Intelligent agent-based service processing method and device, registration method and device, equipment and medium

Abstract

The embodiment of the invention provides an agent-based service processing method and device, a registration method and device, equipment, a medium and a program product. The method comprises the following steps: receiving a service request sent by a user; decomposing the service request into a plurality of service subtasks; respectively sending the plurality of service subtasks to the intelligent agents with the corresponding service capabilities; and receiving a subtask result returned by the intelligent agent, and returning the subtask result to the user. According to the method, the service request is decomposed into the service sub-tasks corresponding to the service capabilities provided by the intelligent agents, so that the intelligent agents with different service capabilities in the network can be coordinated to execute partial service tasks respectively, cooperative processing of the intelligent agents in the network is effectively organized, and the requirement of a user for high-complexity services is met.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of communication technology, in particular to an agent service processing method and device, an agent registration method and device, an electronic device, a storage medium and a computer program product. BACKGROUND

[0002] AI Agents as one of the key technologies in 6G networks have attracted extensive attention in recent years. 3GPP SA1 has made a preliminary definition and passed several standard documents related to new scenarios of AI Agents. SA2 also explicitly studies the impact of AI Agents on the architecture of 6G networks in the 6G project. AI Agents deployed in 6G networks can understand user intent, decompose complex tasks, plan and execute subtasks, and significantly improve the intelligence level of networks.

[0003] Although the current AI Agent technology based on large language models is developing rapidly, its capabilities are still limited and usually focus on a specific professional field, such as perception, AI, or computing power. If only relying on a single centralized agent, problems such as large model illusion may occur, affecting service experience. Therefore, 6G networks need to deploy multiple AI Agents with different service capabilities and implement efficient and reliable execution of complex tasks through effective collaboration mechanisms. SUMMARY

[0004] Embodiments of the present disclosure provide an agent service processing method and device, an agent registration method and device, an electronic device, a storage medium and a computer program product.

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

[0006] According to one aspect of the present disclosure, an agent registration method is provided, which includes receiving a registration request of a first agent; the registration request includes at least service capability information; and registering a correspondence between the first agent and the service capability according to the service capability information.

[0007] In an exemplary embodiment, the method further includes generating agent registration information according to the correspondence between the first agent and the service capability; and sending the agent registration information to a third network element.

[0008] In an exemplary embodiment, the service capability includes at least one of a communication service capability, a perception service capability, an AI service capability, a data service capability, a computing power service capability, and a fusion service capability.

[0009] In an exemplary embodiment, the fused service capability indicates the fusion of multiple sub-service capabilities; the fused service capability includes a list of the multiple sub-service capabilities.

[0010] According to another aspect of this disclosure, a service processing method based on intelligent agents is provided, the method comprising: receiving a service request sent by a user; decomposing the service request into at least one service subtask; each of the service subtasks corresponding to a service capability; sending the at least one service subtask to at least one intelligent agent having the corresponding service capability; the at least one intelligent agent having pre-registered the provided service capability; receiving the subtask result returned by the at least one intelligent agent; and returning the at least one subtask result to the user.

[0011] In an exemplary embodiment, the method further includes: receiving a registration request from a first intelligent agent; the registration request includes at least service capability information; and registering a correspondence between the first intelligent agent and the service capability based on the service capability information.

[0012] In an exemplary embodiment, the method further includes: receiving agent registration information sent by a first network element; the agent registration information includes at least a correspondence between the first agent and service capabilities; wherein the agent registration information is generated by the first network element in response to a registration request from the first agent.

[0013] In an exemplary embodiment, decomposing the service request into at least one service subtask includes: performing service intent analysis on the service request to obtain a service intent analysis result; and decomposing the service request into at least one service subtask based on the service intent analysis result.

[0014] In an exemplary embodiment, decomposing the service request into at least one service sub-task includes: sending the service request to a second network element; receiving a service intent analysis result returned by the second network element in response to the service request; and decomposing the service request into at least one service sub-task based on the service intent analysis result.

[0015] In an exemplary embodiment, decomposing the service request into at least one service subtask includes: determining the service request type based on the service request; and decomposing the service request into at least one service subtask based on a preset correspondence between service request types and service subtasks.

[0016] In an exemplary embodiment, sending the at least one service subtask to at least one agent with corresponding service capabilities includes: sending an agent information request to the first network element; the agent information request includes at least the service capabilities corresponding to each of the service subtasks; the first network element stores service capability information provided by each agent; receiving at least one agent information returned by the first network element in response to the agent information request; the agent information includes at least the correspondence between the agent and the service capability; and sending the at least one service subtask to at least one agent with corresponding service capabilities based on the at least one agent information.

[0017] In an exemplary embodiment, returning at least one of the subtask results to the user includes: generating a service request result based on the at least one subtask result; and returning the service request result to the user.

[0018] In an exemplary embodiment, the service capabilities include at least one of communication service capabilities, perception service capabilities, AI service capabilities, data service capabilities, computing power service capabilities, and fusion service capabilities.

[0019] According to another aspect of this disclosure, an intelligent agent registration device is provided, comprising: a registration request receiving module configured to receive a registration request from a first intelligent agent; the registration request including at least service capability information; and a service capability registration module configured to register a correspondence between the first intelligent agent and the service capability based on the service capability information.

[0020] According to another aspect of this disclosure, an agent-based service processing apparatus is provided, comprising: a request receiving module configured to receive a service request sent by a user; a service decomposition module configured to decompose the service request into at least one service subtask; each of the service subtasks corresponding to a service capability; a task distribution module configured to send the at least one service subtask to at least one agent having the corresponding service capability; the at least one agent pre-registering the provided service capability; a result receiving module configured to receive subtask results returned by the at least one agent; and a result returning module configured to return at least one subtask result to the user.

