Intelligent agent collaborative interaction method and system and electronic equipment

Abstract

The invention provides an agent collaborative interaction method and system and electronic equipment. The agent collaborative interaction method comprises the following steps: registering agent capability information to a network registration function network element; sending a first service retrieval request to the network registration function network element according to the current task, and receiving a first retrieval result returned by the network registration function network element; when the first retrieval result comprises at least one service party agent, determining state information of the service party agent according to the first retrieval result, and selecting the service party agent to send a service negotiation request; when it is determined that a service negotiation response returned by the service party agent based on the service negotiation request is received, sending a co-processing data packet corresponding to the current task to the service party agent through an interaction mode corresponding to the service negotiation response; and receiving a co-processing result corresponding to the co-processing data packet returned by the service agent, and processing the current task according to the co-processing result. According to the embodiment of the invention, the agent interaction efficiency can be improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of information technology, and in particular, to an agent collaborative interaction method and system and electronic equipment. BACKGROUND

[0002] An agent (also referred to as an AI agent or AI proxy) refers to an artificial intelligence entity with the ability to perceive network status, make decisions and execute, to complete specific network tasks (such as resource scheduling, data processing, fault diagnosis), for example, an independently deployed network AI module, an AI functional unit built into a 6G core network element, or a network large model.

[0003] Currently, multiple agents are allowed to be set in a 6G network architecture, and multiple agents are allowed to work collaboratively. In the related art, the 6G core network SBA architecture mainly realizes signaling interaction and data transmission through the HTTP / 2 protocol. This approach has the disadvantages of low protocol transmission efficiency (HTTP / 2 is based on TCP, which has a header blocking problem), resource preemption caused by mixed transmission of signaling and data, and poor adaptability to large bandwidth / low latency services. Therefore, it cannot meet the high real-time, high-bandwidth, and low-packet-loss interaction requirements in the agent collaborative work scenario. Moreover, with the increase in the number of agents, the development time and subject of different agents are different, and the types of agents are diverse, which brings difficulties to the interaction and collaborative work of agents.

[0004] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0005] The purpose of the present disclosure is to provide an agent collaborative interaction method and system and electronic equipment to improve the efficiency of agent collaborative work in a 6G network architecture.

[0006] According to a first aspect of the present disclosure, a method for intelligent agent collaborative interaction is provided, executed by a first intelligent agent, comprising: registering intelligent agent capability information with a network registration function element, the intelligent agent capability information including the intelligent agent type of the first intelligent agent, the types of communication channels supported by the first intelligent agent, and the interaction protocol; when it is determined that the current task needs to be completed through intelligent agent collaboration, sending a first service retrieval request to the network registration function element according to the current task, and receiving a first retrieval result returned by the network registration function element based on the first service retrieval request and the intelligent agent capability information of multiple intelligent agents; when the first retrieval result includes at least one service-party intelligent agent, determining the state information of the service-party intelligent agent according to the first retrieval result, and selecting the service-party intelligent agent to send a service negotiation request according to the compatibility degree between the state information and the current task; when it is determined that a service negotiation response returned by the service-party intelligent agent based on the service negotiation request is accepted, sending a collaborative processing data packet corresponding to the current task to the service-party intelligent agent through the interaction method corresponding to the service negotiation response; receiving a collaborative processing result corresponding to the collaborative processing data packet returned by the service-party intelligent agent through the interaction method corresponding to the service negotiation response, and processing the current task according to the collaborative processing result.

[0007] According to a second aspect of the present disclosure, a method for intelligent agent collaborative interaction is provided, executed by a network registration function element, comprising: receiving an intelligent agent capability information registration request from an intelligent agent, and registering the intelligent agent capability information of the intelligent agent; responding to a service retrieval request from the intelligent agent, and retrieving a service-party intelligent agent matching the service retrieval request based on the intelligent agent capability information of multiple intelligent agents, wherein the service retrieval request includes an intelligent agent type, a communication channel type, and an interaction protocol; when the service-party intelligent agent is retrieved, forming a retrieval result based on the intelligent agent capability information of the service-party intelligent agent; and returning the retrieval result to the intelligent agent.

[0008] According to a third aspect of this disclosure, an intelligent agent collaborative interaction system is provided, comprising: a plurality of intelligent agents for performing any of the methods executed by a first intelligent agent as described above; and a network registration function element communicatively connected to the plurality of intelligent agents for performing the methods executed by the network registration function element as described above.

[0009] According to a fourth aspect of this disclosure, an electronic device is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to perform the method as described in any of the preceding methods based on instructions stored in the memory.

[0010] According to a fifth aspect of the present disclosure, a computer readable storage medium is provided, and the computer readable storage medium stores a program, and the program is executed by a processor to implement the method of the intelligent agent cooperative interaction according to any one of the above aspects.

[0011] According to a sixth aspect of the present disclosure, a computer program product is provided, and the computer program product comprises a computer program, and the computer program is executed by a processor to implement the steps of the method according to any one of the above aspects.

[0012] The embodiments of the present disclosure can make the intelligent agents with different online times, different development modes and different supported interaction modes to negotiate business through the interaction modes supported by both parties, and can flexibly select a specific interaction mode according to different business characteristics and cooperative conditions, so that the intelligent agents can efficiently cooperate and efficiently complete complex network tasks, and thus the service experience of network services is improved.

[0013] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0014] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0015] Figure 1 is a flowchart of the method of intelligent agent cooperative interaction in the exemplary embodiments of the present disclosure.

[0016] Figure 2 is a schematic diagram of the system of intelligent agent cooperative interaction in the exemplary embodiments of the present disclosure.

[0017] Figure 3 is a sub-flowchart of step S2 in the exemplary embodiments of the present disclosure.

[0018] Figure 4 is a schematic diagram of a way of processing the search result in the exemplary embodiments of the present disclosure.

[0019] Figure 5This is a schematic diagram illustrating one method of processing search results in an exemplary embodiment of this disclosure.

[0020] Figure 6 This is a flowchart of the steps performed by the first intelligent agent as a service-oriented intelligent agent in an exemplary embodiment of this disclosure.

[0021] Figure 7 This is a flowchart of an exemplary embodiment of the intelligent agent collaborative interaction method disclosed herein.

