Agent management method and apparatus based on artificial intelligence technology, and related device

Abstract

Provided in the present application are an agent management method and apparatus based on artificial intelligence technology, and a related device. The agent management method based on artificial intelligence technology can be applied to a management platform which manages a plurality of agents. Specifically, after a target task is acquired, a first agent and a second agent can be determined on the basis of the target task. The first agent and the second agent are agents managed by the management platform, and can both process at least one type of task on the basis of artificial intelligence technology. After the first agent and the second agent are determined, a dialogue chain can be generated to configure the first agent and the second agent, so that the first agent and the second agent process the target task on the basis of the dialogue chain. Therefore, even if a task to be completed has relatively high complexity, the task can be completed by means of the cooperation between a plurality of agents, thereby meeting the requirement of completing, by means of the agents, the task having relatively high complexity.

Description

An intelligent agent management method, device and related equipment based on artificial intelligence technology

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on September 26, 2023, with application number 202311253370.1 and invention name “A data processing system, method, computing cluster and related equipment”, and claims priority to the Chinese patent application filed with the China Patent Office on February 7, 2024, with application number CN202410175663.0 and application name “A method, device and related equipment for intelligent body management based on artificial intelligence technology”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of computer technology, and in particular to an intelligent agent management method, apparatus and related equipment based on artificial intelligence technology. Background Art

[0003] An agent is an entity that can observe and make decisions in a given environment. For example, it can be implemented based on an artificial intelligence (AI) model. The agent has the ability to process data. In some scenarios, an agent can be used to complete tasks instead of a natural person. For example, an agent integrated with a natural language processing (NLP) model can be used to complete the task of writing an article instead of a natural person. For another example, an agent integrated with an image recognition model can be used to complete the task of finding key information in an image instead of a natural person. For another example, an agent integrated with a decision-making model can be used to complete the task of making a decision instead of a natural person.

[0004] However, the intelligent agent can only complete some relatively simple tasks and cannot complete tasks with higher complexity.

[0005] Summary of the Invention

[0006] In view of this, embodiments of the present application provide an agent management method based on artificial intelligence technology, which is used to complete tasks with high complexity using models. The present application also provides corresponding apparatuses, computing device clusters, computer-readable storage media, and computer program products.

[0007] In a first aspect, the present application provides an agent management method based on artificial intelligence technology. This method can be applied to a management platform that manages multiple agents to handle complex target tasks. Furthermore, each agent managed by the management platform is capable of handling at least one type of task based on artificial intelligence technology. Specifically, after obtaining a target task, a first agent and a second agent can be determined based on the target task. The first and second agents are agents managed by the management platform and are both capable of handling at least one type of task based on artificial intelligence technology. After determining the first and second agents, a dialogue chain can be generated to obtain a workflow for the first and second agents to handle the target task. The first and second agents can then be configured to handle the target task according to the dialogue chain. Specifically, for complex target tasks, multiple agents can be determined and a dialogue chain generated based on the task requirements. This allows each agent to only handle a portion of the target task, not the completed target task, eliminating the need for the agents to possess the ability to handle complex tasks. This allows multiple agents to collaborate with each other, fully utilizing their task-handling capabilities to handle complex tasks. In this way, even if the task to be completed is of high complexity, it can be completed through the cooperation between multiple intelligent agents, meeting the demand for completing tasks of high complexity through intelligent agents.

[0008] In some possible implementations, the first and second agents can be determined by parsing a target task. Specifically, the target task can be parsed first to determine its subtask information. This subtask information includes information about each of the multiple subtasks required to complete the target task. In other words, by parsing the target task, a more complex target task can be split into multiple less complex subtasks. For example, the subtasks can be tasks of a type that the agent can handle using artificial intelligence technology. Thus, the agent responsible for handling each subtask can be determined based on the information about each subtask. Specifically, if the multiple subtasks include a first subtask and a second subtask, the first subtask is a task of the first type, and the second subtask is a task of the second type. Based on the information about the first subtask in the subtask information, the first agent capable of handling the first type of task can be selected from the multiple agents managed by the management platform as the agent responsible for handling the first subtask. Similarly, based on the information about the second subtask in the subtask information, the second agent capable of handling the second type of task can be selected from the multiple agents managed by the management platform as the agent responsible for handling the second subtask. This approach breaks down complex target tasks into subtasks that can be handled by individual agents, providing a foundation for multiple agents to collaborate and solve the target task. Furthermore, selecting the appropriate agent for each subtask based on its ability to handle the subtask ensures that the selected agent has the ability to handle the target task, thus ensuring high-quality processing.

[0009] In some possible implementations, the subtask information includes not only the information of the subtasks, but also the information between the subtasks, and the information between the subtasks may include the association relationship between the subtasks. Accordingly, the management platform can generate a dialogue chain based on the association relationship between the above-mentioned subtasks, and specifically can generate a workflow for processing subtasks between the agents in the dialogue chain. Specifically, after determining the first agent and the second agent, the workflow for the first agent and the second agent to process the target task can be determined based on the association relationship between the subtask processed by the first agent (i.e., the first subtask) and the subtask processed by the second agent (i.e., the second subtask). In this way, by determining the workflow for the agent to process the target task based on the association relationship between the subtasks processed by the agent, the process for the agent to process the target task can be matched with the process for the subtask, thereby ensuring the processing quality of the target task.

[0010] In some possible implementations, the dialogue chain may also include a workflow for a single agent to process a subtask. The workflow for a single agent to process a subtask indicates the number of iterations in the process of the agent processing the corresponding subtask. When a certain agent processes the workflow of a subtask, the number of iterations in the process of the agent processing the subtask can be determined based on the agent's ability information for processing type tasks and the information of the subtask that needs to be processed. For example, for a first agent, the number of iterations in the process of the first agent processing the first subtask can be determined based on the first agent's ability information for processing the first type of task and the information of the first subtask. In this way, iterative processing based on the number of iterations can ensure that the agent's processing of the subtask meets the requirements of the target task and ensures the processing quality of the target task.

[0011] In some possible implementations, the workflow for a single agent to process a subtask can also be configured by the user. Specifically, the management platform can also obtain workflow configuration information. The workflow configuration information can indicate the target number of iterations for a subtask. Based on the workflow configuration information, the number of iterations of the agent corresponding to the subtask can be determined as the target number of iterations to determine the workflow for the agent to process the subtask. For example, if the workflow configuration information is used to indicate the target number of iterations for the second subtask, then the workflow for the second agent to process the second subtask can be determined based on the target number of iterations. The workflow for the second agent to process the second subtask indicates that the number of iterations in the process of the second agent processing the second subtask is equal to the target number of iterations. In this way, the user can flexibly set the number of iterations of one or more agents in the dialogue chain so that the processing of the target task meets their own needs.

[0012] In the implementation described above, the agent can be determined based on the subtask information. In other possible implementations, the agent can also be determined based on the target task. Specifically, multiple agent combinations can be preset, each agent combination includes at least one agent, and the agents in the agent combination can be used to process at least one type of task. The management platform can be used to manage the above-mentioned preset multiple agent combinations. After obtaining the target task, the target agent combination can be selected from multiple preset agent combinations based on the target task. The target agent combination can include a first agent and a second agent. In this way, it can be ensured that the selected agent combination has the ability to process the target task and the processing quality of the target task is guaranteed.

[0013] In some possible implementations, the agent can also be set by the user. Specifically, the management platform can also determine a third agent based on the target task. For example, the third agent can be determined based on the task configuration information of the target task. The third agent can be the agent set by the user when creating the target task and used to process the target task. Accordingly, when planning a dialogue chain, the planning can be based on the first agent, the second agent, and the third agent. In this way, the user can flexibly set the agent used to process the target task so that the processing of the target task meets their own needs.

[0014] In some possible implementations, in order to ensure the processing quality of the target task, the user can also perform verification during the processing of the target task. Specifically, after the management platform configures the first agent and the second agent, it can provide intermediate processing information. Intermediate processing information is intermediate information obtained during the processing of the target task. For example, the management platform can send intermediate processing information to the client so that the client can display the intermediate processing information to the user. If the user confirms that the intermediate processing information is correct, the user can trigger a confirmation operation on the intermediate processing information displayed by the client. The management platform can continue to process the target task based on the confirmation operation on the intermediate processing information. In this way, the user confirms the intermediate processing information, which can ensure that the processing of the target task is controllable and avoid situations such as "AI hallucinations".

[0015] In some possible implementations, there may be multiple agents with similar functions. Accordingly, the management platform can select a suitable agent to handle the target task based on the agent's evaluation index parameters. For example, there may be multiple agents that are capable of handling a first type of task. In this case, the management platform can select the agent with the best evaluation index parameters (e.g., the first agent) from the multiple agents to handle the target task. In some possible implementations, the evaluation index parameters of the target task can be adjusted based on the completion of the target task. Specifically, during or after processing the target task, the management platform can obtain feedback information. The feedback information can be used to indicate the completion of the target task by the first agent. Then, the evaluation index parameters of the first agent can be adjusted based on the feedback information. For example, if the first agent performs better in completing the target task, the evaluation index parameters of the first agent can be adjusted in a more optimal direction. In this way, feedback evaluation of the agents can optimize the management platform's strategy for selecting agents.

[0016] In a second aspect, the present application provides an agent management device based on artificial intelligence technology, the device being applied to a management platform, the management platform being used to manage multiple agents, each of the multiple agents being used to process at least one type of task based on artificial intelligence technology, the device comprising: an acquisition module for acquiring a target task; an agent determination module for determining a first agent and a second agent based on the target task, the first agent and the second agent belonging to the multiple agents; a dialogue chain generation module for generating a dialogue chain, the dialogue chain being used to instruct the first agent and the second agent to process the workflow of the target task; and an agent configuration module for configuring the first agent and the second agent so that the first agent and the second agent process the target task according to the dialogue chain.

[0017] In some possible implementations, the agent determination module is specifically used to parse the target task and determine the subtask information of the target task, where the subtask information includes information of multiple subtasks required to complete the target task, and the multiple subtasks include a first subtask and a second subtask; based on the information of the first subtask, the first agent is determined, wherein the first subtask is a first type of task among the at least one type of task, and the first agent is used to process the first type of task; based on the information of the second subtask, the second agent is determined, wherein the second subtask is a second type of task among the at least one type of task, and the second agent is used to process the second type of task.

[0018] In some possible implementations, the subtask information is used to describe the association relationship between the multiple subtasks, and the dialogue chain generation module is specifically used to determine the workflow of the first agent and the second agent in processing the target task based on the association relationship between the first subtask and the second subtask.

[0019] In some possible implementations, the dialogue chain further includes a workflow of the first agent processing the first subtask, where the workflow of the first agent processing the first subtask indicates the number of iterations in the process of the first agent processing the first subtask.

