Information processing method and device, electronic equipment and storage medium

Abstract

The invention discloses an information processing method and device, electronic equipment and a storage medium, and relates to the field of artificial intelligence. The method comprises the following steps: acquiring target input information of a user; a large model configuration list and a tool list are created, the large model configuration list is used for providing various different language models, and the tool list is used for providing tools and parameters needed when business work is executed; n intelligent agent systems are set, N is an integer larger than 1, the intelligent agent systems belong to software systems capable of autonomously executing tasks, making decisions and interacting with other entities, and different intelligent agent systems are used for processing different tasks; and processing the target input information according to the large model configuration list, the tool list and the intelligent agent system to obtain a target result. The technical problems of low accuracy and low efficiency when the work content is executed by using a natural language based on a large language model in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and more specifically, to an information processing method, device, electronic device and storage medium. Background Art

[0002] With the development of artificial intelligence technology, multi-agent (Intelligent Agent) working systems based on large language models have attracted widespread attention. Among them, natural language processing technology, dialogue management technology and machine learning technology provide the basis for multi-agent working systems. The application of these technologies not only improves the efficiency of human-computer interaction, but also provides the possibility of solving complex business problems. However, the current agent working system still faces some challenges, mainly including:

[0003] (1) Limitations of user intent understanding: Existing systems usually rely on pre-designed intent recognition rules. For ambiguous, complex, or non-standard natural language input, their understanding accuracy is low, resulting in business processing errors or inefficiencies. Currently, there is no system that dynamically calls the optimal large-scale language model for processing based on actual business needs, resulting in low resource utilization.

[0004] (2) Insufficient flexibility in task execution: When the system executes tasks, it is often limited by the preset execution process and functions and cannot flexibly respond to changes in business needs, which affects the efficiency and effectiveness of business processing and leads to low accuracy of execution results.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The present application provides an information processing method, device, electronic device and storage medium to at least solve the technical problems of low accuracy and low efficiency in the prior art when using natural language to execute work content based on a large language model.

[0007] According to one aspect of the present application, an information processing method is provided, including: obtaining target input information of a user; creating a large model configuration list and a tool list, wherein the large model configuration list is used to provide a variety of different language models, and the tool list is used to provide the tools and parameters required for performing business work, wherein the tool is a software application, plug-in or module; setting N intelligent agent systems, wherein N is an integer greater than 1, and the intelligent agent system is a software system that can autonomously perform tasks, make decisions and interact with other entities, and different intelligent agent systems are used to process different tasks, wherein other entities refer to external systems, hardware devices or data sources that the intelligent agent system needs to interact with when performing tasks and making decisions; processing the target input information according to the large model configuration list, the tool list and the intelligent agent system to obtain the target result.

[0008] Optionally, the N intelligent agent systems include the following intelligent agent systems: a first intelligent agent system, wherein the first intelligent agent system is used to receive target input information from a user; a second intelligent agent system, wherein the second intelligent agent system is used to analyze the target input information; a third intelligent agent system, wherein the third intelligent agent system is used to determine tasks involved in the target input information; a fourth intelligent agent system, wherein the fourth intelligent agent system is used to execute tasks corresponding to the target input information; and a fifth intelligent agent system, wherein the fifth intelligent agent system is used to process tasks that do not involve the second intelligent agent system, the third intelligent agent system, and the fourth intelligent agent system.

[0009] Optionally, the target input information is processed according to the large model configuration list, the tool list and the intelligent agent system to obtain the target result, including: determining the user needs corresponding to the target input information according to the large model configuration list and the second intelligent agent system, wherein the user needs are used to characterize the problems to be solved expressed in the target input information; when the user needs are the needs to execute the target business process, determining the process content of the target business process and the working parameters required to execute the target business process according to the tool list and the third intelligent agent system; determining the target result according to the fourth intelligent agent system, the process content of the target business process and the working parameters required to execute the target business process.

[0010] Optionally, the target result is determined based on the fourth intelligent agent system, the process content of the target business process, and the working parameters required to execute the target business process, including: judging whether the working parameters meet the preset parameter conditions for executing the target work content, wherein the preset parameter conditions are all parameter information required to execute the target work content; if the working parameters do not meet the preset parameter conditions, generating an information feedback request and obtaining feedback results of the user's reply to the information feedback request; determining the target result based on the fourth intelligent agent system, the process content of the target business process, the working parameters required to execute the target business process, and the feedback results.

