Task processing method, task processing device, electronic equipment and storage medium

Abstract

The invention provides a task processing method, a task processing device, electronic equipment and a computer readable storage medium, and belongs to the technical field of communication. The method comprises the following steps: in response to an agent node detected by a network registration function, acquiring intention request data from a user side; analyzing the intention request data, and determining a to-be-processed task; according to a task processing mode corresponding to the to-be-processed task, processing the to-be-processed task to obtain a task processing result; and returning the task processing result to the user side. According to the invention, interaction with the user side can be completed in the network comprising the agent node, and artificial intelligence service is provided for the user.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technologies, and in particular to a task processing method, a task processing device, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the rapid development of artificial intelligence (AI) technology, AI (Artificial Intelligence) agents, with their autonomous decision-making, intelligent interaction, and dynamic adaptability, have become a key technology for the evolution of future networks, such as 6G networks. Future networks will also deeply integrate AI agent technology to achieve a highly autonomous and intelligent communication architecture, driving the digital transformation of the intelligent interconnection of all things. Therefore, AI agents are not only a core enabling technology for communication networks but will also reshape the intelligent ecosystem of future communication networks. However, existing technologies lack the specific interaction methods and processes for agents within the network, making it difficult for networks to utilize these agents to provide AI services to users.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to ordinary technicians in the field. Summary of the Invention

[0004] The present disclosure provides a task processing method, a task processing device, an electronic device, and a computer-readable storage medium, thereby overcoming, at least to a certain extent, the problem that existing networks have difficulty in utilizing the intelligent agents therein to provide artificial intelligence services to users.

[0005] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by practice of the present disclosure.

[0006] According to one aspect of the present disclosure, a task processing method is provided, including: in response to a network registration function detecting an intelligent agent node, obtaining intent request data from a user terminal; parsing the intent request data to determine a task to be processed; processing the task to be processed according to a task processing method corresponding to the task to be processed to obtain a task processing result; and returning the task processing result to the user terminal.

[0007] In an exemplary embodiment of the present disclosure, the method further includes: sending registration request information to the network registration function, and receiving registration response information returned by the network registration function.

[0008] In an exemplary embodiment of the present disclosure, the intelligent agent node includes an intent parsing intelligent agent; parsing the intent request data to determine the tasks to be processed includes: parsing the intent request data through the intent parsing intelligent agent to extract the tasks to be processed from the intent request data.

[0009] In an exemplary embodiment of the present disclosure, the intelligent agent node also includes a task decomposition agent; the task to be processed is processed according to the task processing method corresponding to the task to be processed to obtain a task processing result, including: splitting the task to be processed into one or more subtasks through the task decomposition agent; processing each subtask separately according to the task processing method corresponding to each subtask to obtain a task processing result.

[0010] In an exemplary embodiment of the present disclosure, the intelligent agent node also includes a processing method determination planning intelligent agent; the method also includes: determining the task processing method corresponding to the one or more subtasks through a strategy planning intelligent agent.

[0011] In an exemplary embodiment of the present disclosure, the intelligent agent node also includes a task execution intelligent agent; the task processing method corresponding to each subtask is used to process each subtask separately to obtain a task processing result, including: the task execution intelligent agent processes each subtask separately according to the task processing method corresponding to each subtask to obtain a task processing result.

[0012] In an exemplary embodiment of the present disclosure, the intelligent agent node also includes a task result integration intelligent agent; the method also includes: integrating the task processing results of each subtask through the task result integration intelligent agent to obtain a task integration result; and / or evaluating the task processing results of each subtask through the task result integration intelligent agent to obtain a task evaluation result; returning the task processing result to the user terminal includes: returning the task integration result and / or task evaluation result to the user terminal through the task result integration intelligent agent.

[0013] According to one aspect of the present disclosure, a task processing device is provided, including: an intention request acquisition module, which is used to obtain intention request data from a user terminal in response to the detection of an intelligent agent node by a network registration function; a pending task determination module, which is used to parse the intention request data and determine the pending task; a processing result acquisition module, which is used to process the pending task in accordance with the task processing method corresponding to the pending task to obtain a task processing result; and a processing result return module, which is used to return the task processing result to the user terminal.