[0020] The dialogue chain generation module is further used to determine the number of iterations in the process of the first agent processing the first subtask based on the ability information of the first agent in processing the first type of task and the information of the first subtask.

[0021] In some possible implementations, the dialogue chain also includes a workflow for the second agent to process the second subtask, and the acquisition module is further used to obtain workflow configuration information, and the workflow configuration information is used to indicate the target number of iterations of the second subtask; the dialogue chain generation module is further used to determine the workflow for the second agent to process the second subtask based on the target number of iterations, and the workflow for the second agent to process the second subtask indicates that the number of iterations in the process of the second agent processing the second subtask is equal to the target number of iterations.

[0022] In some possible implementations, the management platform is also used to manage multiple preset agent combinations, and the agents in the agent combination belong to the multiple agents. The agent determination module is used to determine the target agent combination from the multiple preset agent combinations based on the target task, and the target agent combination includes the first agent and the second agent.

[0023] In some possible implementations, the agent determination module is also used to determine a third agent in response to an agent setting operation, and the dialogue chain is specifically used to instruct the first agent, the second agent and the third agent to process the workflow of the target task.

[0024] In some possible implementations, the device further includes a confirmation module, which is configured to provide intermediate processing information, where the intermediate processing information is intermediate information obtained during the processing of the target task; and continue processing the target task in response to a confirmation operation on the intermediate processing information.

[0025] In some possible implementations, the device also includes a feedback module, which is used to obtain feedback information, and the feedback information is used to indicate the completion status of the target task by the first intelligent agent; the evaluation index parameters of the first intelligent agent are adjusted according to the feedback information, and the evaluation index parameters of the first intelligent agent are used to select the first intelligent agent to process the task.

[0026] In a third aspect, the present application provides a computing device cluster, wherein the computing device includes at least one computing device, and the at least one computing device includes at least one processor and at least one memory; the at least one memory is used to store instructions, and the at least one processor executes the instructions stored in the at least one memory, so that the computing device cluster executes the intelligent agent management method based on artificial intelligence technology in the above-mentioned first aspect or any possible implementation of the first aspect. It should be noted that the memory can be integrated into the processor or can be independent of the processor. The at least one computing device may also include a bus. The processor is connected to the memory via a bus. The memory may include a readable memory and a random access memory.

[0027] In a fourth aspect, the present application provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on at least one computing device, the at least one computing device executes the method described in the first aspect or any implementation of the first aspect.

[0028] In a fifth aspect, the present application provides a computer program product comprising instructions, which, when executed on at least one computing device, enables the at least one computing device to execute the method described in the first aspect or any one of the implementations of the first aspect.

[0029] Based on the implementation methods provided in the above aspects, this application can also be further combined to provide more implementation methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0031] FIG1a is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0032] FIG1b is a schematic diagram of another application scenario provided by an embodiment of the present application;

[0033] FIG2a is a flow chart of an agent management method based on artificial intelligence technology provided in an embodiment of the present application;

[0034] FIG2 b is another flow chart of an agent management method based on artificial intelligence technology provided in an embodiment of the present application;

[0035] FIG3 is a schematic diagram of a process for processing a target task according to an embodiment of the present application;

[0036] FIG4 is a schematic structural diagram of an intelligent agent management device based on artificial intelligence technology provided in an embodiment of the present application;

[0037] FIG5 is a schematic diagram of a structure of a computing device provided in an embodiment of the present application;

[0038] FIG6 is a schematic diagram of a structure of a computing device cluster provided in an embodiment of the present application;

[0039] FIG7 is a schematic diagram of an implementation method of a computing device cluster provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] The following will describe the solutions in the embodiments provided in this application in conjunction with the drawings in this application.

[0041] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate and are merely used to describe the manner in which objects with the same attributes are described in the embodiments of this application.

[0042] First, the nouns involved in the embodiments of the present application are introduced.

[0043] Cloud service system: The cloud service system consists of a client and a server. Users can publish tasks through the client. Tasks published by the client can be processed by the server.

[0044] Management Platform: Integrated into the server side of the cloud service system, it has the ability to manage multiple agents. After receiving tasks issued by clients, the management platform can call one or more agents to process the tasks.

[0045] Task: A pending task published by a user through a client (or other means). Optionally, a user may publish a task in the form of task-related information. For example, a user may enter task-related information on a client. The server may receive the task-related information and process the task. In embodiments of the present application, analyzing and / or processing a task may include analyzing and / or processing the task-related information.

[0046] An AI agent is an entity capable of observing and making decisions within a given environment. For example, it can be implemented based on an artificial intelligence (AI) model. An AI agent possesses the ability to process data. Specifically, it can output a specific type of data based on a certain type of input data. In embodiments of the present application, an AI agent can process at least one type of task based on AI technology.

[0047] Dialogue chains are the rules for information exchange between agents when multiple agents are called to complete a task. Dialogue chains indicate the workflow of agents when they complete a task. Dialogue chains can indicate workflows between multiple agents or between individual agents.

[0048] Workflow: refers to the abstract summary of the business rules between the processing flow and its various operation steps. In the embodiment of the present application, the workflow indicated by the dialogue chain is used to describe the rules for information exchange between one or more agents when processing tasks. The workflow between multiple agents refers to the connection relationship between multiple agents. For two interconnected workflows, the output data of one agent can be used as the input data of another agent. The dialogue chain between a single agent can also be called the number of iterations of the agent, which indicates the number of iterative processing performed by a single agent. Iterative processing refers to re-inputting the output data of an agent into the agent as its own input data. Through iterative processing, the accuracy of data processing can be improved.

[0049] With the development of computer technology, intelligent agents, including AI models, have been widely used in many fields. Due to the integration of AI models, intelligent agents are highly efficient and have fast processing speeds, enabling them to replace humans in certain application scenarios. For example, in areas such as article writing, code development, and image processing, using intelligent agents to replace humans offers significant advantages.

[0050] In particular, to meet the needs of certain application scenarios, the capabilities of the intelligent agent can be enhanced. The enhanced intelligent agent may have stronger processing capabilities in certain areas and can better handle certain types of tasks. For example, for natural language processing tasks, the intelligent agent's NLP capabilities can be enhanced, and the enhanced intelligent agent can better process natural language. For another example, for image processing tasks, the intelligent agent's image processing capabilities can be enhanced, and the enhanced intelligent agent can better process images. For another example, for decision-making tasks, the intelligent agent's decision-making capabilities can be enhanced, and the enhanced intelligent agent can better make decisions. Strengthening the model can be achieved, for example, by optimizing the model structure and adjusting the training dataset, which will not be detailed here.

[0051] However, due to the limitations of technological development, it is often possible to strengthen the processing capabilities of intelligent agents only in one or more directions, rather than in all directions. This results in intelligent agents often having relatively narrow capabilities, suitable only for completing certain types of tasks. For example, an intelligent agent with NLP capabilities can complete tasks related to natural language processing, but struggles with tasks related to image processing; an intelligent agent with image processing capabilities can complete tasks related to image processing, but struggles with tasks related to natural language processing; and a model with decision-making capabilities can make decisions, but struggles with tasks related to image processing or natural language processing.

[0052] In real-world scenarios, there may be some highly complex tasks. These tasks may include multiple subtasks. Different subtasks may require different processing capabilities. Therefore, a single model may not be able to complete such complex tasks.

[0053] For example, the task of "developing code according to requirements" can be divided into multiple subtasks, including "understanding code development requirements," "developing code," "testing the developed code," "adjusting the code based on test results," and "generating documentation based on the developed code." Different subtasks require different processing capabilities and cannot be implemented by a unified agent. For example, the subtask "understanding code development requirements" may require the agent to have natural language processing capabilities. The subtask "developing code" may require the agent to have the ability to automatically generate code, and the subtask "testing the developed code" may require the agent to have decision-making capabilities to select appropriate test cases. Due to technological limitations, integrating these functions into a single agent is difficult.

[0054] It can be seen that the current intelligent agents are only suitable for completing tasks with lower complexity and cannot complete tasks with higher complexity.

[0055] Based on this, embodiments of the present application provide an agent management method based on artificial intelligence technology. This method can select multiple agents based on the target task to be processed, thereby handling more complex target tasks. Specifically, for a management platform that manages multiple agents, after obtaining the target task, a first agent and a second agent can be determined based on the target task. The first agent and the second agent are agents managed by the management platform, and both are capable of processing at least one type of task based on artificial intelligence technology. After determining the first agent and the second agent, a dialogue chain can be generated to obtain a workflow for the first and second agents to process the target task. The first and second agents can then be configured to process the target task according to the dialogue chain. In other words, for more complex target tasks, multiple agents can be determined based on the task requirements and a dialogue chain can be generated. In this way, each agent only needs to process a portion of the target task, not the completed target task, which eliminates the need for the agents to have the ability to handle complex tasks. In this way, multiple agents can be used to cooperate with each other, fully utilizing the agents' task-processing capabilities to handle more complex tasks. In this way, even if the task to be completed is of high complexity, it can be completed through the cooperation between multiple intelligent agents, meeting the demand for completing tasks of high complexity through intelligent agents.

[0056] Next, various non-limiting specific implementations of the process of processing tasks are described in detail.

[0057] First, taking the cloud service scenario as an example, the application scenario of the intelligent agent management method based on artificial intelligence technology provided by the embodiment of the present application is introduced.

[0058] Referring to FIG. 1a , FIG. 1a is a schematic diagram illustrating an application scenario of an agent management method based on artificial intelligence technology provided in an embodiment of the present application. The application scenario shown in FIG. 1a includes a user 10, a terminal device 20, a cloud service system 30, an agent 41, an agent 42, and an agent 43. The cloud service system 30 includes a client 31 and a server 32. The client 31 can be software running on the terminal device 20. The server 32 includes a management platform 321. The management platform 321 is used to manage agents 41, 42, and 43.

[0059] The user 10 can call the task processing service provided by the cloud service system 30 through the client 31. Specifically, the user 10 can input relevant information of the target task on the client 31. The client 31 can send the relevant information of the target task to the server 32. The management platform 321 in the server 32 can execute the intelligent agent management method based on artificial intelligence technology provided in the embodiment of the present application to call one or more intelligent agents to process the target task proposed by the user 10. The one or more intelligent agents can include any one or more of the intelligent agents 41, 42 and 43, and can also include other intelligent agents.

[0060] Optionally, the agents managed by management platform 321 (e.g., agent 41, agent 42, and agent 43) can be integrated into cloud service system 30 or can be independent of cloud service system 30. For example, agent 41 can run on server 32 of cloud service system 30. Agent 42 can be independent of cloud service system 30. When management platform 321 manages agent 42 or calls agent 42 to process a task, management platform 321 can exchange information with agent 42 via the network.