[0021] According to another aspect of this disclosure, an electronic device is provided, comprising: one or more processors; and a storage device configured to store one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the agent-based service processing method as described in the above embodiments.

[0022] According to another aspect of this disclosure, a computer-readable storage medium is provided that stores a computer program, which, when executed by a processor, implements the agent-based service processing method as described in the above embodiments.

[0023] According to another aspect of this disclosure, a computer program product is provided, including a computer program / signaling, characterized in that, when the computer program / signaling is executed by a processor, it implements the agent-based service processing method as described in the above embodiments.

[0024] The agent-based service processing method disclosed in this embodiment receives a service request sent by a user; decomposes the service request into multiple service sub-tasks; sends each service sub-task to an agent with corresponding service capabilities; receives the sub-task results returned by the agents; and returns the sub-task results to the user. This method, by decomposing the service request into service sub-tasks corresponding to the service capabilities of each agent, can coordinate agents with different service capabilities in the network to execute parts of the service tasks, thereby effectively organizing the collaborative processing of various agents in the network and meeting the user's needs for highly complex services.

[0025] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0027] Figure 1 A schematic diagram of a network architecture of a communication system to which this disclosure applies is shown; Figure 2 A flowchart of an agent-based service processing method according to an embodiment of this disclosure is shown; Figure 3 A schematic diagram of an agent-based network architecture according to an embodiment of this disclosure is shown; Figure 4 The flowchart of the service request decomposition method according to an embodiment of this disclosure is shown. Figure 1 ; Figure 5 The flowchart of the service request decomposition method according to an embodiment of this disclosure is shown. Figure 2 ; Figure 6 The flowchart of the service request decomposition method according to an embodiment of this disclosure is shown. Figure 3 ; Figure 7A flowchart of a service subtask distribution method according to an embodiment of this disclosure is shown; Figure 8 A schematic flowchart of the agent-based service processing procedure according to an embodiment of the present disclosure is shown; Figure 9 A flowchart of an agent registration method according to an embodiment of this disclosure is shown; Figure 10 A schematic diagram of the structure of an agent-based service processing device according to an embodiment of the present disclosure is shown; Figure 11 A schematic diagram of the structure of an agent registration device according to an embodiment of the present disclosure is shown; Figure 12 A schematic diagram of the structure of an electronic device suitable for implementing exemplary embodiments of the present disclosure is shown. Detailed Implementation

[0028] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary 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.

[0029] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0030] It should be noted that the ordinal numbers such as "first" and "second" mentioned in the embodiments of this disclosure are used to distinguish multiple objects, and are not used to limit the order, timing, priority or importance of multiple objects. Furthermore, the descriptions of "first" and "second" do not limit the objects to necessarily being different.

[0031] To address the aforementioned problems, the technical solutions proposed in this disclosure can be applied to various communication systems. For example, GSM (Global System for Mobile Communications) systems, CDMA (Code Division Multiple Access) systems, WCDMA (Wideband Code Division Multiple Access) systems, LTE (Long Term Evolution) systems, LTE frequency division duplex systems, LTE time division duplex systems, UMTS (Universal Mobile Telecommunication System), WIMAX (Worldwide Interoperability for Microwave Access) communication systems, 5G (5th generation) systems, or future communication systems or other similar communication systems.

[0032] Figure 1 A schematic diagram of a network architecture for a communication system to which embodiments of this disclosure apply is shown. For example... Figure 1As shown, the network architecture includes UE, RAN (Radio Access Network) equipment, AMF (Access and Mobility Management Function) network elements, SMF (Session Management function) network elements, UPF (User Plane Function) network elements, PCF (Policy Control Function) network elements, NSSF (Network Slice Selection Function) network elements, NRF (Network Repository Function) network elements, NWDAF (Network Data Analytics Function) network elements, UDM (Unified Data Management) network elements, UDR (Unified Data Repository) network elements, ASF (Authentication Server Function) network elements, NEF (Network Exposure Function) network elements, AF (Application Function) network elements, and DN (Data Network) connecting to the operator's network.

[0033] The UE can be various electronic devices, deployed on land (indoor or outdoor, handheld, wearable, or vehicle-mounted); on water (e.g., ships); or in the air (e.g., airplanes, balloons, and satellites). The UE can communicate with the core network without RAN equipment, exchanging voice and / or data with RAN equipment. The UE can be a mobile phone, tablet, computer with wireless transceiver capabilities, mobile internet device, wearable device, virtual reality terminal device, augmented reality terminal device, wireless terminal in industrial control, wireless terminal in autonomous driving, wireless terminal in telemedicine, wireless terminal in smart grids, wireless terminal in transportation safety, wireless terminal in smart cities, wireless terminal in smart homes, etc. Optionally, the client applications installed in different UEs can be the same, or clients of the same type of application based on different operating systems. Depending on the terminal platform, the specific form of the application client can also differ; for example, the application client can be a mobile phone client, a computer client, etc.

[0034] RAN equipment is a device in the network used to connect UEs to the wireless network. It can include devices in the access network that communicate with wireless terminals through one or more sectors on the air interface. UEs can access AMF network elements through RAN equipment. Specifically, when a UE accesses an AMF network element through RAN equipment, the UE can access the AMF network element through network-side equipment such as 5G and later versions of base stations (e.g., 5G NR NB) or base stations in other communication systems (e.g., eNB base stations).