[0022] Figure 8 This is a schematic diagram illustrating the interaction between the intelligent agent and the network registration function element in an embodiment of this disclosure.

[0023] Figure 9 This is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0024] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0025] Furthermore, the accompanying drawings are merely illustrative of this disclosure, and the same reference numerals in the drawings denote the same or similar parts, thus 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.

[0026] The exemplary embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0027] Figure 1 This is a flowchart of an agent collaborative interaction method in an exemplary embodiment of this disclosure.

[0028] refer to Figure 1 The intelligent agent collaborative interaction method 100 may include:

[0029] Step S1: Register the agent capability information with the network registration function element. The agent capability information includes the agent type of the first agent, the types of communication channels supported by the first agent, and the interaction protocol.

[0030] Step S2: When it is determined that the current task needs to be completed through the collaboration of intelligent agents, a first service retrieval request is sent to the network registration function network element according to the current task, and a first retrieval result is returned by the network registration function network element based on the first service retrieval request and the intelligent agent capability information of multiple intelligent agents.

[0031] Step S3: When the first search result includes at least one service agent, determine the status information of the service agent based on the first search result, and select the service agent to send a service negotiation request based on the status information and the adaptability of the current task.

[0032] Step S4: When it is determined that the service negotiation response returned by the service party agent based on the service negotiation request is accepted, the collaborative processing data packet corresponding to the current task is sent to the service party agent through the interaction method corresponding to the service negotiation response.

[0033] Step S5: Receive the collaborative processing result corresponding to the collaborative processing data packet returned by the service agent through the interaction method corresponding to the service negotiation response, and process the current task according to the collaborative processing result.

[0034] This embodiment of the disclosure sets up intelligent agents to register their capability information with a network registration function element before interaction. When it is determined that other intelligent agents need to collaborate to complete a task, the intelligent agent sends a first service retrieval request to the network registration function element. The network registration function element returns a first retrieval result based on the first service retrieval request and the intelligent agent capability information of multiple intelligent agents. Then, according to the target interaction method adapted to the service-party intelligent agent recorded in the first retrieval result, the intelligent agent sends an interaction request to the service-party intelligent agent. This enables intelligent agents with different launch times, development methods, and supported interaction methods to conduct business negotiations through interaction methods supported by both parties. They can also flexibly select specific interaction methods according to different business characteristics and collaboration situations, enabling intelligent agents to collaborate efficiently and complete complex network tasks, thereby improving the service experience of network services.

[0035] The steps of the intelligent agent collaborative interaction method 100 will be described in detail below.

[0036] In step S1, the intelligent agent capability information is registered with the network registration function element. The intelligent agent capability information includes the intelligent agent type of the first intelligent agent, the types of communication channels supported by the first intelligent agent, and the interaction protocol.

[0037] The method of this disclosure embodiment can be executed by an intelligent agent, and the intelligent agent executing the method is called the first intelligent agent.

[0038] To better introduce Method 100, let’s first introduce the agent collaborative interaction system to which the first agent is located.

[0039] Figure 2 This is a schematic diagram of an intelligent agent collaborative interaction system in an exemplary embodiment of this disclosure.

[0040] refer to Figure 2 In an exemplary embodiment, the intelligent agent collaborative interaction system 200 includes multiple intelligent agents 1 and a network registration function network element 2.

[0041] Based on their functions, intelligent agents can be categorized into those with comprehensive functions and those with specialized functions. Intelligent agents with comprehensive functions refer to those that can simultaneously cover multiple tasks such as sensing, data processing, and decision-making collaboration, such as a comprehensive control intelligent agent that coordinates the scheduling of regional network resources. Intelligent agents with specialized functions refer to those dedicated to handling tasks in a single domain, such as a sensing and processing intelligent agent responsible for collecting and analyzing network status information, a data processing intelligent agent undertaking the cleaning and computation of massive amounts of sensor data, or an interactive and collaborative intelligent agent performing communication protocol adaptation and command distribution. In other words, intelligent agents can be categorized as comprehensive, sensing, data processing, etc.

[0042] The implementation of intelligent agent 1 includes, but is not limited to, independently deployed network AI modules, AI functional units built into 6G core network elements (such as base stations and core network gateways), and large network models that support specific protocols (such as MCP protocol, ANP protocol, and A2A protocol). Any functional module that can implement the method 100 provided in the embodiments of this disclosure belongs to intelligent agent 1 in the embodiments of this disclosure.

[0043] In this embodiment, the network registration function network element 2 is used to receive and store the intelligent agent capability information reported by multiple intelligent agents 1, register the multiple intelligent agents 1, receive service retrieval requests from intelligent agents 1, and provide retrieval results to intelligent agents 1. In exemplary embodiments, the network registration function network element 2 can be implemented in ways including but not limited to an NRF (Network Repository Function) network element, an independently deployed network function module, a registration service component integrated into the 6G core network management unit, etc.

[0044] In this embodiment, the number of network registration function network elements 2 can be one or more. Due to the wide coverage of 6G networks (e.g., across regions and operators) and the large number and dispersed distribution of intelligent agents, multiple network registration function network elements 2 can be deployed to reduce the load on individual network elements and improve capability discovery and information query efficiency. When there are multiple network registration function network elements 2, multiple intelligent agents 1 can register with different network registration function network elements 2. Different network registration function network elements 2 share the registration information of multiple intelligent agents 1 through a preset information synchronization protocol (e.g., a real-time synchronization mechanism based on a distributed database, or a cross-network element signaling interaction protocol), ensuring that any intelligent agent 1 can query the service provider intelligent agent with matching capabilities across the entire network through the nearest network registration function network element 2.

[0045] In step S1, each agent can send an agent capability information registration request to its corresponding (e.g., the network registration function element 2 of its location) network. The agent capability information registration request carries its own agent type (such as the comprehensive type, perception type, data processing type, etc. mentioned above), supported communication channels, agent interaction protocol and version information, manufacturer information, etc.

[0046] Communication channels may include, for example, SBI (Service Based Interface), data transmission channels, and other communication channels. Agent interaction protocols include, but are not limited to, MCP (Model Context Protocol), ANP (Agent Network Protocol), and A2A (Agent 2 Agent Protocol).

