devices, communication modules within the terminal devices, or circuits or chips within the terminal devices responsible for communication functions (such as modem chips, also known as baseband chips, or system-on-chip (SoC) chips or system-in-package (SIP) chips containing modem cores, etc.). Alternatively, the terminal-side equipment may include terminal-side AI entities. Terminal-side AI entities can be terminal devices or AI entities serving the terminal devices, such as servers, such as over-the-top (OTT) servers or cloud servers.

[0009] Network-side devices can include the network itself, communication modules within the network, or circuits or chips responsible for communication functions within the network (such as modem chips, also known as baseband chips, or system-on-a-chip (SoC) chips or SIP chips containing modem cores, etc.). Alternatively, network-side devices can include network-side AI entities. These AI entities can be network devices or AI entities serving network devices, such as radio access network (RAN) intelligent controllers (RICs), operation administration and maintenance (OAM) systems, or servers, such as OTT servers or cloud servers.

[0010] The equipment on the core network side may include core network elements, functional modules within core network elements, or circuits or chips within core network elements. Alternatively, the equipment on the core network side may include AI entities on the core network side. AI entities on the core network side can be core network elements or AI entities serving core network elements, such as servers, such as OTT servers or cloud servers.

[0011] Based on the above technical solutions, a lifecycle management system suitable for agent-based wireless AI systems is provided, including a first planning function and an execution function. The lifecycle management system provided by this application embodiment is beneficial for optimizing system performance.

[0012] Based on the lifecycle management system provided in this application, the first planning function plans the execution method of the first task based on the acquired data, which helps to determine at least one first tool suitable for executing the first task. When the first planning function instructs the execution function to call at least one first tool to execute the first task, it helps to improve the success rate and / or efficiency of the execution function in executing the first task. For example, based on this application, the first planning function can instruct the execution function to call multiple AI models or functions to execute the task, which, compared to calling a single AI model or function to execute the task, helps to improve the success rate and / or efficiency of the task execution.

[0013] For example, at least one first tool is associated with one or more of the following functional modules on the network side and / or the terminal side: a sending functional module, a receiving functional module, or a measurement functional module.

[0014] For example, at least one first tool includes one or more of the following: an AI model or AI function or non-AI algorithm tool for implementing at least one function of the transmission function module of the network side and / or the terminal side; an AI model or AI function or non-AI algorithm tool for implementing at least one function of the reception function module of the network side and / or the terminal side; and an AI model or AI function or non-AI algorithm tool for implementing at least one function of the measurement function module of the network side and / or the terminal side.

[0015] Based on the above technical solution, the first planning function can instruct the execution function to call different tools to execute tasks according to different tasks, thereby improving task execution efficiency and / or success rate.

[0016] For example, the first data includes one or more of the following: environmental perception data, reference signal measurement results, prior knowledge, or feedback information related to the execution results of the second task.

[0017] The second task is performed before the first task. Feedback information related to the execution result of the second task may include one or more of the following: feedback on whether the second task was successfully executed; environmental perception data obtained through environmental perception after executing the second task; reference signal measurement results obtained through reference signal measurement after executing the second task; and channel measurement results obtained through channel measurement after executing the second task.

[0018] Based on the above technical solution, the first planning function can acquire different types of data according to different tasks, which is conducive to the first planning function determining the task planning result with a high probability of task completion and / or high task execution efficiency based on the acquired data.

[0019] In conjunction with the first aspect, in certain implementations of the first aspect, the first planning function acquires first data related to the first task, including: the first planning function receiving third data from the memory function; and / or, the first planning function receiving fourth data from the perception function; and / or, the first planning function receiving fifth data from the second planning function; the first data includes one or more of the following: third data, fourth data, or fifth data.

[0020] Based on the above technical solutions, the lifecycle management system applicable to agent-based wireless AI systems may also include memory and / or sensing functions, thereby providing the necessary data for other functions in the lifecycle management system.

[0021] In addition, the first planning function can interact with another planning function to obtain data from the other planning function, which helps the first planning function to determine the task planning result with a high probability of task completion and / or high task execution efficiency based on the obtained data.

[0022] For example, the third data includes prior knowledge.

[0023] For example, the fourth data may include one or more of the following: environmental perception data, reference signal measurement results, channel measurement results, or feedback information related to the execution results of the second task.

[0024] For example, the fifth data may include one or more of the following: environmental perception data, reference signal measurement results, channel measurement results, or feedback information related to the execution results of the second task.

[0025] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: a first planning function sending a second instruction to a tool function, the second instruction being used to instruct the activation of at least one first tool, and / or, to instruct the sending of at least one first tool to an execution function.

[0026] Based on the above technical solution, the lifecycle management system applicable to agent-based wireless AI systems can also include tool functions, thereby providing the execution functions in the lifecycle management system with the tools required to perform tasks. Furthermore, the first planning function can also manage the tools included in the tool functions, such as activating tools and / or instructing tool functions to provide the execution functions with the tools required to perform tasks. This facilitates the management of different tools according to different task requirements, and for example, helps to save power consumption caused by activating unnecessary tools.

[0027] In conjunction with the first aspect, in some implementations of the first aspect, the first instruction is used to instruct the invocation of at least one first tool to execute a first subtask included in the first task, and the method further includes: a first planning function sending a third instruction to a second planning function, the third instruction being used to instruct the execution of a second subtask included in the first task, the second subtask being different from the first subtask.

[0028] Based on the above technical solution, the first planning function can interact with another planning function according to the planning result of the first task, so as to instruct the other planning function to assist in the execution of the first task, thereby improving the execution efficiency and / or success rate of the first task.

[0029] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the execution function sending first information to the first planning function, the first information being used to indicate the execution result of the first task.

[0030] In conjunction with the first aspect, in some implementations of the first aspect, the execution result of the first task indicates that the first task has failed. The method further includes: a first planning function acquiring sixth data related to the first task; the first planning function sending a fourth instruction to the execution function based on the sixth data, the fourth instruction being used to instruct the invocation of at least one second tool to execute the first task, wherein the at least one second tool is not completely identical to the at least one first tool.

[0031] Based on the above technical solution, the first planning function can re-plan the first task if the first task fails to execute, thereby instructing the execution function to call at least one second tool different from at least one first tool to re-execute the first task, so as to enable the execution function to successfully execute the first task.

[0032] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the first planning function sending a fifth instruction to the tool function, the fifth instruction being used to instruct the tool to be updated in order to obtain at least one second tool.

[0033] Based on the above technical solution, the first planning function can instruct the tool function to update the tool, thereby improving the efficiency and / or success rate of the execution function in using the updated tool to perform tasks.

[0034] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the first planning function sending seventh data to the tool function, the seventh data being used for tool updates to obtain at least one second tool.

[0035] In conjunction with the first aspect, in some implementations of the first aspect, after receiving the first information, the method further includes: the first planning function sending a sixth instruction to the tool function, the sixth instruction being used to instruct the activation of at least one first tool.

[0036] Based on the above technical solution, the first planning function can instruct the tool function to activate at least one first tool after the execution function calls at least one tool to perform the first task, thereby helping to reduce the power consumption of the tool function.

[0037] Secondly, a communication method is provided, the method comprising: acquiring first data related to a first task; and sending a first instruction to an execution function based on the first data, the first instruction being used to instruct the invocation of at least one first tool to execute the first task.

[0038] This method can be executed by a first planning function, which can be replaced by a device on the terminal side, a device on the network side, or a device on the core network side. Further description of the device on the terminal side, the device on the network side, or the device on the core network side can be found in the first aspect above.

[0039] For example, at least one first tool is associated with one or more of the following functional modules on the network side and / or the terminal side: a sending functional module, a receiving functional module, or a measurement functional module.

[0040] For example, at least one first tool includes one or more of the following: an AI model or AI function or non-AI algorithm tool for implementing at least one function of the transmission function module of the network side and / or the terminal side; an AI model or AI function or non-AI algorithm tool for implementing at least one function of the reception function module of the network side and / or the terminal side; and an AI model or AI function or non-AI algorithm tool for implementing at least one function of the measurement function module of the network side and / or the terminal side.

[0041] For example, the first data includes one or more of the following: environmental perception data, reference signal measurement results, prior knowledge, or feedback information related to the execution results of the second task.

[0042] In conjunction with the second aspect, in some implementations of the second aspect, acquiring first data related to the first task includes: receiving third data from the memory function; and / or receiving fourth data from the perception function; and / or receiving fifth data from the second planning function; the first data includes one or more of the following: third data, fourth data, or fifth data.

[0043] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending a second instruction to a tool function, the second instruction being used to instruct the activation of at least one first tool, and / or, being used to instruct the sending of at least one first tool to an execution function.

[0044] In conjunction with the second aspect, in some implementations of the second aspect, the first instruction is used to instruct the invocation of at least one first tool to execute a first subtask included in the first task, and the method further includes: sending a third instruction to a second planning function, the third instruction being used to instruct the execution of a second subtask included in the first task, the second subtask being different from the first subtask.

[0045] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: receiving first information from the execution function, the first information being used to indicate the execution result of the first task.

[0046] In conjunction with the second aspect, in some implementations of the second aspect, the execution result of the first task indicates that the first task has failed. The method further includes: obtaining sixth data related to the first task; and sending a fourth instruction to the execution function based on the sixth data. The fourth instruction is used to instruct the invocation of at least one second tool to execute the first task, wherein the at least one second tool is not exactly the same as the at least one first tool.

[0047] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending a fifth instruction to the tool function, the fifth instruction being used to instruct a tool update to obtain at least one second tool.

[0048] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending seventh data to the tool function, the seventh data being used for tool updates to obtain at least one second tool.

[0049] In conjunction with the second aspect, in some implementations of the second aspect, after receiving the first information, the method further includes: sending a sixth instruction to the tool function, the sixth instruction being used to instruct the activation of at least one first tool.

[0050] Thirdly, a communication method is provided, the method comprising: receiving a first instruction, the first instruction being used to instruct the invocation of at least one first tool to perform a first task; acquiring second data for performing the first task and at least one first tool; and performing the first task based on the second data and at least one first tool.

[0051] This method can be executed by an execution function, which can be replaced by a device on the terminal side or a device on the network side. Further description of the device on the terminal side or the device on the network side can be found in the first aspect above.

[0052] For example, at least one first tool is associated with one or more of the following functional modules on the network side and / or the terminal side: a sending functional module, a receiving functional module, or a measurement functional module.

[0053] For example, at least one first tool includes one or more of the following: an AI model or AI function or non-AI algorithm tool for implementing at least one function of the transmission function module of the network side and / or the terminal side; an AI model or AI function or non-AI algorithm tool for implementing at least one function of the reception function module of the network side and / or the terminal side; and an AI model or AI function or non-AI algorithm tool for implementing at least one function of the measurement function module of the network side and / or the terminal side.

[0054] In conjunction with the third aspect, in some implementations of the third aspect, obtaining at least one first tool includes: receiving at least one first tool from tool functionality.

[0055] In conjunction with the third aspect, in some implementations of the third aspect, before receiving at least one first tool, the method further includes: sending a first request to the tool function, the first request being for requesting at least one first tool.

[0056] In conjunction with the third aspect, in some implementations of the third aspect, the method further includes: sending first information, which is used to indicate the execution result of the first task.

[0057] Fourthly, a communication method is provided, the method comprising: receiving a second instruction for instructing the activation of at least one first tool, and / or for instructing the sending of at least one first tool to an execution function.

[0058] This method can be executed by a tool function, which can be replaced by a device on the terminal side or a device on the network side. Further description of the terminal-side device or the network-side device can be found in the first aspect above.

[0059] For example, at least one first tool is associated with one or more of the following functional modules on the network side and / or the terminal side: a sending functional module, a receiving functional module, or a measurement functional module.

[0060] For example, at least one first tool includes one or more of the following: an AI model or AI function or non-AI algorithm tool for implementing at least one function of the transmission function module of the network side and / or the terminal side; an AI model or AI function or non-AI algorithm tool for implementing at least one function of the reception function module of the network side and / or the terminal side; and an AI model or AI function or non-AI algorithm tool for implementing at least one function of the measurement function module of the network side and / or the terminal side.

[0061] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the second instruction is used to instruct the execution function to send at least one first tool, and the method further includes: sending at least one first tool to the execution function.

[0062] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the method further includes: receiving a first request from the execution function, the first request being for requesting at least one first tool; and sending at least one first tool to the execution function.