[0035] The AMF network element is mainly used for mobility management and access authentication / authorization of UEs, and is also responsible for transmitting user policies between UEs and PCF network elements.

[0036] SMF network elements are mainly used for session management, UE Internet Protocol address allocation and management, selection of manageable user plane functions, policy control, or terminal points for charging function interfaces, and downlink data notification, etc.

[0037] UPF network elements can be used for packet routing and forwarding, or QoS processing of user plane data. User data can be accessed to the DN through this network element.

[0038] PCF network elements are a unified policy framework used to guide network behavior, providing policy rule information for control plane functional network elements (such as AMF and SMF network elements).

[0039] The NSSF network element is mainly used to select the appropriate network slice for the UE's services.

[0040] NRF network elements are primarily used to provide registration and discovery functions for network elements or the services they provide.

[0041] NWDAF network elements can collect data from various network functions and perform analysis and prediction.

[0042] UDM network elements are mainly used to manage UE subscription information. For example, during the authentication process, they perform authentication vector calculation, key deduction, user identifier decryption, etc. In the resynchronization process, they verify AUTS according to the corresponding algorithm and initiate a re-authentication process.

[0043] UDR network elements are mainly used to store structured data information, including subscription information, policy information, and network data or service data with standard format definitions.

[0044] The AUSF network element is mainly used for security authentication of terminal devices.

[0045] The NEF (Network Element) is located between the 5G core network and external third-party application functions, and may also have some internal application functions. It is responsible for managing the network data exposed to the outside world. All external applications that want to access the internal data of the 5G core network must go through the NEF. The NEF provides corresponding security guarantees to ensure the security of external applications to the network, and provides functions such as opening up QoS customization capabilities for external applications, subscription to mobility state events, and distribution of application function requests.

[0046] AF (Application Filter) network elements are primarily used to convey application-side requests to the network side, such as QoS requirements and user state event subscriptions. AF network elements can be third-party functional entities or application services deployed by the operator. For third-party application functional entities, authorization processing can also be handled through NEF (Network Filter) network elements when interacting with the core network. For example, a third-party application function may directly send a request to an NEF network element. The NEF network element determines whether the AF network element is authorized to send the request. If the verification is successful, the request will be forwarded to the corresponding PCF (Physical Processing Filter) network element or UDM (User Filtering Filter) network element.

[0047] It should be understood that the aforementioned network elements or functions can be network components in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform).

[0048] Figure 2 A flowchart of an agent-based service processing method according to an embodiment of this disclosure is shown. Figure 3 A schematic diagram of an agent-based network architecture according to an embodiment of this disclosure is shown. Figure 2 , 3 As shown, the agent-based service processing method may include the following steps.

[0049] In step S210, a service request sent by the user is received.

[0050] Figure 3 A schematic diagram of an agent-based network architecture according to an embodiment of this disclosure is shown. Figure 3 As shown, the network contains multiple AI agents with different professional service capabilities (such as communication, sensing, AI, data, computing power, and fusion services). Each agent has its own specific service capabilities used to handle tasks within that service capability. Each agent can pre-register its service capabilities with the Network Registration Function (NRF).

[0051] In this embodiment, the agent-based service processing method is applied to the aforementioned network service proxy function network element. In this network structure, the network service proxy function network element serves as the core hub, responsible for uniformly receiving service requests from various users (including UEs, RANs, core network elements, and applications). These requests can be either natural language-based intent requests (such as text descriptions) or standardized service requests (such as 5G signaling or NAS messages). The network service proxy function network element learns about the service capabilities provided by each agent through the network registration function network element. Based on the service request, the network service proxy function network element is responsible for finding an agent with matching service capabilities to process the service.

[0052] It should be noted that the network service proxy function network element and the network registration function network element can be integrated and provided by a common network element.

[0053] In an exemplary embodiment, the service capability may include at least one of the following: communication service capability, perception service capability, AI service capability, data service capability, computing power service capability, and converged service capability. Specifically, communication service capability refers to the intelligent agent's ability to provide connectivity and communication assurance, such as managing network connections, allocating bandwidth, or ensuring transmission quality. Perception service capability refers to the intelligent agent's ability to acquire and process information about the external environment, such as collecting, analyzing, and providing data about network status or the physical environment. AI service capability refers to the intelligent agent's ability to provide artificial intelligence-related processing, such as performing model inference, data analysis, intelligent decision-making, or intent understanding. Data service capability refers to the intelligent agent's ability to provide data manipulation and provision, such as storing, retrieving, processing, exchanging, or protecting the privacy of data. Computing power service capability refers to the intelligent agent's ability to schedule and manage computing resources, such as allocating, optimizing, and ensuring the computing resources required for task execution. Converged service capability refers to the intelligent agent's ability to collaboratively process complex intents across multiple domains, such as coordinating multiple services such as communication, perception, AI, data, and computing power to complete comprehensive tasks.

[0054] In step S220, the service request is decomposed into at least one service subtask; each service subtask corresponds to a service capability.

[0055] In this embodiment of the disclosure, the network service proxy function network element decomposes the service request into at least one service sub-task. Multiple service sub-tasks together constitute the service requested by the service request task. Each service sub-task corresponds to one of the aforementioned service capabilities. These service capabilities are several pre-defined service capability types, corresponding to the service capability types provided by the aforementioned intelligent agent.

[0056] In an exemplary embodiment, the network service proxy function element itself possesses semantic analysis capabilities. By semantically understanding and structurally parsing the semantic content of service requests, this network service proxy function element identifies the user's core needs and implicit service types. Then, based on a predefined service capability framework, it breaks down complex macro-level intentions into multiple independent service sub-tasks, each with a clearly defined service capability orientation.

