A multi-agent collaborative management and control method and device and related equipment

Abstract

This disclosure provides a method, apparatus, and related equipment for collaborative management of multiple intelligent agents, relating to the field of communication technology. The solution involves receiving a collaborative scheduling request from a service terminal; determining a target business workflow template from multiple preset business workflow templates based on the business scenario type; generating a collaborative scheduling strategy based on business requirement information and the target business workflow template; and sending scheduling instructions to a first intelligent agent and / or a second intelligent agent based on the collaborative scheduling strategy, instructing the first and / or second intelligent agents to execute collaborative business tasks according to preset business processes. This application solves the problems of existing technologies lacking a standardized template fixing mechanism for business processes in multi-agent collaborative scenarios, resulting in non-reusable business processes, high difficulty in cross-domain multi-agent collaboration, low business deployment efficiency, and high maintenance costs. It achieves template-based reuse and automated scheduling of business processes, improving business deployment efficiency and multi-agent collaborative execution efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a method, apparatus and related equipment for the collaborative management of multiple agents. Background Technology

[0002] With the development of 6G technology, multi-agent collaboration has become the core support for realizing the intelligent and large-scale application of 6G networks, and the need for collaboration between 6G network element agents and various external application agents is becoming increasingly urgent. Currently, existing technologies mainly rely on network registration function network elements to complete the identity verification and registration of network agents, which can, to a certain extent, ensure the legitimacy of agent access and the completeness of registration information.

[0003] However, while the network registration function in the existing solution can realize the identity registration of intelligent agents, it lacks effective automated scheduling means at the level of multi-agent service collaboration. The task orchestration and capability invocation between intelligent agents mostly rely on manual configuration or temporary negotiation, which easily leads to the need to re-orchestrate and configure the multi-agent skill chain every time a service is triggered. This results in problems such as non-reusable business processes, difficulty in cross-domain multi-agent collaboration, low service deployment efficiency, and high maintenance costs, making it difficult to adapt to the development needs of 6G networks for rapid service deployment and efficient collaboration.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] This disclosure provides a method, apparatus, and related equipment for collaborative management of multiple agents, which at least to some extent overcomes the problems of unusable business processes, high difficulty in cross-domain multi-agent collaboration, low business deployment efficiency, and high maintenance costs caused by the lack of standardized templates for business processes in multi-agent collaborative scenarios.

[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0007] According to one aspect of this disclosure, a collaborative management method for multiple agents is provided, the method comprising: Receive a collaborative scheduling request sent by the business terminal; the collaborative scheduling request includes business scenario type and business requirement information; Based on the business scenario type, a target business workflow template is determined from multiple preset business workflow templates; the target business workflow template incorporates multi-agent collaborative scheduling logic and skill execution chains. Based on the business requirement information and the target business workflow template, a collaborative scheduling strategy is generated; Based on the collaborative scheduling strategy, scheduling instructions are sent to the first intelligent agent and / or the second intelligent agent to instruct the first intelligent agent and / or the second intelligent agent to perform business collaborative tasks according to a preset business process.

[0008] In some embodiments, the first intelligent agent is an external application intelligent agent, and the second intelligent agent is a network element intelligent agent; the network element intelligent agent is an intelligent agent that is valid for a long period after registration, and the external application intelligent agent is an intelligent agent that is renewed periodically after registration.

[0009] In some embodiments, after sending scheduling instructions to the first agent and / or the second agent based on the collaborative scheduling strategy to instruct the first agent and / or the second agent to execute business collaborative tasks according to a preset business process, the multi-agent collaborative management method further includes: Receive renewal application information sent within a preset time period before the expiration of the validity period of the first intelligent agent; Based on the renewal application information and the preset renewal verification rules, the first intelligent agent is subjected to compliance verification, and after the first intelligent agent passes the compliance verification, the renewal operation is performed on the first intelligent agent. Update the validity period information of the first intelligent agent based on the renewal operation result.

[0010] In some embodiments, before receiving the collaborative scheduling request sent by the service terminal, the multi-agent collaborative management method further includes: Obtain template registration information and agent registration information; the template registration information includes information generated after the target business workflow template passes internal structure verification, and the registration information of the first agent includes at least one of agent identifier, capability description information, access address information, and validity period information; Based on the agent registration information and the preset registration verification rules, the registration status of the first agent is determined, and first status synchronization information is generated according to the registration status. Based on the template registration information and the preset template verification rules, the registration status of the target business workflow template is determined, and second status synchronization information is generated based on the registration status. The first intelligent agent's running status is updated based on the first state synchronization information, and the target business workflow template's process status is updated based on the second state synchronization information.

[0011] In some embodiments, after sending scheduling instructions to the first agent and / or the second agent according to the cooperative scheduling strategy, the multi-agent cooperative management method further includes: Monitor the status reporting of the first intelligent agent and / or the second intelligent agent within a first preset time period; If the status reporting status indicates that the first agent and / or the second agent has reported status information within the first preset time period, then third status synchronization information is generated based on the status information; the status information is used to characterize the real-time operating status of the first agent and / or the second agent. The operating status of the first agent and / or the second agent is updated based on the third state synchronization information.

[0012] In some embodiments, the multi-agent collaborative management method further includes: If the status reporting indicates that the first agent or the second agent has not reported the status information within the first preset time period, then it is determined that the first agent or the second agent is in an abnormal operating state. Obtain agent anomaly information of the first agent or the second agent, and generate corresponding abnormal state synchronization information based on the agent anomaly information; The operating status of the first or second intelligent agent is updated based on the abnormal state synchronization information. The abnormal information of the intelligent agent is matched with the abnormal handling strategy in the target business workflow template, and the backup scheduling logic is determined according to the abnormal handling strategy. Control the current workflow to skip the abnormal agent node corresponding to the first agent or the second agent, and enable the backup scheduling logic.

[0013] In some embodiments, after sending scheduling instructions to the first agent and / or the second agent according to the cooperative scheduling strategy, the multi-agent cooperative management method further includes: The system receives a cancellation request and a termination report sent by the first intelligent agent after the business collaboration task; the termination report includes the task completion status and resource usage details of the business collaboration task. The first agent is checked for resource usage based on the termination report and the preset resource check rules, and a resource release command is generated based on the cancellation application information and the resource usage check results. The resource release instruction is sent to the first intelligent agent to instruct the first intelligent agent to release the network resources it occupies, and after the network resources are released, the registration status of the first intelligent agent is updated to the deregistered status.