[0063] In conjunction with the fourth aspect, in some implementations of the fourth aspect, after receiving the second instruction, the method further includes: receiving seventh data, which is used for tool updating to obtain at least one second tool, the at least one second tool being not completely identical to at least one first tool.

[0064] In conjunction with the fourth aspect, in some implementations of the fourth aspect, after receiving the second instruction, the method further includes: receiving a sixth instruction, the sixth instruction being used to instruct the deactivation of at least one first tool.

[0065] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the method further includes receiving eighth data before receiving the second instruction; and obtaining at least one first tool based on the eighth data.

[0066] Fifthly, an apparatus is provided. This apparatus may include functional modules corresponding to each of the methods / operations / steps / actions described in any possible implementation of the first aspect, or may include functional modules corresponding to each of the methods / operations / steps / actions described in any of the second aspect, or may include functional modules corresponding to each of the methods / operations / steps / actions described in any of the third aspect, or may include functional modules corresponding to each of the methods / operations / steps / actions described in any of the fourth aspect. The module may be a hardware circuit, software, or a combination of hardware circuitry and software implementation.

[0067] In one design, the device may include a processing module and a communication module. The communication module is used to perform the sending and receiving actions executed by the first planning function in the method described in the first or second aspect above, while the processing module is used to perform processing-related actions executed by the first planning function in the method described in the first or second aspect above.

[0068] In one design, the device can be a network device, or a device, module, circuit, or chip configured in the network device, or a device that can be used in conjunction with the network device, such as a smart network element with RIC deployed.

[0069] In one design, the device may include a processing module and a communication module. The communication module is used to perform sending and receiving actions executed by the execution function in the method described in the first or third aspect above, while the processing module is used to perform processing-related actions executed by the execution function in the method described in the first or third aspect above.

[0070] In one design, the device can be a terminal device, or a device, module, circuit, or chip configured in the terminal device, or a device that can be used in conjunction with the terminal device, such as an OTT host or cloud server.

[0071] In one design, the device may include a processing module and a communication module. The communication module is used to perform sending and receiving actions performed by the tool function in the methods described in the first or fourth aspect above, while the processing module is used to perform processing-related actions performed by the tool function in the methods described in the first or fourth aspect above.

[0072] In one design, the device can be a terminal device, or a device, module, circuit, or chip configured in the terminal device, or a device compatible with the terminal device, such as an OTT host or cloud server. Alternatively, the device can be a network device, or a device, module, circuit, or chip configured in the network device, or a device compatible with the network device, such as a smart network element with RIC deployed.

[0073] A sixth aspect provides an apparatus comprising a processor and a storage medium storing instructions which, when executed by the processor, cause a method as described in the first aspect or any possible implementation thereof to be implemented, or cause a method as described in the second aspect or any possible implementation thereof to be implemented, or cause a method as described in the third aspect or any possible implementation thereof to be implemented, or cause a method as described in the fourth aspect or any possible implementation thereof to be implemented.

[0074] A seventh aspect provides an apparatus comprising a processing circuit for processing data and / or information such that a method as in the first aspect or any possible implementation thereof is implemented, or a method as in the second aspect or any possible implementation thereof is implemented, or a method as in the third aspect or any possible implementation thereof is implemented, or a method as in the fourth aspect or any possible implementation thereof is implemented.

[0075] The processing circuit may include one or more processors, or all or part of the circuitry in one or more processors used for control or processing functions.

[0076] Optionally, the apparatus may further include a memory for storing programs or instructions, and the processor for executing the programs or instructions to implement the methods as in the first aspect or any possible implementation thereof, or to implement the methods as in the second aspect or any possible implementation thereof, or to implement the methods as in the third aspect or any possible implementation thereof, or to implement the methods as in the fourth aspect or any possible implementation thereof.

[0077] Optionally, the device may also include the transceiver circuit, or an input / output interface.

[0078] Eighthly, a chip is provided, including processing circuitry for running a program or instructions to cause the method as described in the first aspect or any possible implementation thereof to be implemented, or to cause the method as described in the second aspect or any possible implementation thereof to be implemented, or to cause the method as described in the third aspect or any possible implementation thereof to be implemented, or to cause the method as described in the fourth aspect or any possible implementation thereof to be implemented.

[0079] Optionally, the chip may further include a memory for storing programs or instructions.

[0080] Optionally, the chip may also include transceiver circuitry, or input / output interfaces.

[0081] A ninth aspect provides a computer-readable storage medium comprising instructions that, when executed by a processor, cause the method of the first aspect or any possible implementation thereof to be implemented, or cause the method of the second aspect or any possible implementation thereof to be implemented, or cause the method of the third aspect or any possible implementation thereof to be implemented, or cause the method of the fourth aspect or any possible implementation thereof to be implemented.

[0082] In a tenth aspect, a computer program product is provided, the computer program product comprising computer program code or instructions, which, when executed, cause the method of the first aspect and any possible implementation thereof to be implemented, or cause the method of the second aspect and any possible implementation thereof to be implemented, or cause the method of the third aspect and any possible implementation thereof to be implemented, or cause the method of the fourth aspect and any possible implementation thereof to be implemented.

[0083] Eleventhly, a communication system is provided, the communication system including means for performing the second aspect and any possible implementation thereof, or including means for performing the third aspect and any possible implementation thereof, or including means for performing the fourth aspect and any possible implementation thereof.

[0084] It should be understood that the second to eleventh aspects of this application correspond to the technical solutions of the first aspect of this application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation are similar, and will not be repeated here. Attached Figure Description

[0085] Figure 1 is a schematic diagram of a communication system applicable to the communication method of this application embodiment;

[0086] Figure 2 is a schematic diagram of another communication system applicable to the communication method of this application embodiment;

[0087] Figure 3 is a schematic diagram of a possible application framework in a communication system;

[0088] Figure 4 is a schematic diagram of another possible application framework in a communication system;

[0089] Figure 5 is a schematic diagram of the lifecycle management system provided in an embodiment of this application;

[0090] Figure 6 is a schematic diagram of a lifecycle management system provided in another embodiment of this application;

[0091] Figure 7 is a schematic flowchart of the communication method provided in an embodiment of this application;

[0092] Figure 8 is a schematic diagram of the lifecycle management system for the AI ​​model provided in an embodiment of this application;

[0093] Figure 9 is a schematic flowchart of the communication method provided in an embodiment of this application;

[0094] Figure 10 is a schematic block diagram of a communication device provided in an embodiment of this application;

[0095] Figure 11 is another schematic block diagram of the communication device provided in an embodiment of this application;

[0096] Figure 12 is a schematic block diagram of the AI ​​processor provided in an embodiment of this application. Detailed Implementation

[0097] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0098] To facilitate understanding of the embodiments of this application, the following points will be explained first:

[0099] First, in this application, the indication includes direct indication (also known as explicit indication) and indirect indication (also known as implicit indication). Directly indicating information A means including information A; indirectly indicating information A can mean indicating information A through the correspondence between information A and information B and by directly indicating information B; or by indicating information A through a preset rule that can be used to determine A based on B and by directly indicating information B. The correspondence between information A and information B, and the preset rule, can be predefined, pre-stored, pre-burned, or pre-configured.

[0100] Second, in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates an "or" relationship between the preceding and following related objects, but it does not exclude the possibility of indicating an "and" relationship; the specific meaning can be understood in context. "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 can mean: a, b, c; a and b; a and c; b and c; or a and b and c. Here, a, b, and c can be single or multiple.

[0101] Third, the use of prefixes such as "first" and "second" in this application is merely for the purpose of distinguishing and describing different things belonging to the same name category, and does not constrain the order, size, or quantity of things. For example, "first data" and "second data" are simply different data, and do not limit the quantity of data, the order of transmission, or the relationship of priority.

[0102] Fourth, in this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which can include direct transmission via the air interface or indirect transmission by other units or modules via the air interface. "Receive information from YY" can be understood as the source of the information being YY, which can include direct reception from YY via the air interface or indirect reception from YY by other units or modules via the air interface. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface. In other words, sending and receiving can occur between devices, such as between a terminal device and a computing node, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via a bus, wiring, or interface.

[0103] Fifth, in the embodiments of this application, "when," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a time, nor do they require the device to make a judgment action when it is implemented, nor do they mean that there are other limitations.

[0104] Sixth, in this application, the words "example," "exemplarily," "for example," or "such as" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "example," "exemplarily," "for example," or "such as" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "example," "exemplarily," "for example," or "such as" is intended to present the relevant concepts in a specific manner.

[0105] The technical solutions provided in this application can be applied to various communication systems, such as: 5th generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, satellite communication systems, future communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0106] In a communication system, one network element can send signals to or receive signals from another network element. These signals can include information, signaling, or data. The term "network element" can also be replaced by an entity, network entity, device, communication equipment, communication module, node, communication node, etc. This disclosure uses a network element as an example. For instance, a communication system can include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device. It is understood that the terminal device in this disclosure can be replaced by a first network element, and the network device can be replaced by a second network element, both performing the corresponding communication methods described in this disclosure.

[0107] Figure 1 is a schematic diagram of a communication system applicable to the communication method of this application embodiment. As shown in Figure 1, the communication system 100A may include at least one access network device, such as access network device 110 shown in Figure 1; the communication system 100A may also include at least one terminal device, such as terminal device 120 and terminal device 130 shown in Figure 1. Access network device 110 and terminal devices (such as terminal device 120 and terminal device 130) can communicate via a wireless link. The communication devices in this communication system, for example, access network device 110 and terminal device 120, can communicate via multi-antenna technology.

[0108] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, thus requiring increasingly diverse demands. For example, networks need to support ultra-high speeds, ultra-low latency, and / or massive connectivity. This characteristic makes network planning, network configuration, and / or resource scheduling increasingly complex. Furthermore, as network functions become more powerful, such as supporting higher spectrum levels, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming (BF), and supporting beam management, network energy efficiency has become a hot research topic. These new demands, new scenarios, and new characteristics bring unprecedented challenges to network planning, operation, and efficient operation. To meet these challenges, artificial intelligence (AI) technology can be introduced into wireless communication networks to achieve network intelligence. To support AI technology in wireless networks, AI nodes may also be introduced.

[0109] Figure 2 is a schematic diagram of another communication system applicable to the communication method of this application embodiment. Compared with the communication system 100A shown in Figure 1, the communication system 100B shown in Figure 2 further includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building training datasets or training AI models. The AI ​​network element can also be simply referred to as an intelligent network element.

[0110] In one possible implementation, access network device 110 can send data related to the training of the AI ​​model to AI network element 140, which then constructs a training dataset and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by terminal devices. AI network element 140 can send the results of operations related to the AI ​​model to access network device 110, which then forwards them to the terminal devices. For example, the results of operations related to the AI ​​model may include at least one of the following: a trained AI model, model evaluation results, or test results. Exemplarily, a portion of the trained AI model may be deployed on access network device 110, and another portion on terminal devices 120 and / or 130. Alternatively, the trained AI model may be deployed on access network device 110. Or, the trained AI model may be deployed on terminal devices 120 and / or 130.

[0111] It should be understood that Figure 2 is only used as an example of the AI ​​network element 140 being directly connected to the access network device 110. In other scenarios, the AI ​​network element 140 can also be connected to the terminal device. Alternatively, the AI ​​network element 140 can be connected to both the access network device 110 and the terminal device simultaneously. Alternatively, the AI ​​network element 140 can also be connected to the access network device 110 through a third-party network element. This application embodiment does not limit the connection relationship between the AI ​​network element and other network elements. For example, the AI ​​network element 140 can also be set as a module in the access network device and / or the terminal device, for example, in the access network device 110 or the terminal device shown in Figure 1.

[0112] It should be noted that Figures 1 and 2 are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 1 and 2. In practical applications, the communication system may include multiple access network devices and multiple terminal devices. The embodiments of this application do not limit the number of access network devices and terminal devices included in the communication system.

[0113] In the embodiments of this application, the terminal device may also be referred to as UE, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user equipment.

[0114] Terminal devices can be devices that provide voice / data, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, wearable devices, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0115] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0116] In this embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or it can be any device capable of supporting the terminal device in implementing those functions, such as a chip system. This device can be installed in or used in conjunction with the terminal device. In this embodiment, the chip system can be composed of chips or may include chips and other discrete components. This embodiment only uses the terminal device as an example to illustrate the device for implementing the functions of the terminal device, and does not constitute a limitation on the solution of this embodiment.

