Communication method, device and system

Abstract

A communication method, device and system, the method comprising: a first agent sends a query message to a first database, the query message being used for requesting to obtain a context associated with a first task; the first database sends a context associated with the first task to the first agent; the first agent plans and decomposes the first task according to the context associated with the first task and the task description associated with the first task to obtain a plurality of sub-tasks; the first intelligent agent executes part or all of the sub-tasks; and the first agent sends a first task log to the first database, wherein the first task log is used for indicating the completion condition of part or all of the sub-tasks. According to the method, the first task can be deployed in the network, the life cycle management of the first task is realized, and the network intelligence and the network maintenance / operation efficiency are improved.

Description

Technical Field

[0001] This application relates to the field of communication technology, and more specifically, to a communication method, apparatus, and system. Background Technology

[0002] With the continuous advancement of artificial intelligence technology, large language models (LLMs) have attracted widespread attention. An LLM is an artificial intelligence model that uses machine learning techniques to understand and generate human language. Trained on a large amount of data, it is able to understand and generate natural language and other types of content to perform various tasks.

[0003] Currently, LLM has a wide range of applications in the computer field, including natural language processing (NLP), computer vision, speech recognition, and recommendation systems. It mainly focuses on natural language-related tasks, and how to deploy these tasks in a network is an issue that urgently needs to be considered. Summary of the Invention

[0004] This application provides a communication method, apparatus, and system for deploying and managing tasks in a network.

[0005] Firstly, a communication method is provided. This method includes: a first intelligent agent sending a query message to a first database, the query message requesting the acquisition of context associated with a first task; the first database sending the context associated with the first task to the first intelligent agent; the first intelligent agent planning and decomposing the first task according to the context associated with the first task and the task description, obtaining multiple sub-tasks; the first intelligent agent executing some or all of the sub-tasks; and the first intelligent agent sending a first task log to the first database, the first task log indicating the completion status of some or all of the sub-tasks.

[0006] For example, the first intelligent agent can be a central agent (C-agent).

[0007] Based on the above scheme, the first intelligent agent and the first database exchange information to obtain the context associated with the first task. The first intelligent agent then plans and decomposes the first task into multiple sub-tasks, and after the sub-tasks are executed, sends a first task log to the first database to indicate the completion status of the sub-tasks executed by the first intelligent agent. By deploying the first task on the network, lifecycle management of the first task is achieved, improving network intelligence and network maintenance / operation efficiency.

[0008] It should be understood that deployment refers to deploying an artificial intelligence (AI) model locally on the communication device, registering information about the tools included in the tool management unit of the intelligent agent locally on the communication device, and loading information about the data that the data management unit of the intelligent agent can manage locally on the communication device.

[0009] In one possible design, before the first agent sends a query message to the first database, the method further includes: the first agent obtaining the task description associated with the first task.

[0010] In one possible design, the first intelligent agent obtains the task description associated with the first task, including: the task node sending a task request message to the first intelligent agent, the task request message being used to request the execution of the first task, the task request message including task content; the first intelligent agent parsing the first task to obtain the task description.

[0011] For example, the task node can be a device in a communication network, so that the first task can be deployed in the communication network, thereby improving the intelligence of the communication network.

[0012] Based on the above scheme, the first intelligent agent and the task node can obtain the first task to be executed through information interaction. The corresponding task content could be to improve the throughput of aggregated users. Then, by parsing the first task, the task description associated with the first task can be obtained. That is, the field of wireless communication is combined with the field of AI to realize the intelligence of the communication network.

[0013] In one possible design, the method further includes: a first agent creating a first task based on a task description; the first agent sending first task status information to a task node, the first task status information indicating the creation result of the first task; and the task node receiving the first task status information from the first agent.

[0014] Based on the above scheme, the first intelligent agent can create the first task based on the task description and report the creation result of the first task to the task node, so that the task node can obtain whether the first task has been created successfully in a timely manner. By exchanging information between the first intelligent agent and the task node to obtain whether the first task has been created successfully or failed, the field of wireless communication and the field of AI can be combined to realize the intelligence of the communication network.

[0015] In one possible design, if the creation result indicates that the first task has been completed or the creation result is achieved, the first task status information includes a first task identifier, which is used to identify the first task; or, if the creation result indicates that the first task has not been completed, the first task status information includes a reason value, which indicates that the first task has not been completed or the creation has failed.

[0016] Based on the above scheme, if the creation result indicates that the first task has been created successfully, the first agent can send a first task identifier to the task node to identify the first task that has been created successfully; if the creation result indicates that the first task has not been created successfully, the first agent can send a reason value to the task node to indicate the reason why the first task has not been created successfully, such as the first database not storing the context associated with the first task, or the current network outage state, so that the task node can obtain in a timely manner whether the first task has been created successfully, and the reason for the failure.

[0017] In one possible design, when the first agent executes a portion of a plurality of subtasks, the method further includes: the first agent sending a first request message to a second agent, the first request message being used to request the execution of other portions of the plurality of subtasks; the second agent executing the other portions of the subtasks; and the second agent sending a second task log to a first database, the second task log being used to indicate the completion status of the other portions of the subtasks.

[0018] Optionally, a partial subtask may be one or more subtasks, and other partial subtasks may be one or more subtasks. The partial subtasks and other partial subtasks constitute the plurality of subtasks, that is, the other partial subtasks are the subtasks other than the partial subtasks among the plurality of subtasks.

[0019] For example, the second intelligent agent can be the next-level intelligent agent. It should be noted that the parameters / capabilities of the central intelligent agent and the next-level intelligent agent decrease in size, and the functions decrease in level.

[0020] Based on the above scheme, multiple subtasks can be executed entirely by the first intelligent agent, or jointly by the first and second intelligent agents. The latter can reduce the computational and signaling overhead and storage pressure of the first intelligent agent, while also improving network intelligence.

[0021] In one possible design, the method further includes: a first agent obtaining a second task log from a first database; the first agent determining second task status information based on the first and second task logs, the second task status information indicating the task status of multiple subtasks and / or monitoring information of key performance indicators (KPIs) associated with multiple subtasks; the first agent sending the second task status information to task nodes; and task nodes receiving the second task status information from the first agent.

[0022] Based on the above scheme, the first intelligent agent can monitor the status of multiple subtasks in real time during the execution of multiple subtasks and report the execution status of multiple subtasks to the task nodes. This allows the task nodes to obtain the execution status of multiple subtasks in real time and determine whether to trigger a request to execute a higher-priority task based on the completion progress of multiple subtasks. For example, assuming that the current processing progress of the first task is relatively slow, such as 10%, the task node can request the execution of the second task from the first intelligent agent, where the execution priority of the second task is higher than that of the first task. As another example, assuming that the current processing progress of the first task is relatively fast, such as 95%, the task node can trigger a request to the first intelligent agent to execute the second task after the first task is completed, regardless of whether the execution priority of the second task is higher than that of the first task.

[0023] In one possible design, the task status includes one or more of the following: task waiting, task executing, task paused, task completed, task failed, or task terminated.

[0024] In one possible design, the method further includes: a first agent sending a task response message to a task node, the task response message indicating the completion status of the first task.

[0025] In one possible design, the task response message includes a task report, which is generated based on a first task log and a second task log. The task report includes one or more of the following: a first indication message indicating whether the first task has been completed; key performance indicators associated with the first task; a first error message indicating the reason why the first task was not completed; descriptions of multiple subtasks, each subtask corresponding to a specific subtask; a second indication message indicating whether the multiple subtasks have been completed; the execution results of the multiple subtasks; and a second error message indicating the reason why the multiple subtasks were not completed.

[0026] Based on the above scheme, the first intelligent agent can determine the task report based on the acquired first task log and second task log, and then feed the task report back to the task node to notify the task node of the completion status of the multiple sub-tasks (or the first task), such as whether the task has been completed, whether the key indicators have been met, and the reasons for the task not being completed. This enables the task node to obtain the completion status of the first task in a timely manner, realize the deployment and management of the first task in the network, and improve the network intelligence.

[0027] In one possible design, the task description includes one or more of the following: a first task identifier, a first entity identifier, a first cell identifier, a first region identifier, an evaluation metric associated with the first task, task content associated with the first task, a first time period, a second task identifier, multimodal auxiliary information, task classification, relevant domain knowledge in a first database, or task report content associated with the first task; wherein, the first task identifier is used to identify the first task, the first entity identifier is used to identify the effective entity associated with the first task, the first cell identifier is used to identify the effective cell associated with the first task, the first region identifier is used to identify the execution region associated with the first task, the first time period is used to indicate the duration of execution of the first task, the second task identifier is used to identify the second task associated with the first task, the multimodal auxiliary information is used to assist in the execution of the first task, and the relevant domain knowledge in the first database is used to determine the second task associated with the first task.

[0028] In one possible design, multiple sub-tasks are obtained, including: a first intelligent agent acquiring first information, which includes one or more of the following: a sensing signal, a measurement signal, a sensing result, a measurement result, or auxiliary information associated with the first task; the first intelligent agent decomposing the first task based on the first information to obtain multiple sub-tasks.

[0029] In one possible design, the first intelligent agent acquires first information, including: the first intelligent agent acquires auxiliary information associated with the first task from the task node; and / or, the first intelligent agent acquires sensing signals and / or measurement signals from the second intelligent agent.

[0030] Based on the above scheme, the first intelligent agent can decompose the first task into multiple sub-tasks based on the acquired auxiliary information, sensing signals, measurement signals, sensing results, or measurement results, which helps to improve the execution efficiency of the first task.

[0031] In one possible design, the method further includes: a first agent obtaining a second task from a first database based on a task description, the second task being associated with the first task; in the event of a conflict between the first task and the second task, the first agent modifying the execution method of some or all of the subtasks in the first task; and the first agent activating the modified first task.

[0032] For example, the association between the second task and the first task can be understood as follows: the first task and the second task have a dependency relationship, or in other words, the subtasks contained in the first task have a dependency relationship with the subtasks contained in the second task. For example, the first task can be decomposed into subtasks a, b, and c, and the second task can be decomposed into subtasks a, d, and e. Assuming that the first task is executed first, and subtasks a, b, and c are executed sequentially, when the first agent plans the second task, considering that subtask a is already being executed, the second task only needs to execute subtasks d and e. Optionally, if the first agent withdraws the first task, the second task needs to be replanned and executed with subtasks a, d, and e.

[0033] Based on the above solution, in the event of a conflict between the second task and the first task, the conflict can be resolved by modifying the implementation method of the first task without changing the objective of the first task. For example, the first task can be decomposed into multiple sub-tasks.

[0034] In one possible design, the method further includes: a first agent obtaining a second task from a first database based on a task description, the second task being associated with the first task; in the event of a conflict between the first and second tasks, the first agent sending a second request message to a task node, the second request message being used to request a change to the first task; or, in the event of a conflict between the first and second tasks, the first agent modifying the second task; and the first agent activating the modified first task.

[0035] Based on the above scheme, when multiple tasks conflict and cannot be resolved, the first intelligent agent can resolve the task conflict by modifying the implementation of the first or second task. For example, the first intelligent agent can re-split the first or second task into multiple sub-tasks to facilitate the smooth execution of the first task.

[0036] In one possible design, the method further includes: a first agent obtaining a second task from a first database based on a task description, the second task being associated with the first task; if a conflict occurs between the first task and the second task, the first agent suspending the first task; if the second task is not completed after a first time period, the first agent terminating the first task; or, if the second task is completed after the first time period, the first agent activating the first task.

[0037] Based on the above scheme, in the event of a conflict between multiple tasks that cannot be resolved, the first agent can wait for the second task to complete before executing the first task; or, after a period of time (e.g., after a timeout), terminate the first task to resolve the task conflict.

[0038] In one possible design, the method further includes: a first agent modifying a first task into a third task; the first agent obtaining a fourth task from a first database, the fourth task being associated with both the first and third tasks; the first agent replanning the fourth task based on the context associated with it to obtain a fifth task; and the first agent deactivating the first and fourth tasks while activating the third and fifth tasks.

[0039] In one possible design, the method further includes: the first agent withdrawing the first task; the first agent obtaining the sixth task from the first database, the sixth task being associated with the first task; the first agent performing task planning on the sixth task to obtain the seventh task; and the first agent deactivating the first and sixth tasks and activating the seventh task.

[0040] In one possible design, at least one of the task node, the first intelligent agent, the second intelligent agent, or the first database is deployed in any of the following entities: terminal device, network device, core network device, or third-party server.

[0041] In the embodiments of this application, devices, network elements, entities, nodes, or apparatuses can be used interchangeably.

[0042] Based on the above scheme, deploying the task node, the first intelligent agent, the second intelligent agent, or the first database on any of the terminal devices, network devices, core network devices, or third-party servers can combine the wireless communication field with the AI ​​field to deploy and manage the first task, realize the intelligence of the communication network, and improve network maintenance / operation efficiency.

[0043] Secondly, a communication method is provided. This method can be executed by a task node. Unless otherwise specified, "task node" in this application can refer to the monitoring module itself, a component of the task node (e.g., a processor, chip, or chip system), or a logic module or software that can implement all or part of the functions of the task node.

[0044] The method includes: a task node sending a task request message to a first agent, the task request message being used to request the execution of a first task, the task request message including a task description associated with the first task; and the task node receiving a task response message from the first agent, the task response message indicating the completion status of the first task.