[0061] In an embodiment of the present application, the cloud service system 30 can provide multiple types of cloud services to the user 10. Moreover, the multiple types of cloud services include task processing type cloud services. Optionally, the cloud service system 30 can also be a cloud computing system. Accordingly, the cloud services provided to the user 10 by the cloud service system 30 can include cloud computing type services. Optionally, the management platform 321 can be implemented in software. For example, it can be implemented in software running on one or more computing devices. If the management platform 321 runs on multiple computing devices, the multiple computing devices can belong to the same region or different regions.

[0062] The following is a detailed introduction to the specific implementation of the intelligent agent management process based on artificial intelligence technology.

[0063] Refer to Figure 2a, which is a flow chart of the intelligent agent management method based on artificial intelligence technology provided in an embodiment of the present application. The method can be specifically executed by a management platform. The management platform can run on the server side of the cloud service system, and is used to call the intelligent agent to process the task. The management platform can also be called an intelligent agent management device based on artificial intelligence technology. Optionally, the method can be applied to the application scenario shown in Figure 1a above, or it can also be applied to other applicable application scenarios. If the method runs in the application scenario shown in Figure 1a, the method can be implemented by the management platform 321. If the intelligent agent management method based on artificial intelligence technology shown in Figure 2a is implemented by the management platform 321, the management platform can be as shown in Figure 1b. The following is an example of application to the application scenario shown in Figure 1a.

[0064] Specifically, the agent management method based on artificial intelligence technology shown in FIG2a may include:

[0065] S201: Obtain target tasks.

[0066] If a user wants to call an agent to handle a target task, they can send the target task to the management platform through the client. The management platform can obtain the target task, generate a dialogue chain based on the target task, and call the agent to handle the target task.

[0067] In an embodiment of the present application, the management platform obtaining the target task may include the management platform obtaining relevant information about the target task. The relevant information about the target task may be relevant information input by the user through the client to describe the target task. Optionally, the relevant information about the target task may also be referred to as task configuration information of the target task.

[0068] The task configuration information of the target task is used to describe the relevant configuration of the target task. Based on the task configuration information, the management platform can determine what kind of task the target task to be processed is and what capabilities are required to process the target task. For example, the task configuration information of the target task can be used to describe the input and output of the target task, and can also be used to describe the requirements during the process of processing the target task. Optionally, if the target task includes multiple links, the task configuration information of the target task can also include the configuration information corresponding to each link. The configuration information corresponding to the link can be used to describe the input of this link, the output of this link, and the requirements during the process of processing the task of this link.

[0069] In an embodiment of the present application, the task configuration information of the target task may include the to-be-processed data corresponding to the target task, so that the server can process the target task. In addition, the task configuration information of the target task may also include multiple configuration information of the target task, for example, any one or more of the workflow configuration information of the target task, the role configuration information of the target task, and the agent configuration information of the target task. Each of these is introduced below.

[0070] First, the workflow configuration information is introduced.

[0071] The workflow configuration information of the target task is used to describe the workflow of the target task. The workflow of the target task refers to the subtasks that need to be completed by multiple participants in order to process the target task, as well as the rules for information interaction between participants. Optionally, if the target task is originally completed by multiple natural persons, then the above-mentioned "participants" can be natural persons, and the workflow information of the target task can be the subtasks that multiple natural persons need to complete respectively when processing the target task, as well as the rules for interaction between natural persons. In this way, the workflow configuration information in the process of natural persons processing the target task is used as the task configuration information of the target task, so that the intelligent agent determined in the subsequent steps can simulate the natural person to process the target task.

[0072] For example, assuming the target task is a code development task, the task configuration information for the target task may include workflow configuration information for code development tasks. Specifically, this information may include information about the personnel required during the code development process, the work required by each person during the code development process, and information about interactions between these personnel during the code development process. The personnel information required during the code development process can be used to describe the personnel involved in the code development process, such as an executive, product manager, architect, code writer, tester, and user interface (UI) designer. The work required by each person during the code development process can be used to describe what each of these multiple personnel needs to complete, such as a product manager needs to perform requirements analysis, an architect needs to provide a code architecture, a code writer needs to write code, and a tester needs to test the code. The interaction information between these multiple personnel during the code development process can be used to describe the interaction process between these multiple personnel, such as the interaction process of a product manager sending requirements to a code writer, the interaction process of a code writer sending code to a tester after writing it, and the interaction process of a tester sending test results to the code writer after completing the test.

[0073] Optionally, the workflow configuration information may further include process attribute configuration information. The process attribute configuration information may be used to describe attributes related to the processing flow of the target task, indicating the user's specific requirements for the processing flow of the target task.

[0074] In some possible implementations, process attribute configuration information may include information describing specific rules for information exchange between roles or agents. In other words, a user can set the rules for information exchange between two agents within a process. Alternatively, a user can set the number of times information exchanges can occur between agents, or set the specifications for prompts used during information exchange between agents.

[0075] For example, in the process of code development by a team of natural persons, multiple interactions may be required between code writers and testers to identify possible problems in the code and optimize them. Accordingly, the user can instruct the agent used to complete the subtasks completed by the "code writer" in the target process through the process attribute configuration information to interact multiple times with the agent used to complete the subtasks completed by the "tester". Specifically, the process attribute configuration information may include dialogue turn information, which corresponds to the rounds of interaction between the above two agents, and specifically may include the number of dialogues between the agent used to complete the subtasks completed by the "code writer" and the agent used to complete the subtasks completed by the "tester".

[0076] In some possible implementations, the process attribute configuration information may include requirement information describing the overall process flow. In other words, if a user has specific requirements for a specific process flow, they can include these requirements in the process attribute configuration information and send it to the server. The server can then interpret the user's requirements, determine the interaction relationships between agents based on these requirements, and establish the target process flow.

[0077] For example, in traditional code development, there are various development methodologies, including waterfall, extreme programming, and agile. Different development methodologies can employ different methods of interaction between individuals, and the information conveyed during these interactions can also vary. When publishing a target task, users can select a development method based on their needs. Process attribute configuration information can include the identifier of the selected development method. When creating a process flow, users can deploy interactions between agents based on the identifier of the selected development method and define the information conveyed during these interactions.

[0078] The following describes the role configuration information.

[0079] In an embodiment of the present application, the determination of the agent may rely on the role. That is, the management platform may first determine the role played by the agent, and then select a suitable agent to play the corresponding role. In some possible implementations, the above-mentioned role may be obtained by parsing the workflow configuration information or other configuration information of the target task by the server. Alternatively, in some other possible implementations, the task configuration information of the target task may also include role configuration information. The role configuration information is the relevant information given by the user who publishes the target task to describe one or more specific roles. In this way, the user can freely set the role corresponding to the target task, which increases the flexibility of processing the target task and enhances the user experience.

[0080] In other words, if a user wishes to specify the characteristics of a role (or roles) within the target task's processing flow, the task configuration information published by the user can include role configuration information. Role configuration information can be used to describe the attributes of the role, indicating the user's specific requirements for the role. Alternatively, role configuration information can be used to describe the role's capabilities or the hierarchical relationships between roles.

[0081] For example, assuming the target task is a code development task, the roles may include a role responsible for code development. To improve the efficiency of code development and the performance of the developed code, the task configuration information for the target task may include configuration information for the role responsible for code development. For example, it may include information describing the role as "having strong code development capabilities" or "having extensive software development experience in a certain programming language." For another example, in the code development process, the role corresponding to "executive" may be responsible for coordinating and scheduling various personnel during the code development process. The role configuration information for the target task may include information describing the role as "having the ability to coordinate and schedule." For another example, assuming the target task is a legal document writing task, the target task may include roles corresponding to junior lawyers, intermediate lawyers, and senior lawyers. The role configuration information for the target task may include information describing the role as "having the ability to evaluate documents provided by junior lawyers" and "having the ability to evaluate documents provided by intermediate and junior lawyers."

[0082] The following describes the agent configuration information.

[0083] In an embodiment of the present application, the target task can be processed by one or more agents. In some possible implementations, the above-mentioned agent can be obtained by parsing the server according to the task configuration information of the target task. Alternatively, in some other possible implementations, the user can specify the specific information of the agent. In an embodiment of the present application, the information specified by the user for describing the agent can be called agent configuration information. In this way, the user can freely set the role of processing the target task, which increases the flexibility of processing the target task and enhances the user experience.

[0084] In other words, if a user wants to specify a specific agent (or multiple agents) or their characteristics within the target task's processing flow, the task configuration information published by the user can include agent configuration information. Agent configuration information can be used to specify an agent or describe its attributes, indicating the user's specific requirements for the agent.

[0085] In the embodiment of the present application, the user can configure the agent configuration information by triggering the agent setting operation. That is, the user can trigger the agent setting operation on the client to set one or more specific agents in the process of processing the target task.

[0086] The above describes the task configuration information of the target task. The following describes how to obtain the task configuration information of the target task.

[0087] In an embodiment of the present application, the task configuration information of the target task can be set by the user. Specifically, if the server provides the user with the function of processing tasks in the form of a cloud service, then the user can set the task configuration information of the target task on the client. After the user confirms the use of the cloud service for processing tasks, the client can send the task configuration information of the target task to the server. That is, in the implementation shown in Figure 1a, the user 10 can input the task configuration information of the target task on the client 31. The client 31 can send the task configuration information of the target task to the server 32 via the network, so that the management platform 321 in the server 32 can obtain the target task.

[0088] In an embodiment of the present application, a user may set task configuration information of a target task on an interface of a client.

[0089] For example, if the task configuration information of the target task includes workflow configuration information, the user can input or import the workflow configuration information on the client interface. Specifically, the user can pre-plan the workflow corresponding to the target task, and then import the workflow into the client so that the client can obtain the workflow configuration information of the target task. Optionally, the user can import the workflow file into the client to obtain the workflow configuration information of the target task. Alternatively, the client can also display a workflow editing interface, and the user can mark the workflow in the workflow editing interface. Alternatively, the user can also describe the workflow corresponding to the target task in natural language or non-natural language. The information input by the user to describe the workflow corresponding to the target task can be regarded as the aforementioned workflow configuration information.

[0090] For another example, if the task configuration information of the target task includes process attribute configuration information, the user can input the process attribute configuration information on the client. Specifically, the client can display an input box to the user, and receive the process attribute configuration information input by the user through the input box. Alternatively, one or more optional process attribute configuration information can be pre-set. If the user wants to call the intelligent agent to process the target task, the client can display a menu to the user, and the menu includes the above-mentioned pre-set optional process attribute configuration information. The user can select the process attribute configuration information through the menu. For example, if the server provides software development services, the process attribute configuration information can be set in advance according to the above-mentioned multiple development methods. When the user wants to use the intelligent agent for software development, the user can select the required development method from the pre-set development methods in the menu.