[0014] According to one aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any one of the above-mentioned task processing methods by executing the executable instructions.

[0015] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the computer program implements any one of the task processing methods described above.

[0016] The exemplary embodiments of the present disclosure have the following beneficial effects:

[0017] In response to the network registration function detecting the intelligent node, the intention request data is obtained from the user end; the intention request data is parsed to determine the task to be processed; the task to be processed is processed according to the task processing method corresponding to the task to be processed to obtain the task processing result; and the task processing result is returned to the user end. On the one hand, this exemplary embodiment proposes a new task processing method that can be applied to the intelligent agent nodes in the target network. It clarifies the specific interaction methods and processes in the intelligent agent nodes, fills the gap in the existing technology, and can accurately identify the tasks to be processed through the automatic analysis of the user intention request data by the intelligent agent node, and perform task processing to obtain processing results. This exemplary embodiment can effectively promote the evolution of intelligent communication architecture and provide core technical support for the construction of intelligent ecology of future networks such as 6G; on the other hand, compared with the existing technology, there is a lack of interaction methods including intelligent agent nodes, and it is difficult for the network to effectively use intelligent agents to provide services to users. This exemplary embodiment, after detecting the intelligent agent node, can obtain user intention request data, and perform data analysis and task processing through the intelligent agent node, and quickly return the task processing results. This process realizes efficient response to user needs, avoids service delays and errors caused by the lack of interaction processes, significantly improves the convenience and fluency of users using artificial intelligence services, and can provide users with more personalized, intelligent and high-quality services, enhancing user satisfaction and dependence on network services.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0020] Figure 1 A flowchart schematically illustrates a task processing method in this exemplary embodiment;

[0021] Figure 2 A schematic diagram of a target network system structure in this exemplary embodiment is shown schematically;

[0022] Figure 3 An interactive flow chart schematically illustrating a task processing method in this exemplary embodiment;

[0023] Figure 4 A structural block diagram of a task processing device in this exemplary embodiment is schematically shown;

[0024] Figure 5 An electronic device for implementing the above method in this exemplary embodiment is schematically shown. DETAILED DESCRIPTION

[0025] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0026] The exemplary embodiment of the present disclosure first provides a task processing method, which is applied to an intelligent agent node in a target network, wherein the target network can be a 5G network, a 6G network, or other network that can communicate and interact with the user side. An intelligent agent node refers to a node that can provide artificial intelligence services. The intelligent agent node can include an intelligent agent or an intelligent agent module. In this exemplary embodiment, the intelligent agent node can be independent, for example, a dedicated intelligent agent node is configured in a 6G network. The intelligent agent node can also be a network element, for example, an intelligent agent or an intelligent agent module is configured in the network element so that the network element has the function of an intelligent agent. The network element can be any one or more types of network elements in a communication network, for example, an intelligent agent or an intelligent agent module can be configured in any one or more network elements in AMF (Access and Mobility Management Function), SMF (Session Management Function), RAN (Radio Access Network), UPF (User Plane Function), or other NFs (other Network Function), and these network elements can all serve as intelligent agent nodes.

[0027] The following is combined with Figure 1 This exemplary embodiment is further described as follows. Figure 1 As shown, the task processing method may include the following steps S110 to S140:

[0028] Step S110 , in response to the network registration function detecting the agent node, obtaining intent request data from the user terminal.

[0029] Among them, the network registration function can be NRF (Network Repository Function). The NRF network element can be used to maintain relevant information of available network function instances and their supported services. When other network functions need to find specific services or NF instances, they can send query requests to NRF, and NRF can return the conditions that meet the query conditions.

[0030] In this exemplary embodiment, the network registration function can discover or search for intelligent agent nodes in the target network, such as discovering network elements configured with intelligent agents. When the network registration function detects the intelligent agent node, the intelligent agent node can obtain intent request data from the user end.

[0031] The user terminal can be a user device on the user side. For example, a user can access the target network through an electronic device such as a computer, mobile phone, tablet computer, or smart device to seek services. Intent request data refers to data that includes the user's intent to request a service. For example, the intent request data can include data indicating what service the user wants to handle, what services or information the user is looking for, or what questions the user has raised. Specifically, the intent request data can be text data or voice data. For example, a user can enter text information about the service they want to handle through the user terminal, or they can enter a voice message and convert the voice message into text information.