[0011] Optionally, after determining the user needs corresponding to the target input information based on the large model configuration list and the second intelligent agent system, the information processing method also includes: when the user needs are needs unrelated to the execution of business processes, obtaining a fifth intelligent agent system; processing the user needs according to the fifth intelligent agent system.

[0012] Optionally, after setting up the N intelligent agent systems, the information processing method further includes: supervising and managing the N intelligent agent systems through a target management component, wherein the target management component is connected to the N intelligent agent systems.

[0013] Optionally, a large model configuration list and a tool list are created, including: creating a large model configuration list according to the names of M language models, the access addresses of M language models, and the access keys of M language models, where M is an integer greater than 1; creating a tool list according to the names of K tools, the description information of the K tools, and the parameter sets corresponding to the K tools, where K is an integer greater than 1, different tools are used to process different operations, and the parameter set is used to provide at least one parameter required when using the tool to perform the corresponding operation, and the parameter set includes at least parameter name, parameter type, and parameter attribute.

[0014] According to another aspect of the present application, an information processing device is also provided, including: an acquisition unit, which acquires the user's target input information; a creation unit, which creates a large model configuration list and a tool list, wherein the large model configuration list is used to provide a variety of different language models, and the tool list is used to provide the tools and parameters required for performing business work, wherein the tool is a software application, plug-in or module; a setting unit, which sets N intelligent agent systems, wherein N is an integer greater than 1, and the intelligent agent system is a software system that realizes autonomous execution of tasks, makes decisions and interacts with other entities, and different intelligent agent systems are used to process different tasks, wherein other entities refer to external systems, hardware devices or data sources that the intelligent agent system needs to interact with when performing tasks and making decisions; a determination unit, which processes the target input information according to the large model configuration list, the tool list and the intelligent agent system to obtain the target result.

[0015] According to another aspect of the present application, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program runs, the device where the computer-readable storage medium is located executes the above-mentioned information processing method.

[0016] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors execute the above-mentioned information processing method.

[0017] In the present application, the user's target input information is first obtained, and then a large model configuration list and a tool list are created, wherein the large model configuration list is used to provide a variety of different language models, and the tool list is used to provide the tools and parameters required for performing business work, wherein the tool is a software application, plug-in or module, which analyzes the user's input information through a variety of different language models to ensure the accuracy of analyzing the user's intentions, and then N intelligent agent systems are set up, wherein N is an integer greater than 1, and the intelligent agent system is a software system that can autonomously perform tasks, make decisions and interact with other entities, and different intelligent agent systems are used to handle different tasks, wherein other entities refer to external systems, hardware devices or data sources that the intelligent agent system needs to interact with when performing tasks and making decisions. Finally, the target input information is processed according to the large model configuration list, the tool list and the intelligent agent system to obtain the processing result. By setting up multiple intelligent agent systems with different functions, based on their respective functional characteristics, a more accurate understanding and more efficient processing of user requests can be achieved, the accuracy of problem solving and the efficiency of the processing process can be improved, and the effect of processing multiple business tasks can be achieved based on the combination of multiple intelligent agent systems and multiple tools.

[0018] From the above content, it can be seen that compared with the prior art that uses natural language to execute work content based on a large language model, the present application obtains the user's input information, creates a large model configuration list and a tool list, and then sets up multiple intelligent agent systems. Then, the user's work content is processed according to the combination of the large model configuration list, the tool list and multiple intelligent agent systems, and finally the processing result is obtained. This realizes the use of natural language to execute business work based on the intelligent agent system, and reduces the purpose of intermediate programming, thereby achieving the technical effect of improving the accuracy and efficiency of natural language execution of work content, and thus solves the technical problems of low accuracy and low efficiency that exist in the prior art when using natural language to execute work content based on a large language model. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 is a flowchart of an optional information processing method according to an embodiment of the present application;

[0021] Figure 2 is a structural diagram of an optional information processing method according to an embodiment of the present application;

[0022] Figure 3 It is a schematic diagram of an optional information processing device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] It should also be noted that the information and data collected by this application are authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation portals for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or institution through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or institution.