[0014] In some embodiments, the multi-agent collaborative management method further includes: During the deregistration process of the first intelligent agent, if it is detected that the second intelligent agent fails to report the status information within a first preset time period, it is determined that the second intelligent agent is in an abnormal offline state. Obtain the historical registration information of the second intelligent agent, and determine the historical network resource usage information of the second intelligent agent based on the historical registration information; Based on the historical network resource usage information, all network resources occupied by the second agent are reclaimed, and the registration status of the second agent is updated to an abnormal deregistration status.

[0015] According to another aspect of this disclosure, a multi-agent collaborative management device is also provided, the device comprising: The receiving module is used to receive collaborative scheduling requests sent by the business end; the collaborative scheduling request includes business scenario type and business requirement information; The determination module is used to determine a target business workflow template from multiple preset business workflow templates based on the business scenario type; the target business workflow template has built-in multi-agent collaborative scheduling logic and skill execution chain; The generation module is used to generate a collaborative scheduling strategy based on the business requirement information and the target business workflow template. The execution module is used to send scheduling instructions to the first intelligent agent and / or the second intelligent agent based on the collaborative scheduling strategy, so as to instruct the first intelligent agent and / or the second intelligent agent to perform business collaborative tasks according to a preset business process.

[0016] According to another aspect of this disclosure, an electronic device is also provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the multi-agent cooperative management method described in any one of the preceding claims by executing the executable instructions.

[0017] According to another aspect of this disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the multi-agent cooperative management method described in any of the preceding claims.

[0018] According to another aspect of this disclosure, a computer program product is also provided, comprising: a computer program or instructions, wherein the computer program or instructions, when executed by a processor, implement a multi-agent collaborative management method for any of the above-mentioned methods.

[0019] The embodiments of this disclosure provide a multi-agent collaborative management system. First, it receives a collaborative scheduling request from a business client, which includes business scenario type and business requirement information. Then, based on the business scenario type, it automatically determines a target business workflow template from multiple preset business workflow templates. This target business workflow template incorporates multi-agent collaborative scheduling logic and skill execution chains, directly solving the problems in existing technologies where multi-agent orchestration and skill chain configuration must be re-executed for each business trigger, and business processes cannot be reused. This achieves template-based solidification and direct reuse of business processes, fundamentally eliminating the cost of repetitive orchestration and reducing maintenance difficulty. Then, based on the business requirement information and the target business workflow template, it generates a collaborative scheduling strategy, effectively resolving… This technology solves the problem that task orchestration and capability invocation in existing technologies rely heavily on manual configuration, and realizes the automated generation of scheduling strategies. It can complete the conversion of business requirements into execution strategies without human intervention. Finally, based on the collaborative scheduling strategy, scheduling instructions are sent to the first and / or second intelligent agents to instruct them to execute business collaborative tasks according to preset business processes. This solves the problems of existing technologies lacking a standardized template solidification mechanism for business processes in multi-agent collaborative scenarios, which leads to non-reusable business processes, high difficulty in cross-domain multi-agent collaboration, low business deployment efficiency, and high maintenance costs. It realizes the template-based reuse and automated scheduling of business processes, effectively improving business deployment efficiency and multi-agent collaborative execution efficiency, and reducing operation and maintenance costs.

[0020] 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

[0021] 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. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0022] Figure 1 This diagram illustrates the system architecture of a multi-agent collaborative management method according to an embodiment of the present disclosure. Figure 2 This diagram illustrates a flowchart of a multi-agent collaborative management method according to an embodiment of the present disclosure; Figure 3 This diagram illustrates a flowchart of another multi-agent collaborative management method in an embodiment of this disclosure. Figure 4 This diagram illustrates a multi-agent collaborative management and control device according to an embodiment of the present disclosure. Figure 5A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0023] 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.

[0024] 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.

[0025] To facilitate understanding, before introducing the embodiments of this disclosure, the following explanations are provided for several terms involved in the embodiments of this disclosure: 6G network element intelligent agents: evolved from various network elements in the 6G core network, access network, and transmission network, including UPF (User Plane Function) service intelligent agents, network resource scheduling intelligent agents, etc., with core functions such as network resource scheduling and communication link maintenance. They are a core component of the 6G network, and are valid for a long time after registration. Their capabilities and access addresses can be dynamically updated.

[0026] External application intelligent agents: Deployed by third-party application providers, targeting vertical industry scenarios (such as OTT (Over-The-Top) video, industrial control, telemedicine, etc.), with specific business execution capabilities. After registration, they are managed for renewal on a periodic basis. Their capabilities and access addresses can be dynamically adjusted according to business needs and update requests can be submitted.

[0027] Extended Network Registration Function Element: Based on the network registration function element, the functions are extended. As the core node for the full life cycle management of intelligent agents, it is responsible for the registration and review of network intelligent agents, receiving intelligent agent information update and cancellation applications, synchronizing status information to the intelligent agent collaboration platform, and linking with the basic support layer to complete the handling of anomalies and resource management. At the same time, it undertakes the registration, storage, indexing, querying and status management of business workflow templates.

[0028] Intelligent Agent Collaboration Platform: Deeply integrated with the network registration function network element, it is responsible for real-time monitoring of intelligent agent operation status, dynamic renewal, deregistration processing, resource occupation verification, operation termination report review, resource release command issuance, synchronization of intelligent agent status and resource information to the network registration function network element, generation, parsing, registration, scheduling and execution of business workflow templates, process orchestration and fault self-healing, realizing collaborative support for the full lifecycle management of intelligent agents and business flows.

[0029] Basic support unit: includes security support module, computing power support module, and network support module. The security support module provides security protection capabilities such as identity authentication and permission verification; the computing power support module is responsible for the allocation, monitoring and reclamation of computing power resources; the network support module is responsible for the management and control of network bandwidth, network slicing and other resources, responds to the call requirements of the collaborative management and control layer, and ensures the efficiency and stability of the management and control process.

[0030] Business workflow template library: Common business processes are solidified into standardized templates, including: template ID, scenario, version, list of intelligent agents, list of skills, execution order, data flow, trigger / abnormal / scheduling strategy, which can be registered, discovered, reused, and enter the lifecycle management of business process entities.

[0031] The specific implementation methods of the embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0032] Figure 1 A schematic diagram of an exemplary application system architecture is shown, illustrating an application of the multi-agent collaborative management method described in the embodiments of this disclosure. For example... Figure 1 As shown, the system architecture may include terminal device 101, network 102 and server 103.

[0033] Network 102 is a medium used to provide a communication link between terminal device 101 and server 103, and can be a wired network or a wireless network.