[0032] This exemplary embodiment can enable information exchange between the user terminal, the network element containing the intelligent agent, and the network registration function. When the network registration function discovers the intelligent agent in the target network, the user terminal can start using the intelligent agent to complete related tasks to realize the function of providing business services to the user.

[0033] Step S120: parse the intent request data to determine the tasks to be processed.

[0034] In this exemplary embodiment, the intent request data may include different intent requirements in different scenarios. For example, the intent request data may include a user request to process a communication service, a user request to inquire about phone bills, a user request to report a network fault, etc. A pending task refers to a task that needs to be completed corresponding to the intent request data. This exemplary embodiment utilizes an agent in a network element to parse the intent request data and convert the intent request data into a pending task. For example, based on the intent request data such as the semantic content of the user's intention text or voice, a task of inquiring about pending communication services, a task of processing pending communication services, a task of inquiring about phone bills, or a task of reporting a network fault can be determined.

[0035] It should be noted that the intent request data may include one task or multiple tasks, and one task may include multiple subtasks. For example, the task of handling a certain communication service may include the task of querying specific details of the service.

[0036] Step S130 : Process the task to be processed according to the task processing method corresponding to the task to be processed to obtain a task processing result.

[0037] After determining the pending tasks, the pending tasks can be executed to obtain the task processing results. Different pending tasks may correspond to different task processing methods. For example, the task of querying phone charges and the task of reporting a fault may have different task processing methods. In this exemplary embodiment, the execution of the pending tasks can be performed by a network element including an intelligent agent, or by multiple network elements including intelligent agents. For example, when the pending tasks to be executed require multiple network elements to execute together, or to execute in sequence, or when the functions of executing the pending tasks are distributed in different network elements, then the processing of the pending tasks can be performed by multiple network element functions. When a certain network element can independently process the pending tasks, the pending tasks can be processed by the intelligent agent in the network element to obtain the task processing results.

[0038] Step S140: Return the task processing result to the user terminal.

[0039] Finally, the task processing results can be returned to the user terminal. These results can be the result of processing the pending task, specifically related to the task content. For example, they can return the success or failure of a communication service, along with specific service information for successful communication services. They can also return details of queried call charges, such as call duration, data usage, and SMS charges. They can also return network fault repair results, such as successful repair report, suggested solutions, and generated repair ticket information.

[0040] Based on the above description, in this exemplary embodiment, in response to the network registration function detecting the intelligent agent node, the intention request data is obtained from the user end; the intention request data is parsed to determine the task to be processed; the task to be processed is processed according to the task processing method corresponding to the task to be processed to obtain the task processing result; and the task processing result is returned to the user end. On the one hand, this exemplary embodiment proposes a new task processing method that can be applied to the intelligent agent nodes in the target network. It clarifies the specific interaction methods and processes in the intelligent agent nodes, fills the gap in the existing technology, and can accurately identify the tasks to be processed through the automatic analysis of the user intention request data by the intelligent agent node, and perform task processing to obtain processing results. This exemplary embodiment can effectively promote the evolution of intelligent communication architecture and provide core technical support for the construction of intelligent ecology of future networks such as 6G; on the other hand, compared with the existing technology, there is a lack of interaction methods including intelligent agent nodes, and it is difficult for the network to effectively use intelligent agents to provide services to users. This exemplary embodiment, after detecting the intelligent agent node, can obtain user intention request data, and perform data analysis and task processing through the intelligent agent node, and quickly return the task processing results. This process realizes efficient response to user needs, avoids service delays and errors caused by the lack of interaction processes, significantly improves the convenience and fluency of users using artificial intelligence services, and can provide users with more personalized, intelligent and high-quality services, enhancing user satisfaction and dependence on network services.

[0041] In an exemplary embodiment, the task processing method may further include:

[0042] Send a registration request message to the network registration function and receive a registration response message returned by the network registration function.

[0043] After configuring an agent node in the target network, the agent node can first send a registration request to the network registration function. For example, a standalone agent node, or a network element configured with an agent, can send a registration request to the NRF network element. The registration request can include one or more pieces of information, such as the agent's specific capabilities, deployment location, and service coverage area. An agent's capabilities refer to the functions it can perform. Different agents can have different capabilities, such as some agents can parse data intent, while others can divide tasks into multiple subtasks.