[0091] For another example, if the task configuration information of the target task includes role configuration information, the user can enter the role configuration information on the client. Specifically, the client can also display an input box, and the user can manually enter a natural language description of the role through the input box. The natural language description corresponds to the role configuration information. Alternatively, the user can also set the role configuration information based on the workflow configuration information. For example, the user can set the role configuration information in the workflow editing interface. Alternatively, one or more optional role configuration information can be pre-set. If the user wants to call the intelligent agent to process the target task, the client can display a menu to the user, and the menu includes the above-mentioned pre-set optional role configuration information. The user can select the role configuration information through the menu.

[0092] For another example, if the target task's task configuration information includes agent configuration information, the user can enter the agent configuration information on the client. Specifically, the client can present a menu to the user, including information about one or more selectable agents. The user can set the agent configuration information through the menu. Alternatively, the agent configuration information can be set through other methods. The specific setting method can be found in the above description of role configuration information discrepancies and will not be repeated here.

[0093] It should be noted that the above-mentioned implementation method of obtaining the task configuration information of the target task is only an example. In actual scenarios, the task configuration information of the target task can also be obtained through other methods.

[0094] S202: Determine a first agent and a second agent according to the target task.

[0095] After obtaining the target task, the management platform can determine the first agent and the second agent based on the target task, so as to utilize the first agent and the second agent to process the target task. The first agent and the second agent are both agents managed by the management platform, and both can be used to process at least one type of task based on artificial intelligence technology.

[0096] Optionally, the type of tasks that the first agent can handle can be the same as or different from the type of tasks that the second agent can handle. In the embodiment of the present application, to process the target task, it is necessary to process the type of tasks that the first agent can handle, as well as the type of tasks that the second agent can handle. Therefore, the management platform can complete the processing of the target task by configuring the first agent and the second agent to respectively process various corresponding types of tasks when processing the target task.

[0097] Among them, the first intelligent agent is used to process at least one type of task based on artificial intelligence technology, which means that the first intelligent agent has the ability to process the above-mentioned "at least one type of task". In the embodiment of the present application, the first intelligent agent can be said to correspond to the above-mentioned "at least one type of task". That is, the intelligent agent has the ability to process its corresponding type of task. For example, if the first intelligent agent integrates an NLP model, then the first intelligent agent can be used to process natural language recognition type tasks or natural language generation type tasks based on artificial intelligence technology; if the first intelligent agent integrates an image recognition model, then the first intelligent agent can be used to process image recognition type tasks based on artificial intelligence technology.

[0098] Optionally, the correspondence between agents and task types can be obtained when registering the agent. This section is described below and will not be repeated here.

[0099] The following describes how the management platform determines the first agent and the second agent.

[0100] Implementation method (1): The management platform determines the first agent and the second agent by selecting an agent combination.

[0101] In a first implementation, the first agent and the second agent may belong to the same agent group. The management platform may determine an agent combination including the first agent and the second agent based on the target task.

[0102] Specifically, multiple agent combinations can be pre-set. Each agent combination can include multiple agents. Moreover, each agent combination can be used to process a preset type of task. The preset type can be a pre-configured function of the management platform. The agent combination is an agent combination obtained by analyzing the preset type of task. The agent corresponding to the agent combination can process the preset type of task corresponding to the agent combination. Accordingly, after obtaining the target task, the agent combination that matches the target task can be selected from multiple preset agent combinations according to the target task, so as to use the agent combination to process the target task. In this way, it can be ensured that the selected agent combination has the ability to process the target task and the processing quality of the target task can be guaranteed.

[0103] That is to say, assuming that the cloud service system provides users with task processing functions, then before providing users with type A task processing functions, type A tasks can be analyzed in advance to determine which types of agents are needed to process type A tasks, and then agent combination a can be established based on these agents. Similarly, before providing users with type B task processing functions, type B tasks can be analyzed in advance to determine which types of agents are needed to process type B tasks, and then agent combination b can be established based on these agents. In this way, if a user needs to process type A tasks, the management platform can select agent combination a from multiple preset agent combinations (including agent combination a and agent combination b). In this way, by setting the agent combination in advance according to the requirements of the task, the agent combination selected by the management platform has the ability to process the task.

[0104] Optionally, the agent combination may include the identifier of the first agent and the identifier of the second agent. That is, when setting the agent combination, a certain agent (or a plurality of agents) in the agent combination may be pre-set.

[0105] Alternatively, optionally, the agents in the agent combination may also be selected by the management platform. Accordingly, when processing the target task, the management platform may first select an agent combination template based on the target task. There may be one or more items to be configured in the agent combination template. Each item to be configured corresponds to one or more optional agents. Then, the management platform may determine the specific value corresponding to each item to be configured in the agent combination template to obtain an agent combination including a specific agent. Among them, each item to be configured in the agent combination template corresponds to one or more tasks that need to be completed by the agent. The optional agent corresponding to the item to be configured has the ability to complete the task corresponding to the item to be configured.

[0106] Let's take an example. Suppose natural language processing is required in the process of processing the target task. Then the agent combination template corresponding to the target task can include item A to be configured. Item A to be configured corresponds to the above-mentioned "natural language processing" step, and the optional agents corresponding to item A to be configured all have the ability of natural language processing. When determining the agent combination corresponding to the target task, the management platform can select an agent from multiple agents as the agent actually corresponding to item A to be configured based on the actual situation of the target task, so as to use this agent to complete the relevant part of natural language processing in the process of processing the target task.

[0107] Regarding the method of selecting an agent from multiple optional agents, please refer to the introduction of the section on selecting an agent based on subtask information below, which will not be repeated here.

[0108] Implementation method (2): The management platform determines the first agent and the second agent based on the subtask information.

[0109] In a second implementation, the management platform can parse the target task to determine the first and second agents. By parsing the target task, the management platform can determine the conditions required to complete the target task and, based on these conditions, determine the agent to handle the target task. As previously mentioned, the agents managed by the management platform are capable of handling at least one type of task using artificial intelligence technology.

[0110] Specifically, when determining the intelligent agent for processing the target task, the management platform can first parse the target task, split the target into multiple subtasks, obtain the subtask information of the target task, and then determine the intelligent agent based on the subtask information of the target task.

[0111] The subtask information of a target task indicates the subtasks required to complete the target task. That is, the subtask information can include information about each subtask. Subtask information describes the subtasks that an agent needs to complete. A subtask is a task that an agent needs to complete. Each subtask can be completed by an agent, and an agent can complete one or more subtasks. In other words, a subtask is a task that a single agent can complete.

[0112] If the target task includes multiple subtasks, the subtask information may also include information between the subtasks. This information between subtasks can be used to describe the relationships between the subtasks and to generate a conversation chain. In other words, to complete the target task, each subtask must be completed separately according to the relationships between them. Optionally, the relationships between subtasks may also include the information exchange process between the subtasks.

[0113] Optionally, if the task configuration information of the target task includes workflow configuration information, the subtask information can be determined based on the workflow configuration information. Specifically, the information between subtasks in the subtask information can be used to determine based on the workflow configuration information. According to the foregoing introduction, the workflow configuration information can be used to describe the subtasks that a natural person needs to complete in the process of processing the target task. When determining the subtask information, the subtasks that need to be completed in the process of a natural person processing the target task can be referred to to determine the subtasks that need to be completed in the process of an intelligent agent processing the target task. Optionally, the subtask processed by each natural person can be determined as a subtask in the subtask information, or the subtasks completed by a single natural person can be split.

[0114] In some possible implementations, the server can determine subtask information through an agent. That is, the management platform can integrate an agent or have the function of calling an agent, so that the agent can be used to determine the subtask information corresponding to the target task. As mentioned above, the task configuration information of the target task may include relevant information based on natural language descriptions. Accordingly, when determining the subtask information of the target task, an agent with NLP capabilities can be called to process the natural language-related portion of the task configuration information, converting the task configuration information into structured language before subsequent processing.

[0115] For example, a management platform can call an agent over the network to determine subtask information. Specifically, the management platform can generate a prompt message based on the task configuration information of the target task and then send this prompt message to the agent. The agent can parse the task configuration information in the prompt message and return the subtask information to the management platform.

[0116] After determining the subtask information, the corresponding agent for each subtask can be determined based on the subtask information. The agent corresponding to the subtask is used to complete the subtask. That is, if the multiple subtasks obtained by splitting the target task include a first subtask and a second subtask, the management platform can determine the first agent based on the information of the first subtask and the second agent based on the information of the second subtask. The first agent has the ability to complete the type of task corresponding to the first subtask, and the second agent has the ability to complete the type of task corresponding to the second subtask.

[0117] That is to say, the management platform can select an agent (i.e., the first agent) from multiple agents that has the ability to complete the type of task corresponding to the first subtask based on the information of the first subtask, and can select an agent (i.e., the second agent) from multiple agents that has the ability to complete the type of task corresponding to the second subtask based on the information of the second task.

[0118] For ease of explanation, the type of task corresponding to the first subtask is referred to as the first type of task, and the type of task corresponding to the second subtask is referred to as the second type of task. That is, the first subtask is a first type of task among at least one type of task, and the first agent is used to process the first type of task. The second subtask is a second type of task among at least one type of task, and the second agent is used to process the second type of task. That is, if multiple subtasks include a first subtask and a second subtask, the first subtask is a first type of task, and the second subtask is a second type of task. Then, based on the information of the first subtask in the subtask information, the first agent that can be used to process the first type of task can be selected from the multiple agents managed by the management platform as the agent for processing the first subtask. Similarly, based on the information of the second subtask in the subtask information, the second agent that can be used to process the second type of task can be selected from the multiple agents managed by the management platform as the agent for processing the second subtask.

[0119] In some possible implementations, the roles corresponding to the subtasks can be determined based on the subtask information, and then the agents can be determined based on the roles. This is described in detail below.

[0120] Specifically, after determining the subtask information, the management platform can parse the subtask information to determine the conditional information for multiple roles. A role refers to a role that completes a subtask, and an agent is responsible for playing the role to complete the corresponding subtask. The conditional information for a role indicates the conditions required to play the role, i.e., the conditions required to complete the subtask corresponding to the role. Optionally, the step of determining the conditions for multiple roles based on the subtask information can be implemented by the agent.

[0121] In scenarios where a natural person handles a target task, the natural person can play one or more roles to complete the subtasks corresponding to the role. In the embodiments of the present application, however, an agent can play a role to complete the subtasks corresponding to the role. In other words, the condition information of a role is used to indicate the conditions that the agent must meet to play the role. It is understood that "playing a role" here means playing the role in the process of handling the target task.

[0122] As previously mentioned, the target task's task description information can include role configuration information. Accordingly, when determining a role's condition information, this can be combined with the role configuration information and subtask information. Specifically, the corresponding condition information for a role can be determined based on the subtasks the role completes, while also being determined based on user instructions. This ensures that the determined condition information not only reflects the ability to complete the subtasks required of the role but also meets the user's needs.