[0034] Optionally, the aforementioned wireless or wired networks use standard communication technologies and / or protocols. The network is typically the Internet, but can also be any network, including but not limited to Local Area Networks (LANs), Metropolitan Area Networks (MANs), Wide Area Networks (WANs), mobile, wired or wireless networks, private networks, or any combination of virtual private networks. In some embodiments, technologies and / or formats, including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc., are used to represent data exchanged over the network. Furthermore, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Networks (VPNs), and Internet Protocol Security (IPSec) can be used to encrypt all or some links. In other embodiments, custom and / or dedicated data communication technologies can be used to replace or supplement the aforementioned data communication technologies.

[0035] Terminal device 101 can be various electronic devices, including but not limited to smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, wearable devices, augmented reality devices, virtual reality devices, etc.

[0036] Optionally, the client of the application installed on different terminal devices 101 may be the same, or the client of the same type of application based on different operating systems. Depending on the terminal platform, the specific form of the application client may also be different; for example, the application client may be a mobile client, a PC client, etc.

[0037] Server 103 can be a server that provides various services, such as a backend management server that supports the device operated by the user using terminal device 101. The backend management server can analyze and process received requests and other data, and feed the processing results back to the terminal device.

[0038] Optionally, the server can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0039] Those skilled in the art will know that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative; any number of terminal devices, networks, and servers can be included depending on actual needs. This disclosure does not limit the scope of the embodiments.

[0040] Under the above system architecture, this disclosure provides a multi-agent collaborative management method, which can be executed by any electronic device with computing power.

[0041] In some embodiments, the multi-agent collaborative management method provided in this disclosure can be executed by the terminal device of the above-described system architecture; in other embodiments, the multi-agent collaborative management method provided in this disclosure can be executed by the server in the above-described system architecture; in still other embodiments, the multi-agent collaborative management method provided in this disclosure can be implemented by the terminal device and the server in the above-described system architecture through interaction.

[0042] In some embodiments, a multi-agent collaborative management and control system can serve as the execution subject of the multi-agent collaborative management and control method in this embodiment. For ease of description, the multi-agent collaborative management and control system can be simply referred to as the system. This system mainly consists of six core units, which are deeply interconnected to achieve collaborative management and control of the entire lifecycle of 6G agents. The six core units include: 6G network element agents (such as network status assessment agents, resource orchestration agents, and wireless resource scheduling agents), external application agents (such as OTT application intent agents), extended network registration function network elements (i.e., network registration function network elements), an agent collaboration platform, basic support units, and a service workflow template library. The service workflow template library includes multiple preset service workflow templates.

[0043] It should be noted that this embodiment can rely on the functional expansion of the network registration function element and its deep linkage with the intelligent agent collaboration platform. On the one hand, it can construct an integrated management and control system covering the entire lifecycle of intelligent agents, including registration renewal, operation monitoring, deregistration verification, and resource reclamation, to achieve differentiated validity period management, full-cycle state synchronization, automatic resource reclamation, and cross-layer collaborative linkage. On the other hand, it can register business workflow templates as independent management objects to the network registration function element, supporting structured registration, unified discovery, automatic scheduling, and full lifecycle management of multi-agent and multi-skill combination processes, realizing the templated, reusable, and orchestratable nature of business processes. This solves the technical problems in the existing 6G intelligent agent registration and control, such as disconnection between registration and control, inconsistent state synchronization, delayed resource reclamation, insufficient cross-layer linkage, difficulty in solidifying and reusing business processes, difficulty in cross-domain collaboration, and high maintenance costs. It achieves collaborative and standardized management and control of the entire lifecycle of intelligent agents and unified registration and scheduling of business workflows, improving business deployment efficiency, resource utilization, and the level of operation and maintenance automation. It is compatible with the existing network architecture and can adapt to the needs of large-scale intelligent agent collaboration and high automation evolution in 6G.

[0044] This embodiment takes a high-traffic access scenario in a venue as an example. In this scenario, tens of thousands of user terminals simultaneously access the network, resulting in a surge in concurrent OTT video live streaming and on-demand services. Network traffic exhibits characteristics of high instantaneous peak traffic and dynamic changes in service demand over time. To address the network challenges brought about by the aforementioned high-traffic access, this embodiment proposes a multi-agent collaborative management method. This method can achieve dynamic optimization and configuration of network resources by calling multiple network capability agents for collaborative scheduling and resource linkage, thereby ensuring the stability and efficiency of network operation under high-traffic scenarios. The core agents invoked in this embodiment include: a first agent, such as an OTT application intent agent that is registered and periodically renewed; and a second agent, including a network status assessment agent, a resource orchestration agent, and a wireless resource scheduling agent that are valid for a long period after registration. Simultaneously, the method links network registration function network elements, an agent collaboration platform, and the basic support layer to complete the full lifecycle collaborative management of agents and service workflows.

[0045] The network status assessment agent is used to collect real-time on-site network status data, including bandwidth utilization, link packet loss rate, latency, number of access users, and signal coverage strength. Based on the network status data, it performs network health assessment and reports the assessment results to the agent collaboration platform to support subsequent resource scheduling decisions. The resource orchestration agent is used to coordinate the orchestration and allocation of 6G network slices, computing resources, and bandwidth resources. It receives scheduling instructions from the agent collaboration platform, allocates dedicated network slices for business scenarios, and dynamically adjusts the resource allocation ratio to adapt to high traffic demands. The wireless resource scheduling agent is used to perform dynamic scheduling of on-site wireless resources, including spectrum, power, and access channels. It alleviates wireless resource shortages by optimizing user access priorities, reduces user access latency, and improves network access stability. The OTT application intent agent is used to collect on-site OTT application service requirements, including live streaming bitrate, on-demand resolution, and expected number of concurrent users. It converts the service requirements into standardized requirement parameters and synchronizes them to the agent collaboration platform and network registration function network elements to support accurate resource matching.

[0046] like Figure 2 As shown, during the venue business preparation phase, the system can perform a unified registration operation for intelligent agents / workflows. The system can invoke OTT application intent agents as external application agents. First, information filling and registration are completed on the agent collaboration platform, generating agent registration information (including at least one of agent identifier, capability description information, access address information, and validity period information). Simultaneously, to improve the efficiency of multi-agent collaboration, the system can pre-encapsulate the high-traffic access guarantee business process for venues into a standardized business workflow template (i.e., the target business workflow template, including at least one of template identifier, scenario information, version information, agent list, skill list, execution order information, data flow information, triggering strategy, exception strategy, and scheduling strategy). The system uses the agent collaboration platform to perform internal structure verification on the target business workflow template, generating template registration information. After the target business workflow template passes internal structure verification, template construction and registration are performed, and a globally unique WORKFLOW-ID is assigned to the target business workflow template. The system can then store the template in the business workflow template library. This target business workflow template has a built-in complete Skill execution chain, node scheduling logic, exception switching rules, and resource scheduling strategy, supporting global scheduling and reuse.