[0026] According to an embodiment of the present application, an embodiment of an information processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] It should be noted that an intelligent processing system is used as the execution subject of the information processing method of the embodiment of the present application. It is understandable that the information processing method provided in the embodiment of the present application can also be executed by other systems or devices, and the embodiment of the present application does not specifically limit this.

[0028] Figure 1 is a flowchart of an optional information processing method according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0029] Step S101, obtaining target input information of the user.

[0030] Optionally, the intelligent processing system obtains content input by the user.

[0031] Step S102, creating a large model configuration list and tool list.

[0032] In step S102, the large model configuration list is used to provide a variety of different language models, and the tool list is used to provide the tools and parameters required for executing business work.

[0033] In step S102, the tool is a software application, plug-in or module.

[0034] Optionally, the large model configuration list includes access mechanisms for multiple large language models. The intelligent processing system can dynamically adjust and switch different language models to adapt to different types of user requests. This dynamic adjustment capability enables the system to select the most suitable language model for analysis when processing various scenarios.

[0035] Optionally, the tools in the tool list include but are not limited to database query tools, email sending tools, file processing tools, data analysis tools, chart generation tools, chart generation tools, payment gateway interfaces, search engines, maps and geolocation services, and identity authentication services. These tools usually require a series of parameters to be configured so that the intelligent agent system can correctly call and execute the required operations.

[0036] Optionally, the tools in the tool list are integrated with the intelligent agent system through a predefined tool interface, allowing the intelligent agent system to call corresponding tools according to corresponding instructions.

[0037] Step S103, setting N intelligent agent systems.

[0038] In step S103, N is an integer greater than 1. The intelligent agent system is a software system that can autonomously execute tasks, make decisions, and interact with other entities. Different intelligent agent systems are used to process different tasks.

[0039] In step S103, other entities refer to external systems, hardware devices or data sources that the intelligent agent system needs to interact with when performing tasks and making decisions.

[0040] Alternatively, an intelligent agent system (ie, referred to as an agent) is an entity that can perform automated tasks, make decisions, and interact with human users, other agents, or the environment.

[0041] Optionally, the intelligent processing system sets up multiple (N) interconnected agents, which can specialize in processing various different tasks and jointly complete complex workflows through mutual collaboration and communication.

[0042] Step S104, processing the target input information according to the large model configuration list, tool list and intelligent agent system to obtain the target result.

[0043] Optionally, the intelligent processing system analyzes and processes the target input information according to the large model configuration list, tool list and intelligent agent system, and finally generates and outputs the processing results.

[0044] Optionally, the intelligent processing system obtains input information from the user, undergoes multi-agent negotiation, and feedback information provided by the user during the multi-agent negotiation process, and finally outputs a processing result corresponding to the user's needs.

[0045] From the contents of step S101 to step S104, it can be known that in this application, the user's target input information is first obtained, and then a large model configuration list and a tool list are created, wherein the large model configuration list is used to provide a variety of different language models, and the tool list is used to provide the tools and parameters required for performing business work, wherein the tool is a software application, plug-in or module, which analyzes the user's input information through a variety of different language models to ensure the accuracy of analyzing the user's intentions, and then N intelligent agent systems are set up, wherein N is an integer greater than 1, and the intelligent agent system is capable of autonomously executing tasks, making decisions and interacting with other entities. Interactive software systems, different intelligent agent systems are used to handle different tasks, among which other entities refer to external systems, hardware devices or data sources that the intelligent agent system needs to interact with when performing tasks and making decisions. Finally, the target input information is processed according to the large model configuration list, tool list and intelligent agent system to obtain the processing results. Multiple intelligent agent systems with different functions are set up. Based on their respective functional characteristics, they can achieve a more accurate understanding and more efficient processing of user requests, improve the accuracy of problem solving and the efficiency of the processing process, and based on the combination of multiple intelligent agent systems and multiple tools, they can achieve the effect of processing multiple business tasks.