[0057] In an exemplary embodiment, the network service proxy function network element itself does not have semantic analysis capabilities. Instead, it invokes other network elements with relevant capabilities to analyze the service request. Then, based on the analysis results, the service request is decomposed into multiple service sub-tasks.

[0058] For example, when a user expresses the intention to "use a rescue robot to go to the accident site for rescue", the network service agent function network element analyzes and identifies that the task relies on two core capabilities: environmental information perception and intelligent decision-making. It then initially decomposes the task into a sub-task corresponding to the perception service capability, namely "perceiving the real-time road conditions from the departure point to the destination", and a sub-task corresponding to the AI ​​service capability, namely "calculating the optimal route from the destination to the departure point".

[0059] For example, when a user expresses the intention of "I need to hold a VR meeting at xx time and xx location, please ensure communication quality", the network service proxy function network element analyzes and identifies that the task relies on AI service capabilities and computing power service capabilities, and then initially decomposes it into the sub-task of "predicting the communication quality at xx time and xx location" which corresponds to AI service capabilities, and the sub-task of "providing VR rendering services to users at xx time" which corresponds to computing power service capabilities.

[0060] In step S230, the at least one service subtask is sent to at least one intelligent agent with corresponding service capabilities; the at least one intelligent agent has pre-registered the service capabilities it provides.

[0061] In this embodiment, the network service proxy function network element searches for intelligent agents with matching service capabilities based on the service capabilities corresponding to each decomposed service sub-task and the service capabilities provided by each intelligent agent in the pre-registered network. The corresponding service sub-tasks are then sent to the intelligent agents with the corresponding service capabilities. Each intelligent agent in the network pre-registers its provided service capabilities, and a correspondence is established between each intelligent agent and its provided service capabilities.

[0062] In some exemplary embodiments, each intelligent agent may register the service capabilities it provides through the following steps.

[0063] Receive a registration request from a first intelligent agent; the registration request includes at least service capability information; Based on the service capability information, register the correspondence between the first intelligent agent and the service capability.

[0064] In this embodiment, the network service proxy function network element itself has an agent registration function. The network element receives a registration request from a first agent. The first agent can be any agent in the network with service capabilities. The registration request includes at least the agent's identification information and its provided service capabilities, such as communication, sensing, AI, data, computing power, or fusion service capabilities. This service capability information indicates the type of service capability provided by the first agent. Based on the service capability information in the registration request, the network element establishes and stores the correspondence between the agent and its service capabilities in its registration database, thereby providing a relevant data foundation for subsequently matching agents with corresponding service capabilities.

[0065] In some exemplary embodiments, each intelligent agent may register the service capabilities it provides through the following steps.

[0066] Receive agent registration information sent by a first network element; the agent registration information includes at least the correspondence between the first agent and the service capability; The agent registration information is generated by the first network element in response to the registration request of the first agent.

[0067] In this embodiment, the network service proxy function network element itself does not have an agent registration function. Instead, the registration of service capabilities provided by each agent is achieved through a first network element (e.g., a network registration function network element). The first network element receives a registration request from a first agent in advance. The first agent can be any agent in the network with service capabilities. The registration request includes at least the agent's identification information and its provided service capability information, such as communication, sensing, AI, data, computing power, or fusion service capabilities. This service capability information indicates the type of service capability provided by the first agent. Based on the service capability information in the registration request, the first network element establishes and stores the correspondence between the agent and its service capabilities in its registration database. The first network element sends agent registration information to the network service proxy function network element. This agent registration information includes at least the correspondence between each first agent and its service capabilities. By receiving the agent registration information sent by the first network element, the network service proxy function network element obtains the correspondence between each first agent and its service capabilities, thereby providing a relevant data foundation for subsequently matching agents with corresponding service capabilities.

[0068] In step S240, the subtask results returned by the at least one agent are received.

[0069] In this embodiment of the disclosure, after receiving the distributed service subtasks, each agent performs a deeper level of intent understanding and task planning, further decomposing the "service granularity" service subtasks into several independently executable atomic operations. For example, a subtask corresponding to "perception service capability" (such as "perceiving road conditions from origin to destination") will be refined by an agent with this capability into multiple specific executable perception actions such as "real-time obstacle perception" and "real-time weather condition perception"; similarly, an "AI service capability" subtask may also be decomposed into the smallest execution unit conforming to the NWDAF analysis ID specification or multiple model inferences.

[0070] After decomposing the service subtasks, the agent completes these atomic operations either locally or by calling external tools / network elements. Agents with local processing capabilities can calculate the results themselves, while for tasks requiring specific resources or functions (such as calling dedicated sensing network elements to obtain data), the agent will collaborate with other network entities by sending standardized signaling requests. After all atomic operations are completed, the agent will integrate and encapsulate the results to form the corresponding subtask results. The network service proxy function network element asynchronously receives these subtask results returned from different agents.

[0071] In step S250, at least one of the subtask results is returned to the user.

[0072] In this embodiment, the results of each service subtask collectively constitute the service result of the service request. The network service proxy function returns the results of each subtask to the user to complete the processing of the service request.

[0073] In an exemplary embodiment, the network service proxy function network element can integrate the results of the various subtasks to generate an integrated service request result, and return the service request result to the user.