[0047] It should be noted that for second agents that have completed long-term registration in advance (such as network status assessment agents, resource orchestration agents, and wireless resource scheduling agents), their registration information has been stored in the network registration function network element. There is no need to repeat the registration process. They can be directly incorporated into the collaborative management and control system, and their registration status remains valid in the long term.

[0048] Furthermore, such as Figure 2 As shown, the system can perform global state initialization and real-time monitoring operations for intelligent agents / workflows. Specifically, the system can obtain template registration information and intelligent agent registration information, and send these information to the network registration function element using the intelligent agent collaboration platform. Then, the system can call the network registration function element to perform a legality verification on the first intelligent agent (i.e., the OTT application intent intelligent agent) according to preset registration verification rules (such as identity validity verification rules, registration information integrity verification rules, and access address validity verification rules at least one of these). Based on the verification result, the system determines the registration status of the first intelligent agent, which includes successful or failed registration. Simultaneously, when the registration status is successful, the network registration function element generates a successful registration receipt and returns it to the intelligent agent collaboration platform. At the same time, the system can generate first state synchronization information based on the registration status and send it to the intelligent agent collaboration platform. This allows the intelligent agent collaboration platform to initialize the first intelligent agent's operating status to an available state based on the first state synchronization information and synchronize it to the network registration function element, ensuring that the status of all control nodes remains consistent.

[0049] Simultaneously, the system can invoke the network registration function element to perform registration verification on the target business workflow template according to at least one of the preset template verification rules (including syntax format verification rules, topology logic verification rules, dependency integrity verification rules, and structured compliance verification rules, used to verify the structural compliance and executability of the target business workflow template). Based on the verification result, the system determines the registration status of the target business workflow template, which can include successful or failed registration. When the registration status of the target business workflow template is successful, the system can use the network registration function element to register the target business workflow template into the database and generate second status synchronization information based on the registration status. This second status synchronization information is then sent to the intelligent agent collaboration platform, enabling the intelligent agent collaboration platform to initialize the process status of the target business workflow template to an available state based on the second status synchronization information, and simultaneously synchronize it to the network registration function element, achieving global state consistency initialization between the intelligent agent and the business workflow template.

[0050] During the real-time monitoring phase, network status assessment agents, resource orchestration agents, wireless resource scheduling agents, and OTT application intent agents report alarm information, load status, and their own skill availability status at fixed intervals; the venue support workflow synchronously reports process readiness status, node availability status, and anomaly warning information in real time; all types of agent status (such as online, offline, and abnormal) and workflow status (such as normal, blocked, interrupted, and failed) are uniformly collected by the agent collaboration platform and synchronized in real time to the network registration function network element to ensure that the overall status view is unbiased.

[0051] Furthermore, the system can perform collaborative management and control operations involving multiple agents. See details... Figure 3 The figure illustrates a flowchart of another multi-agent collaborative management method according to an embodiment of this disclosure, which includes the following steps: S302 receives a collaborative scheduling request sent by the service terminal.

[0052] In step S302, the collaborative scheduling request includes business scenario type and business requirement information.

[0053] In this embodiment of the application, when a large number of users access the venue and the OTT live broadcast service is triggered, the service terminal initiates a venue high-traffic guarantee service request (i.e., a collaborative scheduling request) to the system. The system can receive the venue high-traffic guarantee service request and parse out the business scenario type (such as the venue high-traffic access scenario and the vertical industry scenario targeted by the external application intelligent agent, such as OTT video scenario (including live broadcast and on-demand), industrial control scenario, telemedicine scenario, etc.) and business requirement information (such as standardized requirement parameters such as live broadcast bitrate, on-demand resolution, and expected number of concurrent users) from the venue high-traffic guarantee service request.

[0054] S304, determine the target business workflow template from multiple preset business workflow templates based on the business scenario type.

[0055] In step S304, the target business workflow template incorporates multi-agent collaborative scheduling logic and skill execution chain.

[0056] In this embodiment, the system can call the network registration function network element to determine the target business workflow template from multiple preset business workflow templates in the business workflow template library according to the business scenario type. The target business workflow template has built-in multi-agent collaborative scheduling logic and skill execution chain, which directly solves the problem that in the prior art, multi-agent orchestration and skill chain configuration need to be re-performed every time a business is triggered, and the business process cannot be reused. It realizes the template solidification and direct reuse of business processes, fundamentally eliminates the cost of repeated orchestration, and reduces the difficulty of maintenance.

[0057] S306 generates a collaborative scheduling strategy based on business requirements information and target business workflow templates.

[0058] In this embodiment, the system utilizes an intelligent agent collaboration platform to parse business requirement information to extract the resource requirement characteristics and execution constraints of the current business. Simultaneously, it invokes the target business workflow template, reading the preset list of intelligent agents, the skill configurations corresponding to each intelligent agent, the execution order between nodes, and the data interaction relationships within the template. Then, the intelligent agent collaboration platform integrates the business requirement information with the collaborative scheduling logic built into the target business workflow template. Based on the execution order information, it determines the invocation sequence of each intelligent agent; based on the data flow information, it determines the data interaction path between intelligent agents; and based on the scheduling strategy, it determines the resource allocation priority and load balancing rules, thereby generating a collaborative scheduling strategy. This collaborative scheduling strategy clarifies the task division, skill invocation order, data transmission relationships, and resource allocation scheme for each participating intelligent agent, providing a direct execution basis for subsequently sending scheduling instructions to the first and / or second intelligent agents. This achieves automated strategy generation from business requirements to multi-agent collaborative execution, effectively solving the problem of task orchestration and capability invocation relying heavily on manual configuration in existing technologies. It realizes automated generation of scheduling strategies, completing the conversion from business requirements to execution strategies without manual intervention.

[0059] S308, based on the collaborative scheduling strategy, a scheduling instruction is sent to the first intelligent agent and / or the second intelligent agent to instruct the first intelligent agent and / or the second intelligent agent to perform business collaborative tasks according to the preset business process.