[0045] In one possible design, before the task node receives the task response message from the first agent, the method further includes: the task node receiving first task status information from the first agent, the first task status information indicating the creation result of the first task.

[0046] In one possible design, if the creation result indicates that the first task has been completed, the first task status information includes a first task identifier, which is used to identify the first task; or, if the creation result indicates that the first task has not been completed, the first task status information includes a reason value, which indicates that the first task has not been completed.

[0047] In one possible design, before the task node receives the task response message from the first agent, the method further includes: the task node receiving second task status information from the first agent, the second task status information indicating the execution result of the first task, the execution result including the completion of execution and / or monitoring information of the KPI corresponding to the first task, or the execution result including the incomplete execution and monitoring information of the KPI corresponding to the first task.

[0048] In one possible design, the task node sends auxiliary information associated with the first task to the first agent.

[0049] In one possible design, at least one of the task node, the first intelligent agent, the second intelligent agent, or the first database is deployed in any of the following entities: terminal device, network device, core network device, or third-party server.

[0050] The second aspect and some of its implementation methods and their beneficial effects can be referred to in the relevant description of the first aspect, and will not be repeated here.

[0051] Thirdly, a communication method is provided. This method can be executed by a first intelligent agent. Unless otherwise specified, the "first intelligent agent" in this application can refer to the first intelligent agent itself, a component of the first intelligent agent (e.g., a processor, chip, or chip system), or a logic module or software that can implement all or part of the functions of the first intelligent agent.

[0052] The method includes: a first intelligent agent sending a query message to a first database, the query message being used to request the acquisition of the context associated with a first task; the first intelligent agent receiving the context associated with the first task from the first database; the first intelligent agent planning and decomposing the first task according to the context associated with the first task and the task description, obtaining multiple sub-tasks; the first intelligent agent executing some or all of the sub-tasks among the multiple sub-tasks; and the first intelligent agent sending a first task log to the first database, the first task log being used to indicate the completion status of some or all of the sub-tasks among the multiple sub-tasks.

[0053] In one possible design, before the first agent sends a query message to the first database, the method further includes: the first agent obtaining the task description associated with the first task.

[0054] In one possible design, the first intelligent agent obtains the task description associated with the first task, including: the first intelligent agent receiving a task request message from a task node, the task request message being used to request the execution of the first task, the task request message including task content; the first intelligent agent parsing the first task to obtain the task description.

[0055] In one possible design, the first agent sends a task response message to the task node, which indicates the completion status of the first task.

[0056] In one possible design, before the first agent sends a task response message to the task node, the method further includes: the first agent creating a first task based on the task description; the first agent sending first task status information to the task node, the first task status information indicating the creation result of the first task.

[0057] In one possible design, if the creation result indicates that the first task has been completed, the first task status information includes a first task identifier, which is used to identify the first task; or, if the creation result indicates that the first task has not been completed, the first task status information includes a reason value, which indicates that the first task has not been completed.

[0058] In one possible design, when the first agent executes some subtasks of multiple subtasks, the method further includes: the first agent sending a first request message to the second agent, the first request message being used to request the execution of other subtasks; the second agent executing the other subtasks; and the second agent sending a second task log to the first database, the second task log being used to indicate the completion status of the other subtasks.

[0059] In one possible design, before the task node receives the task response message from the first agent, the method further includes: the first agent determining second task status information, the second task status information indicating the task status of multiple subtasks and / or monitoring information of KPIs associated with multiple subtasks; the first agent sending the second task status information to the task node.

[0060] In one possible design, the first agent determines the second task status information by: the first agent obtaining a first task log and a second task log from a first database, and the first agent determining the second task status information based on the first task log and the second task log.

[0061] In one possible design, before the first agent sends a task response message to the task node, the method further includes: the first agent obtaining a second task from a first database based on the task description, the second task being associated with the first task; in the event of a conflict between the first task and the second task, the first agent modifying the execution method of some or all of the subtasks in the first task; and the first agent activating the first task.

[0062] In one possible design, before the first agent sends a task response message to the task node, the method further includes: the first agent acquiring first information, which includes one or more of the following: a sensing signal, a measurement signal, a sensing result, a measurement result, or auxiliary information associated with the first task; the first agent decomposing the first task based on the first information to obtain multiple sub-tasks.

[0063] In one possible design, multiple sub-tasks are obtained, including: a first intelligent agent acquiring first information, which includes one or more of the following: a sensing signal, a measurement signal, a sensing result, a measurement result, or auxiliary information associated with the first task; the first intelligent agent decomposing the first task based on the first information to obtain multiple sub-tasks.

[0064] In one possible design, the first intelligent agent acquires first information, including: the first intelligent agent acquires auxiliary information associated with the first task from the task node; and / or, the first intelligent agent acquires sensing signals and / or measurement signals from the second intelligent agent.

[0065] In one possible design, before the first agent sends a task response message to the task node, the method further includes: the first agent obtaining a second task from a first database based on the task description, the second task being associated with the first task; if the first task and the second task conflict, the first agent sending a request message to the task node, the request message being used to request a change to the first task; or, if the first task and the second task conflict, the first agent modifying the second task; and the first agent activating the first task.

[0066] In one possible design, before the first agent sends a task response message to the task node, the method further includes: the first agent obtaining a second task from a first database based on the task description, the second task being associated with the first task; if the first task and the second task conflict, the first agent suspending the first task; if the second task is not completed after a first time period, the first agent terminating the first task; or, if the second task is completed after the first time period, the first agent activating the first task.

[0067] In one possible design, the method further includes: a first agent modifying a first task into a third task; the first agent obtaining a fourth task from a first database, the fourth task being associated with both the first and third tasks; the first agent replanning the fourth task to obtain a fifth task based on the second context associated with the fourth task; and the first agent deactivating the first and fourth tasks while activating the third and fifth tasks.

[0068] In one possible design, the method further includes: the first agent withdrawing the first task; the first agent obtaining the sixth task from the first database, the sixth task being associated with the first task; the first agent performing task planning on the sixth task to obtain the seventh task; and the first agent deactivating the first and sixth tasks and activating the seventh task.

[0069] In one possible design, at least one of the task node, the first intelligent agent, the second intelligent agent, or the first database is deployed in any of the following entities: terminal device, network device, core network device, or third-party server.

[0070] The third aspect and some of its implementation methods and their beneficial effects can be referred to in the relevant description of the first aspect, and will not be repeated here.

[0071] Fourthly, a communication method is provided. This method can be executed by a first database. Unless otherwise specified, "first database" in this application can refer to the first database itself, a component of the first database (e.g., a processor, chip, or chip system), or a logic module or software that can implement all or part of the functions of the first database.

[0072] The method includes: a first database receiving a query message from a first agent, the query message being used to request the acquisition of the context associated with a first task; the first database sending the context associated with the first task to the first agent; and the first database receiving a first task log from the first agent, the first task log being used to indicate the completion status of some or all of the subtasks among multiple subtasks.

[0073] In one possible design, a first database receives a second task log from a second agent, which is used to indicate the completion status of other parts of a plurality of subtasks.

[0074] In one possible design, a first database sends a second task log to a first agent. The second task log is used to indicate the completion status of other parts of multiple subtasks.

[0075] In one possible design, at least one of the task node, the first intelligent agent, the second intelligent agent, or the first database is deployed in any of the following entities: terminal device, network device, core network device, or third-party server.

[0076] The fourth aspect and some of its implementation methods and their beneficial effects can be referred to in the relevant description of the first aspect, and will not be repeated here.

[0077] Fifthly, a communication method is provided. This method can be executed by a second intelligent agent. Unless otherwise specified, the term "second intelligent agent" in this application can refer to the second intelligent agent itself, a component of the second intelligent agent (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the second intelligent agent.

[0078] The method includes: when a first agent executes a portion of a plurality of subtasks, a second agent receives a first request message from the first agent, the first request message being used to request the execution of other portions of the subtasks; the second agent executes the other portions of the subtasks; and the second agent sends a second task log to a first database, the second task log being used to indicate the completion status of the other portions of the subtasks.

[0079] In one possible design, the second agent sends sensing signals and / or measurement signals to the first agent.

[0080] The fifth aspect and some of its implementation methods and their beneficial effects can be referred to in the relevant description of the first aspect, and will not be repeated here.

[0081] Sixthly, a communication system is provided. The communication system includes: a first intelligent agent and a first database; the first intelligent agent is configured to send a query message to the first database, the query message being used to request the acquisition of a context associated with a first task; the first database is configured to send the context associated with the first task to the first intelligent agent; the first intelligent agent is further configured to plan and decompose the first task according to the context associated with the first task and the task description associated with the first task, obtaining multiple sub-tasks; the first intelligent agent is further configured to execute some or all of the multiple sub-tasks; the first intelligent agent is further configured to send a first task log to the first database, the first task log being used to indicate the completion status of the partial or all sub-tasks.

[0082] In one possible design, the first intelligent agent is also used to obtain the task description associated with the first task.

[0083] In one possible design, the communication system includes task nodes. The task nodes are used to send task request messages to a first agent, requesting the execution of a first task, and the task request message includes task content. The first agent is also used to parse the first task to obtain a task description.

[0084] In one possible design, the first intelligent agent is further configured to create a first task based on the task description; the first intelligent agent is further configured to send first task status information to the task node, the first task status information indicating the creation result of the first task; the task node is further configured to receive the first task status information from the first intelligent agent.

[0085] In one possible design, if the creation result indicates that the first task has been completed, the first task status information includes a first task identifier, which is used to identify the first task; or, if the creation result indicates that the first task has not been completed, the first task status information includes a reason value, which indicates that the first task has not been completed.

[0086] In one possible design, when the first agent executes some subtasks of multiple subtasks, the first agent is also used to send a first request message to the second agent, which requests the execution of other subtasks; the second agent executes the other subtasks; the second agent is also used to send a second task log to the first database, which indicates the completion status of the other subtasks.

[0087] In one possible design, the first intelligent agent is further configured to obtain a second task log from a first database; the first intelligent agent is further configured to determine second task status information based on the first task log and the second task log, the second task status information indicating the task status of multiple subtasks and / or monitoring information of KPIs associated with multiple subtasks; the first intelligent agent is further configured to send the second task status information to task nodes; the task nodes are further configured to receive the second task status information from the first intelligent agent.

[0088] In one possible design, the first intelligent agent is also used to send a task response message to the task node, which indicates the completion status of the first task.

[0089] In one possible design, the first intelligent agent is also used to acquire first information, which includes one or more of the following: sensing signals, measurement signals, sensing results, measurement results, or auxiliary information associated with the first task; the first intelligent agent decomposes the first task according to the first information to obtain multiple sub-tasks.

[0090] In one possible design, the first intelligent agent is further configured to acquire auxiliary information associated with the first task from the task node; and / or, the first intelligent agent is further configured to acquire sensing signals and / or measurement signals from the second intelligent agent.

[0091] In one possible design, the first intelligent agent is further configured to retrieve a second task from a first database based on a task description, the second task being associated with the first task; in the event of a conflict between the first and second tasks, the first intelligent agent is further configured to modify the execution method of some or all of the subtasks in the first task; the first intelligent agent is further configured to activate the modified first task.

[0092] In one possible design, the first intelligent agent is further configured to retrieve a second task from a first database based on a task description, the second task being associated with the first task; in the event of a conflict between the first and second tasks, the first intelligent agent is further configured to send a second request message to a task node, the second request message being used to request a change to the first task; or, in the event of a conflict between the first and second tasks, the first intelligent agent is further configured to modify the second task; the first intelligent agent is further configured to activate the modified first task.

[0093] In one possible design, the first intelligent agent is further configured to retrieve a second task from a first database based on a task description, the second task being associated with the first task; in the event of a conflict between the first and second tasks, the first intelligent agent is further configured to suspend the first task; after a first time period, if the second task has not been completed, the first intelligent agent is further configured to terminate the first task; or, after a first time period, if the second task has been completed, the first intelligent agent is further configured to activate the first task.

[0094] In one possible design, the first intelligent agent is further configured to modify the first task into a third task; the first intelligent agent is further configured to obtain a fourth task from the first database, the fourth task being associated with both the first and third tasks; the first intelligent agent is further configured to replan the fourth task based on the context associated with the fourth task to obtain a fifth task; the first intelligent agent is further configured to deactivate the first and fourth tasks, and activate the third and fifth tasks.

[0095] In one possible design, the first intelligent agent is also used to withdraw the first task; the first intelligent agent is also used to obtain the sixth task from the first database, the sixth task being associated with the first task; the first intelligent agent is also used to perform task planning on the sixth task to obtain the seventh task; the first intelligent agent is also used to deactivate the first and sixth tasks and activate the seventh task.

[0096] In one possible design, at least one of the task node, the first intelligent agent, the second intelligent agent, or the first database is deployed in any of the following entities: terminal device, network device, core network device, or third-party server.

[0097] In a seventh aspect, a communication device is provided, which has the function of implementing any one of the second to fifth aspects. For example, the communication device includes a module, unit or means corresponding to the operation involved in any one of the first to fifth aspects. The module or unit or means can be implemented by software, or by hardware, or by a combination of software and hardware.

[0098] For example, the communication device may be a task node, or a module or unit (e.g., a chip, a chip system, or a circuit) in the task node that corresponds one-to-one with the method, operation, step, or action described in the second aspect above, or a device that can be matched with the task node.