[0123] After determining the condition information of multiple roles, the agent corresponding to the role can be determined based on the agent's condition information. In the process of processing the target task, the agent corresponding to the role can play the role to complete one or more subtasks required to be completed by the role. For example, in the implementation shown in Figure 1a, the management platform 321 can select an agent from agent 41, agent 42 and agent 42 based on the condition information of the role to play the role corresponding to the condition information. Optionally, the step of determining the agent based on the condition information of the role can be implemented by the agent. Optionally, the agent used to determine the agent based on the condition information of the role and the aforementioned agent used to parse the target task to determine the subtask information can be the same agent or different agents.

[0124] In the implementation described above, the agent determined based on the conditional information is able to meet the requirements of the conditional information. That is, if the conditional information indicates the conditions required to complete the subtasks that the agent is to perform, then the agent determined based on the conditional information satisfies the conditions indicated by the conditional information. Therefore, the agent has the ability to complete the subtasks required of the role, and the agent is able to play that role while processing the target task, completing one or more subtasks within the target task. The agent's ability to complete subtasks refers to the agent's data processing capabilities.

[0125] In other words, the target task can be broken down into multiple subtasks, and the conditions required to complete each subtask can be determined. Based on these conditions, appropriate agents can then be selected to complete the subtasks. Once multiple agents have been identified, they can each complete the subtasks that comprise the target task, thereby completing the task. This breaks down complex target tasks into subtasks that can be handled by a single agent, providing a foundation for multiple agents to collaborate and solve the target task. Furthermore, selecting the appropriate agent for each subtask based on its ability to handle the subtask ensures that the selected agent has the capability to handle the target task, guaranteeing high-quality processing.

[0126] Similar to the conditional information used to determine roles, if the target task's task configuration also includes agent configuration information, then, when there are multiple agents, the corresponding role can be determined by combining the agent configuration information and the role's conditional information. In other words, the agent that completes the subtasks can be determined based on the conditions required to complete them, while the corresponding conditional information for the role can be determined based on user instructions. This way, the determined conditional information not only provides the ability to complete the subtasks required of the role, but also meets the user's needs.

[0127] In some possible implementations, an agent description database can be pre-established. Thus, when determining an agent based on conditional information, an agent that meets the conditional information can be selected from the agent description database. Specifically, the agent description database can store agent description information for multiple agents. The agent description information for an agent can include information such as the agent's capabilities, input and output information, and call information.

[0128] The agent's capability information can be used to describe the agent's processing capabilities. The agent's processing capabilities can include the types of data the agent is adept at processing. When selecting an agent based on conditional information, the agent's capability information can be referenced to select an agent capable of handling subtasks. In other words, to determine the agent corresponding to role A, the agent description database can be searched based on role A's conditional information to identify an agent capable of handling the subtask required by role A.

[0129] Optionally, the agent's capability information can also be used to describe the strength of the agent's processing capabilities. Optionally, the strength of the agent's processing capabilities can be reflected in information such as the speed at which the agent processes data, the volume and / or complexity of the data the agent can process, and the accuracy with which the agent processes data. Accordingly, if multiple agents are capable of processing the subtask required by role A, the agent with the strongest capability for processing the subtask required by role A can be selected based on the agent's capability information as the agent that will play role A when processing the target task.

[0130] The input and output information of the agent can be used to describe the input and output conditions of the agent. In an embodiment of the present application, the processing of the target task can be achieved through information interaction between agents. Accordingly, in order to achieve information interaction between agents, the input and output of the agent can be adaptively configured so that the message sent by the upstream agent can be processed by the downstream agent. Optionally, the input and output information of the agent can, for example, include the specification of the prompt information of the agent. For an introduction to the input and output information of the agent, please refer to the following text and will not be repeated here.

[0131] The calling information of the agent may include relevant information for calling the agent, for example, the calling interface of the agent. When the agent is used to process a target task, the agent can be called through the calling interface of the agent to complete the processing of the target task. Optionally, the agent can be deployed in the cloud service system or outside the cloud service system. If the agent and the server belong to the same cloud service system, the calling information of the agent may include the internal interface of the agent. If the agent and the server belong to different systems, the calling information of the agent may include the external interface of the agent.

[0132] In addition to the three types of information mentioned above, the agent description information of an agent can also include the agent's evaluation index parameters. The agent's evaluation index parameters indicate the quality of the agent's ability to handle tasks. For example, a higher agent's evaluation index parameter indicates a stronger agent's ability to handle tasks. Accordingly, when selecting an agent, the agent's evaluation index parameters can be combined to make the selection. Specifically, if there are multiple agents that meet the conditions for the same role, the agent's evaluation index parameters can be referenced to select the agent with the strongest ability to handle subtasks as the agent to play that role.

[0133] That is, assuming that the aforementioned multiple roles include role A, then when determining the agent corresponding to role A, one or more candidate agents can first be determined based on the condition information of role A. Each candidate agent can meet the requirements of the condition information of role A. Then, based on the evaluation index parameters of the candidate agents, a candidate agent can be selected from the multiple candidate agents as the agent corresponding to role A. It is understood that if only one candidate agent is determined based on the condition information of role A, this candidate agent can be used as the agent corresponding to role A without referring to the evaluation index parameters of role A.

[0134] In some possible implementations, the evaluation index parameters of the agent can be obtained by the user who requests to call the agent. For example, after calling multiple agents to process the target task, the user who issued the target task can score each of the multiple agents. Based on the user's score for the agent, the evaluation index parameters of the agent in the agent description database can be updated. Alternatively, in some other possible implementations, the evaluation index parameters of the agent can be obtained during the operation of the agent. For example, in the process of processing the target task by multiple agents, the processing status of each agent processing the subtask can be monitored, so that the agent can be scored according to the processing status, and the evaluation index parameters can be updated according to the score of the agent. For an introduction to this part, please refer to the following and will not be repeated here.

[0135] It should be noted that the two implementation methods for determining the first agent and the second agent described above are only examples. In actual application scenarios, agents can also be determined based on other implementation methods.

[0136] For example, in some possible implementations, the agent can also be determined based on the user's designation. Optionally, the user can specify that the management platform use a specific agent to process the target task when creating the target task. Accordingly, the management platform can determine the agent based on the target task. For example, if the task configuration information of the target task includes agent configuration information, and the agent configuration information instructs the management platform to process the target task through a third agent, then the management platform can determine the third agent based on the agent configuration information. Accordingly, the dialogue chain determined below is specifically used to indicate the workflow of the first agent, the second agent, and the third agent to process the target task. In this way, the user can flexibly set the agent used to process the target task so that the processing of the target task meets their own needs.

[0137] S203: Generate a dialogue chain.

[0138] After the first agent and the second agent are determined, a dialogue chain can be generated based on the first agent and the second agent so as to call the first agent and the second agent to process the target task according to the dialogue chain.

[0139] Among them, the dialogue chain can be used to indicate the workflow between agents or the workflow of a single agent.

[0140] The inter-agent workflow is used to describe the information exchange relationship between multiple agents during task processing. For example, in the implementation corresponding to Figure 2a, the management platform processes the target task through a first agent and a second agent. The inter-agent workflow can be used to indicate the information exchange relationship between the first and second agents. In other words, the dialogue chain is used to indicate the common workflow of the first and second agents in processing the target task. During the process of processing the target task, the first and second agents can exchange information according to the requirements of the dialogue chain.

[0141] The information exchange relationship between agents encompasses both the upstream and downstream relationships between agents and the rules governing information transmission between them. These rules include the format, content, and information carried by messages sent from the upstream agent to the downstream agent. The terms upstream agent and downstream agent are relative terms: the upstream agent sends information to the downstream agent, while the downstream agent processes the information sent by the upstream agent.

[0142] The workflow of a single agent is used to describe the information interaction relationship between the agent and itself during the task processing process, for example, it may include the number of iterations of the agent. Accordingly, in the process of processing the task, the agent can perform iterative processing according to the number of iterations. Iterative processing means that after the agent outputs the processing result, the processing result is converted into input content in some way and re-input into the agent so that the processing result can be processed again by the agent. For example, in the implementation method corresponding to Figure 2a, the dialogue chain can indicate the workflow of the first agent and / or the workflow of the second agent. The workflow of the first agent indicates the number of iterations in the process of the first agent processing the first subtask. The workload of the second agent indicates the number of iterations in the process of the second agent processing the second subtask.

[0143] Having introduced conversation chains and workflows above, let's now explore how to determine conversation chains. Specifically, the management platform can determine conversation chains based on subtask information or process attribute configuration information. Each of these methods is described below.

[0144] In a first possible implementation, the management platform can determine the dialogue chain based on the subtask information.

[0145] Specifically, if the dialogue chain is used to indicate the workflow of the first agent and the second agent in processing the target task, then the dialogue chain can be obtained based on the association relationship between the subtasks.

[0146] According to the previous introduction, the first agent is used to process the first subtask, and the second agent is used to process the second subtask. Then, in the process of processing the target task, the association relationship between the first agent and the second agent can match the association relationship between the first subtask and the second subtask. Specifically, the management platform can determine the workflow of the first agent and the second agent in processing the target task based on the association relationship between the first subtask and the second subtask described by the subtask information. For example. Assuming that the output of the first subtask can be used as the input of the second subtask, when determining the dialogue chain, the first agent can be determined as the upstream agent of the second agent based on the association relationship between the first subtask and the second subtask. In this way, the workflow of the agent in processing the target task is determined based on the association relationship between the subtasks processed by the agent, so that the process of the agent processing the target task can be matched with the process of the subtask, thereby ensuring the processing quality of the target task.

[0147] Alternatively, if a dialog chain is used to indicate the workflow of an agent, the dialog chain may be determined based on the capabilities of the agent.

[0148] In the embodiment of the present application, the subtasks of the target task can be completed by the agent, which requires that the processing capability of the agent can meet the requirements of the subtask. However, in actual scenarios, the capabilities of the agent may be limited, making it difficult to meet the requirements of the subtask with only one iteration. To this end, multiple iterations can be used to meet the requirements of the subtask. For example, the processing accuracy required by the first subtask may be high, but the first agent cannot achieve the required accuracy of the first subtask. In this way, the accuracy of the processing result can be improved by calling the first agent multiple times, so that the final processing result can meet the requirements of the first subtask.

[0149] Accordingly, when determining the dialogue chain, the agent's ability information for processing tasks and subtasks can be obtained, and then the agent's workflow can be determined based on the agent's ability information for processing tasks and subtasks. The agent's workflow indicates the number of iterations when the agent processes subtasks. Specifically, when determining the workflow of the first agent, the first agent's ability information for processing first-type tasks and first subtasks can be obtained, and it can be judged whether the first agent's ability to process first-type tasks can meet the requirements for processing the first subtask. If the requirements for processing the first subtask can be met, the number of iterations in the process of the first agent processing the first subtask can be determined to be 1, and the first agent does not need to perform iterative processing. If the requirements for processing the first subtask cannot be met, the number of iterations that can meet the requirements for processing the first subtask can be determined. In this way, iterative processing based on the number of iterations can ensure that the agent processes the subtasks, meets the requirements of the target task, and ensures the processing quality of the target task.