[0060] In this embodiment, the system utilizes an intelligent agent collaboration platform to parse the task allocation information, skill call timing information, and data interaction path information of each intelligent agent according to a collaborative scheduling strategy. Based on this information, it generates scheduling instructions for the first and / or second intelligent agents. The scheduling instructions include at least one of the following: the skill identifier to be executed, input data parameters, execution priority, and resource allocation information. The intelligent agent collaboration platform then sends the scheduling instructions to the corresponding first intelligent agent (i.e., the OTT application intent intelligent agent) and / or second intelligent agent (including the network status assessment intelligent agent, resource orchestration intelligent agent, and wireless resource scheduling intelligent agent). After receiving the scheduling instructions, the first and / or second intelligent agents invoke their own skills according to the skill identifier and execute the business collaboration tasks sequentially according to the preset execution order information in the target business workflow template. During the execution of collaborative business tasks, the first and second intelligent agents interact and synchronize their states based on the data flow information determined in the collaborative scheduling strategy. Each intelligent agent cooperates according to the preset business process to complete the collaborative business task. This solves the problem that existing technologies lack a standardized template mechanism for business processes in multi-agent collaborative scenarios, which leads to non-reusable business processes, high difficulty in cross-domain multi-agent collaboration, low business deployment efficiency, and high maintenance costs. It realizes the template-based reuse and automated scheduling of business processes, effectively improving business deployment efficiency and multi-agent collaborative execution efficiency, and reducing operation and maintenance costs.

[0061] Furthermore, such as Figure 2 As shown, the system can perform dynamic renewal and information update operations for intelligent agents. In this embodiment, the first intelligent agent is a periodically valid external application intelligent agent, which is configured with validity period information during registration (e.g., the validity period of an OTT application intent intelligent agent is 15 days). Within a preset time before the expiration of the validity period (e.g., 3 days before expiration), the first intelligent agent actively sends renewal application information to the intelligent agent collaboration platform. The renewal application information includes at least one of the following: intelligent agent identifier, current validity period information, renewal application duration information, and operation behavior records. The preset duration is pre-configured by the system to ensure that the renewal review process is completed before the expiration of the validity period, avoiding forced cancellation of the intelligent agent or business interruption due to the expiration of the validity period.

[0062] Then, the system can receive renewal application information through the intelligent agent collaboration platform and, in conjunction with the basic support layer, perform compliance verification on the first intelligent agent based on the renewal application information and preset renewal verification rules (including at least one of the following: identity legitimacy verification rules, operational behavior compliance verification rules, and resource usage compliance verification rules). Specifically, firstly, the security support module verifies the legitimacy of the first intelligent agent's identity, confirming that its registration information has not been tampered with and its permissions are valid; then, the intelligent agent collaboration platform verifies the compliance of the first intelligent agent's operational behavior, confirming that its operational logs within the current validity period have no abnormal alarms or records of unauthorized operations; then, the computing power support module and the network support module verify the compliance of the first intelligent agent's resource usage, confirming that its current usage of computing power and network resources is consistent with the capability description information declared during registration, and that there is no over-use or resource abuse. Finally, the intelligent agent collaboration platform comprehensively determines whether the first intelligent agent passes the compliance verification based on the verification results fed back by the above modules. After the first intelligent agent passes all compliance verifications, the intelligent agent collaboration platform performs a renewal operation on the first intelligent agent, updates its validity period (such as extending it by 15 days or setting a new validity period), and generates a renewal success confirmation message.

[0063] Optionally, the system can have the intelligent agent collaboration platform synchronously push the updated validity period information to the network registration function element based on the renewal operation result. After receiving the updated validity period information, the network registration function element updates the validity period record of the first intelligent agent in the registration database, ensuring that the validity period information of the first intelligent agent is consistent between the network registration function element and the intelligent agent collaboration platform. After the update is completed, the first intelligent agent continues to participate in business collaboration tasks with the updated validity period, and its registration status remains available, without needing to re-execute the complete registration process.

[0064] Furthermore, such as Figure 2As shown, the system can perform full-cycle state collaborative monitoring operations. In this embodiment, the intelligent agent collaboration platform establishes a periodic heartbeat mechanism with the first and / or second intelligent agents. That is, the first and / or second intelligent agents report heartbeat packets to the intelligent agent collaboration platform at fixed intervals (such as a first preset duration). The system uses the intelligent agent collaboration platform to determine the status reporting status of the first and / or second intelligent agents within the first preset duration by monitoring whether a heartbeat packet is received within the preset first preset duration (such as 100ms). This allows the system to determine the real-time operating status of the first and / or second intelligent agents (such as various statuses such as registered, pending configuration, running, pending deregistration, etc., as well as at least one of alarm information, load status, and skill availability status). If the status reporting status indicates that the first and / or second intelligent agents have reported status information within the first preset duration (100ms), the system then uses the intelligent agent collaboration platform to parse the status information in the heartbeat packet (including the real-time operating status of the first and / or second intelligent agents), extract status change items as needed, and generate third status synchronization information. Then, the system can update the running status records of the first and / or second intelligent agents on the platform side according to the third state synchronization information by the intelligent agent collaboration platform, and push the third state synchronization information to the network registration function network element in real time, so that the network registration function network element can update the state records in the registration database synchronously, ensuring that the intelligent agent collaboration platform and the network registration function network element are completely consistent with the running status of the first and / or second intelligent agents, and realize the unbiased state view of the whole domain.

[0065] Optionally, when the first or second intelligent agent fails to report status information for a first preset time period, or when the heartbeat packet carries abnormal alarm information, the intelligent agent collaboration platform determines that the first or second intelligent agent is in an abnormal operating state and obtains the intelligent agent's abnormal information. This information may include at least one of the intelligent agent's offline time, cause of the abnormality, and resource usage, and generates abnormal status synchronization information accordingly. Then, the intelligent agent collaboration platform updates the operating status of the first or second intelligent agent to an abnormal or unavailable state, and pushes the abnormal status synchronization information to the network registration function network element, so that the network registration function network element updates its status record synchronously, completely avoiding scheduling failures caused by status deviations. Then, based on the intelligent agent's abnormal information, the intelligent agent collaboration platform reads the preset abnormal handling strategy (including at least one of node skipping rules, backup node mapping relationships, and resource reallocation rules) in the target business workflow template, and matches the intelligent agent's abnormal information with the abnormal handling strategy to determine the backup scheduling logic for the currently abnormal intelligent agent node. Finally, the system can control the current workflow to skip the abnormal intelligent agent node corresponding to the first or second intelligent agent, and enable the backup scheduling logic. That is, during the execution of the business workflow, the intelligent agent collaboration platform will no longer send scheduling instructions to the abnormal intelligent agent node, but will transfer the task flow to the backup intelligent agent node or adjust the subsequent execution path according to the backup scheduling logic. This ensures that the business collaboration task is not interrupted due to the abnormality of a single intelligent agent, realizes the fault self-healing and continuous execution of the business process, and adapts to the cross-domain collaboration requirements of 6G multi-intelligent agents.