[0117] The access network device in this application embodiment can be a device used to communicate with terminal devices. This access network device can also be called a network device, such as a base station. In this application embodiment, the access network device can refer to a RAN node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names such as: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, auxiliary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, a device that performs base station functions in D2D, V2X, and M2M communications, or a device that performs base station functions in future communication systems. A base station can support networks using the same or different access technologies. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in V2X technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technology or equipment form used in the access network equipment.

[0118] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0119] In some deployments, the access network equipment mentioned in the embodiments of this application may be a device including a CU, or a DU, or a device including both CU and DU, or a device with a control plane CU node (central unit-control plane (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)) and a DU node. For example, the access network equipment may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0120] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or RUs. CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio frequency equipment or radio frequency units, such as RRUs, AAUs, or RRHs.

[0121] RAN nodes can support one or more types of fronthaul interfaces, each corresponding to a DU and RU with different functions. If the fronthaul interface between the DU and RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and RU is another type of interface, relative to CPRI, some downlink and / or uplink baseband functions, such as, for downlink, precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix addition (CP), are moved from the DU to the RU; and for uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / cyclic prefix removal (CP), are moved from the DU to the RU. In one possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the segmentation between DU and RU differs, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0122] Taking eCPRI Cat A as an example, for downlink transmission, layer mapping is used as the dividing line. DU is configured to implement one or more functions preceding layer mapping (i.e., coding, rate matching, scrambling, modulation, and layer mapping), while other functions following layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more functions in inverse fast Fourier transform (IFFT) / adding CP) are moved to RU. For uplink transmission, de-RE mapping is used as the dividing line. DU is configured to implement one or more functions preceding de-mapping (i.e., decoding, rate matching de-matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping), while other functions following de-mapping (e.g., digital BF or FFT / removing CP) are moved to RU. Understandably, the functional descriptions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol, and will not be elaborated here.

[0123] In one possible design, the processing unit in the BBU used to implement baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH used to implement baseband functions is called the baseband low (BBL) unit.

[0124] 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 open RAN (ORAN) architecture, CU can also be called open CU (open-CU, O-CU), DU can also be called open DU (open-DU, O-DU), CU-CP can also be called open CU-CP (open-CU-CP) O-CU-CP, CU-UP can also be called open CU-UP (open-CU-UP, O-CU-UP), and RU can also be called open RU (open-RU, O-RU). 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 modules and hardware modules.

[0125] In this embodiment, the apparatus for implementing the functions of a network device can be a network device itself; it can also be an apparatus capable of supporting the network device in implementing those functions, such as a chip system, hardware circuit, software module, or a hardware circuit plus a software module. This apparatus can be installed in the network device or used in conjunction with the network device. In this embodiment, the example of a network device being used to implement the functions of a network device is provided only and does not constitute a limitation on the solutions described in this embodiment.

[0126] Network devices and / or terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located. Furthermore, terminal devices and network devices can be hardware devices, or software functions running on dedicated hardware or general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal devices and network devices.

[0127] Optionally, the AI ​​node can be deployed in one or more of the following locations within the communication system: access network equipment, terminal equipment, or core network elements. Alternatively, the AI ​​node can also 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. The AI ​​node can communicate with other devices in the communication system, which can be, for example, one or more of the following: access network equipment, terminal equipment, or core network elements.

[0128] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, they can be divided based on function, such as different AI nodes being responsible for different functions.

[0129] 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.

[0130] AI nodes can be AI network elements or AI modules.

[0131] Figure 3 illustrates a possible application framework in a communication system. As shown in Figure 3, network elements in the communication system are connected via interfaces (e.g., next-generation (NG) interfaces, Xn interfaces) or air interfaces. The NG interface is the interface between the radio access network and the 5G core network. The Xn interface is the interface between access network devices, and the air interface is the interface between access network devices and terminal devices. These network element nodes, such as core network devices, access network nodes (RAN nodes), terminals, or one or more devices in the OAM, are equipped with one or more AI modules (only one is shown in Figure 3 for clarity). The access network node can be a single RAN node or can include multiple RAN nodes, for example, including RU, CU, and DU. One or more of the RU, CU, or DU can also be equipped with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI modules are configured in CU-CP and / or CU-UP.

[0132] The AI ​​module is used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model 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 bias in the activation function), input parameters (e.g., type and / or dimension of input parameters), or output parameters (e.g., type and / or dimension of output parameters). The bias in the activation function can also be referred to as the neural network bias.

[0133] 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.

[0134] Network devices can be network devices equipped with one or more AI modules. These network devices can include one or more devices from the core network equipment, access network nodes (RAN nodes), or operation administration and maintenance (OAM) systems shown in Figure 3. For example, the AI ​​module can be a RAN intelligent controller (RIC) as shown in Figure 4, such as a near-real-time RIC (near-RT RIC) or a non-real-time RIC (non-RT RIC). For instance, a near-real-time RIC is located in a RAN node (e.g., in a CU or DU), while a non-real-time RIC is located in OAM, a cloud server, a core network device, or other access network devices. The RIC can obtain subsets from multiple terminal devices from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU), reassemble them into a training dataset, and train based on this dataset. Exemplarily, near-real-time RICs and non-real-time RICs can also be configured as separate network elements, and the access network device can be either a near-real-time RIC or a non-real-time RIC.

[0135] Figure 4 illustrates another possible application framework in a communication system. In addition to access network nodes (CU, DU, and RU are shown in the figure) and terminals, the communication system shown in Figure 4 also includes an RIC (Regulator-Integrated Circuit). For example, the RIC could be the AI ​​module shown in Figure 3, which can be used to implement AI-related functions. The RIC includes near-real-time RICs and non-real-time RICs. Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency on the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency on the order of tens of milliseconds.

[0136] The near real-time RIC is used for model training and inference. For example, it can be used to train an AI model and then use that AI model for inference. The near real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data. Optionally, the near real-time RIC can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, the near real-time RIC delivers the inference result to the DU, and the DU sends it to the RU.

[0137] The non-real-time RIC is also used for model training and inference. For example, it can be used to train an AI model and then use that model for inference. The non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., one or more of CU, CU-CP, CU-UP, DU, or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU; for example, the non-real-time RIC delivers the inference results to the DU, which then forwards them to the RU.

[0138] The near real-time RIC and non-real-time RIC can also be set up as separate network elements. Optionally, the near real-time RIC and non-real-time RIC can also be part of other devices. For example, the near real-time RIC can be set in the RAN node (e.g., in CU, DU), while the non-real-time RIC can be set in the OAM, cloud server, core network device, or other network device.

[0139] To facilitate understanding of the embodiments of this application, the terms involved in this application will be briefly explained below.

[0140] 1. AI Model: A function model that maps an input of a certain dimension to an output of a certain dimension. Its parameters can be obtained through machine learning (ML). For example, f(x) = ax 2 +b is a quadratic function model, which can be viewed as an AI model. a and b correspond to the parameters of the model and can be obtained through machine learning training.

[0141] 2. Model training: By selecting an appropriate loss function, the model parameters are trained using optimization algorithms to minimize the difference between the model's predicted value and the ground truth (or target value, label).

[0142] The model training methods involved in this application include supervised learning, self-supervised learning, and knowledge distillation. These methods will be explained in detail below.

[0143] Supervised learning, also known as supervised instruction, involves using machine learning algorithms to learn the mapping relationship between sample values ​​and labels based on collected sample values ​​and labels. This learned mapping relationship is then expressed using a machine learning model. The process of training the machine learning model is the process of learning this mapping relationship. For example, in signal detection, the noisy received signal is the sample, and the corresponding real constellation point is the label. Machine learning aims to learn the mapping relationship between samples and labels through training, that is, to enable the machine learning model to learn a signal detector. During training, the model parameters are optimized by calculating the error between the model's predicted values ​​and the real labels. Once the mapping relationship is learned, it can be used to predict the sample label of each new sample. The mapping relationship learned in supervised learning can include linear and nonlinear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0144] Self-supervised learning is a type of unsupervised learning. Unsupervised learning relies on collected sample values ​​to allow algorithms to discover inherent patterns within the samples themselves. Self-supervised learning uses the samples themselves as supervisory signals; that is, the model learns the mapping relationship from sample to sample. During training, model parameters are optimized by calculating the error between the model's predicted values ​​and the actual samples. Self-supervised learning can be used in signal compression and decompression recovery applications; common algorithms include autoencoders and generative adversarial networks.

[0145] Knowledge distillation: Generally, large models are often single complex networks or collections of networks, possessing excellent performance and generalization ability, while small models, due to their smaller network size, have limited expressive power. Therefore, the knowledge learned by the large model can be used to guide the training of the small model; this process is called knowledge distillation. Knowledge distillation can enable small models to achieve performance comparable to large models, but with fewer parameters and shorter inference latency, thus achieving model compression and acceleration. Furthermore, directly training small models with massive amounts of data often does not yield good performance, while training large models with massive amounts of data and then using the large model to perform knowledge distillation on the small model can achieve better continuation results. In addition, knowledge distillation can also be used to integrate and transfer datasets from different domains.

[0146] Knowledge distillation employs a teacher-student model, where a teacher model assists in training a student model. The teacher model is a complex, large model, while the student model is a simple, small model. Because the teacher model has strong learning capabilities, it can transfer the knowledge it learns to the relatively weaker student model, thereby enhancing the student model's generalization ability. The complex, cumbersome, but effective teacher model remains offline, simply acting as a mentor; the flexible and lightweight student model is the one actually deployed for prediction tasks.

[0147] 3. AI Agent: An AI agent is an intelligent entity capable of perceiving its environment, making decisions, and executing actions, primarily based on a large language model (LLM). Compared to traditional large models, agents can autonomously decompose tasks, plan action steps, and invoke tools to complete tasks after receiving target instructions. The core advantage of an agent lies in its ability to think and act independently. Besides being an intelligent entity, an agent can also be called a proxy, intelligent agent, digital agent, machine agent, or wireless system agent, etc.

[0148] The working principle of an agent can be summarized into four core capabilities:

[0149] (1) Perception: Perceive the environment and acquire external information through sensors or data interfaces.

[0150] (2) Analysis: Use analytical tools such as large language models to extract valuable features and patterns.

[0151] (3) Decision-making: Based on the analysis results, formulate a reasonable action plan.

[0152] (4) Execution: Transform decisions into concrete actions to accomplish target tasks.

[0153] Typical learning methods for agents include:

[0154] (1) In-context learning: Using a general model, the model is provided with cue words, tools, and examples during inference, enabling the model to "learn on the fly" how and when to use these tools for a specific task. For example, the reasoning + acting (ReAct) framework is an example of in-context learning.

[0155] (2) Retrieval-based in-context learning: This involves dynamically populating model prompts by retrieving relevant information, tools, and examples from external storage. For example, the retrieval-augmented generation (RAG) framework is an example of retrieval-based in-context learning.

[0156] (3) Fine-tuning based learning: The model is trained (fine-tuned) with a large number of specific examples, and then inference is performed using the fine-tuned model. The fine-tuned model already has prior knowledge of when and how to use the model tools before processing requests.

[0157] In this application, an intelligent agent can generally be considered as a proxy that can autonomously complete a set goal through action. "Intelligent agent" and "intelligence" are inseparable; it possesses some human-like intelligent abilities and behaviors, such as learning, reasoning, decision-making, and execution capabilities. Optionally, the intelligent agent can be replaced with other terms, such as artificial general intelligence (AGI), artificial intelligence, AI controller, intelligent unit, intelligent entity, or intelligent agent, etc. This application does not limit the name of the intelligent agent, as long as it can achieve the corresponding function.

[0158] In this application, the intelligent agent can be integrated into the existing hardware / software of the communication device, or the intelligent agent can be independent of the existing hardware / software of the communication device. The existing hardware / software may include at least one of the following: a chip, a baseband chip, a modem chip, a SoC chip containing a modem core, a SIP chip, a communication module, a chip system, a processor, a logic module, or software, etc.

[0159] The above description of the terminology is for ease of understanding only and does not limit the scope of protection of the embodiments of this application.

[0160] Current AI model lifecycle management (LCM) is geared towards managing specific models and / or functions. In other words, the goal of current AI model LCM is to achieve optimal or near-optimal performance for a single model or function. Therefore, LCM for AI models is not applicable to agent-based LCM.