[0044] An intelligent agent node may include one or more intelligent agent functions. In this exemplary embodiment, multiple intelligent agent nodes may be configured in the target network. For example, intelligent agent modules may be configured in different network elements, and each intelligent agent module may implement different functions, so that multiple network elements can jointly process pending tasks. The target network may also be configured with one or a small number of intelligent agent nodes. For example, an intelligent agent module may be configured in a single network element, and the intelligent agent module may have multiple functions, so that the network element can independently process pending tasks and return task processing results through the intelligent agent module.

[0045] In an exemplary embodiment, the agent node includes an intent parsing agent;

[0046] Parse the intent request data and determine the tasks to be processed, which may include:

[0047] The intent request data is parsed by the intent parsing agent to extract the tasks to be processed from the intent request data.

[0048] An intent-parsing agent is one that has the ability to parse intent. For example, this functionality can be configured within an agent node. This allows the agent to interpret intent requests and translate them, translating the user's intent into specific tasks.

[0049] In an exemplary embodiment, the agent node further includes a task decomposition agent;

[0050] Process the pending task according to the task processing method corresponding to the pending task to obtain the task processing result, which may include:

[0051] Split the task to be processed into one or more subtasks through the task decomposition agent;

[0052] According to the task processing method corresponding to each subtask, each subtask is processed separately to obtain the task processing result.

[0053] Among them, the task decomposition agent refers to an agent that has the function of orchestrating decomposition tasks. For example, the relevant functions of orchestrating decomposition tasks can be configured for the agent in the agent node.

[0054] In this exemplary embodiment, after determining the task to be processed, the intelligent agent node can discover the task decomposition agent through the network registration function according to business needs, and split the task to be processed into one or more subtasks through the task decomposition agent, for example, breaking down the different processing processes of the telephone charge inquiry task into different subtasks.

[0055] It should be noted that the intelligent agent node can discover the task decomposition agent or the network element where the task decomposition agent is located through the network registration function according to business needs. If the intelligent agent node includes an intent parsing agent and a task decomposition agent, for example, the intent parsing agent and the task decomposition agent are respectively configured in different network elements or different modules of the same network element, then after determining the task to be processed, the network element where the intent parsing agent is located can send a task decomposition request to the network element where the task decomposition agent is located, so that the task decomposition agent can divide the complex task to be processed into one or more independently executable subtasks, each of which may be other independent 6G services, such as communication, AI, perception services, etc. If the intent parsing agent in the intelligent agent node also has the task decomposition capability, there is no need to discover the task decomposition agent or the network element where the task decomposition agent is located through the network registration function. The task to be processed can be directly determined through the intent parsing agent, and the subtask splitting process can be carried out.

[0056] In an exemplary embodiment, the agent node further includes a processing mode determination strategy planning agent;

[0057] The task processing method may further include:

[0058] The task processing method corresponding to one or more subtasks is determined by the strategic planning agent.

[0059] Among them, the strategic planning agent refers to an agent with strategic planning capabilities, which can be the ability to determine how to execute the pending task or execute subtasks. Through the strategic planning agent, the task processing method corresponding to the pending task or one or more subtasks can be determined.

[0060] In this exemplary embodiment, the intelligent agent node can discover the policy planning agent or the network element where the policy planning agent is located through the network registration function according to business needs. If the intelligent agent node includes an intent parsing agent, a task decomposition agent, and a policy planning agent, for example, these three agents are configured as different network elements or configured in different modules of the same network element, then after the task decomposition agent divides the task to be processed into one or more subtasks, it can send a subtask planning request to the policy planning agent. After receiving the subtask planning request, the policy planning agent can plan the specific execution strategy for each subtask. The specific planning content may include one or more of the specific execution process of each subtask, the execution entity of each step, the resource data required to execute the task, or the QoS (Quality of Service) data of the subtask. If the task decomposition agent configured in the intelligent agent node has policy planning capabilities, there is no need to discover the policy planning agent or the network element where it is located through the network registration function. The task to be processed can be directly divided into one or more subtasks through the task decomposition agent and the task processing method corresponding to each subtask can be determined.