[0046] From the above content, it can be seen that compared with the prior art that uses natural language to execute work content based on a large language model, the present application obtains the user's input information, creates a large model configuration list and a tool list, and then sets up multiple intelligent agent systems. Then, the user's work content is processed according to the combination of the large model configuration list, the tool list and multiple intelligent agent systems, and finally the processing result is obtained. This realizes the use of natural language to execute business work based on the intelligent agent system, and reduces the purpose of intermediate programming, thereby achieving the technical effect of improving the accuracy and efficiency of natural language execution of work content, and thus solves the technical problems of low accuracy and low efficiency that exist in the prior art when using natural language to execute work content based on a large language model.

[0047] In an optional embodiment, the N intelligent agent systems include the following intelligent agent systems: a first intelligent agent system, wherein the first intelligent agent system is used to receive target input information from a user, a second intelligent agent system, wherein the second intelligent agent system is used to analyze the target input information, a third intelligent agent system, wherein the third intelligent agent system is used to determine tasks involved in the target input information, a fourth intelligent agent system, wherein the fourth intelligent agent system is used to execute tasks corresponding to the target input information, and a fifth intelligent agent system, wherein the fifth intelligent agent system is used to process tasks that do not involve the second intelligent agent system, the third intelligent agent system, and the fourth intelligent agent system.

[0048] Optionally, the first intelligent agent system is a user agent, which serves as an interface between the user and the system and is responsible for receiving and sending user messages; the second intelligent agent system is a navigator agent, which is the first agent to receive user input information and is responsible for judging the user's intention and transferring the question to the appropriate role; the third intelligent agent system is a business problem determination agent, which is responsible for determining which specific work needs to be performed and outputting relevant parameters when the user intends to perform business work; the fourth intelligent agent system is a work execution agent, which is used to execute the tasks determined by the business problem determination agent and is responsible for understanding the output of the business problem determination agent. When it is necessary to improve the parameters required for executing the work, it organizes the parameter rules in natural language and initiates user feedback requests; the fifth intelligent agent system is an alternative agent, which is used to handle questions that the navigator agent believes are not suitable for other agents to answer.

[0049] From the above content, it can be seen that the intelligent processing system can achieve accurate understanding and efficient processing of user requests by setting up multiple intelligent agent systems with different functions based on their respective functional characteristics. This architecture with clear role division enables the system to process complex and changeable user requests in an orderly manner, thereby improving the accuracy of problem solving and the efficiency of the processing process.

[0050] In an optional embodiment, the intelligent processing system first determines the user needs corresponding to the target input information based on the large model configuration list and the second intelligent agent system, wherein the user needs are used to characterize the problems to be solved expressed in the target input information. When the user needs are the needs to execute the target business process, the process content of the target business process and the working parameters required to execute the target business process are determined based on the tool list and the third intelligent agent system, and then the target result is determined based on the fourth intelligent agent system, the process content of the target business process and the working parameters required to execute the target business process.

[0051] Optionally, after the user agent receives the user's input information, the intelligent processing system first uses the navigator agent in combination with the large model configuration list to parse the user input information to determine the user's needs. When the user's needs are to execute the target business process, the intelligent processing system will determine the specific content and required work parameters of the business process involved in executing the need based on the tool list and the business problem judgment agent. Finally, the processing result is determined based on the work execution agent, the process content of the target business process, and the work parameters required to execute the target business process. For example, the target business process can be report writing, order processing, scheduling, etc.

[0052] Optionally, the navigator agent matches the most suitable model for analyzing the user input information from the large model configuration list according to the information input by the user, so as to improve the accuracy and efficiency of analyzing the user input information.

[0053] Optionally, the business problem determination agent determines the tasks required to be performed in accordance with the user's needs in combination with the tool list, and inputs the tools required to perform the tasks and related parameters of the tools to ensure that the tasks can be performed.

[0054] From the above content, it can be seen that the intelligent processing system uses the combination of a large model configuration list and the second intelligent agent system to improve the accuracy and depth of identifying user needs. Through the combination of the tool list and the third intelligent agent system, the system can be more flexibly adapted to various business processes, and the automated execution of business processes reduces manual intervention, improves efficiency and reduces errors.