[0099] In one possible implementation, the communication device includes: a transceiver unit (or communication module), and a processing unit (or processing module) connected to the transceiver unit. Exemplarily, the transceiver unit is configured to: send a task request message to a first intelligent agent, the task request message requesting the execution of a first task, the task request message including a task description associated with the first task; and receive a task response message from the first intelligent agent, the task response message indicating the completion status of the first task.

[0100] For example, the communication device may be a first intelligent agent, or a module or unit (e.g., a chip, a chip system, or a circuit) in the first intelligent agent that corresponds to each of the methods, operations, steps, or actions described in the third aspect above, or a device that can be used in conjunction with the first intelligent agent.

[0101] In one possible implementation, the communication device includes: a transceiver unit (or communication module), and a processing unit (or processing module) connected to the transceiver unit. Exemplarily, the transceiver unit is configured to send a query message to a first database, the query message requesting the acquisition of the context associated with a first task; the transceiver unit is also configured to receive the context associated with the first task from the first database; the processing unit is configured to plan and decompose the first task according to the context associated with the first task and the task description, obtaining multiple subtasks; the processing unit is also configured to execute some or all of the multiple subtasks; the transceiver unit is also configured to send a first task log to the first database, the first task log indicating the completion status of some or all of the multiple subtasks.

[0102] For example, the communication device may be the first database, or a module or unit (e.g., a chip, a chip system, or a circuit) in the first database that corresponds one-to-one with the method, operation, step, or action described in the fourth aspect above, or a device that can be used in conjunction with the first database.

[0103] In one possible implementation, the communication device includes: a transceiver unit (or communication module), and a processing unit (or processing module) connected to the transceiver unit. Exemplarily, the transceiver unit is configured to: receive a query message from a first intelligent agent, the query message requesting the acquisition of context associated with a first task; send the context associated with the first task to the first intelligent agent; and receive a first task log from the first intelligent agent, the first task log indicating the completion status of some or all of a plurality of subtasks.

[0104] For example, the communication device may be a second intelligent agent, or a module or unit (e.g., a chip, a chip system, or a circuit) in the second intelligent agent that corresponds to each of the methods, operations, steps, or actions described in the fifth aspect above, or a device that can be used in conjunction with the second intelligent agent.

[0105] In one possible implementation, the communication device includes: a transceiver unit (or communication module), and a processing unit (or processing module) connected to the transceiver unit. Exemplarily, the transceiver unit is configured to receive a first request message from the first intelligent agent when the first intelligent agent is executing some sub-tasks of a plurality of sub-tasks; the first request message is used to request the execution of other sub-tasks; the processing unit is configured to execute the other sub-tasks; the transceiver unit is further configured to send a second task log to a first database, the second task log being used to indicate the completion status of the other sub-tasks.

[0106] Eighthly, a communication device is provided. The communication device may be the first intelligent agent, the first database, the task node, or the second intelligent agent described above. The communication device includes a transceiver, a processor, and a memory. The processor controls the transceiver to transmit and receive signals, the memory stores a computer program, and the processor retrieves and runs the computer program from the memory, causing the communication device to perform the methods in any of the possible implementations of the first to seventh aspects described above.

[0107] Optionally, there may be one or more processors and one or more memories.

[0108] Alternatively, the memory can be integrated with the processor, or the memory can be set up separately from the processor.

[0109] Optionally, the communication device may also include a transmitter and a receiver.

[0110] A ninth aspect provides a communication device comprising a memory and one or more processors. The memory stores part or all of a computer program or instructions necessary for implementing the functions described in any of the first to fifth aspects. The one or more processors are executable to carry out the computer program or instructions, such that, when executed, the communication device implements the methods in any possible design or implementation of the first to fifth aspects.

[0111] In one possible design, the communication device may further include an interface circuit, through which the processor communicates with other devices or components.

[0112] In one possible design, the communication device may also include the memory.

[0113] A tenth aspect provides a computer-readable storage medium. This computer-readable storage medium stores computer program code or instructions that, when read and executed by a computer, cause the methods in any of the possible implementations of the first to fifth aspects to be implemented.

[0114] Eleventhly, a computer program product is provided. The computer program product includes computer program code or instructions that, when read and executed by a computer, cause the method in any of the possible implementations of the first to fifth aspects to be implemented.

[0115] In a twelfth aspect, a computer program is provided. When the computer program is run, it causes the methods in any of the possible implementations of the first to fifth aspects to be implemented.

[0116] It should be understood that the beneficial effects of aspects six through twelfth above can be referenced from aspects one through five above and any possible implementation thereof, and will not be elaborated here. Attached Figure Description

[0117] Figures 1 to 3 This is a schematic diagram of a communication system applicable to this application;

[0118] Figure 4 This diagram illustrates the structure of an intelligent agent.

[0119] Figure 5 This is an interactive flowchart of a communication method provided in an embodiment of this application;

[0120] Figure 6 This is a schematic diagram of the structure of task status and task lifecycle management provided in the embodiments of this application;

[0121] Figures 7 to 9 This is a schematic diagram illustrating the correspondence between the task deployment process and the task status provided in the embodiments of this application;

[0122] Figures 10 to 12 This is a flowchart illustrating the solution to multiple task conflicts provided in an embodiment of this application;

[0123] Figure 13 This is a schematic diagram of the task modification process provided in the embodiments of this application;

[0124] Figure 14 This is a schematic diagram of the task withdrawal process provided in an embodiment of this application;

[0125] Figure 15 This is a schematic diagram of a task input to an LLM structure provided in an embodiment of this application;

[0126] Figure 16 This is a schematic block diagram of a communication device provided in an embodiment of this application;

[0127] Figure 17 This is a schematic block diagram of another communication device provided in the embodiments of this application. Detailed Implementation

[0128] To facilitate understanding of the above embodiments provided in this application, the following points are made:

[0129] 1) In this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0130] 2) 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 exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can mean: a, or, b, or, c, or, a and b, or, a and c, or, b and c, or, a, b, and c. Here, a, b, and c can each be single or multiple.

[0131] 3) In this application, the terms "first," "second," and various numerical designations (e.g., #1, #2, etc.) indicate distinctions made for ease of description and are not intended to limit the scope of the embodiments of this application. For example, they may distinguish different messages, rather than describing a specific order or sequence. It should be understood that such descriptions can be interchanged where appropriate to describe solutions other than those in the embodiments of this application.

[0132] 4) In this application, descriptions such as “when…”, “under the circumstances of…” and “if” all refer to the fact that the device will make corresponding processing under certain objective circumstances. They are not time limits, nor do they require the device to make a judgment action when it is implemented, nor do they mean that there are other limitations.

[0133] 5) In this application, "instruction" or "for instruction" can include both direct and indirect instruction. When describing an instruction as being used to instruct A, it may include whether the instruction directly instructs A or indirectly instructs A, but does not necessarily mean that the instruction carries A.

[0134] The indication methods involved in the embodiments of this application should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated. The information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately. Moreover, the sending period and / or sending time of these sub-information can be the same or different. This application does not limit the sending method, for example.

[0135] The "instruction information" in the embodiments of this application can be an explicit instruction, that is, a direct instruction through signaling, or an instruction obtained by combining other rules or parameters with the parameters indicated by the signaling, or by deduction. It can also be an implicit instruction, that is, an instruction obtained based on rules or relationships, or based on other parameters, or by deduction. This application does not specifically limit it in this regard.

[0136] 6) In this application, "protocol" can refer to a standard protocol in the field of communications, such as the 5G protocol, the new radio (NR) protocol, and related protocols applied to future communication systems. This application does not limit this term. "Predefined" can include predefined terms, such as protocol definitions. "Preconfiguration" can be implemented by pre-storing corresponding codes, tables, or other means that can be used to indicate relevant information in the device. This application does not limit the implementation method, for example.

[0137] 7) In this application, "communication" can also be described as "data transmission", "information transmission", "data processing", etc. "Transmission" includes "sending" and "receiving". "Transmission" can be described as "output".

[0138] 8) In this application, "sending information to XX (device)" can be understood as the destination of the information being that device. This can include sending information directly or indirectly to that device. "Receiving information from XX (device), or receiving information from XX (device)" can be understood as the source of the information being that device, and can include receiving information directly or indirectly from that device. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be interpreted similarly, and will not be elaborated further here.

[0139] 9) In this application, the terms "exemplarily," "for example," etc., are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as an "example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the term "example" is intended to present concepts in a concrete manner. In the embodiments of this application, "of," "corresponding, relevant," and "corresponding" may sometimes be used interchangeably, and it should be noted that their intended meanings are consistent unless their distinction is emphasized.

[0140] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0141] The technical solutions of this application can be applied to various communication systems, such as: Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, 5th Generation (5G) systems or NR systems, and future communication systems, such as 6th Generation (6G) mobile communication 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.

[0142] Furthermore, the embodiments of this application are applicable to both homogeneous and heterogeneous network scenarios, and there are no restrictions on the transmission points. Systems such as multi-point collaborative transmission between macro base stations, micro base stations, and macro base stations are all applicable. The embodiments of this application are applicable to both low-frequency scenarios (sub-6G) and high-frequency scenarios (above 6G), terahertz, optical communication, etc.

[0143] In a communication system, a device can send signals to or receive signals from another device. These signals may include reference signals, information, signaling, or data. In this application, "device" can be replaced by an entity, network entity, communication equipment, communication module, node, or communication node.

[0144] Figure 1 This is a schematic diagram of a communication system applicable to an embodiment of this application. For example... Figure 1 As shown, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. RAN 100 includes at least one RAN node (e.g., Figure 1 110a and 110b (collectively referred to as 110) and at least one terminal (such as Figure 1 RAN100, denoted as RAN100, comprises RAN nodes 120a-120j, collectively referred to as RAN120. RAN100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment. Figure 1 (Not shown in the image). Terminal 120 is connected to RAN node 110 wirelessly. RAN node 110 is connected to core network 200 wirelessly or via wired connection. The core network equipment in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0145] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as a 4G mobile communication system, a 5G mobile communication system, or a future-oriented evolution system (such as a 6G mobile communication system). RAN 100 can also be an open access network (open RAN, O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0146] RAN node 110, sometimes also referred to as network equipment, access network equipment, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple RAN nodes 110 in the communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative, for example... Figure 1 Network element 120i can be a helicopter or a drone, and it can be configured as a mobile base station. For terminals 120j that access RAN 100 through network element 120i, network element 120i is a base station; however, for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes referred to as communication devices, for example... Figure 1 Network elements 110a and 110b can be understood as communication devices with base station functions, while network elements 120a-120j can be understood as communication devices with terminal functions.

[0147] In one possible scenario, a RAN node can be a base station (BS), an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a next-generation base station in a 6th-generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system, etc. A RAN node can also be a macro base station (such as...). Figure 1 110a), micro base stations or indoor stations (such as Figure 1 In CRAN scenarios, RAN nodes can be 110b, relay nodes, donor nodes, or wireless controllers. Optionally, RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, in vehicle-to-everything (V2X) technology, the access network equipment can be a roadside unit (RSU).

[0148] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be central units (CU), distributed units (DU), CU-control plane (CU-CP), CU-user plane (CU-UP), radio units (RU), or CU-radio units (CU-RU), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radioheads (RRHs).

[0149] In different systems, CU (including open CU-CP (O-CU-CP) and open CU-UP (O-CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called an open central unit (O-CU), DU can also be called an open distributed unit (O-DU), CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0150] Terminal 120 can be a device or module that accesses the aforementioned communication system and has corresponding communication functions. A terminal can also be referred to as user equipment (UE), terminal, user device, access terminal, user unit, user station, mobile station, mobile station (MS), remote station, remote terminal, mobile device, user terminal, terminal unit, terminal station, terminal device, wireless communication equipment, user agent, or user device. A terminal typically contains a communication module, circuit, or chip that performs the corresponding communication functions. The terminal may also be configured with program instructions for performing these communication functions.

[0151] For example, the terminal in this application embodiment can be a mobile phone, a personal digital assistant (PDA) computer, a laptop computer, a tablet computer, a drone, a computer with wireless transceiver capabilities, a machine type communication (MTC) terminal, a virtual reality (VR) terminal, an augmented reality (AR) terminal, an Internet of Things (IoT) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical care, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home (e.g., game consoles, smart TVs, smart speakers, smart refrigerators, and fitness equipment), a transport vehicle with wireless communication capabilities, a communication module, or a roadside unit (RSU) with terminal capabilities.

[0152] RAN 100 and terminal 120 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 aircraft, balloons, and satellites. The embodiments of this application do not limit the scenarios in which RAN 100 and terminal 120 are located.

[0153] Communication between access network devices and terminal devices follows a specific protocol layer structure. This protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: radio resource control (RRC) layer, packet data convergence protocol (PDCP) layer, radio link control (RLC) layer, media access control (MAC) layer, or physical (PHY) layer, etc. The user plane protocol layer may include at least one of the following: service data adaptation protocol (SDAP) layer, PDCP layer, RLC layer, MAC layer, or physical layer, etc.

[0154] The correspondence between network elements and their achievable protocol layer functions in the ORAN system can be found in Table 1 below.