[0047] In step S2, when it is determined that the current task needs to be completed through the collaboration of intelligent agents, a first service retrieval request is sent to the network registration function element according to the current task, and a first retrieval result is received from the network registration function element based on the first service retrieval request and the intelligent agent capability information of multiple intelligent agents.

[0048] Figure 3 This is a sub-flowchart of step S2 in an exemplary embodiment of this disclosure.

[0049] refer to Figure 3 In an exemplary embodiment, step S2 may include:

[0050] Step S21: Determine the type of intelligent agent required for the service provider based on the current task;

[0051] Step S22: Determine the type of the first communication channel based on the task type of the current task or the load of the first agent;

[0052] Step S23: Determine the first interaction protocol based on the type of the current task and the type of intelligent agent required from the service provider.

[0053] Step S24: Generate a first service retrieval request based on the type of intelligent agent, the type of target communication channel, and the target interaction protocol;

[0054] Step S25: Send a first service retrieval request to the network registration function element.

[0055] refer to Figure 3 The illustrated embodiment. After registration, the intelligent agent can determine whether it needs support from other intelligent agents based on the currently processed task. In this embodiment, the intelligent agent providing support is referred to as the service-oriented intelligent agent.

[0056] In step S21, after determining that the current task requires the support of a service-side intelligent agent, the type of intelligent agent required for the service-side intelligent agent is determined according to the current task.

[0057] For example, when a perception-based agent collects real-time traffic data from the edge of a 6G network, it finds that it can only complete preliminary data collection and cannot perform traffic anomaly analysis or resource scheduling decisions. In this case, it determines that it needs the support of other agents. Similarly, when a large-scale network model agent performs a cross-regional network performance prediction task, it determines that it needs the support of a perception processing agent because it lacks real-time network status data for some areas.

[0058] Next, in steps S22 and S23, the first communication channel type and the first interaction protocol to be used for interaction and collaboration with the service agent are determined. The first communication channel type is the preferred type most suitable for the current task, or the type of communication channel that the first agent can preferentially call under the current resource occupancy. For example, if the current task is to transmit massive edge traffic data, the first communication channel type is preferentially a data transmission channel (rather than SBI) to avoid signaling resource congestion; if the current task only needs to transmit short collaboration instructions, the first communication channel type can be SBI. The first interaction protocol is determined by combining the type of the service agent and the task characteristics of the current task. For example, when the service agent is required to be a large network model or a comprehensive type, the first interaction protocol is preferentially the MCP protocol; if the service agent and the first agent are required to be the same type of agent, the first interaction protocol can be preferentially the ANP protocol to ensure interaction compatibility and efficiency.

[0059] To improve retrieval efficiency, the number of first communication channel types and the number of first interaction protocols can both be multiple.

[0060] After determining the agent type, first communication channel type, and first interaction protocol required for the current task, in step S24, a first service retrieval request is generated according to the preset communication protocol between the network registration function element 2 and the service agent. The content of the first service retrieval request includes at least the agent type, the first communication channel type, and the first interaction protocol.

[0061] Next, in step S25, a first service retrieval request is sent to the network registration function element 2. This first service retrieval request can be sent, for example, through an SBI communication channel. It should be noted that each agent 1 and network registration function element 2 in system 200 needs to support at least one common basic communication channel to enable registration and service provider retrieval and response between agent 1 and network registration function element 2. This basic communication channel can be an SBI communication channel, a pre-agreed dedicated data transmission channel (such as a unified data plane interface designed for cross-region agent interaction), or other standardized communication channels with low latency and high reliability—anything that ensures stable transmission of registration information, service provider retrieval requests, and responses between the agent and the network registration function element can be used as this common basic communication channel.

[0062] After receiving the first service retrieval request, the network registration function element 2 searches among the intelligent agent capability information of multiple intelligent agents for an intelligent agent that matches the type of intelligent agent included in the first service retrieval request and supports the first communication channel type and the first interaction protocol.

[0063] When the network registration function element 2 finds an intelligent agent that matches the type of intelligent agent included in the first service retrieval request and supports the first communication channel type and the first interaction protocol, the network registration function element 2 identifies the intelligent agent as the service provider intelligent agent and returns the relevant information of the service provider intelligent agent, such as the identification information of the service provider intelligent agent, the specific parameters of the supported communication channel (such as bandwidth and latency indicators), the details of the interaction protocol version, the vendor information, the current load status, and the coverage of the network area, as the retrieval result to the first intelligent agent.

[0064] When the network registration function element 2 does not find an intelligent agent that matches the type of intelligent agent included in the first service retrieval request and supports the first communication channel type and the first interaction protocol, it can directly return the retrieval result "No service intelligent agent found" to the first intelligent agent.

[0065] In step S3, when the first search result includes at least one service agent, the state information of the service agent is determined according to the first search result, and the service agent is selected to send a service negotiation request based on the state information and the compatibility of the current task.

[0066] In some embodiments, the search results include multiple service-party intelligent agents. The first intelligent agent can select one or more service-party intelligent agents that are most suitable for supporting and coordinating the current task based on the status information of the service-party intelligent agents recorded in the search results.

[0067] For example, the first agent is a perception-type agent. Its current task is to provide low-latency real-time signal strength data for cross-regional 6G network performance prediction. The first agent determines that the service provider agent in question is a data transmission-type agent. The search results return three matching data transmission-type service providers: Agent A (covering the target area, latency ≤10ms, current load rate 30%), Agent B (covering the target area, latency ≤15ms, current load rate 70%), and Agent C (not fully covering the target edge area, latency ≤8ms, current load rate 40%). The first agent can then prioritize Agent A, which has lower latency and a lighter load, based on the core task requirements (low latency + full area coverage). Agent A's latency meets the task requirements, its low load rate indicates higher data transmission stability, and its coverage area is a perfect match, enabling more efficient real-time signal data transmission coordination. If the task has lower coverage requirements and prioritizes extreme latency, it may further compare Agents A and C, ultimately selecting the service provider agent with the best fit.