[0074] The agent-based service processing method disclosed in this embodiment receives a service request sent by a user; decomposes the service request into multiple service sub-tasks; sends each service sub-task to an agent with corresponding service capabilities; receives the sub-task results returned by the agents; and returns the sub-task results to the user. This method, by decomposing the service request into service sub-tasks corresponding to the service capabilities of each agent, can coordinate agents with different service capabilities in the network to execute parts of the service tasks, thereby effectively organizing the collaborative processing of various agents in the network and meeting the user's needs for highly complex services.

[0075] Figure 4The flowchart of the service request decomposition method according to an embodiment of this disclosure is shown. Figure 1 In this embodiment of the disclosure, in Figure 2 As shown, based on the agent service processing method, such as Figure 4 As shown, step S220 may include the following steps.

[0076] In step S410, the service request is analyzed for service intent to obtain the service intent analysis result.

[0077] In this embodiment, the network service proxy function network element itself has service intent analysis capabilities. The network service proxy function network element first performs service intent analysis on the received user service requests. This process aims to understand the deep semantics and true purpose of the user request, especially when the request is expressed in natural language or fuzzy instructions. By integrating technologies such as Natural Language Understanding (NLU), semantic parsing, or domain knowledge graphs, key operational objects, expected goals, and implicit contextual constraints can be extracted from the service request and transformed into a structured service intent analysis result that can be recognized and processed by the network. This service intent analysis result should at least indicate the type of service capability required by the service request.

[0078] In step S420, based on the service intent analysis results, the service request is decomposed into at least one service subtask.

[0079] In this embodiment, the network service proxy function further decomposes the complex service request into multiple discrete service subtasks with clearly defined capabilities based on the service intent analysis results. Each service subtask corresponds to a service capability. The decomposition process follows a predefined service capability framework and task granularity standard to ensure that each subtask can be executed by an agent in the network with the corresponding service capability.

[0080] Figure 5 The flowchart of the service request decomposition method according to an embodiment of this disclosure is shown. Figure 2 In this embodiment of the disclosure, in Figure 5 As shown, based on the agent service processing method, such as Figure 6 As shown, step S220 may include the following steps.

[0081] In step S510, the service request is sent to the second network element.

[0082] In this embodiment, the network service proxy function network element itself does not have service intent analysis capabilities. Instead, it invokes a second network element with relevant capabilities to analyze the service request. This second network element is a specialized functional entity in the network with deep semantic analysis capabilities, responsible for parsing and understanding the original service request. The network service proxy function network element sends the service request to the second network element, which then invokes the second network element's relevant capabilities to analyze the service request. This solution improves the overall flexibility and scalability of the system by decoupling the functions of the network service proxy function network element and the second network element.

[0083] In step S520, the service intent analysis result returned by the second network element in response to the service request is received.

[0084] In this embodiment of the disclosure, after the network service proxy function network element sends the service request, it receives a processing response from the second network element. This response is the service intent analysis result, which is a structured output generated by the second network element after performing in-depth analysis of the service request using its built-in Natural Language Understanding (NLU), semantic parsing, or domain knowledge graph technologies. The service intent analysis result should at least indicate the type of service capability required by the service request.

[0085] In step S530, based on the service intent analysis results, the service request is decomposed into at least one service subtask.

[0086] In this embodiment, the network service proxy function further decomposes the complex service request into multiple discrete service subtasks with clearly defined capabilities based on the service intent analysis results. Each service subtask corresponds to a service capability. The decomposition process follows a predefined service capability framework and task granularity standard to ensure that each subtask can be executed by an agent in the network with the corresponding service capability.

[0087] Figure 3 The flowchart of the service request decomposition method according to an embodiment of this disclosure is shown. Figure 2 In this embodiment of the disclosure, in Figure 6 As shown, based on the agent service processing method, such as Figure 7 As shown, step S220 may include the following steps.

[0088] In step S610, the service request type is determined based on the service request.

[0089] In this embodiment of the disclosure, if the service request is a standardized service request or an intent request that carries a specific service capability type, then the network service proxy function network element does not need to invoke the service intent analysis capability for analysis. Instead, the service request type is determined based on the service request itself.

[0090] The service request type can be based on a predefined classification system, such as distinguishing between standardized service requests (e.g., specific signaling processes, API calls) or intent-based requests (e.g., natural language descriptions), and can be further refined into specific types such as communication, perception, and AI computing.

[0091] In step S620, the service request is decomposed into at least one service subtask according to the preset correspondence between service request types and service subtasks.

[0092] In this embodiment of the disclosure, after determining the service request type, the network service proxy function network element queries its internal or network-pre-defined mapping table. This mapping table explicitly defines the correspondence between service request types and service subtasks. Based on this correspondence, the network service proxy function network element decomposes the service request into at least one service subtask.

[0093] This disclosure provides different service request task decomposition schemes based on actual conditions. These schemes complement each other and jointly ensure the network's ability to efficiently and reliably decompose and process various service requests in different scenarios.

[0094] Figure 2 A flowchart of a service subtask distribution method according to an embodiment of the present disclosure is shown. In this embodiment, in... Figure 7 As shown, based on the agent service processing method, such as Figure 8 As shown, step S230 may include the following steps.

[0095] In step S710, an agent information request is sent to the first network element; the agent information request includes at least the service capabilities corresponding to each of the service subtasks; the first network element stores the service capability information provided by each agent.

[0096] In this embodiment, the network service proxy function network element itself does not have an agent registration function. Instead, the registration of service capabilities provided by each agent is achieved through a first network element (e.g., a network registration function network element). This first network element receives registration requests from each agent in advance. The agent can be any agent in the network with service capabilities. The registration request includes at least the agent's identification information and its provided service capability information. This service capability information indicates the type of service capability provided by the agent. Based on the service capability information in the registration request, the first network element establishes and stores the correspondence between the agent and its service capabilities in its registration database.