[0155] Table 1

[0156] ORAN network elements 3GPP protocol layer functions O-CU-CP RRC+PDCP-Control Plane (PDCP-C) O-CU-UP SDAP+PDCP - User Plane (PDCP-U) O-DU RLC+MAC+PHY-high O-RU PHY-low

[0157] CN 200 can be a 6G core network, a 5G core network, or an evolved 5G core network. Taking a 5G core network as an example, CN 200 includes access and mobility management (AMF) network elements responsible for mobility management and access management services; session management (SMF) network elements responsible for session management; user plane (UPF) network elements responsible for user plane packet routing and forwarding and quality of service (QoS) control; and policy control (PCF) network elements. These core network elements can work independently or be combined to implement certain control functions. For example, AMF, SMF, and PCF can be combined into a single core network device.

[0158] The communication system 10 provided in this application may further include AI network elements for implementing some or all AI-related operations. AI network elements may also be referred to as AI nodes, AI devices, AI entities, AI modules, AI models, or AI units, etc. The AI ​​network elements may be built into the network elements of the communication system. For example, an AI network element may be an AI module built into access network equipment, core network equipment, cloud servers, or operation, administration and maintenance (OAM) management systems to implement AI-related functions. The OAM may be the management system for core network equipment and / or the management system for access network equipment. Alternatively, the AI ​​network element may be an independently configured network element in the communication system. Optionally, the terminal or its built-in chip may also include an AI entity for implementing AI-related functions.

[0159] Figure 2 This is a schematic diagram of another communication system applicable to the embodiments of this application. For example... Figure 2 As shown, network elements in a communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in the OAM, are equipped with one or more AI modules (for clarity, ...). Figure 5 (Only one is shown in the image). The access network node can be a single RAN node or can include multiple RAN nodes, such as CU and DU. The CU and / or DU can also be configured with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are configured in CU-CP and / or CU-UP.

[0160] 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.

[0161] 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.

[0162] Figure 3 This is a schematic diagram of yet another communication system applicable to the embodiments of this application. For example... Figure 3 As shown, this network architecture can be implemented through a hierarchical structure of artificial general intelligence (AGI) within the network, with parameters / capabilities decreasing in size and functions progressing from higher to lower levels. In practical applications, this application does not limit the number of agents or the number of node levels included in this network architecture.

[0163] like Figure 3 As shown in (a), taking the example where all four levels of nodes possess an agent, the order of these four levels of nodes from upper to lower level is: Level 0 (L0), Level 1 (L1), Level 2 (L2), and Level 3 (L3). From left to right, it represents the process of the upper-level node instructing the lower-level node on decisions (e.g., configuration refinement), and from right to left, it represents the process of the lower-level node providing signal measurement information and / or perception measurement information to the upper-level node. Optionally, the measurement information may include the original measurement results and / or the local processing results of the lower-level node (e.g., signal measurement results, perception measurement results), such as the process by which the lower-level node transforms the raw perception information into the perception results, reflecting the network state that the upper-level node is concerned with, such as uploading the perception results to reduce transmission overhead and protect data privacy.

[0164] like Figure 3 As shown in (b), the network architecture includes a first intelligent agent (central agent), a second intelligent agent (BS agent, A-BS) deployed at the base station, and a third intelligent agent (UE agent, A-UE) deployed at the UE. Tasks in the network are implemented by the first intelligent agent, which controls the task lifecycle. The first intelligent agent can serve as a bidirectional interface for natural language and communication parameters with other intelligent agents. For example, the first intelligent agent acquires a task, plans and decomposes it into multiple sub-tasks, and distributes the BS configuration; the A-BS refines the acquired BS configuration based on the cell state, optimizes the cell, and distributes the UE configuration; the A-UE refines the acquired UE configuration based on the environment perceived by the UE, optimizing the underlying communication.

[0165] In a communication network, different communication nodes, from upper-level nodes to lower-level nodes, may include the following order: network management equipment (e.g., network management OAM equipment, over-the-top (OTT) vendor equipment), core network (CN) equipment / network elements / entities, access network equipment / network elements / entities, and terminal equipment. Optionally, in addition to these implementations, future communication networks may also include other device forms, which can also be applied to… Figure 3 The architecture shown.

[0166] Optionally, core network equipment / elements / entities may include different nodes, which may be ordered as follows from the upper-level node to the lower-level node: policy control function (PCF) network elements, session management function (SMF) network elements, and user plane function (UPF).

[0167] Optionally, the access network device / network element / entity may include different nodes, and the order from the upper-level node to the lower-level node may be as follows: CU, DU, RU; or, in the access network device / network element / entity of the O-RAN architecture, the order from the upper-level node to the lower-level node may be as follows: O-CU, O-DU, O-RU.

[0168] For example, taking the terminal device as a UE, Figure 3 The four-level nodes shown can be implemented as described in Table 2 below.

[0169] Table 2

[0170] L0 L1 L2 L3 CU DU RU UE CN CU DU UE PCF SMF RAN UE PCF SMF UPF RAN OAM / OTT CU DU UE OAM / OTT CN RAN UE OAM / OTT CN1 CN2 RAN

[0171] It should be understood that the above naming is defined solely for the purpose of distinguishing different functions and should not constitute any limitation on this application. This application does not preclude the possibility of using other naming conventions in 5G networks and other future networks. For example, in 6G networks, some or all of the above-mentioned network elements may use the terminology from 5G, or they may use other names, etc.

[0172] Understandable. Figures 1 to 3 This is merely an example and does not constitute a limitation on the scope of protection of this application. The communication method provided in the embodiments of this application may also involve... Figures 1 to 3 The network elements not shown in the diagram may also include, of course, the communication method provided in this application embodiment. Figures 1 to 3 Some of the network elements are shown.

[0173] To facilitate understanding of the embodiments of this application, the basic concepts involved in this application will be explained first.

[0174] 1. AI: AI enables machines to possess human-like intelligence, for example, allowing machines to use computer hardware and software to simulate certain intelligent human behaviors. To achieve artificial intelligence, machine learning methods can be employed. In machine learning, machines learn (or train) models using training data. This model represents the mapping between inputs and outputs. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result (or prediction result).

[0175] 2. Large Model Techniques: Large models refer to neural network models containing an extremely large number of parameters (usually over one billion), and have the following characteristics:

[0176] 1) Huge scale: Large models contain billions of parameters, and their size can reach hundreds of gigabytes (GB) or even larger. This huge model scale provides powerful expressive and learning capabilities.

[0177] 2) Multi-task learning: Large models typically learn multiple different natural language processing (NLP) tasks, such as machine translation, text summarization, or question answering systems. This allows the model to learn broader and more generalized language understanding capabilities. Optionally, large models can also include multimodal models or domain-specific models. Multimodal large models can include inputs of multimodal data such as video, images, speech, and point clouds. Domain-specific large models are used to perform specific domain tasks (such as communication-specific large models) and are trained or fine-tuned using domain-specific data.

[0178] 3) Powerful computing resources: Training large models typically requires hundreds or even thousands of graphics processing units (GPUs) and a significant amount of time, usually ranging from weeks to months. This can accelerate the training process while preserving the ability to train large models.

[0179] 4) Abundant data: Large models require a large amount of data for training. Only with a large amount of data can the advantages of the parameter scale of large models be brought into play.

[0180] Large models are widely used in the field of natural language processing (NLP) and are transforming NLP tasks, giving rise to more powerful and intelligent language technologies. Large models are a key direction in AI development. They also excel in various NLP tasks, such as text classification, sentiment analysis, summarization, and translation. Furthermore, large models can be used in multiple application areas, including automated writing, chatbots, virtual assistants, voice assistants, and automated translation.

[0181] It should be understood that the application of large-scale models in networks requires a series of supporting peripheral functions to truly realize their potential. This system engineering can be called an AI Agent. The AI ​​Agent will be explained in detail below.

[0182] 3. Intelligent Agent: This is a concept in the field of artificial intelligence. Any entity capable of independent thought and interaction with its environment can be abstracted as an intelligent agent. The basic characteristics of an intelligent agent are: it can react to changes in its environment and automatically adjust its behavior and state; different intelligent agents can also interact with other intelligent agents according to their own intentions. Intelligent agents can be considered a type of AI module.

[0183] For example, an agent can use an LLM (Long-Term Memory) as its core, comprising a memory module, a tool module, a planning module, and an action module. The memory module implements long-term and / or short-term memory functions; the tool module contains multiple callable external tools; the planning module contains various planning algorithms, allowing the agent to plan externally inputted tasks based on its memory; and the action module enables the agent to perform actions based on the planning results, such as calling tools.

[0184] Figure 4 A schematic diagram of the structure of an intelligent agent is shown. For example... Figure 4 As shown, in an LLM-supported autonomous agent system, the LLM acts as the brain of the agent (or agent) and includes the following components.

[0185] 1) Planning.

[0186] The planning includes self-reflection, self-criticism, chain of thoughts, and subgoal decomposition.

[0187] Sub-goal decomposition: Agents break down large tasks into smaller, manageable sub-goals (or sub-tasks), enabling them to efficiently handle complex tasks. For example, by instructing the model to "think step by step" through a chain of thoughts (CoT), more testing time is used to compute the breakdown of difficult tasks into smaller, simpler steps. CoT transforms large tasks into multiple manageable tasks and elucidates the explanation of the model's thought process.

[0188] Reflection and Improvement: Intelligent agents can engage in self-criticism and self-reflection on past behaviors, learn from mistakes, and improve future steps, thereby enhancing the quality of the final result.

[0189] 2) Memory.

[0190] Short-term memory: Learning by utilizing the short-term memory of models.

[0191] Long-term memory: Provides agents with the ability to retain and recall (unlimited) information for a long time, usually by utilizing external vector storage and fast retrieval.

[0192] 3) Tools usage.

[0193] Agent learning calls external application programming interfaces (APIs) to obtain additional information missing from the model weights (which is usually difficult to change after pre-training), including current information, code execution capabilities, and access to proprietary information sources.

[0194] For example, tools include, but are not limited to: calendars, calculators, code interpreters, or search tools.

[0195] 4) Task execution (action): The model performs a specific task and records the results.

[0196] 4. Prompt: In large AI models, the primary role of a prompt is to provide the model with contextual information about the input and the model's parameters. When training supervised or unsupervised learning models, a prompt helps the model better understand the intent of the input and respond accordingly. Furthermore, a prompt can improve the model's interpretability and accessibility.

[0197] In layman's terms, a prompt is to provide an AI model with a "hint" or "guidance" to help it better understand and complete tasks.

[0198] For example, a prompt is not just a question or query entered by the user; it also includes instructions, external information (context), and an output prompt. The user output or query is typically a query entered into the system by the user (i.e., the prompter). Instructions tell the model what to do, how to use external information (if provided), how to process the query, and how to build the output. External information (context) acts as an additional source of knowledge for the model. This can be manually inserted into the prompt, obtained through retrieval from a vector database (retrieval enhancement), or introduced through other means (API, computation, etc.). The output indicator marks the beginning of the text to be generated.

[0199] It should be understood that the intelligent agent in this application may also be called an AI controller, intelligent unit, or intelligent entity, etc. This application does not limit the name of the intelligent agent, as long as it can achieve the corresponding function.

[0200] For example, the intelligent agent includes an AI model, a tool management unit, and a data management unit, wherein the tool management unit includes tools that can be called by the AI ​​model, and the data management unit is used to manage data related to the operation of the intelligent agent.

[0201] Optionally, the AI ​​model can be understood as the core of the intelligent agent, such as an LLM core. This AI model is used to coordinate other components (e.g., tool management unit, data management unit, etc.) to plan and schedule tasks based on task requirements. This application does not impose any limitations on the name of the AI ​​model, as long as it can achieve the corresponding function.

[0202] Optionally, the tool management unit includes tools that the AI ​​model can call, such as code compilers, interpreters, performance monitoring, digital twins, ray tracing, or network function virtualization tools, to enable the intelligent agent to perform the corresponding functions.

[0203] Optionally, the data management unit can be used to manage, for example, device operation logs, agent operation logs, domain knowledge, device-supported functions, and the status of device sensing and measurement.

[0204] 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.

[0205] The above text combined Figures 1 to 3 This paper briefly introduces the scenarios in which the communication method provided in the embodiments of this application can be applied, as well as the basic concepts that may be involved in the embodiments of this application. The concept of intelligent agent is introduced in the basic concepts. As can be seen from the above, intelligent agent can realize a variety of functions and has a high degree of intelligence.

[0206] Currently, with the continuous advancement of artificial intelligence technology, LLM focuses primarily on tasks related to natural language processing, which has limitations.

[0207] To address the aforementioned technical problems, this application provides a communication method for deploying and managing tasks in a wireless communication network, thereby enhancing the intelligence of the communication network and improving network maintenance / operation efficiency.

[0208] The communication method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings, and can be applied to the above-mentioned... Figures 1 to 3 The communication system shown. It should be understood that the embodiments of this application can be applied to communication scenarios where the sending end and the receiving end communicate.

[0209] It should also be understood that the embodiments shown below do not particularly limit the specific structure of the execution subject of the method provided in the embodiments of this application, as long as it is possible to communicate according to the method provided in the embodiments of this application by running the code or program that records the method provided in the embodiments of this application. For example, the execution subject of the method provided in the embodiments of this application can be a device, or a functional module in the device that can call and execute a program.

[0210] Figure 5 This is a flowchart illustrating a communication method provided in an embodiment of this application. For example... Figure 5 As shown, the method 500 includes the following steps.