[0061] In an exemplary embodiment, the agent node further includes a task execution agent;

[0062] Process each subtask separately according to the task processing method corresponding to each subtask to obtain the task processing results, which may include:

[0063] The task execution agent processes each subtask separately according to the task processing method corresponding to each subtask to obtain the task processing result.

[0064] Among them, the task execution agent refers to an agent with the ability to execute tasks. It can be a separate agent used to execute tasks, or it can be a multifunctional agent that can perform intention analysis, task decomposition, strategy planning, task execution and other functions.

[0065] In this exemplary embodiment, after determining that one or more subtasks are obtained by decomposition and determining the task processing method corresponding to each subtask, the task execution agent can process each subtask according to the task processing method corresponding to each subtask to obtain the task processing result of each subtask.

[0066] It should be noted that the intelligent agent node can discover the task execution agent or the network element where the task execution agent is located through the network registration function according to business needs. If the intelligent agent node includes an intent parsing agent, a task decomposition agent, a strategy planning agent and a task execution agent, for example, the intent parsing agent, the task decomposition agent, the strategy planning agent and the task execution agent are respectively configured in different network elements, or configured in different modules of the same network element, then the strategy planning agent can send a task execution request to the task execution agent after determining the task processing method of different subtasks. After receiving the task execution request, the task execution agent processes the corresponding subtask according to the task processing method of each subtask and obtains the task processing result of each subtask. If the strategy planning agent has the task execution capability, there is no need to discover the task execution agent or the network element where the task execution agent is located through the network registration function. The task processing method can be directly determined through the strategy planning agent, and the subtask can be directly processed.

[0067] In an exemplary embodiment, the agent node further includes a task result integration agent;

[0068] The above task processing method may further include:

[0069] Integrate the task processing results of each subtask through the task result integration agent to obtain a task integration result; and / or

[0070] The task result integration agent evaluates the task processing results of each subtask and obtains the task evaluation results;

[0071] Return task processing results to the user, including:

[0072] The task result integration agent returns the task integration results and / or task evaluation results to the user end.

[0073] After determining the task processing results of different subtasks, they can be returned to the user end, or the task processing results of different subtasks can be integrated and / or the task processing results of the subtasks or the integrated processing results can be evaluated, and finally the task integration results and / or task evaluation results can be returned to the user end.

[0074] In this exemplary embodiment, the agent node may further include a task result integration agent, which may be capable of integrating the task processing results of the subtasks and evaluating the task processing results of the subtasks. The evaluation of the task processing results of the subtasks may be an evaluation of the task processing results of a single subtask or an evaluation of the result of integrating the task processing results of the subtasks.

[0075] It should be noted that an agent node can discover a task result integration agent or the network element where the task result integration agent resides through the network registration function based on business needs. If an agent node includes an intent parsing agent, a task decomposition agent, a strategy planning agent, a task execution agent, and a task result integration agent—for example, if the intent parsing agent, the task decomposition agent, the strategy planning agent, the task execution agent, and the task result integration agent are configured in different network elements or in different modules of the same network element—then, after determining the task processing methods for different subtasks, the task execution agent can send a task execution result integration request to the task result integration agent. Upon receiving the task execution result integration request, the task result integration agent can integrate and evaluate the task processing results of all subtasks to obtain a task integration result and a task evaluation result. If the task execution agent has the ability to integrate and evaluate task results, it does not need to discover the task result integration agent or the network element where the task result integration agent resides through the network registration function. Instead, the task execution agent can directly process the subtasks and integrate and evaluate the subtask processing results.

[0076] Figure 2 A schematic diagram of the target network system structure in this exemplary embodiment is shown, which includes a UE (User Equipment) 202, as well as multiple network elements including an AMF 204, an SMF 206, an NRF 208, other NFs 210, a RAN 212, an UPF 214, and a DN (Data Network) 216. UE 202, AMF 204, SMF 206, other NFs 210, RAN 212, and UPF 214 can have built-in agents. These nodes can then function as agent nodes, executing corresponding task processing when users request agent services. Based on a service-based interface (SBI), one or more functional agents can be connected to the network elements. These agents may include, but are not limited to, an intent parsing agent 218, a task decomposition agent 220, a strategy planning agent 222, a task execution agent 224, and a task result integration agent 226. There may be multiple task execution agents 224. Configuring intelligent agents in the above network elements can be configuring intelligent agents with different functions in different network elements respectively, or configuring intelligent agents with multiple different functions in the same network element. The specific settings can be based on the network structure or the specific task requirements. For example, some tasks involve network elements AMF, and some network elements involve SMF. It may be necessary to configure intelligent agents with different functions in different network elements.