[0161] In view of this, embodiments of this application provide an LCM suitable for AI agents, thereby helping to optimize the performance of communication systems.

[0162] The communication method provided in this application embodiment will be described below with reference to the accompanying drawings, taking the interaction between various devices as an example.

[0163] To facilitate understanding of this application, the system for LCM of AI agents provided in the embodiments of this application will first be described in detail with reference to Figures 5 and 6.

[0164] As shown in Figure 5, the LCM system includes sensing, planning, execution, and tooling functions. Optionally, the LCM system also includes a memory function.

[0165] Sensing Function: Used to acquire data. For example, the sensing function acquires the following types of data: channel measurement data collected via the air interface, signal measurement data collected via the air interface, synthetic data, sensor data or environmental data from the terminal side, environmental data from the network side, application data, etc. Channel measurement data and / or signal measurement data can also be referred to as observation data. Optionally, data acquired by the sensing function after the execution function has performed at least one task can be referred to as task-related feedback information or reflection data. The sensing function also sends the acquired data to the memory function, planning function, or execution function. As shown in Figure 5, the data sent by the sensing function to the memory function may include environmental data and / or feedback information. The data sent by the sensing function to the planning function may include observation data and / or reflection data. The data sent by the sensing function to the execution function may include observation data. Exemplarily, the sensing function can be deployed on the terminal side or the network side.

[0166] Memory function: This function receives data from the sensing function and stores and / or processes the received data. For example, data processing methods include cleaning, filtering, preprocessing, normalization, compression, or feature extraction. The memory function also sends stored unprocessed and / or processed data to the planning and / or tooling functions. For instance, the memory function can perform feature extraction on received environmental and / or observation data; the processed data obtained from feature extraction can be referred to as prior knowledge. The memory function can then send this prior knowledge to the planning function. Exemplarily, the memory function can be deployed on the network side or the core network side.

[0167] Planning Function: This function uses received data to plan upcoming tasks and obtain planning results. These results may include one or more of the following: the tools required to execute the task, the data types needed for the task, and the data acquisition methods required for the task. The planning function can also manage other functions within the LCM system. For example, it can manage the data acquisition methods and cycles of the sensing function. It can manage the data processing methods of the memory function. For example, it can manage the tools included in the tool function, such as activation, deactivation, or update tools. It can manage the task execution methods and cycles of the execution function. For example, the planning function can be deployed on the network side or the core network side.

[0168] Execution function: Executes tasks based on instructions from the planning function. For example, an execution function executes a task by invoking at least one tool from the tool functions, based on instructions from the planning function. For instance, the execution function can be deployed on the terminal side or the network side.

[0169] Tool Functionality: Includes at least one tool and provides the tool to the execution function so that the execution function can perform tasks using the tool provided by the tool functionality. The tool functionality can also update the tool based on data from memory and / or perception functions. Exemplarily, the tool functionality can be deployed on the terminal side or the network side.

[0170] For example, the tool functionality includes at least one tool associated with one or more of the following: a network-side transmission function module, a network-side reception function module, a network-side measurement function module, a terminal-side transmission function module, a terminal-side reception function module, or a terminal-side measurement function module.

[0171] For example, the at least one tool includes one or more of the following: an AI model or AI function for implementing at least one function of a network-side transmission function module; a non-AI algorithm tool for implementing at least one function of a network-side transmission function module; an AI model or AI function for implementing at least one function of a network-side reception function module; a non-AI algorithm tool for implementing at least one function of a network-side reception function module; an AI model or AI function for implementing at least one function of a network-side measurement function module; a non-AI algorithm tool for implementing at least one function of a network-side measurement function module; an AI model or AI function for implementing at least one function of a terminal-side transmission function module; a non-AI algorithm tool for implementing at least one function of a terminal-side transmission function module; an AI model or AI function for implementing at least one function of a terminal-side reception function module; a non-AI algorithm tool for implementing at least one function of a terminal-side reception function module; an AI model or AI function for implementing at least one function of a terminal-side measurement function module; and a non-AI algorithm tool for implementing at least one function of a terminal-side measurement function module.

[0172] For example, the transmission function module on the network side and / or the terminal side includes one or more of the following: baseband processing module, digital front-end (DFE), and radio frequency processing module.

[0173] 1. The baseband processing module includes one or more of the following functions or functional modules.

[0174] Channel coding: Adding redundant information (such as low-density parity check code, turbine code, polar code, etc.) to the original data to improve anti-interference and error correction capabilities.

[0175] Modulation: Converting digital bit streams into analog symbols (such as quadrature phase shift keying (QPSK), quadrature amplitude modulation (QAM), 256QAM, etc.) to adapt to the characteristics of wireless channels.

[0176] Multicarrier modulation (orthogonal frequency division multiplexing (OFDM) / orthogonal frequency division multiplexing access (OFDMA)): improves spectrum efficiency by dividing spectrum resources through orthogonal subcarriers.

[0177] MIMO processing: Supports multi-antenna technologies (such as spatial multiplexing, beamforming, and precoding) to improve channel capacity and coverage.

[0178] Resource mapping: Mapping data to physical resource blocks (PRBs) to complete the allocation of time-frequency resources.

[0179] 2. The digital front end includes one or more of the following functions or functional modules.

[0180] Digital upconverter (DUC): Shifts the baseband signal to the intermediate frequency (IF).

[0181] Digital pre-distortion (DPD): compensates for nonlinear distortion in a power amplifier (PA).

[0182] Beamforming: Achieves directional signal transmission by adjusting the phase and amplitude of the antenna array (a core function in massive MIMO).

[0183] 3. The radio frequency processing module includes one or more of the following functions or functional modules.

[0184] Mixer: Upconverts intermediate frequency signals to radio frequency (such as Sub-6 GHz or millimeter wave bands).

[0185] Power amplifier: Amplifies signal power to meet coverage requirements, while balancing efficiency and linearity.

[0186] Filters: Suppress out-of-band spurious signals and ensure compliance with spectrum specifications (e.g., low-pass / band-pass filters).

[0187] RF switch / duplexer: Enables shared antenna for both transmit and receive (switching between TDD / FDD modes).

[0188] For example, the receiving function module on the network side and / or the terminal side includes one or more of the following: radio frequency processing module, digital front end, baseband processing module or control and auxiliary module.

[0189] 1. The radio frequency processing module includes one or more of the following functions or functional modules.

[0190] Low noise amplifier (LNA): Amplifies weak received signals while minimizing noise introduction (corresponding to the power amplifier on the transmitting side).

[0191] Filters: Suppress out-of-band interference and noise (such as bandpass filters).

[0192] Mixer: Converts radio frequency signals down to intermediate frequency (IF) or baseband frequency.

[0193] RF switch / duplexer: Enables transmit and receive isolation in TDD / FDD mode to avoid signal interference.

[0194] 2. The digital front end includes one or more of the following functions or functional modules.

[0195] Digital downconverter (DDC): Converts intermediate frequency signals to baseband.

[0196] Automatic gain control (AGC): Dynamically adjusts the signal gain to match the dynamic range of the analog-to-digital converter (ADC).

[0197] Anti-aliasing filtering: Eliminates high-frequency components and prevents aliasing of the sampled signal.

[0198] 3. The baseband processing module includes one or more of the following functions or functional modules.

[0199] Synchronization and timing recovery: (1) Frame synchronization: locate the frame start position of the signal; (2) Carrier synchronization: compensate for frequency offset and phase noise; (3) Symbol synchronization: determine the precise sampling time of the symbol (e.g., through a matched filter).

[0200] Channel estimation and equalization: (1) Use reference signals (such as pilots, demodulation reference signals (DMRS)) to estimate channel characteristics and eliminate multipath effects and frequency selective fading; (2) Use equalization algorithms (such as minimum mean squared error (MMSE) and zero-forcing (ZF) equalization) to compensate for channel distortion.

[0201] MIMO detection: Separating multiple signals in a multi-antenna system (e.g., maximum likelihood detection, successive interference cancellation (SIC), ZF / MMSE detection algorithm).

[0202] Demodulation: Mapping symbols back to the bitstream (e.g., QPSK, 16QAM demodulation).

[0203] Channel decoding: Using error-correcting codes (such as LDPC and Turbo codes) to recover the original data and correct bit errors during transmission.

[0204] Multi-carrier demodulation (OFDM / OFDMA): Converts the time-domain signal into frequency-domain subcarriers using FFT and extracts the data on each subcarrier.

[0205] 4. The control and auxiliary module includes one or more of the following functions or functional modules.

[0206] Interference cancellation: suppressing co-channel interference and multi-user interference (such as SIC technology in non-orthogonal multiple access (NOMA) systems).

[0207] Resource demapping: Extracting user data from physical resource blocks (PRBs).

[0208] The medium / media access control (MAC) layer processes: parsing control signaling and coordinating multi-user scheduling.

[0209] For example, the measurement function module on the network side and / or the terminal side includes one or more of the following functions or modules: channel measurement based on reference signals, channel feedback, or channel acquisition. The type of reference signal can be any of the following: sounding reference signal (SRS), demodulation reference signal (DMRS), phase tracking reference signal (PT-RS), channel state information reference signal (CSI-RS), or synchronization signal (SS). The synchronization signal can include a primary synchronization signal (PSS) and a secondary synchronization signal (SSS).

[0210] As shown in Figure 6, the aforementioned perception function can be called agent perception. The aforementioned planning function can be called agent planning. The aforementioned execution function can be called agent execution. The aforementioned tool function can be called a tool library. Optionally, the tool library shown in Figure 6 can possess the functions of the aforementioned memory function.

[0211] As shown in Figure 6, agent perception can acquire data through measurement (e.g., measuring reference signals) and / or environmental perception. Agent perception can also send data (e.g., training data) to a tool library. Accordingly, the tool library can update tools based on the training data. Agent perception can also send data (e.g., inference data) to agent execution. Accordingly, agent execution can perform tasks (e.g., performing inference tasks) based on the inference data. Agent perception can also send data (e.g., monitoring data) to agent planning. Accordingly, agent planning can monitor the performance of tools in the tool library and / or monitor the task execution process of the agent based on the monitoring data.

[0212] Optionally, as shown in Figure 6, the agent execution can also send execution feedback to the agent planner or tool library to provide feedback on the execution results of the tasks performed by the agent. Accordingly, the tool library can update its tools based on the execution feedback. The agent planner can update its planned path based on the execution feedback, such as updating the tools invoked by the agent execution for performing the tasks.

[0213] Optionally, as shown in Figure 6, different agents can also interact with each other, such as by exchanging data and / or task planning results.

[0214] The communication method provided in this application embodiment will be described below with reference to Figure 7, taking the interaction between various devices as an example.

[0215] It should be noted that the first device or the sixth device in the following embodiments is a device for deploying the planning function described above. Alternatively, the first device or the sixth device may be a functional entity, network element, circuit, or chip, etc., that deploys the planning function described above. The first device and the sixth device are different devices. The first device or the sixth device can be replaced by a planning function.

[0216] In the embodiments described below, the second device is a device for deploying the execution function described above, or the second device may be a functional entity, network element, circuit, or chip, etc., for deploying the execution function described above. The second device can be replaced by the execution function.

[0217] In the embodiments below, the third device is a device for deploying the memory function described above, or the third device may be a functional entity, network element, circuit, or chip, etc., that deploys the memory function described above. The third device can be replaced by the memory function.

[0218] In the embodiments described below, the fourth device is a device for deploying the sensing function described above. Alternatively, the fourth device may be a functional entity, network element, circuit, or chip that deploys the sensing function described above. The fourth device can be replaced by the sensing function itself.

[0219] In the embodiments described below, the fifth device is a device for deploying the tool functions described above. Alternatively, the fifth device may be a functional entity, network element, circuit, or chip, etc., that deploys the tool functions described above. The fifth device may be replaced by a tool function.