[0068] The first intelligent agent can prioritize the selected service-party intelligent agents and then send service negotiation requests to the service-party intelligent agents according to their priorities, in order to request the service-party intelligent agents to provide collaborative processing for the current task.

[0069] The interaction method used when sending a service negotiation request to the service provider is only the interaction method used during the negotiation process, and is not necessarily the interaction method used during formal business collaboration. In this embodiment, the interaction method used when sending a service negotiation request to the service provider can be the default basic communication channel and default communication protocol (consistent with the interaction method used when sending the first search request), the aforementioned first communication channel type and first interaction protocol, or a communication channel and communication protocol determined based on the relevant information of the service provider. For example, in step S3, the first agent first finds the service provider that has not been requested and has the highest priority. Then, based on the communication channels and protocols supported by the service provider, as well as its own supported communication channels and protocols and the type of the current task, the first agent selects the most suitable interaction method to send the service negotiation request.

[0070] Since service negotiation requests are signaling, the preferred interaction method for sending service negotiation requests is the SBI communication channel and a standardized protocol adapted to signaling transmission (such as HTTP / 2, which is maturely applied to signaling interaction in the 5G core network SBA architecture and features header compression and multiplexing, reducing signaling transmission latency and bandwidth consumption). If both the service agent and the first agent support enhanced protocols more adapted to 6G signaling scenarios (such as SBI extension protocols based on QUIC), then such protocols can be prioritized in combination with the SBI communication channel. This leverages the service-oriented architecture advantages of SBI to ensure the reliability of signaling interaction while further reducing signaling transmission latency and packet loss rate through enhanced protocols, ensuring that service negotiation requests are delivered to the service agent efficiently and stably.

[0071] In an exemplary embodiment, the service negotiation request may include information such as the type of the current task (e.g., data acquisition, traffic analysis, resource scheduling), task load (e.g., data transmission volume, computing power requirements), task priority (e.g., real-time task / non-real-time task), task coverage area (e.g., edge network A area / core network backbone node), task completion time limit, as well as the aforementioned first communication channel type and first interaction protocol, so that the service provider intelligent agent can determine whether it can provide collaborative processing for the current task based on the service negotiation request, and whether it can provide collaborative processing for the current task through the first communication channel type and first interaction protocol.

[0072] In other embodiments, the first agent may also, based on the state information of the service agent recorded in the search results, the current state of the first agent, and the latest state of the current task, redetermine the most suitable first communication channel type and first interaction protocol for collaborative processing of the current task corresponding to a service agent, and carry the redetermined first communication channel type and first interaction protocol in the service negotiation request. The redetermined first communication channel type and first interaction protocol may be different from or completely different from the first communication channel and first interaction protocol carried in the first service search request.

[0073] For example, the first agent initially specifies a "dedicated data transmission channel" as the first communication channel and an "ANP protocol" as the first interaction protocol in the first service retrieval request to adapt to cross-regional data collaboration tasks. However, after obtaining the retrieval results, it is found that the dedicated data transmission channel of the service provider's most suitable agent for handling the current task is currently fully loaded (status information shows that its bandwidth utilization rate of this channel is 95%), while the first agent itself is experiencing a shortage of computing resources due to temporarily receiving new edge node data (current status change), and the current task has doubled its data transmission volume due to a sudden increase in traffic (task latest status update). At this time, the first agent can re-determine the first communication channel as an "enhanced SBI channel" (this channel shows low load in the status information of both parties) and the first interaction protocol as the "MCP protocol" (more suitable for context synchronization of large traffic data), and carry the updated first communication channel type and first interaction protocol in the service negotiation request.

[0074] For example, the original first communication channel was the "SBI channel" and the first interaction protocol was the "HTTP / 2 protocol." However, the search results only included one compatible service agent. Although this service agent supported the combination, its HTTP / 2 protocol version was too low to be compatible with the newly added encrypted transmission requirements of the current task (the latest state of the task). Meanwhile, the first agent had already enabled the QUIC protocol module (its own state changed). Therefore, the first agent re-specified the first interaction protocol as the "QUIC-based SBI extension protocol" in the service negotiation request, while retaining the "SBI channel" as the communication channel, forming a new combination with some parameter adjustments.

[0075] In an exemplary embodiment, when collaboration involves a large network model (either the service agent or the first agent), the MCP protocol is primarily considered as the first interaction protocol; when collaboration involves collaboration between AI agents from different vendors, the A2A protocol is primarily considered as the first interaction protocol; and when collaboration involves collaboration between AI agents from the same vendor, the ANP protocol may be primarily considered as the first interaction protocol.

[0076] Therefore, by redetermining the type of the first communication channel and the first interaction protocol based on the search results, it is possible to better match the real-time status and task requirements, thereby improving the success rate of collaboration.

[0077] After receiving a service negotiation request, the service agent determines whether it can provide collaborative processing for the current task based on its remaining computing power, the maximum task load it can bear, and the resource usage of the tasks already connected. Then, based on the current state of the first communication channel (such as whether the bandwidth and latency match the current task requirements) and the version of the first interaction protocol (whether it is consistent with or compatible with the first interaction protocol), it determines whether it can provide collaborative processing for the current task through the type of the first communication channel and the first interaction protocol.

[0078] If the service agent determines that it can provide collaborative processing for the current task through the first communication channel type and the first interaction protocol, it will reply to the first agent with a service negotiation response including information such as "agree".

[0079] If the service agent determines that it cannot provide negotiation processing for the current task, it replies to the first agent with a service negotiation response including information such as "currently unable to provide support".

[0080] If the service agent determines that it can provide negotiation processing for the current task, but cannot provide collaborative processing for the current task through the first communication channel type and / or the first interaction protocol, then it determines the third communication channel type and / or the third interaction protocol that it can use, and replies to the first agent with a service negotiation response including "third communication channel type and / or third interaction protocol".

[0081] In step S4, when it is determined that the service negotiation response returned by the service party agent based on the service negotiation request is accepted, the collaborative processing data packet corresponding to the current task is sent to the service party agent through the interaction method corresponding to the service negotiation response.

[0082] If the service negotiation response includes information such as "agree", then the first intelligent agent sends the collaborative processing data packet corresponding to the current task to the service provider intelligent agent according to the first communication channel type and the first interaction protocol.