[0077] This exemplary embodiment enables different intelligent agents, as well as agents and other network elements, to discover and select each other and jointly complete complex tasks. Compared to the current network task execution process, on the one hand, users only need to express their intentions, without the need for specialized knowledge to make specific service requests, and the intelligent agents configured in the target network can provide them with artificial intelligence services. On the other hand, the network can complete complex and multi-dimensional tasks more quickly and efficiently.

[0078] Figure 3 The interactive flow chart of a task processing method in this exemplary embodiment is shown. In this exemplary embodiment, the task processing method involves a user terminal 310, an intelligent agent node 320, and a network registration function 330. The intelligent agent node 320 may include an intent parsing agent 321, a task decomposition agent 322, a strategy planning agent 323, a task execution agent 324, and a task result integration agent 325. The task processing method may specifically include the following steps:

[0079] The agent node 320 executes step S321 to send a registration request message to the network registration function 330. Specifically, the intention parsing agent 321, the task decomposition agent 322, the strategy planning agent 323, the task execution agent 324, and the task result integration agent 325 may each send a registration request message to the network registration function 330.

[0080] The network registration function 330 executes step S331 and returns registration response information to the agent node 320; for example, the registration response information is returned to the intention analysis agent 321, the task decomposition agent 322, the strategy planning agent 323, the task execution agent 324, and the task result integration agent 325;

[0081] When the user needs the agent service, the user terminal 310 executes step S311 to send a service request to the network registration function;

[0082] The network registration function 330 executes step S332 to discover the intent parsing agent 321 through the network registration function 330 according to its specific needs, and returns a response message to the user terminal 310;

[0083] The user terminal 310 executes step S312 and sends the intent request data to the intent parsing agent 321;

[0084] The intention parsing agent 321 executes step S3211 to receive the intention request data and translate the intention request data to convert the user intention into a specific task to be processed;

[0085] The intent parsing agent 321 executes step S3212 to discover the task decomposition agent 322 through the network registration function according to business needs and receives the response information returned by the network registration function. If the user intent receiving and translating AI agent also has the task decomposition function, this step is not required.

[0086] The intention parsing agent 321 executes step S3213 to send a task decomposition request to the task decomposition agent 322. If the intention parsing agent 321 also has the task decomposition function, this step is not required.

[0087] The task decomposition agent 322 executes step S3221 to orchestrate and decompose the pending task, breaking down the complex pending task into one or more independently executable subtasks; each subtask may be another independent 6G service, such as communication, AI, or perception services;

[0088] The task decomposition agent 322 executes step S3222 to discover the strategy planning agent 323 through the network registration function according to business needs and receives the response information returned by the network registration function. If the task decomposition agent 322 also has the task strategy planning capability, this step is not required.

[0089] The task decomposition agent 322 executes step S3223 and sends a task planning request to the strategy planning agent 323. If the task decomposition agent 322 also has the task strategy planning function, this step is not required.

[0090] The strategy planning agent 323 executes step S3231 to plan the specific execution strategy for each subtask, including the specific process of each subtask, the execution entity of each step, the required resources, the QoS of the subtask, etc.

[0091] The strategy planning agent 323 executes step S3232 to discover the task execution agent 324 through the network registration function according to business needs and receives the response information returned by the network registration function. If the strategy planning agent 323 also has the task execution capability, this step is not required. The entity that executes the task can be an AI agent or a network element. For example, when executing the perception subtask, the subtask execution entity is the perception function SF.

[0092] The strategy planning agent 323 executes step S3233 and sends a task execution request to the task execution agent 324, carrying the relevant information in step S3232. If the strategy planning agent 323 also has the task execution function, this step is not required.

[0093] The task execution agent 324 executes step S3241 to execute the subtask according to the business requirement. The business requirement may be related to the specific business type. For example, the business requirements for checking phone charges and reporting network faults may be different, and the corresponding subtasks to be executed are also different.