[0211] S510, the first intelligent agent (e.g., the central agent, C-agent) sends a query message to the first database (e.g., database);

[0212] Accordingly, the first database receives query messages from the first intelligent agent.

[0213] The query message is used to request the context associated with the first task.

[0214] For example, the first agent sends a vector or token to the first database to request the context associated with the first task. The vector or token may be carried in the query message.

[0215] In this embodiment of the application, the first intelligent agent and the first database can be regarded as Figure 4 The agent in the text, the second intelligent agent, can also be seen as... Figure 4 In this network, the agent (or second agent) may optionally also have a corresponding database. For example, the first agent can be the central agent (C-agent), and the second agent can be a lower-level agent. It should be noted that the parameters / capabilities of the central agent and the lower-level agents decrease in size, and their functions decrease from high-level to low-level, thus implementing a hierarchical AGI architecture in the network.

[0216] In this application, an intelligent agent is generally considered to be an agent that can autonomously complete a set goal through action. An "intelligent agent" is inseparable from "intelligence"; it possesses some human-like intelligent abilities and behaviors, such as learning, reasoning, decision-making, and execution capabilities. Optionally, an intelligent agent can be replaced with other terms, such as Artificial General Intelligence (AGI), Artificial Intelligence, or intelligent agent.

[0217] Optionally, in a communication device, 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. For example, the existing hardware / software may include chips, baseband chips, modem chips, system-on-chip (SoC) chips containing modem cores, system-in-package (SIP) chips, communication modules, chip systems, processors, logic modules, or software, etc.

[0218] Optionally, the intelligent agent includes at least one of the following: an AI model (e.g., a large language model LLM, or a large model), a tool module, a database module, or an execution module. Optionally, the AI ​​model can recognize languages ​​other than natural language, such as machine language.

[0219] The AI ​​model is used to determine (decompose) multiple sub-tasks based on the first task. The tool module is used to call one or more tools to determine the function information corresponding to the multiple sub-tasks, and the one or more tools include at least one of functions, data, models, and algorithms. The database module is used to store functions for executing the multiple sub-tasks, and the dataset includes at least one of historical task information, log information of one or more communication devices, perception data of one or more communication devices, measurement data of one or more communication devices, and domain knowledge. Optionally, before the first agent sends a query message to the first database, the first agent obtains the task description {Taskdescription} associated with the first task, that is, before executing step S510, the method further includes the following step S501.

[0220] S501, the first intelligent agent obtains the task description associated with the first task.

[0221] In one implementation, a task node sends a task request message to a first intelligent agent, for example, through a human-AI interface. This task request message requests the execution of a first task. The message includes task content (which can be natural language), comprising an object and a task objective, such as increasing the throughput of aggregated users. The first intelligent agent parses the task request message to obtain a task description, such as increasing the throughput of aggregated users, or increasing the coverage of a cell (denoted as cell B), or a cell (denoted as cell C) experiencing a special event requiring guaranteed cell throughput, or improving the spectral efficiency of a cell (denoted as cell D).

[0222] For example, for the first intelligent agent, the task description may affect the decomposition of multiple subtasks, thereby affecting whether the task objective can be achieved. The task description may include at least one of the following fields: task identifier, entity identifier, cell identifier, region identifier, evaluation metric associated with the first task, task report content associated with the first task, time period, second task identifier, multimodal auxiliary information, task classification, task content associated with the first task, or relevant domain knowledge from the first database, as specifically interpreted below.

[0223] (1) Task ID;

[0224] For example, a task identifier is used to identify the first task.

[0225] (2) Entity ID;

[0226] For example, an entity identifier is used to identify the active entity associated with the first task.

[0227] (3) Cell ID;

[0228] For example, the cell identifier is used to identify the active cell associated with the first task.

[0229] (4) Task area identification;

[0230] For example, a region identifier is used to identify the execution region associated with the first task.

[0231] (5) Evaluation indicators (Task KPIs) associated with the first task;

[0232] For example, evaluation metrics are used to indicate the current progress of the first task.

[0233] (6) Task report content associated with the first task;

[0234] For example, LLM task descriptions can be used to report task information in a targeted manner, such as whether the first task is completed, the key performance indicators associated with the first task, the reasons why the first task is not completed, descriptions of multiple subtasks, whether multiple subtasks are completed, the execution results of multiple subtasks, or the reasons why multiple subtasks are not completed.

[0235] (7) Task duration;

[0236] For example, a time period is used to indicate the duration of performing the first task, and a time period can be replaced by a set of times or a moment, etc.

[0237] (8) Correlated task ID;

[0238] For example, a second task identifier is used to identify a second task associated with the first task, and is used for multi-task management.

[0239] (9) Multi-modal content;

[0240] For example, multimodal auxiliary information is used to assist in performing the primary task, including but not limited to images, videos, and audio.

[0241] (10) Task classification, used to select the base prompt;

[0242] (11) Task content associated with the first task;

[0243] For example, task content includes the task object and the task objective.

[0244] (12) Related domain knowledge in the first database.

[0245] S520, the first database sends the context associated with the first task to the first intelligent agent;

[0246] Accordingly, the first agent receives the context associated with the first task from the first database.

[0247] For example, the first database queries locally and obtains the context associated with the first task based on a vector or token, and then feeds it back to the first intelligent agent.

[0248] S530, the first intelligent agent plans and decomposes the first task according to the context and task description associated with the first task, and obtains multiple subtasks.

[0249] It should be understood that these multiple subtasks can be understood as multiple steps included in the execution of the first task, and the implementation of each subtask may not be unique.

[0250] It should be understood that the first task can be decomposed into multiple sub-tasks. This can be understood as the first task corresponding to these multiple sub-tasks; that is, the first task is used to determine multiple sub-tasks, and the first task is completed through the execution of these multiple sub-tasks. For example, the first task (e.g., task 1) could be to construct a radio map of a cell (denoted as cell A). The signal coverage area of ​​this cell could include multiple regions. Correspondingly, the multiple sub-tasks could indicate multiple sub-task objectives, and these sub-task objectives could respectively indicate the construction of radio maps for these multiple regions. Another example is improving the coverage area of ​​cell B. Correspondingly, sub-task 1 could be increasing the base station power, and sub-task 2 could be changing the uplink waveform of the terminal, etc. Yet another example is that task 1 could be addressing a special event in a cell (denoted as cell C) that requires ensuring cell throughput. Correspondingly, sub-task 1 could be increasing the base station power, sub-task 2 could be increasing the base station bandwidth, and sub-task 3 could be increasing the scheduling priority. Yet another example is that task 1 could be improving the spectral efficiency of a cell (denoted as cell D). Correspondingly, sub-task 1 could be constructing a radio map for cell D.

[0251] As an example, a task can indicate a target requirement for one or more objects, and a subtask can indicate a target requirement for one or more sub-objects; wherein the target requirement for one or more sub-objects can be used to satisfy the target requirement of the one or more objects.

[0252] For example, taking a cell as the object, the first task can indicate the coverage requirement for one or more cells; correspondingly, the sub-objects can include the network equipment corresponding to (or belonging to) the one or more cells, and the terminal equipment accessing the one or more cells. One of the multiple sub-tasks can indicate that the transmit power of the network equipment corresponding to (or belonging to) the one or more cells is adjusted to a first target value, and another of the multiple sub-tasks can indicate that the signal waveform of the terminal equipment accessing the one or more cells is adjusted to a second target value; wherein, the target requirement for one or more sub-objects can include the first target value and the second target value.

[0253] As another example, a task can indicate one or more task objectives, and a subtask can indicate one or more subtask objectives; wherein, one or more subtask objectives can be used to complete one or more task objectives.

[0254] Optionally, before the first agent decomposes the first task, the first agent creates the first task and feeds back the creation result of the first task to the task node. That is, the method further includes the following steps S502-S503.

[0255] S502, the first intelligent agent creates a task for the first task according to the task description and obtains the creation result.

[0256] This application does not specify a particular method for creating the first task; methods for creating tasks in existing solutions can be referenced. For example, the first agent plans according to the task description, including external tools and data calls, and obtains a result indicating whether the task creation was successful or failed.

[0257] S503, the first intelligent agent sends first task status information to the task node, which indicates the creation result of the first task; accordingly, the task node receives the first task status information from the first intelligent agent and determines the creation result of the first task.

[0258] In one example, if the creation result indicates that the first task has been created, the first task status information may include a first task identifier (e.g., task ID) used to identify the first task.

[0259] In another example, if the creation result indicates that the creation of the first task was incomplete, the status information of the first task may include a reason value indicating that the creation of the first task was incomplete. For example, the context associated with the first task may not be stored in the first database, or the task feasibility analysis may have failed, or there may be a task conflict that cannot be resolved, or the task wait timeout may have occurred.

[0260] For ease of description and understanding, the technical solution of this application is based on the completion of the creation of the first task. That is, based on the completion of the creation of the first task, the first intelligent agent subsequently executes multiple sub-tasks, or the first intelligent agent and the second intelligent agent jointly execute multiple sub-tasks.

[0261] The first intelligent agent can decompose the first task into multiple sub-tasks, which can be achieved with the help of the first information.

[0262] In one implementation, the first intelligent agent acquires first information, which includes one or more of the following: a sensing signal, a measurement signal, a sensing result, a measurement result, or auxiliary information associated with the first task; the first intelligent agent decomposes the first task into multiple sub-tasks based on the first information.

[0263] For example, the first intelligent agent obtains auxiliary information associated with the first task from the task node; and / or, the first intelligent agent obtains sensing signals, measurement signals, sensing results, and / or measurement results from the second intelligent agent. The sensing results are obtained based on the sensing signals, and the measurement results are obtained based on the measurement signals.

[0264] For example, the auxiliary information associated with the first task may include, but is not limited to, information not carried in the task request message (or, missing information), and this information is necessary for the first agent to decompose the task into multiple sub-tasks. For example, the first agent can send a request message to the task node to obtain the auxiliary information associated with the first task; or, the first agent can also obtain the auxiliary information associated with the first task through sensing / measurement with the second agent. This application does not specifically limit the name of the missing information. For example, after obtaining the missing information, the first agent plans the first task again, thereby decomposing the first task into multiple sub-tasks (or multiple steps), thus completing the decomposition of the first task. Optionally, if the first agent fails to obtain the auxiliary information associated with the first task, it means that the creation of the first task has failed, and there will be no subsequent task decomposition and execution. It should be understood that by inputting the task description, task planning and decomposition, and function matching prompts into the first agent, the first agent can complete the decomposition and planning of the first task and select multiple sub-tasks from the first database that match functions.

[0265] S540, the first intelligent agent executes some or all of the subtasks in a series of subtasks.

[0266] In other words, if the first intelligent agent can execute some of the subtasks among multiple subtasks, then the other subtasks can be executed by the second intelligent agent; or, the first intelligent agent can execute all of the subtasks among multiple subtasks, in which case no other intelligent agent needs to execute the subtasks. Optionally, this application does not limit the number of second intelligent agents.

[0267] For example, taking the joint completion of multiple sub-tasks by a first agent and a second agent as an example, the first task may include N sub-tasks. The first agent, based on the task description and a first function stored in a first database, can execute N1 sub-tasks (i.e., some sub-tasks) out of the N sub-tasks; that is, it can execute N1 sub-tasks by running or calculating the first function. Correspondingly, the other N-N1 sub-tasks (i.e., other partial sub-tasks) out of the N sub-tasks can be executed by the second agent. For example, the second agent, based on the task description and a second function stored in the second database (corresponding to the second agent), can execute N-N1 sub-tasks; that is, it can execute N-N1 sub-tasks by running or calculating the second function, where N is an integer greater than or equal to 2.

[0268] Optionally, N1+N2≥N, meaning that after the first task is decomposed into N subtasks, they can be executed by the first agent and the second agent respectively. For example, the first agent and the second agent can independently execute N1 and N2 subtasks respectively; or, the first agent and the second agent can jointly execute one or more subtasks, that is, the N1 subtasks and the N2 subtasks contain the same subtasks.

[0269] Optionally, this application does not limit the number of first functions and second functions. For example, the first agent can execute N1 sub-tasks by running one or more (e.g., N1) first functions, and the second agent can execute N2 sub-tasks by running one or more (e.g., N2) second functions. This application does not limit this.

[0270] For ease of description, the following embodiments use the example of a first intelligent agent and a second intelligent agent jointly executing multiple sub-tasks. The implementation method of the first intelligent agent executing all the sub-tasks in the multiple sub-tasks is similar, and will not be repeated for the sake of brevity.

[0271] S550, the first intelligent agent sends the first task logs to the first database;

[0272] Accordingly, the first database receives the first task log from the first intelligent agent.

[0273] The first task log is used to indicate the completion status of some or all of the subtasks in a series of subtasks.

[0274] For example, the first task log includes one or more of the following:

[0275] (1) Instruction message #1;

[0276] For example, the indication information #1 is used to indicate whether some subtasks in a series of subtasks have been completed. For instance, 1 bit can be used to indicate whether some subtasks have been completed, such as "0" indicating that the subtask has been completed and "1" indicating that the subtask has not been completed.

[0277] (2) Key performance indicators associated with some subtasks;

[0278] For example, some key performance indicators associated with subtasks include: the target user's throughput is A, or the user power is B.

[0279] (3) Error message #1;

[0280] For example, error message #1 indicates the reason why some subtasks were not completed, including: a user's power reached the limit, or the model fine-tuning could not converge, or insufficient parameters could not be collected, etc.