[0220] In the embodiments below, the different devices among the first to fifth devices can be the same device or different devices, and this application does not limit this. In other words, the different functions among the planning function, execution function, memory function, perception function, and tool function mentioned above can be deployed on the same device or on different devices, and this application does not limit this. If the multiple devices among the first to fifth devices in the embodiments below are the same device, then the steps involving interaction between the multiple devices in the embodiments below can be interactions between different functional modules of the same device. For example, if the first device and the fifth device below are the same device, then the interaction between the first device and the fifth device is the interaction between the planning function and the tool function of the same device. That is, the first device to the fifth device can be replaced by the first entity to the fifth entity, or the first functional entity to the fifth functional entity, respectively. Similarly, the sixth device mentioned in the embodiments below and the different devices among devices #a to #c can be the same device or different devices. If the sixth device and the multiple devices among devices #a to #c are the same device, then the interaction between the sixth device and the multiple devices among devices #a to #c can be the interaction between different functional modules of the same device. That is, the sixth device and devices #a to #c can be replaced by the sixth entity and entities #a to #c, or the sixth functional entity and functional entities #a to #c. For example, if the sixth device and device #a are the same device in the following text, then the interaction between the sixth device and device #a is the interaction between the planning function and the execution function of the same device.

[0221] It should also be noted that the first to fifth devices in the following embodiments can be replaced by devices on the terminal device side, devices on the network device side, or devices on the core network (CN) side.

[0222] The devices on the terminal device side can include the terminal device itself, the communication module within the terminal device, or the circuits or chips within the terminal device responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core, etc.), or can be included in the AI ​​entities on the terminal device side. The AI ​​entities on the terminal device side can be the terminal device itself, or they can be AI entities that serve the terminal device, such as servers, such as OTT servers or cloud servers.

[0223] Network device-side equipment can include the network device itself, communication modules within the network device, or circuits or chips within the network device responsible for communication functions (such as modem chips, also known as baseband chips, or system-on-a-chip (SoC) chips or SIP chips containing modem cores, etc.), or it can include AI entities on the network device side. AI entities on the network device side can be the network device itself, or AI entities serving the network device, such as RICs, OAMs, or servers, such as OTT servers or cloud servers.

[0224] The equipment on the core network side may include the core network element itself, the communication module in the core network element, or the circuit or chip in the core network element responsible for communication functions, or it may include AI entities on the core network side. The AI ​​entities on the core network side can be the core network element itself, or they can be AI entities that serve the core network element, such as servers, such as OTT servers or cloud servers.

[0225] Figure 7 is a schematic flowchart of a communication method 700 provided in an embodiment of this application. The steps of method 700 will be described in detail below.

[0226] S701, Fourth device acquires data #1.

[0227] For example, data #1 may include one or more of the following: acquired data (e.g., measurement data), synthetic data (e.g., data generated by a simulation model or generative model), sensor data (e.g., velocity information, position information, etc.), or environmental perception data (e.g., environmental images). The above data acquired by the fourth device may be obtained by the fourth device through measurement, environmental perception, etc., or may be sent to the fourth device by other devices; this application does not limit this.

[0228] Optionally, the fourth device may periodically acquire data #1, or acquire data #1 based on a triggering action by the first device. For example, the first device may send data acquisition configuration information to the fourth device to trigger the fourth device to acquire data #1.

[0229] The data acquisition configuration information may include one or more of the following: data type, data acquisition area, data acquisition time, data acquisition cycle, configuration information for the reference signal used to obtain the data, acquired data content, and system configuration information used to obtain the data. The data type may include one or more of the following: acquired data (e.g., measurement data), synthetic data (e.g., data generated through a generative model), simulation data, sensor data, or environmental perception data.

[0230] S702, the fourth device transmits data #1.

[0231] Accordingly, the third device receives data #1.

[0232] After receiving data #1, the third device can store data #1.

[0233] Optionally, the third device may also process the data #1. For example, the third device may process the data #1 in one or more of the following ways: data cleaning, data filtering, normalization, compression, or feature extraction.

[0234] The purpose of data cleaning is to remove noise, duplication, and outliers from the data to ensure data quality and accuracy. For example, data cleaning may include the following steps: (1) Remove duplicate data: delete duplicate records by comparing data; (2) Deal with missing values: solve the problem of missing values ​​by using interpolation, deletion, or filling methods according to the characteristics of the data; (3) Handle outliers: identify and handle outliers in the dataset that are significantly outside the normal range.

[0235] Data filtering is a method used to select, exclude, or extract specific portions of a dataset. The purpose of data filtering is to narrow down the dataset, focusing on key data to improve the efficiency and accuracy of data use. Through data filtering, data that meets specific conditions or rules can be selected from the overall dataset to satisfy specific needs or conduct further analysis. For example, comparison operators (such as greater than, less than, or equal to) can be used to filter data that meets specific criteria. Another example is filtering data by limiting the data collection area and / or the data collection time.

[0236] Data normalization aims to transform numerical data of different ranges, scales, or units into a uniform, dimensionless scale, typically within a specific small interval, such as [0, 1] or [-1, 1]. This process is achieved through linear transformation, ensuring that all features or variables are on the same basis when compared and analyzed.

[0237] Data compression is the process of encoding original data with less space. That is, it is a technical method that reduces the amount of data to reduce storage space and improve the efficiency of data transmission, storage and processing without losing useful information, or reorganizes data according to certain algorithms to reduce data redundancy and storage space.

[0238] Feature extraction involves selecting, transforming, and combining relevant information from raw data to better represent the essential characteristics of the data.

[0239] For example, the data processed by the third device after processing data #1 can be referred to as prior knowledge.

[0240] It should be noted that S702 is an optional step. For example, if the fourth device has the function of storing data, then the fourth device may not need to send data #1 to the third device. Or, for example, the fourth device may directly send the acquired data #1 to the device that uses data #1, such as the first device, the second device, or the fifth device, without sending data #1 to the third device, so that the third device can store data #1.

[0241] S703, the third device transmits data #1.

[0242] Accordingly, the fifth device receives data #1 (an example of the eighth data in the invention).

[0243] Optionally, if the third device processes data #1, the third device may send the processed data to the fifth device.

[0244] Optionally, after receiving data #1, the fifth device can obtain at least one first tool based on data #1. For example, the fifth device can update the initialized tool based on data #1 to obtain at least one first tool. Alternatively, the fifth device can update at least one previously obtained tool #a based on data #1 to obtain at least one first tool.

[0245] Optionally, after obtaining at least one first tool, the fifth device may send information about the at least one first tool to the first device. For example, if the at least one first tool includes AI model #1, the fifth device may send the identifier of AI model #1 and / or the function of AI model #1 to the first device. Alternatively, if the first device can directly read or obtain information about the at least one first tool included in the fifth device, the fifth device may not need to send information about the at least one first tool to the first device. For example, if the first device and the fifth device are the same device, the first device can directly read or obtain information about the at least one first tool included in the fifth device.

[0246] For example, at least one first tool is associated with one or more of the following: a network-side transmission function module, a network-side reception function module, a network-side measurement function module, a terminal-side transmission function module, a terminal-side measurement function module, or a terminal-side reception function module.

[0247] For example, the at least one first tool includes one or more of the following: an AI model or AI function for implementing at least one function of a network-side transmission function module; a non-AI algorithm tool for implementing at least one function of a network-side transmission function module; an AI model or AI function for implementing at least one function of a network-side reception function module; a non-AI algorithm tool for implementing at least one function of a network-side reception function module; an AI model or AI function for implementing at least one function of a network-side measurement function module; a non-AI algorithm tool for implementing at least one function of a network-side measurement function module; an AI model or AI function for implementing at least one function of a terminal-side transmission function module; a non-AI algorithm tool for implementing at least one function of a terminal-side transmission function module; an AI model or AI function for implementing at least one function of a terminal-side reception function module; a non-AI algorithm tool for implementing at least one function of a terminal-side reception function module; an AI model or AI function for implementing at least one function of a terminal-side measurement function module; and a non-AI algorithm tool for implementing at least one function of a terminal-side measurement function module.

[0248] For further description of the transmission and / or reception and / or measurement function modules on the network side and / or terminal side, please refer to the description in Figure 5 above.

[0249] For example, taking at least one first tool as an example, which includes an AI model, the fifth device manages the AI ​​model in the manner shown in Figure 8.

[0250] The AI ​​model lifecycle management process shown in Figure 8 mainly covers the following content.

[0251] Data Collection: The fifth device collects various data required for model training, management, and inference, such as data related to CSI feedback enhancement, beam management enhancement, and positioning accuracy enhancement. For example, the fifth device receives data #1 from the third or fourth device.

[0252] Model Training: The fifth device uses the collected data to train, test, and optimize the AI ​​model. Model training can be flexibly conducted online or offline.

[0253] Model transfer: The fifth device transfers the model from one place to another, such as from the training platform (i.e., the fifth device) to the inference platform (such as the device that calls the AI ​​model).

[0254] Model inference operation: Input the inference data into the trained model to obtain the corresponding model inference output.

[0255] Model monitoring: Monitor the performance of the AI ​​model to ensure that the AI ​​model is always running in an optimal or good state, such as a state that meets performance requirements.

[0256] Model update: The fifth device updates and optimizes the model based on monitoring data and actual application needs to improve the model's performance and adaptability.

[0257] For example, the above-mentioned model inference operation can be performed by the fifth device or by the device that calls the AI ​​model (such as the second device). If the above-mentioned model inference step is performed by the fifth device, then the device that calls the AI ​​model refers to obtaining the inference result of the AI ​​model. If the above-mentioned model inference step is performed by the device that calls the AI ​​model, then the device that calls the AI ​​model refers to obtaining the AI ​​model (such as the model file and / or model parameters of the AI ​​model).

[0258] For example, the above-mentioned model monitoring operation can be performed by the fifth device or by the device that invokes the AI ​​model.

[0259] It should be noted that S703 is an optional step. For example, the fourth device can directly send the acquired data #1 to the fifth device without having to go through the third device for forwarding.

[0260] S704, the first device acquires first data related to the first task.

[0261] For example, the first data includes one or more of the following: environmental perception data, reference signal measurement results, channel measurement results, prior knowledge, or feedback information related to the execution results of the second task.

[0262] The second task is performed before the first task. Feedback information related to the execution result of the second task may include one or more of the following: feedback on whether the second task was successfully executed; environmental perception data obtained through environmental perception after executing the second task; reference signal measurement results obtained through reference signal measurement after executing the second task; and channel measurement results obtained through channel measurement after executing the second task.

[0263] For example, if the first task is CSI compression and feedback, then the first data may include reference signal measurement results and / or channel measurement results.

[0264] For example, the first data acquired by the first device is used by the first device to plan a first task. For instance, the first device may determine, based on the first data, at least one first tool to be invoked to execute the first task. Or, for example, the first device may determine, based on the first data, the cycle or method of executing the first task.

[0265] For example, if the first task is CSI compression and feedback, the first device can determine the CSI compression method as one or more of time-domain compression, frequency-domain compression, or spatial-domain compression based on the reference signal measurement results and / or channel measurement results.

[0266] For example, the first task may be initiated by the first device or by other devices, and this application does not limit this.

[0267] For example, the first device may acquire first data through one or more steps in S704a to S704c. The first data includes one or more of the third, fourth, or fifth data described below.

[0268] S704a, the third device sends third data.

[0269] Accordingly, the first device receives the third data.

[0270] For example, the third data may include prior knowledge. For instance, the third data is data obtained by the third device after processing the aforementioned data #1.

[0271] Optionally, prior to S704a, the first device may also request third data from the third device. For example, the first device sends a request message #a to the third device, whereby the request message #a requests data related to the first task. Accordingly, the third device sends third data to the first device based on the request message #a.

[0272] S704b, the fourth device sends the fourth data.

[0273] Accordingly, the first device receives the fourth data.

[0274] For example, the fourth data may include one or more of the following: environmental perception data, reference signal measurement results, channel measurement results, or feedback information related to the execution results of the second task.

[0275] Optionally, prior to S704b, the first device may also request fourth data from the fourth device. For example, the first device sends a request message #b to the fourth device, whereby the request message #b requests data related to the first task. Accordingly, the fourth device sends fourth data to the first device based on the request message #b.

[0276] S704c, the sixth device sends the fifth data.

[0277] Accordingly, the first device receives the fifth data.

[0278] For example, the fifth data may include one or more of the following: environmental perception data, reference signal measurement results, channel measurement results, or feedback information related to the execution results of the second task.

[0279] For example, the fifth data is obtained by the sixth device from a sensing device connected to the sixth device. The sensing device connected to the sixth device is different from the fourth device.

[0280] Optionally, prior to S704b, the first device may also request fifth data from the sixth device. For example, the first device sends a request message #c to the sixth device, whereby the request message #c requests data related to the first task. Accordingly, the sixth device sends the fifth data to the first device based on the request message #c.