[0094] The task execution agent 324 executes step S3242 to discover the task result integration agent 325 through the network registration function according to business needs and receives the response information returned by the network registration function. If the task execution agent 324 also has the task execution result integration capability, this step is not required.

[0095] The task execution agent 324 executes step S3243 and sends a task execution result integration request to the task result integration agent 325. If the task execution agent 324 also has the task execution result integration function, this step is not required.

[0096] The task result integration agent 325 executes step S3251 to integrate and evaluate the execution results of all subtasks to obtain a task integration result and a task evaluation result;

[0097] The task result integration agent 325 executes step S3252 to feed back the task integration result and the task evaluation result to the user terminal 310.

[0098] In an exemplary embodiment, the above-mentioned task processing method can be applied to 6G networks. When the 6G network can provide 6G services based on AI agents to users, third-party applications and entities within the network, through the method of this patent, different network AI agents and network elements can discover and select each other, thereby improving overall service efficiency and performance. With subsequent development, the capabilities of NWDAF (Network Data Analytics Function) network elements in 5G networks continue to increase. Through this exemplary embodiment, NWDAF network elements can also provide AI-based agent services to user terminals. When multiple AI agents or agent nodes are deployed in the network, through this exemplary embodiment, multiple network AI agents or agent nodes can collaborate with each other to jointly meet business needs.

[0099] The exemplary embodiments of the present disclosure also provide a task processing device. Figure 4The device 400 may include an intention request acquisition module 410, which is used to obtain intention request data from the user terminal in response to the network registration function detecting the intelligent node; a pending task determination module 420, which is used to parse the intention request data and determine the pending task; a processing result acquisition module 430, which is used to process the pending task according to the task processing method corresponding to the pending task and obtain the task processing result; and a processing result return module 440, which is used to return the task processing result to the user terminal.

[0100] In an exemplary embodiment, the task processing apparatus further includes: a registration module, configured to send registration request information to the network registration function and receive registration response information returned by the network registration function.

[0101] In an exemplary embodiment, the agent node includes an intent parsing agent; the pending task determination module 420 includes: a data parsing unit for parsing the intent request data through the intent parsing agent to extract the pending tasks from the intent request data.

[0102] In an exemplary embodiment, the intelligent agent node also includes a task decomposition intelligent agent; the processing result acquisition module 430 includes: a subtask splitting unit, which is used to split the task to be processed into one or more subtasks through the task decomposition intelligent agent; a subtask processing unit, which is used to process each subtask separately according to the task processing method corresponding to each subtask to obtain the task processing result.

[0103] In an exemplary embodiment, the intelligent agent node also includes a processing method determination strategy planning intelligent agent; the task processing device also includes: a processing method determination module, which is used to determine the task processing method corresponding to one or more subtasks through the strategy planning intelligent agent.

[0104] In an exemplary embodiment, the agent node also includes a task execution agent; a subtask processing unit, which is used to process each subtask separately according to the task processing method corresponding to each subtask through the task execution agent to obtain a task processing result.

[0105] In an exemplary embodiment, the intelligent agent node also includes a task result integration intelligent agent; the task processing device also includes: a task integration module, which is used to integrate the task processing results of each subtask through the task result integration intelligent agent to obtain a task integration result; and / or a task evaluation module, which is used to evaluate the task processing results of each subtask through the task result integration intelligent agent to obtain a task evaluation result; the processing result return module 440 includes: a result return unit, which is used to return the task integration result and / or task evaluation result to the user end through the task result integration intelligent agent.

[0106] The specific details of each module / unit in the above device have been described in detail in the embodiments of the method part. For undisclosed details, please refer to the embodiments of the method part, so they will not be repeated here.

[0107] Exemplary embodiments of the present disclosure also provide an electronic device capable of implementing the above method.

[0108] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods, or program products. Therefore, various aspects of the present disclosure may be implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits," "modules," or "systems."

[0109] Refer to the following Figure 5 5. The electronic device 500 according to this exemplary embodiment of the present disclosure is described below. Figure 5 The electronic device 500 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0110] like Figure 5 As shown, electronic device 500 is implemented as a general-purpose computing device. Components of electronic device 500 may include, but are not limited to, the aforementioned at least one processing unit 510, the aforementioned at least one storage unit 520, a bus 530 connecting various system components (including storage unit 520 and processing unit 510), and a display unit 540.