[0150] In a second possible implementation manner, the management platform may determine the dialog chain based on the process attribute configuration information.

[0151] As described above, the workflow configuration information may also include process attribute configuration information. Accordingly, when determining a dialog chain, it may also be determined based on the process attribute configuration information in the workflow configuration information.

[0152] Alternatively, assuming the process attribute configuration information includes dialogue turn information, the processing flow can be determined based on the dialogue turn information, agent interaction information, and multiple agents. The dialogue turns between agents in the processing flow match the dialogue turn information. For example, assuming the dialogue turn information indicates that 10 iterations are required between a "coder" and a "tester," then in the processing flow, the agent responsible for completing the subtasks performed by the "coder" and the agent responsible for completing the subtasks performed by the "tester" can engage in 10 dialogue turns.

[0153] In this way, users can flexibly set the number of iterations of one or more agents in the dialogue chain so that the processing of the target task meets their own needs.

[0154] As previously described, the process attribute configuration information can also include requirement information for describing the overall processing flow. If the process attribute configuration information includes requirement information for describing the overall processing flow, the processing flow can be determined by referring to the specific rules for information interaction indicated by the process attribute configuration information.

[0155] If the process attribute configuration information includes information for describing the overall requirements of the processing flow, then the information describing the overall requirements of the processing flow can be parsed first, and then the agent interaction information can be determined. For example, assuming that the target task is a software development type task, and the process attribute configuration information indicates that the user selects the "waterfall development" method as the method for completing the target task, then since the "waterfall development" method emphasizes reducing iterations and feedback, it can be determined that the content of the interaction between agents is the content output by the agent. That is, the input of the downstream agent can be the output of the upstream agent. For another example, assuming that the target task is a software development type task, and the process attribute configuration information indicates that the user selects the "extreme programming development" method as the method for completing the target task, then since the "extreme programming development" method emphasizes feedback with the user, it can be determined that the content of the interaction between agents includes not only the content output by the agent, but also the content input by the user. Optionally, the above-mentioned user input content can include the data to be processed corresponding to the target task.

[0156] In this way, users can set or adjust the processing flow of the target task through the process attribute configuration information, which improves the flexibility of target task processing and enhances the user experience.

[0157] S204: Configure the first agent and the second agent so that the first agent and the second agent process the target task according to the dialogue chain.

[0158] After determining the first and second agents and the corresponding dialogue chain, multiple agents can be called upon according to the dialogue chain to process the target task. When calling an agent to process a subtask, pre-processed data can be sent to the agent and then the processed data returned by the agent. Because the agents are determined based on the target task, the target task can be completed through the coordination of multiple subtasks.

[0159] In other words, multiple roles and the corresponding agents for each role can be determined based on the needs of completing the target task, so that the corresponding roles can be played by the agents to complete the tasks required by the roles. After determining multiple agents, multiple agents can be called to process the target task. It can be seen that by parsing the subtask information, it is possible to determine which roles the agents need to play in order to complete the target type of task. Then, based on the characteristics of the role and the characteristics of the agent, an agent that is capable of playing the role is selected to complete the subtasks required by the role, and finally multiple agents are called to complete the target task. In this way, based on the requirements of the task, an agent that can meet the requirements of the task can be selected, so that the task can be processed by calling multiple appropriate agents. In this way, even if the task to be completed is of high complexity, it can be completed through the cooperation between multiple agents, meeting the need to complete tasks of high complexity through agents.

[0160] Specifically, after determining a dialogue chain, multiple agents can be called sequentially according to the dialogue chain to process the pending data for the target task. Before processing the pending data, initialization can be performed. This initialization provides the basic execution environment that supports agent interaction, including language, event-driven development, environmental understanding, workflow, and logging, so that agents can be called to process the target task.

[0161] In some possible implementations, the multiple agents described above may include internal agents and external agents. For example, in the case of a management platform running on a cloud service system, internal agents refer to those running on the cloud service system, while external agents are provided by systems other than the cloud service system. Accordingly, during information exchange, the management platform can serve as a transit point, enabling unified invocation of internal and external agents.

[0162] In an embodiment of the present application, tasks can be processed by an agent integrated with an artificial intelligence model. However, due to the limitations of technological development, the output of the agent may deviate from what the user wants to see. This phenomenon can be called "AI illusion". In particular, in an embodiment of the present application, the processing of tasks is completed by multiple agents, and in the process of processing tasks, multiple agents can have multiple rounds of dialogue. The dialogue between multiple agents and the multiple rounds of dialogue between agents may further amplify the AI ​​illusion, resulting in a large deviation between the processing result of the target task and the result required by the user.

[0163] To avoid the aforementioned issues, in some implementations, intermediate processing information can also be displayed to the user. Intermediate processing information is intermediate information obtained by multiple agents while processing the target task. Subsequently, based on the user-triggered action, processing of the target task can be continued or interrupted. If the user-triggered action is a confirmation action regarding the intermediate processing information, processing of the target task can be continued. If the user-triggered action is a rejection action regarding the intermediate processing information, processing of the target task can be interrupted.

[0164] For example, in the implementation shown in FIG1a , the management platform 321 can obtain information sent by the upstream agent to the downstream agent and send this information as intermediate processing information to the client 31. The client 31 can call the display module of the terminal device 20 to display the Zhang Yongjian processing information to the user 10. The client 31 can also display a confirmation control and a rejection control to the user. The confirmation control is used to trigger a confirmation operation for the intermediate processing information, and the rejection control is used to trigger a rejection operation for the intermediate processing information.

[0165] Among them, the intermediate processing information may include information sent by the agent during the interaction process, for example, it may include information sent by the upstream agent to the downstream agent. By viewing the intermediate processing information, the user can determine whether the processing of the target task meets his or her own needs. If the user finds that the processing of the target task does not meet his or her own needs, the user can handle the processing of the target task. If the user finds that the processing of the target task meets his or her own needs, the user can trigger a confirmation operation for the intermediate processing information so that the client sends a confirmation instruction to the management puzzle. According to the confirmation instruction, the management platform can continue to process the target task. In this way, the intermediate processing information is displayed to the user, so that the user can understand the intermediate data generated in the process of processing the target task, and thus determine whether the intermediate data meets his or her own requirements. In this way, the user is provided with the ability to intervene in the processing of the target task, so that the processing of the target task can be supervised to avoid the occurrence of AI hallucinations.

[0166] Optionally, taking the example of a user publishing a target task through the client of the cloud service system and the management platform calling an intelligent agent to complete the task, the intelligent agent management method based on artificial intelligence technology provided in the embodiment of the present application is introduced.

[0167] Refer to Figure 2b, which is another flow chart of an agent management method based on artificial intelligence technology provided in an embodiment of the present application. The method can be specifically executed by a management platform in a cloud service system server.

[0168] Specifically, the agent management method based on artificial intelligence technology shown in FIG2b may include:

[0169] S211: The cloud service client obtains the target task configured by the user.

[0170] In the implementation corresponding to Figure 2b, the user can configure the target task through the cloud service client. For example, the user can select or input task configuration information of the target task on the cloud service client.

[0171] S212: The cloud service client sends the target task to the management platform in the cloud service client.

[0172] After obtaining the target task, the cloud service client can send the target task to the cloud service server through the network. Through forwarding by one or more devices or modules in the cloud service server, the management platform can obtain the target task.

[0173] S213: The management platform determines the first agent and the second agent according to the target task and generates a dialogue chain.

[0174] After obtaining the target task, the management platform can determine the first agent and the second agent according to the target task and generate a dialogue chain.

[0175] S214: The management platform configures the first agent and the second agent so that the first agent and the second agent process the target task according to the dialogue chain.

[0176] After determining the agent and dialogue chain for processing the target task, the management platform can configure the agent so that the agent processes the target task according to the dialogue chain.

[0177] For a detailed description of S213 and S214, please refer to the description of the embodiment corresponding to FIG2a above, which will not be repeated here.

[0178] S215: The management platform sends the intermediate processing information to the cloud service client.

[0179] To avoid "AI hallucinations," the server can also send intermediate processing information to the client for user confirmation. Specifically, the management platform can send intermediate processing information to the cloud service client. Intermediate processing information can include, for example, the output data of the first agent, the output data of the second agent, or other intermediate data generated during the processing of the target task.

[0180] S216: The cloud service client displays the intermediate processing information.

[0181] After obtaining the intermediate processing information, the cloud service client can display the intermediate processing information to the user so that the user can trigger a confirmation operation or a rejection control.

[0182] S217: In response to the confirmation operation triggered by the user on the intermediate processing information, the cloud service client sends a confirmation instruction to the management platform.

[0183] If the user triggers the confirmation operation, it means that the user believes that the intermediate processing information meets his or her requirements for the target task. Accordingly, based on the confirmation operation, the cloud service client can send a confirmation instruction to the management platform.

[0184] S218: The management platform continues to process the target task according to the confirmation instruction.

[0185] After receiving the confirmation instruction, the management platform can continue to process the target task according to the confirmation instruction. Moreover, after completing the processing of the target task, the management platform can send the processing result to the scope client for the user to view.

[0186] As can be seen, by confirming the multiple agents and dialogue chains required to handle the target task through the management platform, the processing of the duplicated target task is achieved. Furthermore, user confirmation of intermediate processing information can avoid "AI illusions" and ensure that the processing of the target task remains within a controllable range.

[0187] The following takes the target task of "developing code according to project requirements" as an example to introduce the process of the intelligent agent, dialogue chain and management platform configuring the intelligent agent to handle the target task.

[0188] The process of developing code based on project requirements can be divided into multiple subtasks: understanding the code development requirements, developing the code, testing the developed code, adjusting the code based on test results, and generating documentation for the developed code. Different subtasks require different processing capabilities. Accordingly, analyzing the subtask information reveals that four agents (hereafter referred to as Agent A, Agent B, Agent C, and Agent D) are required to handle the target task.

[0189] Agent A possesses natural language processing capabilities, specifically the ability to convert unstructured natural language into structured language, and is capable of completing the subtask "understanding code development requirements." Agent B possesses the ability to automatically generate code, and is capable of completing the subtasks "developing code" and "adjusting code based on test results." Agent C possesses the ability to simulate code execution and analyze code issues based on the results, and is capable of completing the subtask "testing developed code." Agent D possesses code comprehension and natural language processing capabilities, and is capable of completing the subtask "understanding code development requirements."