[0083] If the service negotiation response includes information such as "third communication channel type and / or third interaction protocol", and the first agent determines that it can complete the collaborative processing of the current task through the third communication channel type and / or third interaction protocol, then the first agent sends the collaborative processing data packet corresponding to the current task to the service agent according to the interaction method corresponding to the first communication channel service negotiation response, namely, the first communication channel type / third communication channel type and the first interaction protocol / third interaction protocol.

[0084] If the service negotiation response includes information such as "currently unable to provide support", then the first agent sends a service negotiation request to the next service agent according to the priority of the selected service agent agents.

[0085] In some embodiments, if the service negotiation response includes information such as "third communication channel type and / or third interaction protocol", and the first agent determines that it is not possible or suitable to complete the collaborative processing of the current task through the third communication channel type and / or third interaction protocol, then a request to end is sent to the service agent, and if there is a next service agent in the search results, a service negotiation request is sent to the next service agent.

[0086] In step S5, the collaborative processing result corresponding to the collaborative processing data packet is received from the service agent through the interaction method corresponding to the service negotiation response, and the current task is processed according to the collaborative processing result.

[0087] In step S5, the collaborative processing results are used to process the current task scenario. For example, when a perception-type intelligent agent collects real-time traffic data from the edge area of ​​a 6G network, it finds that it can only complete the initial data collection and cannot perform traffic anomaly analysis and resource scheduling decisions. It needs to use a data processing intelligent agent for collaborative processing. Then, the service-side intelligent agent is determined through the methods corresponding to steps S2 to S4 above. The collected traffic data is transmitted to the service-side intelligent agent for anomaly identification according to the negotiated interaction method. Then, the resource scheduling intelligent agent is used to formulate a bandwidth adjustment plan to jointly complete the edge network traffic optimization task.

[0088] For example, when a large network model agent performs a cross-regional network performance prediction task, it may lack real-time network status data for some regions. Therefore, it determines that it needs the support of a perception processing agent. It then uses the methods described in steps S2-S4 to identify the perception agent for the corresponding region as the service agent. Based on a negotiated interaction method, it obtains real-time network status data for that region (such as base station load, signal strength, and number of user connections), and inputs this data into its own prediction model for training and computation, generating a cross-regional network performance prediction report (the collaborative processing result). Subsequently, based on this prediction report, the large network model agent further formulates network resource pre-allocation strategies (such as pre-scheduling backup bandwidth for high-load areas and optimizing base station handover parameters) to complete the current task of cross-regional network performance optimization.

[0089] In this embodiment of the disclosure, the first intelligent agent can simultaneously request support from multiple service-party intelligent agents, determine multiple service-party intelligent agents using the methods corresponding to steps S2 to S4 above, send service negotiation requests to the multiple service-party intelligent agents, and send different collaborative processing data packets to different service-party intelligent agents. Based on the collaborative processing results returned by different service-party intelligent agents corresponding to the different collaborative processing data packets, the current task is completed by combining the results.

[0090] For example, when performing emergency communication support tasks, a comprehensive intelligent agent needs a sensing agent to provide real-time signal coverage data for the disaster area, and a data processing agent to analyze the causes of communication interruptions. After determining the two types of service-oriented intelligent agents through steps S2 to S4, the comprehensive intelligent agent receives the signal blind zone distribution map returned by the sensing agent (first collaborative processing result) and the interruption cause analysis report returned by the data processing agent (second collaborative processing result). Combining the information from both, it formulates an emergency base station deployment plan and signal enhancement strategy, ultimately completing the emergency communication support task.

[0091] Furthermore, in the exemplary embodiment, the first intelligent agent and each service-party intelligent agent can interact multiple times, send multiple collaborative processing data packets, obtain multiple collaborative processing results, and realize collaborative processing of the current task.

[0092] For example, in the dynamic adjustment task of 6G network slicing, the first intelligent agent (network management intelligent agent) and the service-side intelligent agent (resource scheduling intelligent agent) need to complete the collaboration through multiple rounds of interaction: In the initial stage, the first intelligent agent sends the first collaborative processing data packet (containing the load data and service type requirements of the current network slice), and the service-side intelligent agent returns a preliminary resource allocation scheme (the first collaborative processing result); based on the scheme, the first intelligent agent evaluates and finds that the bandwidth of a certain service slice is still insufficient, and then sends the second collaborative processing data packet (supplementing the real-time traffic data of high-priority services), and the service-side intelligent agent recalculates and returns the optimized bandwidth adjustment strategy (the second collaborative processing result); if the slice latency problem still exists, the first intelligent agent continues to send data packets containing the distribution of latency-sensitive services, and the service-side intelligent agent finally returns a comprehensive solution combined with the deployment of edge computing nodes (the third collaborative processing result). Through these three interactions, the two parties gradually refine the task parameters and finally complete the dynamic optimization of the network slice.

[0093] In addition to the scenarios mentioned above where service retrieval and service negotiation can be successfully completed, this disclosure also includes provisions for handling abnormal scenarios.

[0094] Figure 4 This is a schematic diagram illustrating one method of processing search results in an exemplary embodiment of this disclosure.

[0095] refer to Figure 4 In an exemplary embodiment, the process of processing the search results may include:

[0096] Step S401: When the first search result is that no service agent corresponding to the first service search request is found, determine the second communication channel type and the second interaction protocol corresponding to the current task.

[0097] Step S402: Generate a second service retrieval request based on the type of intelligent agent, the type of the second communication channel, and the second interaction protocol;

[0098] Step S403: Send a second service retrieval request to the network registration function element.

[0099] exist Figure 4In the illustrated embodiment, when a suitable service agent for handling the current task cannot be obtained through the first service retrieval request, for example, if the retrieval result is that no service agent corresponding to the first service retrieval request is found, or if the relevant information of the service agents in the retrieval results determines that none of the service agents included in the retrieval results are suitable for handling the current task, or if the service negotiation responses of each service agent in the retrieval results include information such as "currently unable to provide support" or the provided third communication channel type / third communication protocol is not suitable for handling the current task, the first agent can form a second service retrieval request based on the second communication channel type and second interaction protocol it supports, requesting the network registration function element 2 to retrieve more service agents.