[0097] In this embodiment of the disclosure, after the network service proxy function network element completes the decomposition of the service request and obtains each service sub-task, it sends an agent information request to the first network element. The agent information request includes at least the service capabilities corresponding to each of the service sub-tasks, and is used to request agent information with the corresponding service capabilities from the first network element.

[0098] In step S720, at least one agent information returned by the first network element in response to the agent information request is received; the agent information includes at least the correspondence between the agent and the service capability.

[0099] In this embodiment of the disclosure, the network service proxy function network element receives at least one agent information returned by the first network element in response to the agent information request. This agent information is generated by the first network element based on the correspondence between its stored agents and their service capabilities, matching the agent information that meets the service capabilities required for each service subtask.

[0100] In step S730, based on the at least one agent information, the at least one service subtask is sent to at least one agent with corresponding service capabilities.

[0101] In this embodiment of the disclosure, the correspondence between each service subtask and each intelligent agent is determined based on the correspondence between intelligent agents and service capabilities included in the information of the plurality of intelligent agents. Based on the determined correspondence, at least one service subtask is sent to at least one intelligent agent with the corresponding service capability.

[0102] Figure 8 A schematic flowchart illustrating the agent-based service processing procedure according to an embodiment of this disclosure is shown. Figure 9 As shown, in this network structure, the network contains multiple AI agents with different professional service capabilities. Each agent has its own specific service capability to handle tasks corresponding to that service capability. Each agent can pre-register its service capabilities with the Network Registration Function (NRF) (steps 0a and 0b).

[0103] In steps 0a / 0b, agents with various service capabilities in the network pre-register their provided service capabilities with the Network Registration Function (NRF) element. Based on the service capability information in the registration request, the NRF element establishes and stores the correspondence between the agent and its service capabilities in its registration database. Upon completion of registration for each agent, a registration response is returned to each agent. During this registration process, the Network Service Proxy Function (NRF) element can obtain agent registration information from the NRF element in advance, or send an agent information request to the NRF element after the service request has been decomposed.

[0104] In step 1, a service request is received from a user (such as a consumer).

[0105] In step 2, after receiving the service request, the network service proxy function network element performs semantic understanding and intent analysis on it, and initially decomposes the complex user intent into multiple service sub-tasks corresponding to the service capabilities (such as perception service, AI service, etc.).

[0106] In step 3, the network service proxy function network element sends an agent information request to the NRF network element. This agent information request includes at least the service capabilities corresponding to each service subtask. The network element receives at least one agent information response to the agent information request. This agent information includes at least the correspondence between agents and service capabilities.

[0107] In steps 4a / 4b, the network service agent function network element sends each service subtask to an intelligent agent with corresponding service capabilities based on information from at least one intelligent agent.

[0108] In steps 5a / 5b, after each agent receives the distributed service subtask, it processes the service subtask based on its own service capabilities to obtain the corresponding subtask result.

[0109] In steps 6a / 6b, each agent returns the obtained subtask results to the network service agent function element.

[0110] In step 7, the network service proxy function network element integrates the results of each subtask, generates an integrated service request result, and returns the service request result to the user.

[0111] Figure 9 A flowchart of an agent registration method according to an embodiment of this disclosure is shown. Figure 10 As shown, the agent registration method may include the following steps.

[0112] In step S910, a registration request from the first intelligent agent is received; the registration request includes at least service capability information.

[0113] In step S920, the correspondence between the first intelligent agent and the service capability is registered according to the service capability information.

[0114] In this embodiment, the network structure includes an agent registration network element. This agent registration network element is used to provide registration for any agent in the network with service capabilities. This agent registration network element can be the aforementioned network service proxy function network element, network registration function network element (NRF), or other network elements. This network element receives a registration request from a first agent. The first agent can be any agent in the network with service capabilities. The registration request includes at least the agent's identification information and its provided service capability information, such as communication, sensing, AI, data, computing power, or fusion service capabilities. This service capability information indicates the type of service capability provided by the first agent. Based on the service capability information in the registration request, the network element establishes and stores the correspondence between the agent and its service capabilities in its registration database, thereby providing a relevant data foundation for subsequently matching agents with corresponding service capabilities.

[0115] In some exemplary embodiments, the agent registration network element can aggregate the registration information of various agents and provide it to other network elements in the network that require relevant registration information. Specifically, this may include the following steps.

[0116] Based on the correspondence between the first intelligent agent and the service capabilities, intelligent agent registration information is generated; The registration information of the intelligent agent is sent to the third network element.

[0117] In this embodiment, the agent registration network element establishes and stores the correspondence between the agent and its service capabilities in its registration database based on the service capability information in the registration request. Then, based on the correspondence between each first agent and its service capabilities, agent registration information is generated. This agent registration information includes at least the correspondence between each first agent and its service capabilities. The agent registration network element sends the generated agent registration information to a third network element. This third network element is another network element that needs the agent registration information, such as a network service proxy function network element. By receiving the agent registration information, the third network element obtains the correspondence between each first agent and its service capabilities, thereby providing a relevant data foundation for subsequently matching agents with corresponding service capabilities.