[0066] like Figure 2 As shown, after the venue activity ends and the business is completed, the system can perform a standardized deregistration operation. Specifically, after the business collaboration task is completed, the first intelligent agent can proactively send deregistration application information and a termination report to the intelligent agent collaboration platform. This termination report details the task completion status of the business collaboration task, including at least one of the following: task execution result, completion time, and skill chain information invoked during execution; it also lists resource usage details, including at least one of the following: bandwidth resources, computing power resources, network slice resources, wireless spectrum resources, and access channel resources used by the first intelligent agent during the execution of the business collaboration task, forming a complete resource usage list to provide an accurate basis for subsequent resource reclamation. Then, after receiving the deregistration application information and the termination report, the intelligent agent collaboration platform can perform resource usage verification on the first intelligent agent according to preset resource verification rules (including at least one of the resource usage consistency verification rules and resource release integrity verification rules). Then, the intelligent agent collaboration platform compares the resource usage details in the operation termination report with the actual resource allocation information recorded by the basic support layer item by item, checks whether the resource usage reported by the first intelligent agent is consistent with the actual usage, confirms whether there is any unreported residual resource usage, and generates resource usage verification results.

[0067] Then, the intelligent agent collaboration platform generates a resource release instruction based on the cancellation application information and resource usage verification results. After the resource usage verification is passed, confirming the accuracy of the resource usage details, the generated resource release instruction clearly lists the types, quantities, and release order of the network resources to be released. If the verification reveals discrepancies between the resource usage details and the actual records, an anomaly is first flagged and supplementary verification is performed before generating a resource release instruction for the actually occupied resources. Finally, the intelligent agent collaboration platform sends the resource release instruction to the first intelligent agent. Upon receiving the instruction, the first intelligent agent releases all network resources it occupies according to the instruction requirements, including at least one of bandwidth, computing power, and network slices. After completing the release of all resources, the first intelligent agent sends a confirmation message to the intelligent agent collaboration platform confirming the completion of resource release.

[0068] Optionally, after receiving confirmation of resource release completion, the intelligent agent collaboration platform can send the verification result back to the network registration function element, confirming that the first intelligent agent has completed resource release and there is no residual occupation. Subsequently, the intelligent agent collaboration platform updates the registration status of the first intelligent agent to "deregistered" and synchronizes it to the network registration function element, so that the network registration function element marks the first intelligent agent's registration information as deregistered, ensuring the accuracy of registration information across the entire domain. At the same time, the intelligent agent collaboration platform archives and saves the first intelligent agent's entire registration information, operation logs, and status change records, achieving full-process traceability and auditability.

[0069] In one feasible implementation, the system can continuously maintain a heartbeat monitoring mechanism for the second intelligent agent (such as a wireless resource scheduling intelligent agent) throughout the entire lifecycle after the first intelligent agent initiates a deregistration request and before completing resource release. If no heartbeat packet or status report information is received from the second intelligent agent within a first preset time period, it is determined that the second intelligent agent has experienced abnormal offline status or hardware failure, rather than completing the deregistration process normally. Then, the intelligent agent collaboration platform extracts the capability description information, access address information, and resource allocation records (i.e., historical registration information) submitted by the second intelligent agent during registration from the registration database. Based on this, it accurately identifies all network resources actually occupied by the second intelligent agent throughout its entire lifecycle (i.e., historical network resource occupancy information), including at least one of wireless spectrum, access channels, network slices, bandwidth, and computing power resources, forming a complete historical network resource occupancy list as an accurate basis for forced reclamation. Finally, the intelligent agent collaboration platform issues a forced resource reclamation command to the basic support layer. The computing power support module and the network support module then reclaim all network resources occupied by the second intelligent agent item by item according to the historical network resource occupancy list, ensuring no residual occupancy. At the same time, the intelligent agent collaboration platform coordinates with the network registration function network element to update the registration status of the second intelligent agent to an abnormal deregistration status, simultaneously deregistering the abnormal registration information of the second intelligent agent in the network registration function network element, and recording the abnormal log. The abnormal log includes offline time, resource occupancy status, and the cause of the abnormality, ensuring that the registration information across the entire domain is accurate and the entire process is traceable.

[0070] The multi-agent collaborative management method provided in this application embodiment achieves unified full lifecycle management of the above four types of agents and business workflows in high-traffic access scenarios in venues. This effectively reduces the latency of global state synchronization, ensures consistency between the agent and business workflow states without deviation, completely eliminates the risk of scheduling failure, and significantly improves the stability of business process operation. On the other hand, it automates the entire process of agent renewal, information update, and resource release without manual intervention, significantly improving operation and maintenance efficiency. Furthermore, it enables direct reuse of business workflows and automatic switching in case of anomalies, effectively adapting to high-traffic, high-concurrency scenarios and significantly enhancing business assurance capabilities. At the same time, it enables precise resource recovery without idle waste, greatly improving network resource utilization. Moreover, the entire process is traceable and auditable, fully meeting the automated operation and maintenance needs of 6G networks.

[0071] It should be noted that the acquisition, storage, use, and processing of data in this disclosed technical solution comply with the relevant provisions of national laws and regulations. The various types of data, such as personal identity data, operational data, and behavioral data related to individuals, customers, and groups, obtained in the embodiments of this disclosure have all been authorized.

[0072] Based on the same inventive concept, this disclosure also provides a multi-agent collaborative management and control device, as shown in the following embodiment. 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 device embodiment can refer to the implementation of the above-described method embodiment, and repeated details will not be elaborated further.

[0073] Figure 4 This diagram illustrates a multi-agent collaborative management and control device according to an embodiment of the present disclosure, such as... Figure 4 As shown, the device includes: a receiving module 401, a determining module 402, a generating module 403, and an execution module 404; The receiving module 401 is used to receive the collaborative scheduling request sent by the business end; the collaborative scheduling request includes the business scenario type and business requirement information; The determination module 402 is used to determine the target business workflow template from multiple preset business workflow templates based on the business scenario type; the target business workflow template has built-in multi-agent collaborative scheduling logic and skill execution chain; The generation module 403 is used to generate a collaborative scheduling strategy based on business requirement information and target business workflow template; The execution module 404 is used to send scheduling instructions to the first intelligent agent and / or the second intelligent agent based on the collaborative scheduling strategy, so as to instruct the first intelligent agent and / or the second intelligent agent to perform business collaborative tasks according to the preset business process.

[0074] Optionally, the first intelligent agent is an external application intelligent agent, and the second intelligent agent is a network element intelligent agent; the network element intelligent agent is an intelligent agent that is valid for a long time after registration, and the external application intelligent agent is an intelligent agent that is renewed periodically after registration.