[0100] The second communication channel type and the second interaction protocol may be partially or completely different from the first communication channel type and the first interaction protocol. The first communication channel type and the first interaction protocol are the preferred communication channel type and interaction protocol of the first intelligent agent for the current task, while the second communication channel type and the second interaction protocol are the secondary communication channel type and interaction protocol of the first intelligent agent for the current task. To improve the success rate of supplementary retrieval, there can be multiple second communication channel types and multiple second interaction protocols to expand the retrieval scope.

[0101] In addition to active retrieval, in the exemplary embodiment, when a suitable service agent for handling the current task cannot be obtained through the first service retrieval request, the first agent can also publish the task for other agents to determine whether to accept the task.

[0102] Figure 5 This is a schematic diagram illustrating one method of processing search results in an exemplary embodiment of this disclosure.

[0103] refer to Figure 5 In an exemplary embodiment, the process of processing the search results may include:

[0104] Step S501: When the first search result is that no service agent corresponding to the first service search request is found, determine the second communication channel type and the second interaction protocol corresponding to the current task.

[0105] Step S502: Generate a service support request based on the type of intelligent agent, the type of the second communication channel, and the second interaction protocol;

[0106] Step S503: Send a service support request to the network registration function network element so that the network registration function network element broadcasts the service support request to multiple intelligent agents that match the type of intelligent agent.

[0107] and Figure 4 The embodiments shown are partially the same, inFigure 5 In the illustrated embodiment, when a suitable service agent for handling the current task cannot be obtained through the first service retrieval request, the first agent determines the next selected communication channel type and interaction protocol, namely the second communication channel type and the second interaction protocol. The number of the second communication channel type and the number of the second interaction protocol can both be multiple.

[0108] Next, a service support request is generated based on the second communication channel type and the second interaction protocol, and the service support request is sent to the network registration function element so that the network registration function element broadcasts the service support request to multiple intelligent agents that match the intelligent agent type.

[0109] exist Figure 5 In the illustrated embodiment, considering the real-time state changes of other intelligent agents, the second communication channel type may include the first communication channel type, and the second interaction protocol may include the first interaction protocol.

[0110] Upon receiving the service support request, each agent determines whether to provide support to the first agent based on its own circumstances. If support is deemed possible, a service support response is sent to the first agent, selecting the desired third communication channel type and third interaction protocol from the second communication channel type and second interaction protocol. Since the second communication channel type and second interaction protocol are those supported by the first agent, agents cannot propose communication channel types and interaction protocols beyond the scope of these second communication channel types and second interaction protocols.

[0111] If each agent determines that it is unable to support the current task, or is unable to support the current task through the second communication channel type and the second interaction protocol, then the broadcast need not be processed.

[0112] Within a first preset time period after the first agent publishes the service support request, if a service support response is received from any agent, the agent negotiates with the agent corresponding to the service support response according to the above process; if service support responses are received from multiple agents, the agents are sorted according to the service support responses received within a second preset time period, and then negotiations are conducted with each agent separately; if no service support response is received within the first preset time period, it is determined that the current task cannot be collaboratively processed, and a task processing failure message is returned, or the agent processes the current task according to its own capabilities.

[0113] The above describes the steps performed by the first intelligent agent as a service requester, i.e., a consumer. In this embodiment, steps performed by the first intelligent agent as a service provider are also provided.

[0114] Figure 6This is a flowchart of the steps performed by the first intelligent agent as a service-oriented intelligent agent in an exemplary embodiment of this disclosure.

[0115] refer to Figure 6 In an exemplary embodiment, method 100 further includes:

[0116] Step S601: Receive a service negotiation request from the second intelligent agent. The service negotiation request includes a first communication channel type and a first interaction protocol.

[0117] Step S602: When it is determined that the service negotiation request is accepted, a service negotiation response is returned to the second intelligent agent. The service negotiation response includes a first communication channel type and a first interaction protocol, or the service negotiation response includes a third communication channel type and / or a third interaction protocol determined based on the service negotiation request.

[0118] Figure 6 In the illustrated embodiment, the second intelligent agent initiates the service negotiation request, while the first intelligent agent acts as the service provider. The process by which the service provider generates a service negotiation response based on the service negotiation request has been detailed in the above embodiments and will not be repeated here.

[0119] Figure 7 This is a flowchart of an exemplary embodiment of the intelligent agent collaborative interaction method disclosed herein.

[0120] Figure 7 The method 700 shown is executed by the network registration function network element 2 in system 200.

[0121] refer to Figure 7 The intelligent agent collaborative interaction method 700 may include:

[0122] Step S71: Receive an agent capability information registration request from the agent and register the agent capability information of the agent.

[0123] Step S72: Respond to the service retrieval request from the intelligent agent. Based on the intelligent agent capability information of multiple intelligent agents, retrieve the service provider intelligent agent that matches the service retrieval request. The service retrieval request includes the type of intelligent agent, the type of communication channel, and the interaction protocol.

[0124] Step S73: When the service provider intelligent agent is retrieved, the search results are generated based on the intelligent agent capability information of the service provider intelligent agent;

[0125] Step S74: Return the search results to the agent.

[0126] The agent in method 700 is, for example, the first agent in method 100 above, that is, any agent 1 in system 200.

[0127] The service retrieval request in method 700 can be either the first service retrieval request in method 100 or the second service retrieval request in method 100.

[0128] In an exemplary embodiment, method 700 further includes: responding to a service support request from an intelligent agent, determining the type of intelligent agent corresponding to the service support request, and broadcasting the service support request to multiple intelligent agents matching the type of intelligent agent. That is, network registration function element 2 can participate. Figure 5 Execution of the illustrated embodiment.

[0129] The functions of network registration function element 2 have been described in detail in the above embodiments and will not be repeated here.

[0130] Figure 8 This is a schematic diagram illustrating the interaction between the intelligent agent and the network registration function element in an embodiment of this disclosure.

[0131] refer to Figure 8 In event 801, multiple agents (e.g., agent A and agent B) send agent capability information registration requests to the network registration function element, providing their own agent capability information.