[0281] (4) Execution results of some subtasks;

[0282] For example, some subtasks may be executed successfully or fail, or some subtasks may be completed or not completed.

[0283] (5) The number of first functions;

[0284] (6) The task status of some subtasks (such as task waiting, task being executed, task paused, task completed, task failed, or task terminated).

[0285] Based on step S550, when the first agent is executing some sub-tasks of multiple sub-tasks, the first agent can request the second agent to execute other sub-tasks, including the following steps.

[0286] S504, the first intelligent agent sends a first request message to the second intelligent agent;

[0287] Accordingly, the second agent receives the first request message from the first agent.

[0288] The first request message is used to request the execution of other subtasks.

[0289] S505, the second agent performs other sub-tasks.

[0290] S506, the second agent sends the second task log to the first database;

[0291] Accordingly, the first database receives the second task log from the second agent.

[0292] The second task log is used to indicate the completion status of other sub-tasks.

[0293] For example, the second task log includes one or more of the following:

[0294] (1) Instruction message #3;

[0295] For example, indication information #3 is used to indicate whether other parts of a subtask have been completed. For instance, 1 bit can be used to indicate whether a part of a subtask has been completed, such as "0" indicating that the subtask has been completed and "1" indicating that the subtask has not been completed.

[0296] (2) Key performance indicators associated with other sub-tasks;

[0297] For example, key performance indicators associated with other subtasks include: the target user's throughput is A, or the user power is B.

[0298] (3) Error message #1;

[0299] For example, error message #1 is used to indicate the reason why other subtasks were not completed, including: a user's power reached the limit, or the model fine-tuning could not converge, or insufficient parameters could not be collected, etc.

[0300] (4) Execution results of other subtasks;

[0301] For example, other subtasks may execute successfully or fail, or other subtasks may complete or fail to complete.

[0302] (5) The number of second functions;

[0303] (6) The task status of other subtasks (such as task waiting, task being executed, task paused, task completed, task failed, or task terminated).

[0304] Optionally, during the processing of multiple subtasks, the first intelligent agent can monitor the task status of multiple subtasks and report the task status of multiple subtasks to the task node, which includes the following steps.

[0305] S507, the first agent retrieves the second task log from the first database.

[0306] For example, the first intelligent agent sends a query request to the first database to request the second task log corresponding to other parts of the multiple subtasks. The query request may carry the task description, vector or token associated with the other parts of the subtask.

[0307] S508, the first intelligent agent determines the status information of the second task based on the first task log and the second task log.

[0308] The second task status information indicates the task status of multiple subtasks and / or the monitoring information of KPIs associated with multiple subtasks.

[0309] S509, the first intelligent agent sends the second task status information to the task node;

[0310] Accordingly, the task node receives the second task status information from the first intelligent agent.

[0311] For example, assuming there are N = 4 subtasks, the first agent executes N1 = 2 subtasks (e.g., subtask #1 and subtask #2), and the second agent executes N - N1 = 2 subtasks (e.g., subtask #3 and subtask #4). Then the status information of the second task reported by the first agent can include: subtask #1 has been completed, subtask #2 is being executed with a progress of 80%; subtask #3 has been completed, subtask #4 is being executed with a progress of 50%, etc.

[0312] For example, a task status may include one or more of the following: task pending, task active, task inactive, task complete, task failed, or task terminated, as specifically defined below.

[0313] (1) Task waiting: waiting for preliminary planning, such as feasibility analysis, conflict analysis between tasks, etc.

[0314] (2) The task is being executed: such as multiple subtasks being executed.

[0315] (3) Task pause: such as initiating a task pause request, or a conflict with a higher priority task.

[0316] (4) Task completed: This means that multiple subtasks have been completed and the KPI has been achieved.

[0317] (5) Task failure: such as task cancellation, task targets not being met, task being infeasible, task conflict, or task timeout.

[0318] (6) Task termination: such as task completion, task failure, task cancellation, etc.

[0319] Figure 6 This is a schematic diagram of the task status and task lifecycle management structure provided in an embodiment of this application. For example... Figure 6 As shown, the states include task waiting, task executing, task paused, task completed, task failed, or task terminated. Assuming a first task exists, the first agent creates the first task, and then the first task enters a task waiting state.

[0320] (1) If the task is activated, the first agent executes the first task, that is, the first task is in the task execution state.

[0321] (a) If a task fails (e.g., task is canceled, task targets are not met, task conflicts occur, or task times out), then the first task is in a failed state.

[0322] (b) If the task is completed and the KPI is achieved, the first task is in the task completion state;

[0323] (c) If there are other higher priority tasks in the task waiting state, the first agent can activate the first task, that is, the first task is in the task paused state; if other higher priority tasks are completed, or after a period of time, the first agent can activate the first task to continue to execute the first task, that is, the first task is in the task executing state; furthermore, if the task is completed and the KPI is reached, the first task is in the task completed state.

[0324] (2) If the task fails (e.g., the task is canceled or the task timeout occurs), the first task is in a failed state.

[0325] Regarding the above-mentioned task failure state, task completion state, or task pause state (e.g., task cancellation), the first task eventually enters the task termination state, which is the process of managing and deploying tasks in the network until the task is terminated, thus realizing task lifecycle management.

[0326] For the correspondence between different task states and different steps in the task deployment process, please refer to the following: Figures 7 to 9 The relevant explanations will not be provided here.

[0327] Optionally, in response to the task request message in step S501 above, the first intelligent agent may send a task response message back to the task node, that is, the method further includes the following steps.

[0328] S511, the first intelligent agent sends a task response message to the task node;

[0329] Accordingly, the task node receives the task response message from the first intelligent agent.

[0330] The task response message indicates the completion status of the first task.

[0331] For example, the task response message includes a task report, which is generated based on a first task log and a second task log.

[0332] For example, a task report is used to indicate the completion status of a first task. For instance, if the task indicates a target requirement for one or more objects, the task report can indicate the achievement of that requirement. Similarly, if the task indicates one or more task objectives, the task report can indicate the achievement of those objectives.

[0333] For example, the task report could indicate the radio map of cell A. As another example, the task report could indicate the access capacity of cell B, or the edge user throughput of cell B. Yet another example, the task report could indicate that cell C has a certain value for cell throughput, fairness, and gain over a certain time period.

[0334] The task report includes one or more of the following:

[0335] (1) First instruction information, which is used to indicate whether the first task has been completed;

[0336] For example, the first indication information is used to indicate whether the first task is completed. For instance, 1 bit can be used to indicate whether the first task is completed, such as "0" indicating that the first task is completed and "1" indicating that the first task is not completed.

[0337] (2) Key performance indicators associated with the first task;

[0338] For example, the key performance indicators associated with the first task include: the target user's throughput is A, or the user power is B.

[0339] (3) First error message, which indicates the reason why the first task was not completed;

[0340] For example, the first error message is used to indicate the reason why the first task was not completed, including: a user's power reached the limit, or the model fine-tuning could not converge, or insufficient parameters could not be collected, etc.

[0341] (4) Multiple subtask descriptions, each subtask description corresponds to a subtask;

[0342] For descriptions of multiple subtasks, please refer to the relevant explanations of the task description associated with the first subtask mentioned above. For the sake of brevity, these will not be repeated here.

[0343] (5) Second instruction information, which is used to indicate whether multiple subtasks have been completed;

[0344] For example, the second indication information is used to indicate whether multiple subtasks have been completed. For instance, a bitmap can be used to indicate whether multiple subtasks have been completed, such as "0" indicating a subtask is not completed and "1" indicating a subtask is completed; alternatively, the completion status of multiple subtasks can be indicated by their numbers, indices, or identifiers. As an example, assuming there are four subtasks, and the first and third subtasks are completed, while the second and fourth subtasks are not completed, then bitmap = "1010"; or, the completion status of multiple subtasks can be indicated by their numbers, indices, or identifiers. Assuming there are four subtasks, and the first and second subtasks are completed, while the third and fourth subtasks are not completed, then two bits are used to indicate the incomplete subtasks, such as "10" and "11".

[0345] (6) Second error message, which indicates the reason why multiple subtasks were not completed.

[0346] For example, the first error message is used to indicate the reason why multiple subtasks were not completed, including: a user's power reached the limit, or the model fine-tuning could not converge, or insufficient parameters could not be collected, etc.

[0347] Optionally, at least one of the task nodes, the first intelligent agent, the second intelligent agent, or the first database in this application may be deployed in any of the following entities: terminal equipment, network equipment, core network equipment, or third-party server.

[0348] Optionally, in the embodiments of this application, devices, network elements, entities, nodes, or apparatuses can be used interchangeably.

[0349] It should be understood that, unless otherwise specified, the "terminal device, network device, core network device, or third-party server" in this application can refer to the terminal device, network device, core network device, or third-party server itself, or it can be a component of the terminal device, network device, core network device, or third-party server (e.g., processor, chip, or chip system), or it can be a logical module or software that can implement all or part of the functions of the terminal device, network device, core network device, or third-party server. For example, chips, baseband chips, modem chips, system-on-chip (SoC) chips containing modem cores, system-in-package (SIP) chips, communication modules, chip systems, processors, logical modules, or software in terminal devices, network devices, core network devices, or third-party servers.

[0350] The following is an example of the deployment locations of the first agent, the first database, the task node, and the second agent in the wireless communication network in the above method 500, with reference to Table 3.

[0351] It should be understood that deployment refers to deploying the AI ​​model locally on the communication device, registering the tool management unit of the intelligent agent locally on the communication device, including the tool information, and loading the data management unit of the intelligent agent locally on the communication device, which can manage the data information.

[0352] Table 3

[0353]

[0354] As shown in Table 1 above, this application does not limit the deployment location of the task nodes. They can be deployed in core network equipment, radio access network equipment, terminal equipment, servers, or third-party equipment, such as OAM, OTT, CN, RAN, or UE. The first and second intelligent agents can be implemented through AGI layering in the network, i.e., parameters / capabilities from large to small, and functions from high to low. The deployment location of the first database can be together with the calling first intelligent agent, such as in core network equipment or RAN equipment, or the first database can be implemented separately, for example, deployed in OTT. It should be noted that Table 1 above is only an example given for ease of understanding, and other solutions are not excluded. For example, the first intelligent agent can be deployed in core network equipment (e.g., CN), the first database can be deployed in access network equipment (e.g., RAN), and the second intelligent agent can be deployed in terminal equipment (e.g., UE), improving the intelligence of the communication network and thus improving network maintenance / operation efficiency.

[0355] Optionally, during the execution of the first task, there may be conflicts between the first task and other tasks (e.g., the second task). The following is an example of how to resolve task conflicts.

[0356] It should be understood that task conflict refers to a situation where there is a contradiction between two or more tasks. For example, a task conflict between task 1 and task 2 can mean that multiple sub-tasks contained in task 1 are contradictory or opposed to multiple sub-tasks contained in task 2.

[0357] In one implementation, the task conflict can be resolved by modifying the implementation of the first task without changing the first task objective. For example, the first task can be decomposed into multiple subtasks. It should be understood that the decomposition into multiple subtasks is different from the decomposition into multiple subtasks in step S530 above, but the final implementation objective is the same.

[0358] For example, the first intelligent agent obtains a second task from the first database according to the task description, and the second task is associated with the first task; if the first task and the second task conflict, the first intelligent agent modifies the execution method of some or all of the subtasks in the first task; the first intelligent agent activates the modified first task.

[0359] It should be understood that the relationship between the first and second tasks can be interpreted as a dependency between them, or that the subtasks contained in the first task are dependent on the subtasks contained in the second task. For example, the first task can be decomposed into subtasks a, b, and c, and the second task can be decomposed into subtasks a, d, and e. Assuming the first task is executed first, and subtasks a, b, and c are executed sequentially, when the first agent plans the second task, considering that subtask a is already being executed, the second task only needs to execute subtasks d and e. Optionally, if the first agent withdraws the first task, then the second task needs to be replanned and executed with subtasks a, d, and e.

[0360] Figure 10 This is a flowchart illustrating a solution to multiple task conflicts provided in an embodiment of this application, which includes the following steps.

[0361] S1010, the first intelligent agent sends the task 1 description (i.e. the task description associated with the first task) to the first database;

[0362] Accordingly, the first database receives a description of Task 1 from the first agent.

[0363] The relevant explanations of Task 1 can be found in the relevant descriptions of Method 500 above, and will not be repeated here for the sake of brevity.

[0364] Optionally, before executing step S1010, the method further includes: the first intelligent agent receiving and parsing the task request. For the specific implementation, please refer to the relevant description of method 500 above. For the sake of brevity, it will not be elaborated here.

[0365] S1020, the first database performs a vector search based on the description of task 1 to obtain the associated task 0 (i.e., the second task). The specific implementation of the vector search can refer to the existing scheme.

[0366] S1030, the first database sends task 0 to the first intelligent agent;

[0367] Accordingly, the first intelligent agent receives task 0 from the first database.

[0368] Furthermore, the first agent performs planning and can modify the implementation of task 1 without changing the task objective of task 1 (e.g., increasing the throughput of aggregated users). For example, the first agent can decompose task 1 into multiple sub-tasks and then activate the modified task 1.