[0075] Optionally, the multi-agent collaborative management device also includes: The first receiving module is used to receive renewal application information sent by the first intelligent agent within a preset time period before the expiration of the validity period after sending a scheduling instruction to the first intelligent agent and / or the second intelligent agent based on the collaborative scheduling strategy to instruct the first intelligent agent and / or the second intelligent agent to perform business collaborative tasks according to the preset business process. The compliance verification module is used to perform compliance verification on the first intelligent agent based on the renewal application information and the preset renewal verification rules, and to perform the renewal operation on the first intelligent agent after the first intelligent agent passes the compliance verification. The first update module is used to update the validity period information of the first intelligent agent based on the renewal operation results.

[0076] Optionally, the multi-agent collaborative management device also includes: The first acquisition module is used to acquire template registration information and agent registration information before receiving the collaborative scheduling request sent by the business terminal. The template registration information includes information generated after the target business workflow template is verified through internal structure. The registration information of the first agent includes at least one of agent identifier, capability description information, access address information, and validity period information. The first determining module is used to determine the registration status of the first intelligent agent based on the intelligent agent registration information and the preset registration verification rules, and generate first status synchronization information based on the registration status. The second determination module is used to determine the registration status of the target business workflow template based on the template registration information and the preset template verification rules, and generate second status synchronization information based on the registration status. The second update module is used to update the running status of the first intelligent agent based on the first state synchronization information, and to update the process status of the target business workflow template according to the second state synchronization information.

[0077] Optionally, the multi-agent collaborative management device also includes: The monitoring module is used to monitor the status reporting status of the first intelligent agent and / or the second intelligent agent within a first preset time period after sending scheduling instructions to the first intelligent agent and / or the second intelligent agent according to the collaborative scheduling strategy. The first generation module is used to generate third state synchronization information based on the state information if the state reporting status indicates that the first intelligent agent and / or the second intelligent agent has reported state information within a first preset time period; the state information is used to characterize the real-time operating status of the first intelligent agent and / or the second intelligent agent. The third update module is used to update the operating status of the first agent and / or the second agent based on the third state synchronization information.

[0078] Optionally, the multi-agent collaborative management device also includes: The third determination module is used to determine that the first or second intelligent agent is in an abnormal operating state if the status reporting status indicates that the first intelligent agent or the second intelligent agent has not reported status information within a first preset time period. The second generation module is used to obtain the agent abnormality information of the first agent or the second agent, and generate corresponding abnormal state synchronization information based on the agent abnormality information. The fourth update module is used to update the running status of the first or second agent based on the abnormal state synchronization information; The matching module is used to match the exception handling strategy in the target business workflow template based on the exception information of the intelligent agent, and to determine the backup scheduling logic based on the exception handling strategy. The control module is used to control the current workflow to skip the abnormal agent node corresponding to the first or second agent and to enable the backup scheduling logic.

[0079] Optionally, the multi-agent collaborative management device also includes: The second receiving module is used to receive the deregistration application information and operation termination report sent by the first intelligent agent after the business collaboration task is completed, after sending the scheduling instruction to the first intelligent agent and / or the second intelligent agent according to the collaborative scheduling strategy; the operation termination report includes the task completion status and resource usage details of the business collaboration task. The verification module is used to verify the resource usage of the first agent according to the operation termination report and the preset resource verification rules, and to generate a resource release instruction based on the cancellation application information and the resource usage verification results; The deregistration module is used to send resource release instructions to the first intelligent agent to instruct the first intelligent agent to release the network resources it occupies, and to update the registration status of the first intelligent agent to the deregistered status after the network resources are released.

[0080] Optionally, the multi-agent collaborative management device also includes: The fourth determination module is used to determine that the second intelligent agent is in an abnormal offline state if it is detected that the second intelligent agent has not reported status information within a first preset time period during the first intelligent agent's deregistration process. The second acquisition module is used to acquire the historical registration information of the second intelligent agent and determine the historical network resource occupancy information of the second intelligent agent based on the historical registration information; The fifth update module is used to reclaim all network resources occupied by the second agent based on historical network resource usage information, and update the registration status of the second agent to an abnormal deregistration status.

[0081] It should be noted that the examples and application scenarios implemented by the modules in the above device embodiments and the corresponding steps in the method embodiments are the same, but are not limited to the content disclosed in the above method embodiments. It should also be noted that the above modules, as part of the device, can be executed in a computer system such as a set of computer-executable instructions.

[0082] Those skilled in the art will understand that various aspects of this disclosure can be implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which can be collectively referred to herein as a "circuit", "module" or "system".

[0083] Based on the same inventive concept, this disclosure also provides an electronic device, which includes: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the multi-agent cooperative management method described above by executing the executable instructions. Since the principle by which this electronic device solves the problem is similar to that of the above method embodiments, the implementation of this electronic device embodiment can refer to the implementation of the above method embodiments, and repeated details will not be elaborated further.

[0084] The following reference Figure 5 To describe an electronic device 500 according to such an embodiment of the present disclosure. Figure 5 The electronic device 500 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0085] like Figure 5 As shown, the electronic device 500 is manifested in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: at least one processing unit 510, at least one storage unit 520, and a bus 530 connecting different system components (including storage unit 520 and processing unit 510).

[0086] The storage unit stores program code, which can be executed by the processing unit 510, causing the processing unit 510 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 510 can perform the following steps of the above method embodiments: S302, Receive a collaborative scheduling request sent by the business end; the collaborative scheduling request includes the business scenario type and business requirement information; S304, determine the target business workflow template from multiple preset business workflow templates based on the business scenario type; the target business workflow template has built-in multi-agent collaborative scheduling logic and skill execution chain; S306, Generate a collaborative scheduling strategy based on business requirements information and target business workflow template; S308, based on the collaborative scheduling strategy, send scheduling instructions to the first intelligent agent and / or the second intelligent agent to instruct the first intelligent agent and / or the second intelligent agent to perform business collaborative tasks according to the preset business process.

[0087] Storage unit 520 may include readable media in the form of volatile storage units, such as random access memory (RAM) 5201 and / or cache memory 5202, and may further include read-only memory (ROM) 5203.

[0088] Storage unit 520 may also include a program / utility 5204 having a set (at least one) program module 5205, such program module 5205 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.

[0089] Bus 530 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.

[0090] Electronic device 500 can also communicate with one or more external devices 540 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 500, and / or with any device that enables electronic device 500 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 550. Furthermore, electronic device 500 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 560. As shown, network adapter 560 communicates with other modules of electronic device 500 via bus 530. 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 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0091] 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.

[0092] Based on the same inventive concept, this disclosure also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the multi-agent cooperative management method described above. Since the principle by which this computer-readable storage medium embodiment solves the problem is similar to that of the above method embodiments, the implementation of this computer-readable storage medium embodiment can refer to the implementation of the above method embodiments, and repeated details will not be elaborated further.