[0281] After the first device obtains the first data based on one or more of the steps S704a to S704c, it can plan the first task based on the first data and then send the planning result of the first task (such as sending a first instruction) to the second device so that the second device can execute the first task.

[0282] S705, the first device sends the first command.

[0283] Accordingly, the second device receives the first instruction.

[0284] For example, the first instruction is used to instruct the invocation of at least one first tool to perform a first task.

[0285] Optionally, the first instruction may also be used to indicate the manner and / or period of performing the first task. For example, if the first task is CSI compression and feedback, the first instruction may also be used to indicate that the CSI compression is performed in one or more of time-domain compression, spatial-domain compression, or frequency-domain compression.

[0286] Optionally, the first instruction is used to instruct the invocation of at least one first tool to execute a first sub-task included in the first task. For example, if the first task is a task that requires the cooperation of multiple devices, i.e., the second device is used to execute the first sub-task of the first task, then the first instruction sent by the first device to the second device is used to instruct the invocation of at least one first tool to execute the first sub-task included in the first task.

[0287] For example, the first task is to locate the second device using AI. The method of locating the second device using AI may include: the second device obtaining a channel response by measuring reference signals from at least two devices #c; the second device inputting the obtained channel response into an AI model for location, thereby obtaining the location information of the second device as the output of the AI ​​model. Device #c is another device different from the second device. Based on the above method of locating the second device, the first task includes at least a first sub-task and a second sub-task. The first sub-task includes: the second device measuring reference signals from device #c to obtain a channel response; the second device obtaining the location information of the second device based on the channel response and the AI ​​model. The second sub-task includes: device #c sending a reference signal to the second device. Correspondingly, a first instruction sent by the first device to the second device instructs the invocation of the AI ​​model for location to perform the task of locating the second device.

[0288] S706, the first device sends the second command.

[0289] Accordingly, the fifth device receives the second instruction.

[0290] The second instruction is used to instruct the activation of at least one first tool, and / or the first instruction is used to instruct the delivery of at least one first tool to the second device.

[0291] Optionally, if tool #a, other than at least one first tool, is active, the first instruction is also used to instruct tool #a to be deactivated.

[0292] It should be noted that S706 is an optional step. For example, if at least one first tool is already active, then method 700 does not include S706.

[0293] S707, the first device sends the third command.

[0294] Accordingly, the sixth device receives the third instruction.

[0295] For example, the third instruction is used to instruct the execution of a second subtask that includes the first task, the second subtask being different from the first subtask.

[0296] As mentioned above, the first task requires the cooperation of multiple devices. That is, in addition to the second device executing the first sub-task, other devices different from the first device are needed to perform the first task. For example, a device with execution capabilities connected to the sixth device (denoted as device #a) can be used to execute the second sub-task included in the first task, in which case the first device can send a third instruction to the sixth device. As mentioned above, the second sub-task is to send a reference signal to the second device, and the third instruction is used to instruct the sending of the reference signal to the second device.

[0297] Accordingly, after receiving the third instruction, the sixth device can send the third instruction #1 to device #a to instruct device #a to invoke at least one first tool #a to execute the second subtask. A description of the at least one first tool #a can be found in the description of the at least one first tool above.

[0298] For example, at least one first tool #a is a tool included in a tool-functional device (denoted as device #b) connected to the sixth device. Device #b is different from the fifth device. Exemplarily, the tools included in device #b and the tools included in the fifth device are associated with transmission and / or reception and / or measurement function modules on different network sides, and / or, the tools included in device #b and the tools included in the fifth device are associated with transmission and / or reception and / or measurement function modules on different terminal sides. For example, at least one first tool included in the fifth device is associated with the transmission function module of network device #1 and the reception and measurement function modules of terminal device #1, and at least one first tool #a included in device #b is associated with the transmission function module of network device #1 and the reception and measurement function modules of terminal device #2.

[0299] In one possible implementation, device #a can perform the second subtask without invoking at least one first tool #a. For example, if the second subtask is to send a reference signal to a second device, then device #a can directly send the reference signal to the second device without invoking at least one first tool #a.

[0300] In one possible implementation, if the sixth device has the function of executing the second subtask, then the sixth device can execute the second subtask according to the instruction of the third instruction. In this case, the sixth device no longer sends the third instruction #1 to device #a. For example, if the second subtask is to send a reference signal to the second device, and the sixth device has the function of sending a reference signal, then the sixth device can send a reference signal to the second device according to the instruction of the third instruction.

[0301] S708, the fourth device sends the second data.

[0302] Accordingly, the second device receives the second data.

[0303] The second data is used to perform the first task. For example, if the first task is CSI compression and feedback, then the second data could be uncompressed CSI.

[0304] Optionally, prior to S708, the second device may also request second data from the fourth device. For example, the second device sends a request message #d to the fourth device, whereby the request message #d requests data for performing the first task. Accordingly, the fourth device sends the second data to the second device based on the request message #d.

[0305] Optionally, the second device may also receive data from the third device for performing the first task.

[0306] S709, the fifth device sends at least one first tool.

[0307] Accordingly, the second device receives at least one first tool.

[0308] Taking at least one first tool including an AI model as an example, the fifth device can send the model file and / or model parameters of the AI ​​model to the second device, so that the second device can determine the AI ​​model based on the model file and / or model parameters.

[0309] Optionally, if in S706 the fifth device receives a second instruction, and the second instruction is used to instruct the sending of at least one first tool to the second device, then in S709 the fifth device may send at least one first tool to the second device according to the instruction of the second instruction.

[0310] Optionally, prior to S709, the second device may also request at least one first tool from the fifth device. For example, the second device sends a request message #e (corresponding to an example of the first request in the invention description) to the fifth device, the request message #e being used to request at least one first tool. Accordingly, the fifth device sends at least one first tool to the second device based on the request message #e.

[0311] After the second device acquires second data and / or at least one first tool for performing the first task, it can perform the first task.

[0312] Optionally, method 700 may further include one or more of steps S710 to S715.

[0313] S710, the second device sends the first information.

[0314] Accordingly, the first device receives the first information.

[0315] The first message is used to indicate the result of the execution of the first task.

[0316] For example, the execution result of the first task is used to indicate that the first task was executed successfully, or the execution result of the first task is used to indicate that the first task failed.

[0317] For example, the result of executing the first task is the output obtained by the second device executing the first task. For instance, if the first task is CSI compression and feedback, then the output obtained by the second device executing the first task can be CSI feedback information obtained by compressing CSI.

[0318] Optionally, the execution result of the first task may also include the confidence level of the output obtained by the second device in executing the first task. For example, if the first task is a task based on an AI model, then the confidence level of the output obtained by the second device in executing the first task may be the accuracy of the AI ​​model used to execute the first task.

[0319] Optionally, after receiving the first information, the first device may also send a sixth instruction to the fifth device.

[0320] S711, the first device sends the sixth command.

[0321] Accordingly, the fifth device receives the sixth instruction.

[0322] For example, the sixth instruction is used to instruct the activation of at least one first tool. For instance, if at least one first tool is not used for other tasks after the second device performs the first task, the first device may instruct the fifth device to activate at least one first tool.

[0323] It should be noted that S711 is an optional step. For example, if the fifth device activates at least one first tool by default after at least one first tool has been in an active state for a first duration, then method 700 may not include S711.

[0324] Optionally, if the execution result of the first task indicates that the first task has failed, or if the confidence level of the output obtained by the second device from executing the first task is lower than the confidence level threshold, then the first device can re-plan the first task. That is, method 700 may include one or more steps in S712 to S715.

[0325] S712, the first device acquires the sixth data.

[0326] The sixth data is related to the first task. Further description of the sixth data, and how the first device acquires it, can be found in the description of S704, and will not be repeated here.

[0327] It should be noted that S712 is an optional step. For example, the first device can re-plan the first task based on the first data obtained earlier, then method 700 may not include S712.

[0328] S713, the first device sends the fourth command.

[0329] Accordingly, the second device receives the fourth instruction.

[0330] For example, the fourth instruction is used to instruct the invocation of at least one second tool to perform the first task. The at least one second tool is not exactly the same as the at least one first tool. Further description of the at least one second tool can be found in the description of the at least one first tool above.

[0331] S714, the first device sends the fifth instruction and / or the seventh data.

[0332] Accordingly, the fifth device receives the fifth instruction and / or the seventh data.

[0333] For example, the fifth instruction is used to instruct a tool update to obtain at least one second tool. For instance, the fifth instruction is used to instruct an update of at least one first tool to obtain at least one second tool.

[0334] For example, the seventh data is used for tool updates to obtain at least one second tool. For instance, the seventh data is the confidence level of the output obtained by the second device performing a first task based on at least one first tool.

[0335] Optionally, in S714, the fifth device may also receive data from the fourth and / or third devices for tool updates.

[0336] Optionally, after obtaining at least one second tool, the fifth device may send information about the at least one second tool to the first device. For example, if the first device can directly read or obtain information about the at least one second tool included in the fifth device, the fifth device may not send information about the at least one second tool to the first device.

[0337] S715, the second device acquires data and / or tools for performing a task.

[0338] For example, in S715, the second device acquires data for performing the first task and at least one second tool based on the fourth instruction. The method by which the second device acquires the data for performing the first task can be referred to in S708 above. The method by which the second device acquires at least one second tool can be referred to in S709 above.

[0339] This application provides a lifecycle management system suitable for agent-based wireless AI systems, including planning, execution, perception, and tool functions. Optionally, it also includes a memory function. The lifecycle management system provided by this application is beneficial for optimizing system performance.

[0340] For example, during the task planning process, the planning function can interact with other functions in the lifecycle management system to obtain data for task planning (such as initial data) and information about the tools used to execute the task (such as information about at least one tool). This helps determine task planning results that maximize the probability of task completion and / or task execution efficiency. Improving the probability of task completion and / or task execution efficiency helps optimize system performance. Furthermore, the planning function can trigger tool management processes based on the task execution results, such as tool deactivation and tool updates, thereby further optimizing system performance.

[0341] For example, compared to a lifecycle management system that uses AI models or functions as the granularity, the tool functions provided in this application embodiment can include multiple AI models or functions. This means that the lifecycle management system provided in this application can realize the lifecycle management of multiple AI models or functions, thereby improving the efficiency of system optimization.

[0342] The method provided in this application embodiment will be described below with reference to Figure 9, taking the first, third, and fifth devices as network device-side devices (network device #1 in Figure 9), the second device as terminal device-side device (UE #2 in Figure 9), the fourth device as terminal device-side device (UE #1 in Figure 9), and the sixth device as network device-side device (network device #2 in Figure 9) as examples. In other words, UE #1 in Figure 9 has the perception function described above, network device #1 has the planning function, memory function, and tool function described above, UE #2 has the execution function described above, and network device #2 has the planning function described above.

[0343] Figure 9 is a schematic flowchart of a communication method 900 provided in an embodiment of this application. The steps of method 900 will be described in detail below.

[0344] S901, UE#1 obtains data #1.

[0345] For example, the data #1 acquired by UE#1 may include one or more of the following: measurement data (such as reference signal measurement results obtained by measuring reference signals from network device #1), synthetic data, or sensor data from the UE#1 side (such as speed information, location information, etc. of UE#1).

[0346] For more details on S901, please refer to S701 above.

[0347] S902, UE#1 sends data #1.

[0348] Accordingly, network device #1 receives data #1.

[0349] For example, after receiving data #1, network device #1 can store data #1. Optionally, network device #1 can also process data #1. A description of how network device #1 processes data #1 can be found in S702 above.

[0350] For example, after receiving data #1, network device #1 can obtain at least one first tool based on data #1. Further description of the at least one first tool can be found in method 700 above.

[0351] Optionally, method 900 also includes S903.

[0352] S903, Network device #2 sends the fifth data.

[0353] Accordingly, network device #1 receives the fifth data.

[0354] The fifth data may be data obtained by network device #2 through measurement and / or environmental awareness, or it may be data sent by a UE (such as UE #3) connected to network device #2 to network device #2, without limitation.

[0355] Furthermore, network device #1 can plan the first task based on data #1 (i.e., an example of the first data), or plan the first task based on data #1 and fifth data (the combination of data #1 and fifth data is another example of the first data), and then send the planning result of the first task to UE #2 (such as sending a first instruction) so that UE #2 can execute the first task.