[0118] In an exemplary embodiment, the service capability may include at least one of the following: communication service capability, perception service capability, AI service capability, data service capability, computing power service capability, and converged service capability. Specifically, communication service capability refers to the intelligent agent's ability to provide connectivity and communication assurance, such as managing network connections, allocating bandwidth, or ensuring transmission quality. Perception service capability refers to the intelligent agent's ability to acquire and process information about the external environment, such as collecting, analyzing, and providing data about network status or the physical environment. AI service capability refers to the intelligent agent's ability to provide artificial intelligence-related processing, such as performing model inference, data analysis, intelligent decision-making, or intent understanding. Data service capability refers to the intelligent agent's ability to provide data manipulation and provision, such as storing, retrieving, processing, exchanging, or protecting the privacy of data. Computing power service capability refers to the intelligent agent's ability to schedule and manage computing resources, such as allocating, optimizing, and ensuring the computing resources required for task execution. Converged service capability refers to the intelligent agent's ability to collaboratively process complex intents across multiple domains, such as coordinating multiple services such as communication, perception, AI, data, and computing power to complete comprehensive tasks.

[0119] In an exemplary embodiment, the fusion service capability refers to the fusion of multiple sub-service capabilities. These sub-service capabilities can be any of the aforementioned communication service capabilities, perception service capabilities, AI service capabilities, data service capabilities, and computing power service capabilities. An intelligent agent with fusion service capability simultaneously possesses multiple sub-service capabilities and can combine these multiple sub-service capabilities to provide fusion service capability. The fusion service capability includes a list of the various sub-service capabilities to indicate which sub-service capabilities it possesses.

[0120] Based on the same inventive concept, this disclosure provides an agent-based service processing device and an agent registration device, as described in the following embodiments. Since the principle by which this device embodiment solves the problem is similar to that of the above-described method embodiment, the implementation of this communication authentication device embodiment can be directly referenced to the above-described method embodiment; repeated details will not be elaborated further.

[0121] Figure 10 A schematic diagram of the structure of an agent-based service processing device according to an embodiment of this disclosure is shown. Figure 11 As shown, the agent-based service processing device 1000 may include: a request receiving module 1010, a service decomposition module 1020, a task distribution module 1030, a result receiving module 1040, and a result return module 1050.

[0122] The request receiving module 1010 is configured to receive service requests sent by users. The service decomposition module 1020 is configured to decompose the service request into at least one service subtask; each service subtask corresponds to a service capability. The task distribution module 1030 is configured to send the at least one service subtask to at least one intelligent agent with corresponding service capabilities; the at least one intelligent agent has pre-registered the service capabilities it provides. The result receiving module 1040 is configured to receive the subtask results returned by the at least one intelligent agent; Result return module 1050 is configured to return at least one of the subtask results to the user.

[0123] In an exemplary embodiment, a registration request for a first intelligent agent is received; the registration request includes at least service capability information; and a correspondence between the first intelligent agent and the service capability is registered based on the service capability information.

[0124] In an exemplary embodiment, intelligent agent registration information sent by a first network element is received; the intelligent agent registration information includes at least the correspondence between the first intelligent agent and the service capability; The agent registration information is generated by the first network element in response to the registration request of the first agent.

[0125] In an exemplary embodiment, the service decomposition module 1020 is further configured to perform service intent analysis on the service request to obtain a service intent analysis result; and decompose the service request into at least one service subtask based on the service intent analysis result.

[0126] In an exemplary embodiment, the service decomposition module 1020 is further configured to send the service request to a second network element; receive a service intent analysis result returned by the second network element in response to the service request; and decompose the service request into at least one service subtask based on the service intent analysis result.

[0127] In an exemplary embodiment, the service decomposition module 1020 is further configured to determine the service request type based on the service request; and to decompose the service request into at least one service subtask based on a preset correspondence between the service request type and the service subtask.

[0128] In an exemplary embodiment, the task distribution module 1030 is further configured to send an agent information request to the first network element; the agent information request includes at least the service capabilities corresponding to each of the service sub-tasks; the first network element stores service capability information provided by each agent; receive at least one agent information returned by the first network element in response to the agent information request; the agent information includes at least the correspondence between the agent and the service capability; and send the at least one service sub-task to at least one agent with the corresponding service capability according to the at least one agent information.

[0129] In an exemplary embodiment, the result return module 1050 is further configured to generate a service request result based on the result of the at least one subtask, and return the service request result to the user.

[0130] In an exemplary embodiment, the service capabilities include at least one of communication service capabilities, perception service capabilities, AI service capabilities, data service capabilities, computing power service capabilities, and fusion service capabilities.

[0131] Figure 11 A schematic diagram of the structure of an agent registration device according to an embodiment of this disclosure is shown. Figure 12 As shown, the intelligent agent registration device 1100 may include: a registration request receiving module 1110 and a service capability registration module 1120.

[0132] The registration request receiving module 1110 is configured to receive a registration request from the first intelligent agent; the registration request includes at least service capability information.

[0133] The service capability registration module 1120 is configured to register the correspondence between the first intelligent agent and the service capability based on the service capability information.

[0134] In an exemplary embodiment, the agent registration information module is configured to generate agent registration information based on the correspondence between the first agent and the service capability, and send the agent registration information to the third network element.

[0135] In an exemplary embodiment, the service capabilities include at least one of communication service capabilities, perception service capabilities, AI service capabilities, data service capabilities, computing power service capabilities, and fusion service capabilities.

[0136] In an exemplary embodiment, the fused service capability indicates the fusion of multiple sub-service capabilities; the fused service capability includes a list of the multiple sub-service capabilities.