[0132] In Event 802, the network registration function network element registers the agent capability information of multiple agents. The registration process is as follows: First, the request is validated for legality, verifying the compliance of the capability metadata format and signature (if required); then, the validated agent capability information is stored in the distributed capability index library according to the agent type, supported communication channel type, and interaction protocol.

[0133] In event 803, agent A processes the current task.

[0134] In event 804, agent A determines that the current task needs to be completed through agent collaboration, and determines the required agent type, the preferred first communication channel type, and the first communication protocol.

[0135] In event 805, agent A sends a first service retrieval request to the network registration function element according to the agent type, the preferred first communication channel type, and the first communication protocol.

[0136] In Event 806, the network registration function element retrieves the service provider intelligent agent based on the first service retrieval request and the intelligent agent capability information of each intelligent agent.

[0137] In Event 807, the network registration function element sends the search results to agent A. The network registration function element can include information such as the communication channels supported by each service provider agent, agent interaction protocols and version information, and vendor information in the search results.

[0138] In event 808, agent A identifies the search results. If the search results include the service agent, then proceed to event 809; otherwise, send a second service search request to the network registration function network element according to the method described in the above embodiment.

[0139] In event 809, agent A sorts the service agents according to their state information.

[0140] In event 810, agent A selects agent B, which has the highest priority and has not been requested before, and sends a service negotiation request according to priority from high to low.

[0141] In event 811, agent B determines the service negotiation response based on the service negotiation request and its own state.

[0142] In event 812, agent B sends a service negotiation response to agent A.

[0143] At event 813, agent A determines whether the service negotiation response indicates that agent B can provide collaborative processing for the current task. If so, it proceeds to event 813; otherwise, it sends a second service retrieval request to the network registration function element according to the method described in the above embodiment.

[0144] At event 814, agent A determines whether the service negotiation response proposes a third communication channel type and / or a third interaction protocol. If so, proceed to event 815; otherwise, proceed to event 816.

[0145] At event 815, agent A determines whether to accept the third communication channel type and / or the third interaction protocol. If accepted, it proceeds to event 816; otherwise, it sends a second service retrieval request to the network registration function element according to the method described in the above embodiment.

[0146] In event 816, agent A sends a collaborative processing data packet to agent B based on the interaction method determined by the service negotiation response.

[0147] In event 817, agent B processes the collaborative processing data packet to form a collaborative processing result.

[0148] In event 818, agent B sends the result of the collaborative processing to agent A.

[0149] In event 819, agent A processes the current task based on the results of collaborative processing.

[0150] exist Figure 8 In the interaction process shown, agent A is the consumer and agent B is the service provider.

[0151] If consumers discover a service provider's network AI agent or network big model with matching communication capabilities through the network registration function, then the consumers shall determine the specific communication channel, agent interaction protocol and version based on the specific business characteristics and the service provider's capabilities.

[0152] If consumers cannot find a suitable service provider through the online registration function, they can either submit a second service search request to supplement the search, or... Figure 5 In the illustrated embodiment, the consumer submits a service support request containing information such as the supported intelligent agent communication protocol, version, and manufacturer. This request is then broadcast by the network registration function element to multiple potential service providers, who then determine the specific communication channels, intelligent agent interaction protocols, and versions.

[0153] In some embodiments, the consumer, i.e., the first intelligent agent, can also directly send service negotiation requests to multiple second intelligent agents that meet the requirements of the current task, without needing to retrieve the service provider intelligent agent through the network registration function (e.g., the consumer has configured the corresponding service provider intelligent agent locally, or the consumer has stored relevant information about the service provider intelligent agents with which it has interacted in the past). When it is determined that the current task needs to be completed through intelligent agent collaboration, it can also send service negotiation requests to multiple second intelligent agents based on historical interaction records and preset interaction correspondences (e.g., prioritizing collaboration with a certain intelligent agent). When sending service negotiation requests, requests can be sent to multiple second intelligent agents simultaneously, or priorities can be determined according to historical interaction records and preset interaction correspondences, and then the second intelligent agent with the highest priority can be selected to send the request.

[0154] The service negotiation request may also carry the communication channel, agent interaction protocol and version information supported by the first agent. The communication channel type and interaction protocol carried in the service negotiation request may be the preferred first communication channel type and first interaction protocol mentioned above.

[0155] Each second agent determines whether it can provide support based on its own state, and sends a service negotiation response when it determines that it can provide support.

[0156] Exemplary application scenarios of the methods provided in this disclosure may include:

[0157] (1) If network AI agents are deployed in the 6G core network, different network AI agents can negotiate specific collaboration and communication methods based on specific services and communication information through the methods of this embodiment, thereby achieving efficient collaboration and communication between different network AI agents. Network AI agents can be deployed independently or integrated into network elements as part of their functionality. Collaboration between AI agents mainly considers ANP and A2A protocols.

[0158] (2) If a large network model is deployed in the 6G core network, communication between the large network model and other network elements can be achieved through the methods of this embodiment. The large network model can be deployed independently or embedded within network elements. The coordination and communication involving the large network model can mainly consider the MCP protocol.

[0159] (3) Multiple network AI agents and network big models can be deployed in a 6G network. Through the method of the present disclosure, different network AI agents and network big models can negotiate specific communication and collaboration methods with each other according to specific business conditions to achieve efficient collaboration.

[0160] In summary, the collaborative interaction method between network AI agents proposed in this disclosure involves the network AI agent or network big model registering with the network registration function element the communication channels, agent interaction protocols and version information, vendor information, etc., supported by the network AI agent or network big model. This enables different network AI agents or network big models to discover service provider network AI agents or network big models with matching communication capabilities. Service consumer network AI agents or network big models and service provider network AI agents or network big models negotiate specific collaborative interaction methods through SBI, which can improve collaborative efficiency and thus enhance the service experience.

[0161] 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.

[0162] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0163] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: entirely hardware implementations, entirely software implementations (including firmware, microcode, etc.), or implementations combining hardware and software aspects, collectively referred to herein as “circuits,” “modules,” or “systems.”

[0164] The following reference Figure 9 To describe an electronic device 900 according to this embodiment of the present invention. Figure 9 The electronic device 900 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.