[0356] For example, after planning the first task, network device #1 can also activate the tools required to perform the first task, and / or activate other tools besides those required to perform the first task.

[0357] S904, Network device #1 sends the first command.

[0358] Accordingly, UE#2 receives the first instruction.

[0359] For example, the first instruction is used to instruct the invocation of at least one first tool to perform a first task.

[0360] Optionally, the first instruction may also be used to indicate the manner and / or period of performing the first task. For example, if the first task is CSI compression and feedback, the first instruction may also be used to indicate that the CSI compression is performed in one or more of time-domain compression, spatial-domain compression, or frequency-domain compression.

[0361] Optionally, the first instruction may also include at least one first tool.

[0362] Optionally, the first instruction is used to instruct the invocation of at least one first tool to execute the first sub-task included in the first task. For example, if the first task is a task that requires the cooperation of multiple UEs, i.e., UE#2 is used to execute the first sub-task of the first task, then the first instruction sent by network device #1 to UE#2 is used to instruct the invocation of at least one first tool to execute the first sub-task included in the first task.

[0363] S905, Network device #1 sends the third instruction.

[0364] Correspondingly, network device #2 receives the third instruction.

[0365] For example, the third instruction is used to instruct the execution of a second subtask that includes the first task, the second subtask being different from the first subtask.

[0366] As mentioned above, the first task requires the cooperation of multiple UEs. That is, in addition to UE#2 performing the first sub-task, other UEs different from UE#2 are also needed to perform the first task. For example, UE#3 connected to network device #2 can be used to perform the second sub-task included in the first task, and then network device #1 can send a third instruction to network device #2.

[0367] Accordingly, after receiving the third instruction, network device #2 can send a third instruction #1 to UE #3 to instruct UE #3 to invoke at least one first tool #a to execute the second subtask.

[0368] S906, Network device #1 sends second data.

[0369] Accordingly, UE#2 receives the second data.

[0370] The second data is used to perform the first task. For example, if the first task is CSI compression and feedback, the second data can be uncompressed CSI or a downlink reference signal, such as CSI-RS.

[0371] S907, Network device #1 sends at least one first tool.

[0372] Accordingly, UE#2 receives at least one first tool.

[0373] Taking at least one first tool including an AI model as an example, network device #1 can send the model file and / or model parameters of the AI ​​model to UE #2 so that UE #2 can determine the AI ​​model based on the model file and / or model parameters.

[0374] It should be noted that S907 is an optional step. For example, if UE#2 has already obtained at least one first tool, or if the first instruction sent by network device #1 includes at least one first tool, then method 900 may not include S907.

[0375] After UE#2 obtains the second data and / or at least one first tool for performing the first task, it can perform the first task.

[0376] Optionally, method 900 may further include one or more of steps S908 to S911.

[0377] S908, UE#2 sends the first message.

[0378] Accordingly, network device #1 receives the first information.

[0379] The first information is used to determine the execution result of the first task.

[0380] For example, if the first task is CSI compression and feedback, then the result of the first task can be the CSI feedback information obtained by compressing the CSI.

[0381] For more details on the first information, please refer to S710 above.

[0382] For example, after receiving the first information, network device #1 may also deactivate at least one first tool, and / or update at least one first tool to obtain at least one second tool.

[0383] Optionally, if the execution result of the first task indicates that the first task failed, or if the confidence level of the output obtained by UE#2 from executing the first task is lower than the confidence level threshold, then network device #1 can re-plan the first task. That is, method 900 may include one or more steps in S909 to S911.

[0384] S909, Network device #1 obtains the sixth data.

[0385] The sixth data is related to the first task. For example, in S909, UE#1 can obtain the sixth data again through measurement or environmental awareness, and send the sixth data to network device #1.

[0386] It should be noted that S909 is an optional step. For example, network device #1 can re-plan the first task based on the first data obtained earlier, then method 900 may not include S909.

[0387] S910, network device #1 sends the fourth instruction.

[0388] Accordingly, UE#2 receives the fourth instruction.

[0389] For example, the fourth instruction is used to instruct the invocation of at least one second tool to perform the first task. The at least one second tool is not exactly the same as the at least one first tool. Further description of the at least one second tool can be found in the description of the at least one first tool in Method 700 above.

[0390] S911, UE#2 obtains data and / or tools for performing tasks.

[0391] For example, in S911, UE#2 obtains data for performing the first task and at least one second tool based on the fourth instruction. The method by which UE#2 obtains the data for performing the first task can be referred to in S906 above. The method by which UE#2 obtains at least one second tool can be referred to in S907 above.

[0392] In this embodiment, the network device can plan the task to be executed based on the acquired data. Furthermore, the network device can instruct the terminal device to invoke the necessary tools to execute the task based on the task planning results. Since the network device can plan the task based on the acquired data and the tools on the network device side, it is beneficial to obtain task planning results that maximize the probability of task completion and / or improve task execution efficiency. In addition, the network device can update the tools based on the results of the terminal device's task execution, thereby improving the efficiency and / or accuracy of task execution based on the tools, and ultimately optimizing system performance.

[0393] Based on this, a communication system composed of network devices and terminal devices can achieve lifecycle management of agent-based wireless AI systems through several functions such as planning, execution, tools, and perception, thereby helping to optimize system performance.

[0394] The methods provided in the embodiments of this application have been described in detail above with reference to several accompanying drawings. The apparatus provided in the embodiments of this application will now be described with reference to the accompanying drawings.

[0395] Figures 10 and 11 are schematic block diagrams of possible apparatuses provided in embodiments of this application. These apparatuses can be used to implement the terminal-side or network-side functions in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments.

[0396] Figure 10 is a schematic block diagram of an apparatus provided in an embodiment of this application. The apparatus 1000 shown in Figure 10 may include a processing module 1010 and a communication module 1020.

[0397] In one possible design, device 1000 can be used to implement the communication method implemented by the first device in the embodiment shown in FIG. 7, or to implement the communication method implemented by the network device in the embodiment shown in FIG. 9. For example, processing module 1010 is used to implement the processing-related steps performed by the first device or network device in each method embodiment; communication module 1020 is used to implement the sending and / or receiving steps performed by the first device or network device in each method embodiment, such as sending one or more of the following: sending a first instruction, sending a second instruction, and sending a third instruction.

[0398] For example, the processing module 1010 is used to acquire first data related to the first task; the communication module 1020 is used to send a first instruction based on the first data, the first instruction being used to instruct the invocation of at least one first tool to perform the first task.

[0399] A more detailed description of the processing module 1010 and the communication module 1020 can be obtained directly from the relevant descriptions in the method embodiments shown in Figure 7 or Figure 9, and will not be repeated here.

[0400] In another possible design, device 1000 can be used to implement the communication method implemented by the second device in the embodiment shown in FIG7, or to implement the communication method implemented by the terminal device in the embodiment shown in FIG9. For example, processing module 1010 is used to implement the processing-related steps performed by the second device or the terminal device in each method embodiment; communication module 1020 is used to implement the sending and / or receiving steps performed by the second device or the terminal device in each method embodiment, such as receiving a first instruction.

[0401] For example, the communication module 1020 is used to receive a first instruction, which is used to instruct the invocation of at least one first tool to perform a first task; the processing module 1010 is used to obtain second data for performing the first task and at least one first tool; the processing module 1010 is also used to perform the first task based on the second data and at least one first tool.

[0402] A more detailed description of the processing module 1010 and the communication module 1020 can be obtained directly from the relevant descriptions in the method embodiments shown in Figure 7 or Figure 9, and will not be repeated here.

[0403] In another possible design, device 1000 can be used to implement the communication method implemented by the fifth device in the embodiment shown in FIG7, or to implement the communication method implemented by the network device in the embodiment shown in FIG9. For example, processing module 1010 is used to implement the processing-related steps performed by the fifth device or network device in each method embodiment; communication module 1020 is used to implement the sending and / or receiving steps performed by the fifth device or network device in each method embodiment, such as receiving a second instruction.

[0404] For example, the communication module 1020 is used to receive a second instruction, which is used to instruct the activation of at least one first tool, and / or to instruct the sending of at least one first tool to the execution function.

[0405] A more detailed description of the processing module 1010 and the communication module 1020 can be obtained directly from the relevant descriptions in the method embodiments shown in Figure 7 or Figure 9, and will not be repeated here.

[0406] It should be noted that the communication module can also be called a transceiver module, transceiver unit, transceiver, transceiver device, or transceiver apparatus, etc. The processing module can also be called a processor, processing board, processing unit, or processing apparatus, etc. Optionally, the communication module is used to execute the sending and receiving operations of the first or second communication device in the above method. The device in the communication module that implements the receiving function can be considered as the receiving module, and the device in the communication module that implements the sending function can be considered as the sending module; that is, the communication module can include both a receiving module and a sending module.

[0407] It should also be noted that, in one possible design, the aforementioned processing module and / or communication module can be implemented through virtual modules. For example, the processing module can be implemented through software functional units or virtual devices, and the communication module can be implemented through software functions or virtual devices. In another possible design, the processing module or communication module can also be implemented through physical devices. For example, if the device is implemented using a chip / chip circuit, the communication module can be an input / output circuit and / or a communication interface, performing input operations (corresponding to the aforementioned receiving operation) and output operations (corresponding to the aforementioned sending operation); the processing module can be an integrated processor, a microprocessor, or an integrated circuit.

[0408] The module division in this embodiment is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. Furthermore, the functional modules in the various examples of this embodiment can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0409] Figure 11 is a schematic diagram of the structure of a communication device provided in another embodiment of this application. As shown in Figure 11, the device 1100 includes a processing circuit 1110 and a communication circuit 1120. The processing circuit 1110 and the communication circuit 1120 are coupled to each other.

[0410] It can be understood that the processing circuit 1110 can be one or more processors, or it can be all or part of the circuits with processing functions in one or more processors.

[0411] Understandably, the communication circuit 1120 can be a transceiver or an input / output interface.

[0412] Optionally, the device 1100 may further include a memory 1130 for storing instructions executed by the processing circuit 1110, or storing input data required for the running instructions of the processing circuit 1110, or storing data generated after the running instructions of the processing circuit 1110.

[0413] It is understood that the memory 1130 may be located outside the processing circuit 1110 or inside the processing circuit 1110.

[0414] As an example, the processing circuit 1110 is used to implement the functions of the processing module 1010, and the communication circuit 1120 is used to implement the functions of the communication module 1020.

[0415] As an example, device 1100 can be a communication device or a chip used in a communication device.

[0416] When device 1100 is a communication device, the communication circuit can be a transceiver; when device 1100 is a chip, the communication circuit can be an input / output circuit, a bus, pins, or other types of communication interfaces, wherein the input circuit in the input / output circuit can be used for receiving, and the output interface can be used for transmitting.

[0417] In one possible implementation, device 1100 is used to implement the various processes and steps corresponding to the first device or network device in the above method embodiments. In another possible implementation, device 1100 is used to implement the various processes and steps corresponding to the second device or terminal device in the above method embodiments. In yet another possible implementation, device 1100 is used to implement the various processes and steps corresponding to the fifth device or network device in the above method embodiments.

[0418] It is understood that device 1100 may specifically be the first device, second device, or fifth device in the above embodiments, or it may be a chip or chip system. Correspondingly, the communication circuit may be the interface circuit of the chip, or an input / output circuit, which is not limited here. Specifically, device 1100 may be used to execute the various steps and / or processes corresponding to the first device, second device, or fifth device in the above method embodiments.

[0419] When the aforementioned communication device is a chip or OTT device applied to the first device (or network device), the chip or OTT device of the first device (or network device) implements the functions of the first device (or network device) in the above method embodiments, for example, implementing the processing functions of the first device (or network device). The chip or OTT device of the first device (or network device) receiving information from other devices can be understood as the information being first received by other modules (such as radio frequency modules or antennas) in the first device, and then sent by these modules to the chip or OTT device of the first device. The chip or OTT device of the first device (or network device) sending information to other devices can be understood as the information being first sent by the chip or OTT device of the first device to other modules (such as radio frequency modules or antennas) in the first device, and then sent by these modules to the other devices.