[0137] Figure 12 A schematic diagram of the structure of an electronic device suitable for implementing exemplary embodiments of the present disclosure is shown. Referring below... Figure 12 To describe an electronic device 1200 according to this embodiment of the present invention. Figure 12 The electronic device 1200 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0138] like ​As shown, the electronic device 1200 is presented in the form of a general-purpose computing device. The components of the electronic device 1200 may include, but are not limited to: at least one processing unit 1210, at least one storage unit 1220, a bus 1230 connecting different system components (including storage unit 1220 and processing unit 1210), and a display unit 1240.

[0139] Storage unit 1220 may include readable media in the form of volatile storage units, such as random access memory (RAM) 12201 and / or cache memory 12202, and may further include read-only memory (ROM) 12203.

[0140] Storage unit 1220 may also include a program / utility 12204 having a set (at least one) of program modules 12205, such program modules 12205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0141] Bus 1230 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0142] Electronic device 1200 can also communicate with one or more external devices 1270 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 1200, and / or with any device that enables electronic device 1200 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 1250. Furthermore, electronic device 1200 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1260. As shown, network adapter 1260 communicates with other modules of electronic device 1200 via bus 1230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 1200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0143] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored.

[0144] In some possible implementations, various aspects of the present invention may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present invention.

[0145] According to embodiments of the present invention, a program product for implementing the above-described method may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with a signaling execution system, apparatus, or device.

[0146] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0147] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various 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, capable of sending, propagating, or transmitting programs for use by or in conjunction with a signaling execution system, apparatus, or device.

[0148] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0149] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0150] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0151] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0152] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several signaling instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the method according to the embodiments of this disclosure.

[0153] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

[0154] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. An agent registration method, characterized by, The method comprises: receiving a registration request of a first agent; the registration request at least comprising service capability information; registering a corresponding relationship between the first agent and the service capability according to the service capability information.

2. The method of claim 1, wherein, The method further comprises: generating agent registration information according to the corresponding relationship between the first agent and the service capability; sending the agent registration information to a third network element.

3. The method of claim 1, wherein, The service capability comprises at least one of communication service capability, perception service capability, AI service capability, data service capability, computing power service capability, and fusion service capability.

4. The method of claim 3, wherein, The fusion service capability indicates that multiple sub-service capabilities are fused; the fusion service capability comprises a list of the multiple sub-service capabilities.

5. An agent-based service processing method, characterized by, The method comprises: receiving a service request sent by a user; decomposing the service request into at least one service subtask; each service subtask corresponds to a service capability; sending the at least one service subtask to at least one agent having a corresponding service capability; the at least one agent pre-registers a provided service capability; receiving a subtask result returned by the at least one agent; returning the at least one subtask result to the user.

6. The method of claim 5, wherein, The method further comprises: receiving a registration request of a first agent; the registration request at least comprising service capability information; registering a corresponding relationship between the first agent and the service capability according to the service capability information.

7. The method of claim 5, wherein, The method further comprises: receiving agent registration information sent by a first network element; the agent registration information at least comprising a corresponding relationship between a first agent and a service capability; The agent registration information is generated by the first network element in response to the registration request of the first agent.

8. The method of claim 5, wherein, The decomposition of the service request into at least one service subtask comprises: performing service intent analysis on the service request to obtain a service intent analysis result; decomposing the service request into at least one service subtask according to the service intent analysis result.

9. The method of claim 5, wherein, The decomposition of the service request into at least one service subtask comprises: sending the service request to a second network element; receiving a service intent analysis result returned by the second network element in response to the service request; decomposing the service request into at least one service subtask according to the service intent analysis result.

10. The method of claim 5, wherein, The decomposition of the service request into at least one service subtask comprises: determining a service request type according to the service request; decomposing the service request into at least one service subtask according to a preset corresponding relationship between the service request type and the service subtask.

11. The method of claim 5, wherein, The sending of the at least one service subtask to at least one agent having a corresponding service capability comprises: sending an agent information request to the first network element; the agent information request at least comprising a service capability corresponding to each service subtask; the first network element stores service capability information provided by each agent; receive at least one agent information returned by the first network element in response to the agent information request; the agent information at least including a correspondence between an agent and a service capability; according to the at least one agent information, send the at least one service subtask to at least one agent having a corresponding service capability respectively.

12. The method of claim 5, wherein, the returning of the at least one subtask result to the user comprises: generating a service request result based on the at least one subtask result; returning the service request result to the user.

13. The method of claim 5, wherein, the service capability comprises at least one of a communication service capability, a perception service capability, an AI service capability, a data service capability, a computing power service capability, and a fusion service capability.

14. An agent registration apparatus characterized by comprising: comprise: a registration request receiving module configured to receive a registration request of a first agent; the registration request at least including service capability information; a service capability registration module configured to register a correspondence between the first agent and the service capability according to the service capability information.

15. An agent service processing apparatus based on the method of any one of claims 1 to 14. comprise: a request receiving module configured to receive a service request sent by a user; a service decomposition module configured to decompose the service request into at least one service subtask; each service subtask corresponds to a service capability respectively; a task distribution module configured to send the at least one service subtask to at least one agent having a corresponding service capability respectively; the at least one agent pre-registers a provided service capability; a result receiving module configured to receive a subtask result returned by the at least one agent; a result returning module configured to return the at least one subtask result to the user.

16. An electronic device, comprising: comprise: one or more processors; a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method according to any one of claims 1 to 13.

17. A computer-readable storage medium, the computer-readable storage medium storing a computer program, characterized in that, the computer program is executed by the processor to implement the method according to any one of claims 1 to 13.

18. A computer program product comprising a computer program / signalling, characterized in that, the computer program / signaling is executed by the processor to implement the method according to any one of claims 1 to 13.

Images