[0165] likeFigure 9 As shown, the electronic device 900 is presented in the form of a general-purpose computing device. The components of the electronic device 900 may include, but are not limited to: at least one processor 910, at least one memory 920, and a bus 930 connecting different system components (including memory 920 and processor 910).

[0166] The memory stores program code that can be executed by the processor 910, causing the processor 910 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present invention. For example, the processor 910 can perform methods as shown in embodiments of this disclosure.

[0167] The memory 920 may include a readable medium in the form of volatile memory, such as random access memory (RAM) 9201 and / or cache 9202, and may further include read-only memory (ROM) 9203.

[0168] The memory 920 may also include a program / utility 9204 having a set (at least one) of program modules 9205, including but not limited to: an 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.

[0169] Bus 930 can represent one or more of several types of bus structures, including a memory bus or memory controller, peripheral bus, graphics acceleration port, processor, or a local bus using any of the various bus structures.

[0170] Electronic device 900 can also communicate with one or more external devices 1000 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 900, and / or with any device that enables electronic device 900 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 950. Furthermore, electronic device 900 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 960. As shown, network adapter 960 communicates with other modules of electronic device 900 via bus 930. 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 900, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0171] 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 instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0172] 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. In some possible embodiments, various aspects of the 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 of the various exemplary embodiments of the invention described in the "Exemplary Methods" section of this specification.

[0173] The program product for implementing the above-described method according to embodiments of the present invention 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, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0174] 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.

[0175] 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 an instruction execution system, apparatus, or device.

[0176] 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.

[0177] 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).

[0178] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0179] 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 concept of this disclosure are indicated by the claims.

Claims

1. A method for collaborative interaction among intelligent agents, characterized in that, Executed by the first intelligent agent, including: Register agent capability information with network registration function network element, wherein the agent capability information includes the agent type of the first agent, the types of communication channels supported by the first agent, and the interaction protocol. When it is determined that the current task needs to be completed through the collaboration of intelligent agents, a first service retrieval request is sent to the network registration function element according to the current task, and a first retrieval result is received from the network registration function element based on the first service retrieval request and the intelligent agent capability information of multiple intelligent agents. When the first search result includes at least one service agent, the state information of the service agent is determined according to the first search result, and the service agent is selected to send a service negotiation request based on the state information and the degree of adaptation of the current task. When it is determined that the service negotiation response returned by the service party agent based on the service negotiation request will be accepted, the collaborative processing data packet corresponding to the current task will be sent to the service party agent through the interaction method corresponding to the service negotiation response. Receive the collaborative processing result corresponding to the collaborative processing data packet returned by the service agent through the interaction method corresponding to the service negotiation response, and process the current task according to the collaborative processing result.

2. The intelligent agent collaborative interaction method as described in claim 1, characterized in that, Sending a first service retrieval request to the network registration function element according to the current task includes: Determine the type of intelligent agent required for the service provider intelligent agent based on the current task; The type of the first communication channel is determined based on the task type of the current task or the load of the first agent. The first interaction protocol is determined based on the type of the current task and the type of intelligent agent required from the service provider. The first service retrieval request is generated based on the type of intelligent agent, the type of the first communication channel, and the first interaction protocol. The network element performing the network registration function sends the first service retrieval request.

3. The intelligent agent collaborative interaction method as described in claim 1 or 2, characterized in that, Also includes: When the first search result is that no service agent corresponding to the first service search request is found, the second communication channel type and the second interaction protocol corresponding to the current task are determined. A second service retrieval request is generated based on the type of intelligent agent, the type of the second communication channel, and the second interaction protocol. Send the second service retrieval request to the network registration function element.

4. The intelligent agent collaborative interaction method as described in claim 1 or 2, characterized in that, Also includes: When the first search result is that no service agent corresponding to the first service search request is found, the second communication channel type and the second interaction protocol corresponding to the current task are determined. A service support request is generated based on the type of intelligent agent, the type of the second communication channel, and the second interaction protocol. The network registration function element sends the service support request to the network registration function element so that the network registration function element broadcasts the service support request to multiple intelligent agents that match the type of intelligent agent.

5. The intelligent agent collaborative interaction method as described in claim 1, characterized in that, The service negotiation request includes a first communication channel type and a first interaction protocol, and the service negotiation response includes a third communication channel type and / or a third interaction protocol determined by the service agent based on the service negotiation request. The method further includes: When it is determined that the service negotiation response is not accepted, a request to end is sent to the service provider's intelligent agent; If a next service provider agent is found in the search results, the service negotiation request is sent to that next service provider agent.

6. The intelligent agent cooperative interaction method as described in claim 1, characterized in that, Also includes: Receive a service negotiation request from a second intelligent agent, the service negotiation request including a first communication channel type and a first interaction protocol; Upon determining that the service negotiation request is accepted, a service negotiation response is returned to the second agent. The service negotiation response includes the first communication channel type and the first interaction protocol, or the service negotiation response includes a third communication channel type and / or a third interaction protocol determined based on the service negotiation request.

7. A method for collaborative interaction among intelligent agents, characterized in that, Performed by the network registration function network element, including: Receive an agent capability information registration request from an agent and register the agent capability information of the agent. In response to a service retrieval request from the intelligent agent, based on the intelligent agent capability information of multiple intelligent agents, a service-oriented intelligent agent matching the service retrieval request is retrieved. The service retrieval request includes the type of intelligent agent, the type of communication channel, and the interaction protocol. When the service provider intelligent agent is retrieved, a retrieval result is generated based on the intelligent agent's capability information. The search results are returned to the agent.

8. The intelligent agent collaborative interaction method as described in claim 7, characterized in that, Also includes: In response to a service support request from the agent, determine the type of agent corresponding to the service support request; The service support request is broadcast to multiple agents that match the agent type.

9. A collaborative interaction system for intelligent agents, characterized in that, include: Multiple intelligent agents are configured to perform the method as described in any one of claims 1-6; The network registration function element is communicatively connected to the plurality of intelligent agents and is used to execute the method as described in claim 7 or 8.

10. An electronic device, characterized in that, include: Memory; as well as A processor coupled to the memory, the processor being configured to perform the method as described in any one of claims 1-8 based on instructions stored in the memory.

Images