[0420] When the aforementioned communication device is a chip or OTT device applied to a second device (or terminal device), the chip or OTT device of the second device (or terminal device) implements the functions of the second device (or terminal device) in the above method embodiments, for example, implementing the processing functions of the second device (or terminal device). The chip or OTT device of the second device (or terminal device) receiving information from other devices can be understood as the information being first received by other modules (such as radio frequency modules or antennas) in the second device, and then sent by these modules to the chip or OTT device of the second device. The chip or OTT device of the second device (or terminal device) sending information to other devices can be understood as the information being first sent by the chip or OTT device of the second device to other modules (such as radio frequency modules or antennas) in the second device, and then sent by these modules to the other devices.

[0421] When the aforementioned communication device is a chip or OTT device applied to a fifth device (or network device), the chip or OTT device of the fifth device (or network device) implements the functions of the fifth device (or network device) in the above method embodiments, for example, implementing the processing functions of the fifth device (or network device). The chip or OTT device of the fifth device (or network device) receiving information from other devices can be understood as the information being first received by other modules (such as radio frequency modules or antennas) in the fifth device, and then sent by these modules to the chip or OTT device of the fifth device. The chip or OTT device of the fifth device (or network device) sending information to other devices can be understood as the information being first sent by the chip or OTT device of the fifth device to other modules (such as radio frequency modules or antennas) in the fifth device, and then sent by these modules to the other devices.

[0422] This application also provides a computer program product that, when run on a processor, can implement the communication method executed by the first device (or network device) or the communication method executed by the second device (or terminal device) or the communication method executed by the fifth device (or network device) in the above method embodiments.

[0423] This application also provides a computer-readable storage medium containing computer instructions that, when executed on a processor, can implement the communication method executed by the first device (or network device), the second device (or terminal device), or the fifth device (or network device) in the above method embodiments.

[0424] This application also provides a communication system, including the aforementioned first device (or network device), second device (or terminal device) and fifth device.

[0425] It is understood that the processor in the embodiments of this application may be any of the following devices or all or part of the circuitry used for processing functions: a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), processors for AI, field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.

[0426] For example, the processor used for AI can be one or more of the following: graphics processing unit (GPU), neural processing unit (NPU), tensor processing unit (TPU), and data processing unit (DPU).

[0427] For example, one possible implementation of a processor for AI could be the AI ​​processor 1200 shown in Figure 12.

[0428] As shown in Figure 12, the AI ​​processor 1200 may include one or more of the following: AI core, digital vision pre-processing (DVPP) module, task scheduler (TS), L3 cache, AI CPU, control CPU, L2 cache, universal serial bus (USB) interface, network card, peripheral component interconnect express (PCIe) interface (PCIe is a high-speed serial computer expansion bus standard), double data rate (DDR) / high bandwidth memory (HBM) interface, generation purpose input / output (GPIO) / inter-integrated circuit (I2C) bus, etc.

[0429] The terms “unit”, “module”, etc., used in this specification may be used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution.

[0430] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented 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 each specific application, but such implementation should not be considered beyond the scope of this application.

[0431] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0432] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0433] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0434] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0435] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. This computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0436] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0437] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, include: The first planning function obtains the first data related to the first task; The first planning function sends a first instruction to the execution function based on the first data. The first instruction is used to instruct the invocation of at least one first tool to execute the first task. The execution function acquires second data for performing the first task and the at least one first tool; The execution function performs the first task based on the second data and the at least one first tool.

2. The method according to claim 1, characterized in that, The at least one first tool is associated with one or more of the following functional modules on the network side and / or the terminal side: a sending functional module, a receiving functional module, or a measurement functional module.

3. The method according to claim 2, characterized in that, The at least one first tool includes one or more of the following: an AI model or AI function or non-AI algorithm tool for implementing at least one function of the transmission function module of the network side and / or the terminal side; an AI model or AI function or non-AI algorithm tool for implementing at least one function of the reception function module of the network side and / or the terminal side; and an AI model or AI function or non-AI algorithm tool for implementing at least one function of the measurement function module of the network side and / or the terminal side.

4. The method according to any one of claims 1 to 3, characterized in that, The first planning function acquires first data related to the first task, including: The first planning function receives third data from the memory function; and / or, The first planning function receives fourth data from the sensing function; and / or, The first planning function receives the fifth data from the second planning function; The first data includes one or more of the following: the third data, the fourth data, or the fifth data.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: The first planning function sends a second instruction to the tool function, the second instruction being used to instruct the activation of the at least one first tool, and / or to instruct the sending of the at least one first tool to the execution function.

6. The method according to any one of claims 1 to 5, characterized in that, The first instruction is used to instruct the invocation of the at least one first tool to perform a first subtask included in the first task, and the method further includes: The first planning function sends a third instruction to the second planning function, the third instruction being used to instruct the execution of a second subtask included in the first task, the second subtask being different from the first subtask.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: The execution function sends first information to the first planning function, the first information being used to indicate the execution result of the first task.

8. The method according to claim 7, characterized in that, The execution result of the first task indicates that the first task failed, and the method further includes: The first planning function obtains the sixth data related to the first task; The first planning function sends a fourth instruction to the execution function based on the sixth data. The fourth instruction is used to instruct the invocation of at least one second tool to execute the first task. The at least one second tool is not exactly the same as the at least one first tool.

9. The method according to claim 8, characterized in that, The method further includes: The first planning function sends a fifth instruction to the tool function, the fifth instruction being used to instruct the tool to be updated in order to obtain the at least one second tool.

10. The method according to claim 8 or 9, characterized in that, The method further includes: The first planning function sends seventh data to the tool function, the seventh data being used for tool updates to obtain the at least one second tool.

11. The method according to any one of claims 7 to 10, characterized in that, After receiving the first information, the method further includes: The first planning function sends a sixth instruction to the tool function, the sixth instruction being used to instruct the activation of the at least one first tool.

12. The method according to any one of claims 1 to 11, characterized in that, The first data includes one or more of the following: environmental perception data, reference signal measurement results, prior knowledge, or feedback information related to the execution results of the second task.

13. A communication method, characterized in that, Applied to the first planning function, including: Obtain the first data related to the first task; Based on the first data, a first instruction is sent to the execution function, the first instruction being used to instruct the invocation of at least one first tool to execute the first task.

14. The method according to claim 13, characterized in that, The at least one first tool is associated with one or more of the following functional modules on the network side and / or the terminal side: a sending functional module, a receiving functional module, or a measurement functional module.

15. The method according to claim 14, characterized in that, The at least one first tool includes one or more of the following: an AI model or AI function or non-AI algorithm tool for implementing at least one function of the transmission function module of the network side and / or the terminal side; an AI model or AI function or non-AI algorithm tool for implementing at least one function of the reception function module of the network side and / or the terminal side; and an AI model or AI function or non-AI algorithm tool for implementing at least one function of the measurement function module of the network side and / or the terminal side.

16. The method according to any one of claims 13 to 15, characterized in that, The first data includes one or more of the following: environmental perception data, reference signal measurement results, prior knowledge, or feedback information related to the execution results of the second task.

17. The method according to any one of claims 13 to 16, characterized in that, The acquisition of the first data related to the first task includes: Receive third data from memory functions; and / or, Receive fourth data from the sensing function; and / or, Receive the fifth data from the second planning function; The first data includes one or more of the following: the third data, the fourth data, or the fifth data.

18. The method according to any one of claims 13 to 17, characterized in that, The method further includes: Send a second instruction to the tool function, the second instruction being used to instruct the activation of the at least one first tool, and / or to instruct the sending of the at least one first tool to the execution function.

19. The method according to any one of claims 13 to 18, characterized in that, The first instruction is used to instruct the invocation of the at least one first tool to perform a first subtask included in the first task, and the method further includes: A third instruction is sent to the second planning function, the third instruction being used to instruct the execution of a second subtask included in the first task, the second subtask being different from the first subtask.

20. The method according to any one of claims 13 to 19, characterized in that, The method further includes: Receive first information from the execution function, the first information being used to indicate the execution result of the first task.

21. The method according to claim 20, characterized in that, The execution result of the first task indicates that the first task failed, and the method further includes: Obtain the sixth data related to the first task; Based on the sixth data, a fourth instruction is sent to the execution function, the fourth instruction being used to instruct the invocation of at least one second tool to execute the first task, the at least one second tool being not exactly the same as the at least one first tool.

22. The method according to claim 21, characterized in that, The method further includes: A fifth instruction is sent to the tool function, the fifth instruction being used to instruct a tool update to obtain the at least one second tool.

23. The method according to claim 21 or 22, characterized in that, The method further includes: Send seventh data to the tool function, the seventh data being used for tool updates to obtain the at least one second tool.

24. The method according to any one of claims 20 to 23, characterized in that, After receiving the first information, the method further includes: A sixth instruction is sent to the tool function, the sixth instruction being used to instruct the deactivation of the at least one first tool.

25. A communication method, characterized in that, Applied to perform functions, including: Receive a first instruction, the first instruction being used to instruct the invocation of at least one first tool to perform a first task; Acquire second data for performing the first task and the at least one first tool; The first task is performed based on the second data and the at least one first tool.

26. The method according to claim 25, characterized in that, The at least one first tool is associated with one or more of the following functional modules on the network side and / or the terminal side: a sending functional module, a receiving functional module, or a measurement functional module.

27. The method according to claim 26, characterized in that, The at least one first tool includes one or more of the following: an AI model or AI function or non-AI algorithm tool for implementing at least one function of the transmission function module of the network side and / or the terminal side; an AI model or AI function or non-AI algorithm tool for implementing at least one function of the reception function module of the network side and / or the terminal side; and an AI model or AI function or non-AI algorithm tool for implementing at least one function of the measurement function module of the network side and / or the terminal side.

28. The method according to any one of claims 25 to 27, characterized in that, Acquiring the at least one first tool includes: Receive the at least one first tool from the tool function.

29. The method according to claim 28, characterized in that, Before receiving the at least one first tool, the method further includes: Send a first request to the tool function, the first request being used to request the at least one first tool.

30. The method according to any one of claims 25 to 29, characterized in that, The method further includes: Send a first message, which indicates the execution result of the first task.

31. A communication method, characterized in that, include: Receive a second instruction, the second instruction being used to instruct the activation of at least one first tool, and / or to instruct the sending of the at least one first tool to the execution function.

32. The method according to claim 31, characterized in that, The at least one first tool is associated with one or more of the following functional modules on the network side and / or the terminal side: a sending functional module, a receiving functional module, or a measurement functional module.

33. The method according to claim 32, characterized in that, The at least one first tool includes one or more of the following: an AI model or AI function or non-AI algorithm tool for implementing at least one function of the transmission function module of the network side and / or the terminal side; an AI model or AI function or non-AI algorithm tool for implementing at least one function of the reception function module of the network side and / or the terminal side; and an AI model or AI function or non-AI algorithm tool for implementing at least one function of the measurement function module of the network side and / or the terminal side.

34. The method according to any one of claims 31 to 33, characterized in that, The second instruction is used to instruct the sending of the at least one first tool to the execution function, and the method further includes: Send the at least one first tool to the execution function.

35. The method according to any one of claims 31 to 33, characterized in that, The method further includes: Receive a first request from the execution function, the first request being used to request the at least one first tool; Send at least one first tool to the execution function.

36. The method according to any one of claims 31 to 35, characterized in that, After receiving the second instruction, the method further includes: Receive seventh data, which is used for tool updates to obtain at least one second tool, which is not exactly the same as the at least one first tool.

37. The method according to any one of claims 31 to 36, characterized in that, After receiving the second instruction, the method further includes: Receive a sixth instruction, the sixth instruction being used to instruct the deactivation of the at least one first tool.

38. The method according to any one of claims 31 to 37, characterized in that, Before receiving the second instruction, the method further includes: Receive the eighth data; Based on the eighth data, the at least one first tool is obtained.

39. A communication device, characterized in that, Includes functional modules for implementing the method as described in any one of claims 1 to 38.

40. A communication device, characterized in that, It includes one or more processors for executing programs or instructions that, when executed, cause the communication device to perform the method as described in any one of claims 1 to 38.

41. A communication system, characterized in that, It includes one or more of the following devices: devices for implementing the method as described in any one of claims 1 to 12, devices for implementing the method as described in any one of claims 13 to 24, devices for implementing the method as described in any one of claims 25 to 30, or devices for implementing the method as described in any one of claims 31 to 38.

42. A readable storage medium, characterized in that, Used to store programs or instructions that, when executed, cause the method as described in any one of claims 1 to 38 to be implemented.

43. A program product, characterized in that, Includes a program or instructions that, when executed, cause the method as described in any one of claims 1 to 38 to be implemented.