[0190] After Agents A, B, C, and D are determined, a conversation chain can be generated. Assuming Agent A's natural language processing capabilities are relatively weak, the conversation chain could instruct Agent A to perform five iterations before sending the parsed content to Agent B. If the user has high code requirements, the task configuration could instruct Agents B and C to perform ten iterations. Furthermore, to avoid AI hallucinations, the user can confirm Agent A's parsing.

[0191] In this way, the processing flow of the target task obtained can be shown in Figure 3. In the application scenario shown in Figure 3, the following steps are included:

[0192] Step 1: Agent A can obtain the project requirement information set by the user through the client and parse the project requirement information through 5 iterations;

[0193] Step 2: Agent A can send the parsed project requirement information to the client. In response to the confirmation operation, Agent A sends the parsed project requirement information to Agent B.

[0194] Step 3: Agent B generates the first version of the code based on the project requirements and sends it to Agent C;

[0195] Step 4: Agent C tests the first version of the code and provides feedback to Agent B.

[0196] Step 5: Repeat the above steps 9 times;

[0197] Step 6: Agent B generates the 11th version of code based on the 10th feedback from Agent C;

[0198] Step 7: Agent B sends version 11 code to Agent D;

[0199] Step ⑧, Agent D generates a description document based on the 11th version of the code;

[0200] Step 9: Send the 11th version of the code and documentation to the client.

[0201] It should be noted that during the code development process, the agent can also call third-party tools, such as search engines to perform searches, or test cases in the test case library to test the code.

[0202] In the implementations described above, appropriate first and second agents can be selected based on the target task to handle the target task. In some implementations, the selected agents may not be able to effectively complete the subtasks they are required to complete, for example, due to issues such as low processing efficiency or poor processing accuracy. Consequently, some subtasks of the target task may not be properly completed.

[0203] To this end, some possible implementations can set evaluation index parameters for agents and update them based on how well the agents complete subtasks. Specifically, as multiple agents process a target task, feedback can be obtained, and the agent evaluation index parameters can be adjusted accordingly. For example, if a higher evaluation index parameter indicates that the agent is more suitable for the task, the evaluation index parameter can be increased for agents with high efficiency and accuracy, while the evaluation index parameter for agents with low efficiency and accuracy can be decreased.

[0204] For example, there may be multiple agents that have the ability to handle the first type of task, then the management platform can select the agent with the best evaluation index parameters (such as the first agent) from the above multiple agents to handle the target task. In some possible implementations, the evaluation index parameters of the target task can be adjusted according to the completion of the target task. Specifically, during the process of processing the target task, or after processing the target task, the management platform can obtain feedback information. The feedback information can be used to indicate the completion of the target task by the first agent. Then, the evaluation index parameters of the first agent can be adjusted according to the feedback information. For example, if the first agent has a better completion of the target task, the evaluation index parameters of the first agent can be adjusted in a more optimal direction. In this way, feedback evaluation of the agent can optimize the management platform's strategy for selecting agents.

[0205] Optionally, the feedback information can be user feedback, for example, by accessing a feedback page on a client and entering feedback information there. Alternatively, the feedback information can be obtained by monitoring the agent processing the target task. This is described in detail below.

[0206] In some implementations, the agent's performance in handling subtasks can be monitored and then evaluated. Feedback can include the agent's evaluation. Optionally, an evaluation agent can be invoked to evaluate the agent. Specifically, the agent can be evaluated based on one or more dimensions. The following describes some implementations for agent evaluation.

[0207] In a first implementation, the evaluation of an agent may include an evaluation of the agent's work quality. The agent's work quality indicates the quality with which the agent processes subtasks. Alternatively, if the agent's work quality is evaluated using an evaluation agent, an evaluation index corresponding to the work quality may be first obtained, and then input into the evaluation agent to obtain an evaluation of the agent's work quality.

[0208] For example, assuming the target task is a software development task, the evaluation indicators corresponding to the above work quality may include indicators such as the code standardization of the developed software, code vulnerabilities, code memory leaks, software network vulnerabilities, software functional completeness, software execution performance, performance comparison of the software with similar software, software resource consumption, software reliability output, the completeness of the corresponding software documentation, test cases and installation and deployment packages. Optionally, the above multiple evaluation indicators can be determined by a monitoring process deployed in the processing flow, or based on the test results provided by an intelligent agent acting as a "tester".

[0209] In a second implementation, the evaluation of the agent may include an evaluation of the agent's work efficiency. The agent's work efficiency indicates how efficiently the agent processes subtasks. Alternatively, if the agent's work efficiency is evaluated using an evaluation agent, an evaluation index corresponding to the work efficiency may be first obtained, and then input into the evaluation agent to obtain an evaluation of the agent's work efficiency.

[0210] For example, the aforementioned work efficiency evaluation metrics may include the total time spent processing the target task, the total number of dialogue chain iterations during the target task processing, and the number of tokens used. Assuming the target task is a software development task, the aforementioned work efficiency evaluation metrics may also include the number of software builds.

[0211] In a third implementation, the evaluation of an agent may include an evaluation of its resource consumption. The agent's resource consumption represents the total resources consumed by multiple agents during the processing of a target task. Alternatively, the agent's resource consumption may include, for example, the total number of tokens used during the processing of the target task and / or the fees converted from these tokens.

[0212] In a fourth implementation, the evaluation of an agent can include an evaluation of its consistency. The consistency of an agent indicates the degree of consistency in the output of the agent when it processes the same data multiple times. Alternatively, if the consistency of the agent is evaluated using an evaluation agent, the agent can be used to perform multiple processing operations, obtaining multiple processing results, which are then input into the evaluation agent to evaluate the consistency of the agent. Alternatively, the similarity between the multiple processing results can be used to represent the consistency of the agent.

[0213] It should be noted that the above four implementation methods are only examples. In actual scenarios, a variety of implementation methods can be used to evaluate the agent. Optionally, if the agent is evaluated comprehensively across multiple dimensions, the evaluation indicators of multiple dimensions can be uniformly input into the evaluation agent to obtain the score of the target agent. Alternatively, the evaluation indicators of multiple dimensions can be input into the evaluation agent separately, and the evaluations given by multiple evaluation agents can be summarized to obtain the score of the target agent. After obtaining the score of the target agent, the evaluation indicator parameters of the target agent can be updated based on the score of the target agent.

[0214] The present application also provides an intelligent agent management device based on artificial intelligence technology. The intelligent agent management device based on artificial intelligence technology can be applied to the management platform 321 in the implementation shown in FIG. 1 a to implement the functions of the intelligent agent management device based on artificial intelligence technology in the implementation shown in FIG. 2 a. Specifically, as shown in FIG. 4 , the intelligent agent management device 400 based on artificial intelligence technology includes:

[0215] An acquisition module 410 is used to acquire a target task;

[0216] An agent determination module 420 is configured to determine a first agent and a second agent according to the target task, wherein the first agent and the second agent belong to the plurality of agents;

[0217] A dialogue chain generation module 430 is used to generate a dialogue chain, wherein the dialogue chain is used to instruct the first agent and the second agent to process the workflow of the target task;

[0218] The agent configuration module 440 is used to configure the first agent and the second agent so that the first agent and the second agent process the target task according to the dialogue chain.

[0219] The acquisition module 410, agent determination module 420, conversation chain generation module 430, and agent configuration module 440 can all be implemented via software or hardware. For example, the implementation of agent determination module 420 will be described below using agent determination module 420 as an example. Similarly, the implementation of acquisition module 410, conversation chain generation module 430, and agent configuration module 440 can be similar to the implementation of agent determination module 420.

[0220] As an example of a software functional unit, the intelligent agent determination module 420 may include code running on a computing instance. The computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Furthermore, the computing instance may be one or more. For example, the intelligent agent determination module 420 may include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the code may be distributed in the same region or in different regions. Furthermore, the multiple hosts / virtual machines / containers used to run the code may be distributed in the same availability zone (AZ) or in different AZs, each AZ including one data center or multiple geographically close data centers. Typically, a region may include multiple AZs.

[0221] Similarly, multiple hosts / virtual machines / containers running the code can be distributed within the same virtual private cloud (VPC) or across multiple VPCs. Typically, a VPC is set up within a region. Cross-region communication between two VPCs within the same region, or between VPCs in different regions, requires a communication gateway within each VPC to interconnect the VPCs.

[0222] As an example of a hardware functional unit, the agent determination module 420 may include at least one computing device, such as a server. Alternatively, the agent determination module 420 may be implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0223] The multiple computing devices included in the agent determination module 420 can be distributed in the same region or in different regions. The multiple computing devices included in the agent determination module 420 can be distributed in the same AZ or in different AZs. Similarly, the multiple computing devices included in the agent determination module 420 can be distributed in the same VPC or in multiple VPCs. The multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0224] It should be noted that, in other embodiments, the acquisition module 410 can be used to execute any step in the agent management method based on artificial intelligence technology, the agent determination module 420 can be used to execute any step in the agent management method based on artificial intelligence technology, the dialogue chain generation module 430 can be used to execute any step in the agent management method based on artificial intelligence technology, and the agent configuration module 440 can be used to execute any step in the agent management method based on artificial intelligence technology. The steps that the acquisition module 410, agent determination module 420, dialogue chain generation module 430, and agent configuration module 440 are responsible for implementing can be specified as needed. By having the acquisition module 410, agent determination module 420, dialogue chain generation module 430, and agent configuration module 440 respectively implement different steps in the agent management method based on artificial intelligence technology, the full functionality of the agent management device based on artificial intelligence technology is realized.

[0225] This application also provides a computing device 500. As shown in Figure 5, computing device 100 includes a bus 102, a processor 104, a memory 106, and a communication interface 108. Processor 104, memory 106, and communication interface 108 communicate with each other via bus 102. Computing device 400 can be a server or a terminal device. It should be understood that this application does not limit the number of processors and memories in computing device 100.

[0226] Bus 102 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, among others. Buses may be classified as address buses, data buses, control buses, and the like. For ease of illustration, FIG5 shows a single line, but this does not imply a single bus or type of bus. Bus 102 may include a path for transmitting information between various components of computing device 100 (e.g., memory 106, processor 104, and communication interface 108).

[0227] The processor 104 may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0228] The memory 106 may include volatile memory, such as random access memory (RAM). The memory 106 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0229] Memory 106 stores executable program code. Processor 104 executes this executable program code to implement the functions of the aforementioned acquisition module 410, agent determination module 420, conversation chain generation module 430, and agent configuration module 440, thereby implementing an agent management method based on artificial intelligence technology. In other words, memory 106 stores instructions for executing this stored method.

[0230] Alternatively, the memory 106 stores executable code, and the processor 104 executes the executable code to implement the functions of the aforementioned intelligent agent management device based on artificial intelligence technology, thereby implementing the intelligent agent management method based on artificial intelligence technology. In other words, the memory 106 stores instructions for executing the intelligent agent management method based on artificial intelligence technology.