[0055] In an optional embodiment, the intelligent processing system first determines whether the working parameters meet the preset parameter conditions for executing the target work content, wherein the preset parameter conditions are all parameter information required to execute the target work content. If the working parameters do not meet the preset parameter conditions, an information feedback request is generated, and the feedback result of the user's reply to the information feedback request is obtained. Then, the target result is determined based on the fourth intelligent agent system, the process content of the target business process, the working parameters required to execute the target business process, and the feedback result.

[0056] Optionally, before executing the target work content, the intelligent processing system will first perform a key judgment: verify whether the work parameters meet the preset parameter conditions. The preset parameter conditions here refer to the complete parameter information set required for the smooth execution of the target work content. If the system detects that the provided work parameters do not meet these preset conditions, that is, there are missing or incomplete parameters, the system will automatically generate an information feedback request and ask the user for the missing information. After receiving this information feedback request, the user will provide necessary supplementary information as feedback results. The intelligent processing system will receive and process these feedback results, and then combine the functions of the fourth intelligent agent system, the specific content of the target business process, the complete work parameters and the user's feedback results, and comprehensively determine the final target result based on this information. This process ensures that even when the initial parameters are incomplete, the system can collect the required information through interaction with the user, accurately complete the business process, and finally generate the processing results.

[0057] Optionally, when user feedback parameters are required, the system will process the parameter rules into natural language, and then initiate a user feedback request based on the processed rules to finally obtain feedback results.

[0058] From the above content, it can be seen that the intelligent processing system ensures the accuracy and reliability of business process execution by verifying the matching degree between working parameters and preset parameter conditions. When the parameters do not meet the conditions, the system can flexibly obtain the required information through interaction. By automatically generating feedback requests and processing user feedback, it improves interactivity with users and enhances user experience. The system can request and obtain necessary information in a timely manner when problems are found, reducing business processing delays caused by parameter problems and improving processing efficiency. It optimizes business processes based on intelligent judgment, automatic feedback and real-time updates to ensure that the target work content can be achieved efficiently and accurately under various circumstances.

[0059] In an optional embodiment, when the user demand is unrelated to the execution of the business process, the intelligent processing system obtains the fifth intelligent agent system, and then processes the user demand according to the fifth intelligent agent system.

[0060] Optionally, when the navigator agent identifies the user's needs as unrelated to the execution of business processes, such as general inquiries or service requests, the system will call the fifth intelligent agent system, wherein the fifth intelligent agent system is specially designed to handle needs that are not within the scope of typical business process processing. The intelligent agent system will handle these needs according to preset response rules or knowledge bases. It can provide information query, answer questions, give suggestions or other non-business process operations. For example, if the user asks for information about a product, the fifth intelligent agent system may retrieve relevant information and provide it to the user.

[0061] From the above content, it can be seen that by introducing the fifth intelligent agent system, the intelligent processing system can handle a wider range of user needs, including those that are not business process needs, ensuring that the system can respond to all user needs, regardless of whether these needs are directly related to business process execution.

[0062] In an optional embodiment, the intelligent processing system supervises and manages N intelligent agent systems through a target management component, wherein the target management component is connected to the N intelligent agent systems.

[0063] Optionally, the intelligent processing system sets up a target management component to monitor and manage the messages of all agents, whose responsibilities include starting or ending sessions, managing message history, conversation rounds, monitoring termination events, feedback events, etc.

[0064] Optionally, the goal management component has a session management mechanism that can record and manage the conversation history between multiple agents to ensure the continuity of the conversation and the integrity of problem solving. In a continuous conversation, such as a user searching for products, placing orders, consulting logistics and other multi-step operations on an e-commerce platform, the goal management component can ensure the continuity of the entire conversation process, avoid information loss, and improve user experience. The goal management component also includes a message round control function that can control the message transmission order between agents, as well as the termination and feedback mechanism of the conversation according to the conversation process and business needs. This control mechanism is particularly important when dealing with businesses that require multi-step verification or decision-making, such as bank loan applications, insurance claims, etc., which can ensure the correctness and integrity of the process and reduce errors and omissions.

[0065] Optionally, the user authorizes a user agent to ask a question, and the user agent forwards the question to the target management component, and the target management component opens a session to communicate with other agents.