[0369] Based on the above solution, in the event of a conflict between the second task and the first task, the conflict can be resolved by modifying the implementation of the first task, for example, by decomposing the first task into multiple sub-tasks, without changing the objective of the first task. Optionally, this application does not limit the number of conflicting tasks (e.g., the first task and the second task).

[0370] In one implementation, the task conflict cannot be resolved; that is, the first agent can interact with the task initiator and resolve the task conflict by modifying the task objectives of the first or second task.

[0371] For example, the first intelligent agent retrieves a second task from a first database based on the task description, and the second task is associated with the first task; if the first task and the second task conflict, the first intelligent agent sends a second request message to the task node, which is used to request a change to the first task; or, if the first task and the second task conflict, the first intelligent agent modifies the second task; the first intelligent agent activates the modified first task.

[0372] Figure 11 This is a flowchart illustrating a solution to multiple task conflicts provided in an embodiment of this application, which includes the following steps.

[0373] S1110, the first intelligent agent sends the task 1 description (i.e. the task description associated with the first task) to the first database;

[0374] Accordingly, the first database receives a description of Task 1 from the first agent.

[0375] The relevant explanations of Task 1 can be found in the relevant descriptions of Method 500 above, and will not be repeated here for the sake of brevity.

[0376] Optionally, before executing step S1010, the method further includes: the first intelligent agent receiving and parsing the task request. For the specific implementation, please refer to the relevant description of method 500 above. For the sake of brevity, it will not be elaborated here.

[0377] S1120, the first database performs a vector search based on the description of task 1 to obtain the associated task 0 (i.e., the second task). The specific implementation of the vector search can refer to the existing scheme.

[0378] S1130, the first database sends task 0 to the first intelligent agent;

[0379] Accordingly, the first intelligent agent receives task 0 from the first database.

[0380] Furthermore, the first intelligent agent can perform task planning and interact with the task initiator to request the reactivation of the modified task 1 by modifying the first or second task, in order to resolve the task conflict issue.

[0381] Based on the above scheme, when multiple tasks conflict and cannot be resolved, the first intelligent agent can resolve the task conflict by modifying the implementation of the first or second task.

[0382] In one implementation, the task conflict cannot be resolved, meaning the first agent can set the first task to a task waiting state, and execute the first task or terminate the first task after the second task is completed or after a period of time (e.g., after a timeout).

[0383] For example, the first intelligent agent obtains a second task from the first database according to the task description, and the second task is associated with the first task; if the first task and the second task conflict, the first intelligent agent suspends the first task; if the second task is not completed after the first time period, the first intelligent agent terminates the first task; or, if the second task is completed after the first time period, the first intelligent agent activates the first task.

[0384] Figure 12 This is a flowchart illustrating a solution to multiple task conflicts provided in an embodiment of this application, which includes the following steps.

[0385] S1210, the first intelligent agent sends the task 1 description (i.e. the task description associated with the first task) to the first database;

[0386] Accordingly, the first database receives a description of Task 1 from the first agent.

[0387] The relevant explanations of Task 1 can be found in the relevant descriptions of Method 500 above, and will not be repeated here for the sake of brevity.

[0388] Optionally, before executing step S1010, the method further includes: the first intelligent agent receiving and parsing the task request. For the specific implementation, please refer to the relevant description of method 500 above. For the sake of brevity, it will not be elaborated here.

[0389] S1220, the first database performs a vector search based on the description of task 1 to obtain the associated task 0 (i.e., the second task). The specific implementation of the vector search can refer to the existing scheme.

[0390] S1230, the first database sends task 0 to the first intelligent agent;

[0391] Accordingly, the first intelligent agent receives task 0 from the first database.

[0392] Furthermore, the first intelligent agent can perform task planning, which can put task 1 in a task waiting state. That is, task 0 is executed first, and task 1 is activated only after task 0 is completed; or, if task 0 is not completed and the waiting timeout occurs, task 1 is terminated. The waiting timeout period can be predefined or preconfigured, and this application does not limit it.

[0393] Based on the above solution, in the event of a conflict between the second task and the first task, the first task can be executed after the second task is completed; or, after a period of time (e.g., after a timeout), the first task can be terminated.

[0394] Optionally, during the execution of the first task, there may be situations where the first task is modified and / or withdrawn. The following is an example of the task modification and / or task withdrawal process.

[0395] In one implementation, the first agent modifies the first task into a third task; the first agent obtains a fourth task from the first database, and the fourth task is associated with both the first and third tasks; the first agent re-plans the fourth task based on the context associated with the fourth task to obtain a fifth task; the first agent deactivates the first and fourth tasks, and activates the third and fifth tasks.

[0396] Figure 13 This is an interactive illustration of the task modification process provided in the embodiments of this application, which includes the following steps.

[0397] S1310, the first intelligent agent initiates a task modification to the first database, such as modifying task 0 to task 0.1 (i.e., the third task).

[0398] S1320, the first database performs a vector search to obtain associated task 1 (i.e., the fourth task). The specific implementation of the vector search can refer to existing solutions. Task 1 is associated with both task 0 and task 0.1.

[0399] S1330, the first database sends task 1 to the first intelligent agent;

[0400] Accordingly, the first intelligent agent receives task 1 from the first database.

[0401] Optionally, if there is no task in the first database that is associated with both task 0 and task 0.1, this step will not be performed, and task 0 will not be able to be modified.

[0402] Furthermore, the first agent re-plans the first task, for example, by using associated task 1 as the context for re-planning, such as changing task 1 to task 1.1, deactivating task 0 and task 1, and activating task 0.1 and task 1.1.

[0403] In one implementation, the first agent withdraws the first task; the first agent retrieves the sixth task from the first database, and the sixth task is associated with the first task; the first agent performs task planning on the sixth task to obtain the seventh task; the first agent deactivates the first task and the sixth task, and activates the seventh task.

[0404] Figure 14 This is an interactive illustration of the task modification process provided in the embodiments of this application, which includes the following steps.

[0405] S1410, the first intelligent agent initiates task modification to the first database, such as withdrawing task 0;

[0406] S1420, the first database performs a vector search to obtain associated task 1 (i.e., the sixth task). The specific implementation of the vector search can refer to existing solutions.

[0407] S1430, the first database sends task 1 to the first intelligent agent;

[0408] Accordingly, the first intelligent agent receives task 1 from the first database.

[0409] Furthermore, the first intelligent agent re-plans the first task to obtain task 1.1, deactivates task 0 and task 1, terminates task 0, and activates task 1.1.

[0410] Based on the above solution, a task modification and task withdrawal process is provided for situations involving multiple conflicting tasks, thereby achieving network intelligence.

[0411] Below, in conjunction with Figures 7 to 9 This diagram illustrates the correspondence between the task deployment process and task status described in method 500 above. The left side of the diagram shows the task deployment process, and the right side shows the task status and corresponding management actions.

[0412] like Figure 7The diagram illustrates the process of task creation -> task activation -> task failure (e.g., KPI not completed) -> task termination. Specifically, in step S710, after receiving a task request message from the task node, the first agent analyzes and plans the first task, and in step S720, it feeds back first status information to the task node, corresponding to a task waiting state. In step S730, the first agent obtains auxiliary information associated with the first task, decomposes the first task into multiple sub-tasks, and processes these sub-tasks, corresponding to a task in execution state. The first agent obtains second task status information by monitoring the status of the multiple sub-tasks, and in step S740, it feeds back the second status information to the task node; since the sub-tasks failed, this corresponds to a task failure state. Finally, in step S750, the first agent feeds back a first task report to the task node, corresponding to a task termination state.

[0413] like Figure 8 As shown, the process mainly focuses on task creation -> task activation -> task completion -> task termination. Specifically, in step S810, after receiving the task request message from the task node, the first agent analyzes and plans the first task, and in step S820, it feeds back the first status information to the task node, corresponding to the task waiting state. In step S830, the first agent obtains the auxiliary information associated with the first task, decomposes the first task into multiple sub-tasks, and then processes these sub-tasks, corresponding to the task being executed state. The first agent obtains the second task status information by monitoring the status of the multiple sub-tasks, and in step S840, it feeds back the second status information to the task node; since the sub-tasks have been completed, this corresponds to the task completion state. Finally, in step S850, the first agent feeds back the first task report to the task node, corresponding to the task termination state.

[0414] like Figure 9As shown, the process mainly focuses on the creation of Task 0 -> activation of Task 0 -> deactivation of Task 0 -> activation of Task 0 -> completion of Task 0 -> termination of Task 0. Task 0 is deactivated midway because a higher-priority Task 1 needs to be completed, and a conflict occurs between Task 1 and Task 0. Therefore, Task 0 can wait until Task 1 is completed before activating and executing. Specifically, in step S910, after receiving the Task 0 request message from the task node, the first agent analyzes and plans Task 0, and in step S920, it feeds back Task 0 status information #1 to the task node, corresponding to the waiting state of Task 0; in step S930, the first agent obtains the auxiliary information associated with Task 0, decomposes Task 0 into multiple subtasks, and then processes these subtasks, corresponding to the executing state of Task 0; in step S940, after receiving the Task 1 request message from the task node, the first agent analyzes and plans Task 1, and in step S950, it feeds back Task 1 status information to the task node. Information #1 corresponds to the waiting state of Task 1. In step S960, the first agent obtains the auxiliary information associated with Task 1, decomposes Task 1 into multiple subtasks, and then processes these subtasks, corresponding to the executing state of Task 1. Further, after Task 1 is completed, it enters the task completion state. The first agent obtains Task 1 status information #2 by monitoring the status of multiple subtasks. In step S970, the first agent feeds back Task 1 status information #2 to the task node. Since the subtasks have been completed, this corresponds to the task completion state. Finally, in step S980, the first agent feeds back Task 1 report to the task node, corresponding to the task termination state. Next, the first agent continues to process Task 0, obtaining Task 0 status information #2 by monitoring the status of multiple subtasks. In step S990, it feeds back Task 0 status information #2 to the task node. Since the subtasks have been completed, this corresponds to the task completion state. Finally, in step S900, the first agent feeds back Task 0 report to the task node, corresponding to the task termination state.

[0415] Below, in conjunction with Figure 15 This section provides an example illustrating the application of inputting tasks into an LLM using prompt word templates.

[0416] Figure 15 This is a schematic diagram of a task input to an LLM structure provided in an embodiment of this application. For example... Figure 15 As shown, for LLM, the input prompt has a significant impact on its performance. A prompt template can be used to format `{Taskdescription}` before feeding it into the LLM. For example, using... Figure 5Taking the multiple fields included in the task description as an example, the prompt word template of this application is as follows: Assume an expert in the {Task classification} domain needs to execute task #{TaskID}, the task content is {Task content}, the required KPI is {Task KPI}, the task needs to be executed for {TaskDuration}, and after execution, a task report is generated based on the task log, which needs to include {task reportcontent}. Optionally, related domain knowledge {related art} or task #{related task ID} in the first database can be referenced to assist in completing the task. Optionally, other modal data can be processed, such as referring to multi-modal content {Multi-modal content} to obtain additional auxiliary information to achieve the task objective.

[0417] Optionally, the prompt word template can be implemented by predefinition or preconfiguration, or it can be indicated by signaling. Predefinition can include pre-defined, such as protocol definition. Preconfiguration can be implemented by pre-saving the corresponding code, table, function, text, string or other means that can be used to indicate the prompt word template in LLM, agent or task node, etc. This application does not limit the specific implementation method.

[0418] Based on the above solution, in the technical solution of this application, the deployment process of the first task is completed by the first intelligent agent and the first database, and the life management cycle of the first task is controlled, so as to deploy and manage tasks in the wireless communication network, improve the intelligence of the communication network, and thus improve the network maintenance / operation efficiency.

[0419] The above text combined Figures 1 to 15 The communication method embodiments of this application are described in detail below, and will be combined with... Figures 16 to 17 This application describes in detail the communication device-side embodiments. It should be understood that the descriptions of the device embodiments correspond to the descriptions of the method embodiments; therefore, any parts not described in detail can be found in the preceding method embodiments.

[0420] Figure 16 This is a schematic block diagram of the communication device 1600 provided in an embodiment of this application. Figure 16As shown, the communication device 1600 includes a processing module 1610 and a communication module 1620. The communication device 1600 can be a transmitting device, or a communication device applied to or used in conjunction with a transmitting device to implement a method executed by the transmitting device, such as a chip, chip system, or circuit; or, the communication device 1600 can be a receiving device, or a communication device applied to or used in conjunction with a receiving device to implement a method executed by the receiving device, such as a chip, chip system, or circuit.

[0421] The communication module can also be called a transceiver module, transceiver, transceiver unit, or transceiver device. The processing module can also be called a processor, processing board, processing unit, or processing device. Optionally, the communication module is used to execute the sending and receiving operations of the sending and receiving devices in the above method. The device in the communication module that implements the receiving function can be considered a receiving unit, and the device in the communication module that implements the sending function can be considered a sending unit; that is, the communication module includes a receiving unit and a sending unit.

[0422] Optionally, the communication device 1600 may also include a storage module 1630 for storing device program code and / or data.

[0423] In one example, when the communication device 1600 is applied to the first intelligent agent, the processing module 1610 can be used to implement the processing function of the first intelligent agent in the above embodiments, and the communication module 1620 can be used to implement the sending and receiving function of the first intelligent agent in the above embodiments.

[0424] In another example, when the communication device 1600 is applied to the first database, the processing module 1610 can be used to implement the processing function of the first database in the above embodiments, and the communication module 1620 can be used to implement the sending and receiving function of the first database in the above embodiments.