[0093] More specific examples of computer-readable storage media in this disclosure may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, 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 of the foregoing.

[0094] In this disclosure, a computer-readable storage medium may include a data signal 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 transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device.

[0095] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0096] In practice, program code for performing the operations of this disclosure 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 computing 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).

[0097] Based on the same inventive concept, this disclosure also provides a computer program product, including: a computer program or instructions, which, when executed by a processor, implement the multi-agent collaborative management method of any one of the above method embodiments. Since the principle by which this computer program product embodiment solves the problem is similar to that of the above method embodiments, the implementation of this computer program product embodiment can refer to the implementation of the above method embodiments, and repeated details will not be elaborated further.

[0098] 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.

[0099] 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.

[0100] 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, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0101] 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 disclosure 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.

Claims

1. A multi-agent collaborative management and control method, characterized in that, The method includes: Receive a collaborative scheduling request sent by the business terminal; the collaborative scheduling request includes business scenario type and business requirement information; Based on the business scenario type, a target business workflow template is determined from multiple preset business workflow templates; the target business workflow template incorporates multi-agent collaborative scheduling logic and skill execution chains. Based on the business requirement information and the target business workflow template, a collaborative scheduling strategy is generated; Based on the collaborative scheduling strategy, scheduling instructions are sent to the first intelligent agent and / or the second intelligent agent to instruct the first intelligent agent and / or the second intelligent agent to perform business collaborative tasks according to a preset business process.

2. The collaborative control method according to claim 1, characterized in that, The first intelligent agent is an external application intelligent agent, and the second intelligent agent is a network element intelligent agent; the network element intelligent agent is an intelligent agent that is valid for a long time after registration, and the external application intelligent agent is an intelligent agent that is renewed periodically after registration.

3. The collaborative control method according to claim 1, characterized in that, After sending scheduling instructions to the first agent and / or the second agent based on the collaborative scheduling strategy to instruct the first agent and / or the second agent to execute business collaborative tasks according to a preset business process, the method further includes: Receive renewal application information sent within a preset time period before the expiration of the validity period of the first intelligent agent; Based on the renewal application information and the preset renewal verification rules, the first intelligent agent is subjected to compliance verification, and after the first intelligent agent passes the compliance verification, the renewal operation is performed on the first intelligent agent. Update the validity period information of the first intelligent agent based on the renewal operation result.

4. The collaborative control method according to claim 1, characterized in that, Before receiving the collaborative scheduling request sent by the service terminal, the method further includes: Obtain template registration information and agent registration information; the template registration information includes information generated after the target business workflow template passes internal structure verification, and the registration information of the first agent includes at least one of agent identifier, capability description information, access address information, and validity period information; Based on the agent registration information and the preset registration verification rules, the registration status of the first agent is determined, and first status synchronization information is generated according to the registration status. Based on the template registration information and the preset template verification rules, the registration status of the target business workflow template is determined, and second status synchronization information is generated based on the registration status. The first intelligent agent's running status is updated based on the first state synchronization information, and the target business workflow template's process status is updated based on the second state synchronization information.

5. The collaborative control method according to claim 1, characterized in that, After sending scheduling instructions to the first agent and / or the second agent according to the cooperative scheduling strategy, the method further includes: Monitor the status reporting of the first intelligent agent and / or the second intelligent agent within a first preset time period; If the status reporting status indicates that the first agent and / or the second agent has reported status information within the first preset time period, then third status synchronization information is generated based on the status information; the status information is used to characterize the real-time operating status of the first agent and / or the second agent. The operating status of the first agent and / or the second agent is updated based on the third state synchronization information.

6. The collaborative control method according to claim 5, characterized in that, The method further includes: If the status reporting indicates that the first agent or the second agent has not reported the status information within the first preset time period, then it is determined that the first agent or the second agent is in an abnormal operating state. Obtain agent anomaly information of the first agent or the second agent, and generate corresponding abnormal state synchronization information based on the agent anomaly information; The operating status of the first or second intelligent agent is updated based on the abnormal state synchronization information. The abnormal information of the intelligent agent is matched with the abnormal handling strategy in the target business workflow template, and the backup scheduling logic is determined according to the abnormal handling strategy. Control the current workflow to skip the abnormal agent node corresponding to the first agent or the second agent, and enable the backup scheduling logic.

7. The collaborative control method according to claim 1, characterized in that, After sending scheduling instructions to the first agent and / or the second agent according to the cooperative scheduling strategy, the method further includes: The system receives a cancellation request and a termination report sent by the first intelligent agent after the business collaboration task; the termination report includes the task completion status and resource usage details of the business collaboration task. The first agent is checked for resource usage based on the termination report and the preset resource check rules, and a resource release command is generated based on the cancellation application information and the resource usage check results. The resource release instruction is sent to the first intelligent agent to instruct the first intelligent agent to release the network resources it occupies, and after the network resources are released, the registration status of the first intelligent agent is updated to the deregistered status.

8. The collaborative control method according to claim 7, characterized in that, The method further includes: During the deregistration process of the first intelligent agent, if it is detected that the second intelligent agent fails to report the status information within a first preset time period, it is determined that the second intelligent agent is in an abnormal offline state. Obtain the historical registration information of the second intelligent agent, and determine the historical network resource usage information of the second intelligent agent based on the historical registration information; Based on the historical network resource usage information, all network resources occupied by the second agent are reclaimed, and the registration status of the second agent is updated to an abnormal deregistration status.

9. A multi-agent collaborative control device, characterized in that, The device includes: The receiving module is used to receive collaborative scheduling requests sent by the business end; the collaborative scheduling request includes business scenario type and business requirement information; The determination module is used to determine a target business workflow template from multiple preset business workflow templates based on the business scenario type; the target business workflow template has built-in multi-agent collaborative scheduling logic and skill execution chain; The generation module is used to generate a collaborative scheduling strategy based on the business requirement information and the target business workflow template. The execution module is used to send scheduling instructions to the first intelligent agent and / or the second intelligent agent based on the collaborative scheduling strategy, so as to instruct the first intelligent agent and / or the second intelligent agent to perform business collaborative tasks according to a preset business process.

10. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the multi-agent cooperative management method according to any one of claims 1 to 8 by executing the executable instructions.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the multi-agent cooperative management method according to any one of claims 1 to 8.

12. A computer program product, comprising: A computer program or instruction, characterized in that, when executed by a processor, the computer program or instruction implements the multi-agent cooperative management method according to any one of claims 1 to 8.

Images