[0231] The communication interface 108 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 100 and other devices or a communication network.

[0232] Embodiments of the present application also provide a computing device cluster. The computing device cluster includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.

[0233] As shown in Figure 6, the computing device cluster includes at least one computing device 100. The memory 106 in one or more computing devices 100 in the computing device cluster may store the same instructions for executing the agent management method based on artificial intelligence technology.

[0234] In some possible implementations, the memory 106 of one or more computing devices 100 in the computing device cluster may also store partial instructions for executing the agent management method based on artificial intelligence technology. In other words, the combination of one or more computing devices 100 can jointly execute instructions for executing the agent management method based on artificial intelligence technology.

[0235] It should be noted that the memory 106 in different computing devices 100 within the computing device cluster may store different instructions, each for executing a portion of the functions of the agent management apparatus based on artificial intelligence technology. Specifically, the instructions stored in the memory 106 in different computing devices 100 may implement the functions of one or more of the acquisition module 410, agent determination module 420, conversation chain generation module 430, and agent configuration module 440.

[0236] In some possible implementations, one or more computing devices in a computing device cluster may be connected via a network. The network may be a wide area network or a local area network, etc. FIG7 shows a possible implementation. As shown in FIG7 , two computing devices 100A and 100B are connected via a network. Specifically, the connection to the network is made through a communication interface in each computing device. In this type of possible implementation, the memory 106 in the computing device 100B stores instructions for executing the functions of the acquisition module 410, the agent determination module 420, and the dialogue chain generation module 430. At the same time, the memory 106 in the computing device 100A stores instructions for executing the functions of the agent configuration module 440.

[0237] The connection method between the computing device clusters shown in Figure 7 can be based on the consideration that the intelligent agent management method based on artificial intelligence technology provided in this application can be divided into two parts: determining the intelligent agent and the dialogue chain, and processing the target task. Therefore, it is considered that the function of determining the intelligent agent and the dialogue chain is handed over to the computing device 100B for execution, and the function of processing the target task is handed over to the computing device 100A for execution.

[0238] It should be understood that the functions of the computing device 100A shown in FIG7 may also be completed by multiple computing devices 100. Similarly, the functions of the computing device 100B may also be completed by multiple computing devices 100.

[0239] The present application also provides another computing device cluster. The connection relationship between the computing devices in this computing device cluster can be similar to the connection method of the computing device cluster described in Figures 6 and 7. However, the memory 106 of one or more computing devices 100A in this computing device cluster can store the same instructions for executing the agent management method based on artificial intelligence technology.

[0240] In some possible implementations, the memory of one or more computing devices 100B in the computing device cluster may also store partial instructions for executing the agent management method based on artificial intelligence technology. In other words, the combination of one or more computing devices can jointly execute instructions for executing the agent management method based on artificial intelligence technology.

[0241] It should be noted that the memory 106 in different computing devices 100A in the computing device cluster can store different instructions for executing partial functions of the agent management device based on artificial intelligence technology. In other words, the instructions stored in the memory 106 in different computing devices 100A can implement the functions of one or more devices in the cloud service system.

[0242] The present application also provides a computer program product comprising instructions. The computer program product may be software or a program product comprising instructions that can be executed on a computing device or stored on any available medium. When the computer program product is executed on at least one computing device, the computer program product causes the at least one computing device to execute an agent management method based on artificial intelligence technology.

[0243] The embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center that contains one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute an intelligent agent management method based on artificial intelligence technology, or instruct the computing device to execute an intelligent agent management method based on artificial intelligence technology.

[0244] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the protection scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An agent management method based on artificial intelligence technology, characterized in that: The method is applied to a management platform, the management platform is used to manage multiple intelligent agents, each of the multiple intelligent agents is used to process at least one type of task based on artificial intelligence technology, and the method includes: Get the target task; According to the target task, determining a first agent and a second agent, wherein the first agent and the second agent belong to the plurality of agents; Generate a dialogue chain, wherein the dialogue chain includes a workflow of the first agent and the second agent processing the target task; The first agent and the second agent are configured so that the first agent and the second agent process the target task according to the dialogue chain.

2. The method according to claim 1, characterized in that Determining the first agent and the second agent according to the target task includes: Parsing the target task to determine subtask information of the target task, wherein the subtask information includes information of multiple subtasks required to complete the target task, and the multiple subtasks include a first subtask and a second subtask; Determine the first agent according to information of the first subtask, wherein the first subtask is a first type of task among the at least one type of tasks, and the first agent is used to process the first type of task; The second agent is determined according to information of the second subtask, wherein the second subtask is a second type of task among the at least one type of tasks, and the second agent is used to process the second type of task.

3. The method according to claim 2, characterized in that The subtask information is used to describe the association relationship between the multiple subtasks, and generating a dialogue chain includes: A dialog chain is generated according to the association relationship between the first subtask and the second subtask, wherein the dialog chain includes a workflow of the first agent and the second agent processing the target task.

4. The method according to claim 2 or 3, characterized in that: The generating of the dialogue chain comprises: The dialogue chain is generated based on the ability information of the first agent in processing the first type of task and the information of the first subtask. The dialogue chain also includes a workflow for the first agent in processing the first subtask. The workflow for the first agent in processing the first subtask indicates the number of iterations in the process of the first agent processing the first subtask.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Acquire workflow configuration information, where the workflow configuration information is used to indicate a target number of iterations of the second subtask.

6. The method according to claim 5, characterized in that The generating of the dialogue chain comprises: The dialogue chain is generated according to the target number of iterations, and the dialogue chain also includes a workflow for the second agent to process the second subtask, and the workflow for the second agent to process the second subtask indicates that the number of iterations in the process of the second agent processing the second subtask is equal to the target number of iterations.

7. The method according to claim 1, characterized in that The management platform is further used to manage a plurality of preset agent combinations, wherein the agents in the agent combination belong to the plurality of agents, and the determining of the first agent and the second agent according to the target task comprises: According to the target task, a target agent combination is determined from a plurality of preset agent combinations, and the target agent combination includes the first agent and the second agent.

8. The method according to any one of claims 1 to 7, characterized in that: Before generating the conversation chain, the method further includes: In response to the agent setting operation, a third agent is determined, and the dialog chain is specifically used to instruct the first agent, the second agent and the third agent to process the workflow of the target task.

9. The method according to any one of claims 1 to 8, characterized in that: After configuring the first agent and the second agent, the method further includes: Providing intermediate processing information, wherein the intermediate processing information is intermediate information obtained during the process of processing the target task; In response to a confirmation operation on the intermediate processing information, the target task continues to be processed.

10. The method according to any one of claims 1 to 9, characterized in that: During the process of processing the target task, or after processing the target task, the method further includes: Acquiring feedback information, where the feedback information is used to indicate the completion status of the target task by the first agent; The evaluation index parameters of the first agent are adjusted according to the feedback information, and the evaluation index parameters of the first agent are used to select the first agent to process the task.

11. An intelligent agent management device based on artificial intelligence technology, characterized in that: The device is applied to a management platform, the management platform is used to manage multiple agents, each of the multiple agents is used to process at least one type of task based on artificial intelligence technology, and the device includes: An acquisition module is used to acquire target tasks; An agent determination module, used to determine a first agent and a second agent according to the target task, wherein the first agent and the second agent belong to the plurality of agents; A dialog chain generation module, used to generate a dialog chain, wherein the dialog chain is used to instruct the first agent and the second agent to process the workflow of the target task; An agent configuration module is used to configure the first agent and the second agent so that the first agent and the second agent process the target task according to the dialogue chain.

12. The device according to claim 11, characterized in that The agent determination module is specifically used to parse the target task and determine the subtask information of the target task, wherein the subtask information includes information of multiple subtasks required to complete the target task, and the multiple subtasks include a first subtask and a second subtask; determine the first agent based on the information of the first subtask, wherein the first subtask is a first type of task among the at least one type of tasks, and the first agent is used to process the first type of task; determine the second agent based on the information of the second subtask, wherein the second subtask is a second type of task among the at least one type of tasks, and the second agent is used to process the second type of task.

13. The device according to claim 12, characterized in that The subtask information is used to describe the association relationship between the multiple subtasks. The dialogue chain generation module is specifically used to determine the workflow for the first agent and the second agent to process the target task according to the association relationship between the first subtask and the second subtask.

14. The device according to claim 12 or 13, characterized in that The dialog chain further includes a workflow of the first agent processing the first subtask, wherein the workflow of the first agent processing the first subtask indicates the number of iterations in the process of the first agent processing the first subtask. The dialogue chain generation module is also used to determine the number of iterations in the process of the first agent processing the first subtask based on the ability information of the first agent processing the first type of task and the information of the first subtask.

15. The device according to any one of claims 12 to 14, characterized in that The dialogue chain also includes a workflow for the second agent to process the second subtask, The acquisition module is further used to acquire workflow configuration information, where the workflow configuration information is used to indicate a target number of iterations for the second subtask.

16. The device according to claim 15, characterized in that The dialogue chain generation module is also used to determine the workflow of the second agent processing the second subtask based on the target number of iterations, and the workflow of the second agent processing the second subtask indicates that the number of iterations in the process of the second agent processing the second subtask is equal to the target number of iterations.

17. The device according to claim 11, characterized in that The management platform is also used to manage multiple preset agent combinations, where the agents in the agent combination belong to the multiple agents. The agent determination module is used to determine a target agent combination from a plurality of preset agent combinations according to the target task, and the target agent combination includes the first agent and the second agent.

18. The device according to any one of claims 11 to 17, characterized in that The agent determination module is also used to determine a third agent in response to an agent setting operation, and the dialogue chain is specifically used to instruct the first agent, the second agent and the third agent to process the workflow of the target task.

19. The device according to any one of claims 11 to 18, characterized in that The device also includes a confirmation module, The confirmation module is used to provide intermediate processing information, where the intermediate processing information is intermediate information obtained during the process of processing the target task; in response to a confirmation operation on the intermediate processing information, continue to process the target task.

20. The device according to any one of claims 11 to 19, characterized in that The device also includes a feedback module, The feedback module is used to obtain feedback information, and the feedback information is used to indicate the completion status of the target task by the first agent; the evaluation index parameters of the first agent are adjusted according to the feedback information, and the evaluation index parameters of the first agent are used to select the first agent to process the task.

21. A computing device cluster, characterized in that: The computing device cluster includes at least one computing device, each computing device including a processor and a memory: The memory is used to store instructions; The processor is configured to cause the computing device cluster to execute the method according to any one of claims 1 to 10 according to the instructions.

22. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, which, when executed on a computing device, enable the computing device to perform the method according to any one of claims 1 to 10.

23. A computer program product comprising instructions which, when executed on a computing device, cause the computing device to perform the method according to any one of claims 1 to 10.

Images