[0111] The storage unit stores program codes, which can be executed by the processing unit 510, so that the processing unit 510 performs the steps described in the "Exemplary Method" section of this specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 510 can execute Figure 1 or Figure 3 Steps shown, etc.

[0112] The storage unit 520 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 521 and / or a cache memory unit 522 , and may further include a read-only memory unit (ROM) 523 .

[0113] The storage unit 520 may also include a program / utility 524 having a set (at least one) of program modules 525, such program modules 525 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0114] Bus 530 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0115] The electronic device 500 can also communicate with one or more external devices 600 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 500, and / or any device that enables the electronic device 500 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication can occur via an input / output (I / O) interface 550. Furthermore, the electronic device 500 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 560. As shown, the network adapter 560 communicates with other modules of the electronic device 500 via a bus 530. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 500, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0116] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the exemplary embodiment of the present disclosure.

[0117] The exemplary embodiments of the present disclosure further provide a computer-readable storage medium having stored thereon a program product capable of implementing the methods described above in this specification. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product comprising program code that, when executed on a terminal device, causes the terminal device to execute the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of the present disclosure.

[0118] The exemplary embodiments of the present disclosure further provide a program product for implementing the above-mentioned method, which can be a portable compact disc read-only memory (CD-ROM) and includes program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0119] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0120] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0121] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0122] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0123] Furthermore, the figures above are merely illustrative of the processes included in the methods according to exemplary embodiments of the present disclosure and are not intended to be limiting. It is readily understood that the processes illustrated in the figures above do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0124] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0125] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

[0126] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A task processing method, characterized in that: Applied to an intelligent agent node in a target network; the method comprises: In response to the network registration function detecting the agent node, obtaining intent request data from the user end; Parsing the intent request data to determine tasks to be processed; Processing the task to be processed according to the task processing method corresponding to the task to be processed to obtain a task processing result; Return the task processing result to the user terminal.

2. The method according to claim 1, characterized in that The method further comprises: Sending registration request information to the network registration function, and receiving registration response information returned by the network registration function.

3. The method according to claim 1, characterized in that The agent node includes an intent parsing agent; The step of parsing the intent request data and determining tasks to be processed includes: The intent request data is parsed by an intent parsing agent to extract tasks to be processed from the intent request data.

4. The method according to claim 1 or 3, characterized in that The agent node also includes a task decomposition agent; The step of processing the task to be processed according to the task processing method corresponding to the task to be processed to obtain a task processing result includes: Splitting the task to be processed into one or more subtasks by a task decomposition agent; Each of the subtasks is processed separately according to the task processing method corresponding to each subtask to obtain a task processing result.

5. The method according to claim 4, characterized in that The agent node also includes a processing mode determination strategy planning agent; The method further comprises: The task processing method corresponding to the one or more subtasks is determined by a strategic planning agent.

6. The method according to claim 4, characterized in that The agent node also includes a task execution agent; The subtasks are processed separately according to the task processing methods corresponding to the subtasks to obtain task processing results, including: The task execution agent processes each of the subtasks separately according to the task processing method corresponding to each of the subtasks to obtain the task processing result.

7. The method according to claim 6, characterized in that The agent node also includes a task result integration agent; The method further comprises: Integrate the task processing results of each subtask through the task result integration agent to obtain a task integration result; and / or The task result integration agent evaluates the task processing results of each subtask and obtains the task evaluation results; The returning the task processing result to the user terminal includes: The task result integration agent returns the task integration result and / or task evaluation result to the user terminal.

8. A task processing device, characterized in that: Applied to an intelligent agent node in a target network; the device comprises: an intent request acquisition module for acquiring intent request data from a user terminal in response to the network registration function detecting an agent node; A pending task determination module, configured to parse the intent request data and determine pending tasks; A processing result obtaining module is used to process the task to be processed according to the task processing method corresponding to the task to be processed to obtain the task processing result; The processing result returning module is used to return the task processing result to the user terminal.

9. An electronic device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor is configured to perform the method according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images