[0425] Furthermore, it should be noted that the aforementioned communication module and / or processing 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. Alternatively, the processing module or communication module can also be implemented through physical devices, such as chips / circuits (e.g., integrated circuits or logic circuits). 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 is an integrated processor, microprocessor, or circuit (e.g., integrated circuits or logic circuits).

[0426] The module division in this application is illustrative and represents only one logical functional division. In actual implementation, other division methods are possible. Furthermore, the functional modules in the various examples of this application 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.

[0427] In one example, the functional unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as: one or more application-specific integrated circuits (ASICs), or one or more central processing units (CPUs), one or more microcontroller units (MCUs), one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0428] In one example, storage module 1630 may include random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory and / or registers, etc.

[0429] Figure 17 This is a schematic block diagram of a communication device 1700 provided in an embodiment of this application. Optionally, the communication device 1700 may be a chip or a chip system. Optionally, in this application, the chip system may be composed of chips or may include chips and other discrete devices.

[0430] like Figure 17 As shown, the communication device 1700 can be used to implement the functions of any device in the communication system described in the foregoing examples. The communication device 1700 may include at least one processor 1710. Optionally, the processor 1710 is coupled to a memory, which may be located within the device, integrated with the processor, or located outside the device. For example, the communication device 1700 may also include at least one memory 1720. The memory 1720 stores computer programs, computer programs or instructions, and / or data necessary for implementing any of the above examples; the processor 1710 may execute the computer program stored in the memory 1720 to perform the methods in any of the above examples.

[0431] The communication device 1700 may also include a communication interface 1730, through which the communication device 1700 can interact with other devices. For example, the communication interface 1730 may be a transceiver, circuit, bus, module, pin, or other type of communication interface. When the communication device 1700 is a chip-based device or circuit, the communication interface 1730 in the device 1700 may also be an input / output circuit, capable of inputting information (or receiving information) and outputting information (or sending information). The processor 1710 may be an integrated processor, microprocessor, integrated circuit, or logic circuit, etc., and the processor can determine the output information based on the input information.

[0432] In one example, when the communication device 1700 is applied to the first intelligent agent, the processor 1710 can be used to implement the processing function of the first intelligent agent in the above embodiments, and the communication interface 1730 can be used to implement the sending and receiving function of the first intelligent agent in the above embodiments.

[0433] In another example, when the communication device 1700 is applied to the first database, the processor 1710 can be used to implement the processing function of the first database in the above embodiments, and the communication interface 1730 can be used to implement the sending and receiving function of the first database in the above embodiments.

[0434] The coupling in this application refers to indirect coupling or communication connection between devices, units, or modules, which can be electrical, mechanical, or other forms, used for information exchange between devices, units, or modules. The processor 1710 may operate in conjunction with the memory 1720 and the communication interface 1730. This application does not limit the specific connection medium between the processor 1710, the memory 1720, and the communication interface 1730.

[0435] Optionally, such as Figure 17 As shown, the processor 1710, the memory 1720, and the communication interface 1730 are interconnected via a bus 1740. Optionally, the bus may include buses of the types such as address buses, data buses, and control buses. Furthermore, for ease of illustration, Figure 17 The diagram shows a bus 1740, but this does not mean that there is only one bus or one type of bus.

[0436] It should be understood that the processor mentioned in the embodiments of this application can be one of the following devices or a portion of the circuitry used for processing functions: a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0437] It should also be understood that the memory mentioned in the embodiments of this application can be volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes the following forms: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0438] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0439] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0440] This application also provides a computer-readable storage medium storing computer instructions for implementing the methods executed by the communication device in the above-described method embodiments.

[0441] This application also provides a computer program product comprising instructions which, when executed by a computer, implement the methods performed by the communication device in the above-described method embodiments.

[0442] This application also provides a communication system, which includes the first intelligent agent and / or the first database described in the above embodiments.

[0443] Optionally, the communication system may also include a task node and / or a second intelligent agent as described in the above embodiments.

[0444] The explanations and beneficial effects of the relevant contents in any of the devices provided above can be found in the corresponding method embodiments provided above, and will not be repeated here.

[0445] In the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0446] This application will present various aspects, embodiments, or features relating to systems that may include multiple devices, components, modules, etc. It should be understood and appreciated that individual systems may include additional devices, components, modules, etc., and / or may not include all the devices, components, modules, etc. discussed in conjunction with the accompanying drawings. Furthermore, combinations of these approaches are also possible.

[0447] In this application, examples may reference each other without logical contradiction. For example, methods and / or terms between method embodiments may reference each other, functions and / or terms between device embodiments may reference each other, and functions and / or terms between device examples and method examples may reference each other.

[0448] It should be understood that the above embodiments are mainly illustrated using devices in existing network architectures as examples, and the specific form of the devices is not limited in the embodiments of this application. For example, any device that can achieve the same function in the future is applicable to the embodiments of this application.

[0449] 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.

[0450] Those skilled in the art will clearly 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 described again here.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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 existing solutions, 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, external hard drives, ROM, RAM, magnetic disks, or optical disks.

[0455] 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 intelligent agent sends a query message to the first database, the query message being used to request the context associated with the first task; The first database sends the context associated with the first task to the first agent; The first intelligent agent plans and decomposes the first task according to the context and task description associated with the first task, and obtains multiple sub-tasks; The first intelligent agent executes some or all of the multiple subtasks; The first intelligent agent sends a first task log to the first database, the first task log being used to indicate the completion status of some or all of the sub-tasks.

2. The method according to claim 1, characterized in that, Before the first intelligent agent sends a query message to the first database, the method further includes: The first intelligent agent obtains the task description associated with the first task.

3. The method according to claim 2, characterized in that, The first intelligent agent obtains the task description associated with the first task, including: The task node sends a task request message to the first intelligent agent. The task request message is used to request the execution of the first task and includes task content. The first intelligent agent parses the first task to obtain the task description.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: The first intelligent agent creates a task for the first task based on the task description; The first intelligent agent sends first task status information to the task node, and the first task status information indicates the creation result of the first task; The task node receives the first task status information from the first intelligent agent.

5. The method according to claim 4, characterized in that, If the creation result indicates that the first task has been created, the first task status information includes a first task identifier, which is used to identify the first task; or... If the creation result indicates that the first task creation is incomplete, the first task status information includes a reason value, which indicates that the first task creation is incomplete.

6. The method according to any one of claims 1 to 5, characterized in that, When the first agent executes a portion of the multiple subtasks, the method further includes: The first intelligent agent sends a first request message to the second intelligent agent, the first request message being used to request the execution of other parts of the plurality of subtasks; The second intelligent agent executes the other sub-tasks; The second agent sends a second task log to the first database, which is used to indicate the completion status of the other sub-tasks.

7. The method according to claim 6, characterized in that, The method further includes: The first intelligent agent retrieves the second task log from the first database; The first intelligent agent determines the second task status information based on the first task log and the second task log. The second task status information indicates the task status of the multiple sub-tasks and / or the monitoring information of the key performance indicators (KPIs) associated with the multiple sub-tasks. The first intelligent agent sends the second task status information to the task node; The task node receives the second task status information from the first intelligent agent.

8. The method according to claim 7, characterized in that, The task status includes one or more of the following: Task pending, task in progress, task paused, task completed, task failed, or task terminated.

9. The method according to any one of claims 3 to 8, characterized in that, The method further includes: The first intelligent agent sends a task response message to the task node, the task response message indicating the completion status of the first task.

10. The method according to claim 9, characterized in that, The task response message includes a task report, which is generated based on the first task log and the second task log. The task report includes one or more of the following: first instruction information, key performance indicators associated with the first task, first error information, descriptions of multiple subtasks, second instruction information, execution results of the multiple subtasks, or second error information, wherein the descriptions of the multiple subtasks correspond one-to-one with the multiple subtasks; Wherein, the first indication information indicates whether the first task is completed, the first error information indicates the reason why the first task is not completed, the second indication information indicates whether the plurality of sub-tasks are completed, the second error information indicates the reason why the plurality of sub-tasks are not completed, and the execution result of the plurality of sub-tasks is used to indicate whether the plurality of sub-tasks are executed successfully or failed.

11. The method according to any one of claims 1 to 10, characterized in that, The task description includes one or more of the following: First task identifier, first entity identifier, first cell identifier, first area identifier, evaluation index associated with the first task, task content associated with the first task, first time period, second task identifier, multimodal auxiliary information, task classification, or task report content associated with the first task; Wherein, the first task identifier is used to identify the first task, the first entity identifier is used to identify the effective entity associated with the first task, the first cell identifier is used to identify the effective cell associated with the first task, the first region identifier is used to identify the execution region associated with the first task, the first time period is used to indicate the duration of execution of the first task, the second task identifier is used to identify the second task associated with the first task, and the multimodal auxiliary information is used to assist in the execution of the first task.

12. The method according to any one of claims 1 to 11, characterized in that, The process yields multiple sub-tasks, including: The first intelligent agent acquires first information, which includes one or more of the following: sensing signals, measurement signals, sensing results, measurement results, or auxiliary information associated with the first task; The first intelligent agent decomposes the first task based on the first information to obtain the multiple sub-tasks.

13. The method according to claim 12, characterized in that, The first intelligent agent acquires first information, including: The first intelligent agent obtains auxiliary information associated with the first task from the task node; and / or, The first intelligent agent obtains the sensing signal and / or the measurement signal from the second intelligent agent.

14. The method according to any one of claims 1 to 13, characterized in that, The method further includes: The first intelligent agent retrieves a second task from the first database based on the task description, and the second task is associated with the first task; In the event of a conflict between the first task and the second task, the first agent modifies the execution method of some or all of the subtasks in the first task. The first intelligent agent activates the modified first task.

15. The method according to any one of claims 1 to 13, characterized in that, The method further includes: The first intelligent agent retrieves a second task from the first database based on the task description, and the second task is associated with the first task; If a conflict arises between the first task and the second task, the first agent sends a second request message to the task node, the second request message being used to request a change to the first task; or... In the event of a conflict between the first task and the second task, the first agent modifies the second task; The first intelligent agent activates the modified first task.

16. The method according to any one of claims 1 to 13, characterized in that, The method further includes: The first intelligent agent retrieves a second task from the first database based on the task description, and the second task is associated with the first task; If the first task conflicts with the second task, the first agent will suspend the first task. If the second task is not completed after the first time period, the first agent terminates the first task; or, If the second task is completed after the first time period, the first agent activates the first task.

17. The method according to any one of claims 1 to 13, characterized in that, The method further includes: The first intelligent agent modifies the first task into a third task; The first intelligent agent obtains a fourth task from the first database, and the fourth task is simultaneously associated with the first task and the third task; The first intelligent agent re-plans the fourth task based on the context associated with the fourth task to obtain the fifth task; The first intelligent agent activates the first task and the fourth task, and also activates the third task and the fifth task.

18. The method according to any one of claims 1 to 13, characterized in that, The method further includes: The first intelligent agent withdraws the first task; The first intelligent agent obtains the sixth task from the first database, and the sixth task is associated with the first task; The first intelligent agent performs task planning on the sixth task to obtain the seventh task; The first intelligent agent activates the first task and the sixth task, and also activates the seventh task.

19. The method according to any one of claims 1 to 18, characterized in that, The task node, the first agent, the second agent, or at least one of the first databases are deployed in any of the following entities: Any one of the following: terminal equipment, network equipment, core network equipment, or third-party server.

20. A communication system, characterized in that, include: The first intelligent agent and the first database; The first intelligent agent is used to send a query message to the first database, the query message being used to request the context associated with the first task; The first database is used to send the context associated with the first task to the first intelligent agent; The first intelligent agent is further configured to plan and decompose the first task according to the context associated with the first task and the task description associated with the first task, to obtain multiple sub-tasks; The first intelligent agent is also used to execute some or all of the multiple subtasks; The first intelligent agent is further configured to send a first task log to the first database, the first task log being used to indicate the completion status of some or all of the sub-tasks.

21. The communication system according to claim 20, characterized in that, The communication system also includes task nodes; The task node is used to send a task request message to the first intelligent agent. The task request message is used to request the execution of the first task and includes task content. The first intelligent agent is also used to parse the first task to obtain the task description.

22. The communication system according to claim 20 or 21, characterized in that, When the first agent executes some of the sub-tasks of the plurality of sub-tasks, the communication system further includes a second agent; The first intelligent agent is further configured to send a first request message to the second intelligent agent, the first request message being used to request the execution of other parts of the plurality of subtasks; The second intelligent agent is used to execute the other sub-tasks; The second intelligent agent is also configured to send a second task log to the first database, the second task log being used to indicate the completion status of the other sub-tasks; The first intelligent agent is also configured to retrieve the second task log from the first database.

23. A communication device, characterized in that, The device includes a processor coupled to a memory for storing computer programs or instructions, the processor executing the computer program instructions in the memory to cause the method as described in any one of claims 1 to 19 to be performed.

24. A chip system, characterized in that, Includes: a processor for retrieving and running a computer program from memory to cause the method as described in any one of claims 1 to 19 to be performed.

25. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program that, when run on a computer, causes the method as described in any one of claims 1 to 19 to be performed.

26. A computer program product, characterized in that, When the computer program product is run on a computer, the method as described in any one of claims 1 to 19 is performed.

Images