[0066] Optionally, various agents within the intelligent processing system work together to solve user problems. If user feedback is required, the target management component is delegated to prompt the user for input and interact with the user through the target management component. Once the user receives the request and provides the required feedback, the input will be received by the target management component and forwarded to the corresponding agent.

[0067] Optionally, Figure 2 is a structural diagram of an optional information processing method according to an embodiment of the present application, such as Figure 2 As shown, first create a large model configuration list ( Figure 2 OAI_CONFIG_LIST in the language model), which contains at least the name of the language model, the address of the language model, and the access key of the language model. Then create a tool list ( Figure 2 The information of the tool includes at least the tool name, tool description and tool parameter set (parameter name, parameter type, parameter attribute, and required parameters). After configuration, set multiple agents, such as user agent ( Figure 2 User in), navigator agent ( Figure 2 Navigator in the Figure 2 QuestionManager in the Figure 2 ActionManager in), other agents ( Figure 2 , then set the group conversation administrator ( Figure 2Finally, according to the large model configuration list, tool list, multiple agents and group conversation managers work together to output the processing results ( Figure 2 in the outputs).

[0068] Optionally, in Figure 2 In the example, the user agent is the object of the user to send and receive messages; the navigator agent is the first recipient of user information and an information router. After determining the user's intention, it transfers the question to the appropriate role. At the same time, the agent is set to be able to select the most capable model from the large model configuration list to analyze the user information; the business problem determination agent, if the navigator agent believes that the user intends to perform a certain business task, the question will be transferred to the agent. The agent has access to the tool list and determines which task should be performed and outputs the parameters required to perform the relevant task; the work execution agent is used to execute the task determined by the business problem determination agent, and if the navigator agent believes that the user intends to perform a certain business task, the question will be transferred to the agent. The agent has access to the tool list and determines which task should be performed and outputs the parameters required to perform the relevant task; the work execution agent is used to execute the task determined by the business problem determination agent, and if the navigator agent believes that the user intends to perform a certain business task, the question will be transferred to the agent. The intention is to improve the working parameters. The agent understands the output of the business problem determination agent, and organizes and polishes the required parameter rules in natural language, then initiates a user feedback request and performs corresponding work according to the feedback results; other agents, if the navigator agent believes that the user intention is not suitable for the above agent's answer, it will be forwarded to the agent for processing; the group conversation administrator supervises and manages the messages of all agents. If user feedback is required, the user entrusts the user agent agent to ask a question, and the user agent agent forwards the question to the GroupChatManager. The GroupChatManager opens a session and prompts the user to input; finally, the work results are presented in a formatted page based on the completion of the specified work content.

[0069] As can be seen from the above, the intelligent processing system uses a key component, namely the target management component, whose function is to supervise and manage all intelligent agents (N intelligent agent systems) in the system. These intelligent agent systems may be responsible for various tasks, such as processing user requests, executing business logic, managing data, etc. The target management component is connected to each intelligent agent system, which means that it can monitor the activities of the agents in real time, ensure that they operate as expected, and effectively coordinate the interactions between them.

[0070] In an optional embodiment, the intelligent processing system creates a large model configuration list based on the names of M language models, the access addresses of the M language models, and the access keys of the M language models, where M is an integer greater than 1, and creates a tool list based on the names of K tools, the description information of the K tools, and the parameter sets corresponding to the K tools, where K is an integer greater than 1. Different tools are used to process different operations, and the parameter set is used to provide at least one parameter required when using the tool to perform the corresponding operation, and the parameter set includes at least parameter name, parameter type, and parameter attributes.

[0071] Optionally, the large model configuration list also includes model performance indicators, model update frequency, and model operating environment configuration information, so that the relevant intelligent agent system can select the optimal model according to the characteristics of the user request. For example, when processing a large number of real-time requests, a model with higher performance and faster response can be selected; when processing complex semantic understanding, a model with high update frequency and strong understanding ability can be selected.

[0072] Optionally, Table 1 is an example of the information format of an optional large model configuration list according to an embodiment of the present application. As shown in Table 1, the large model configuration list includes at least a model name, a model address, and a model access key.

[0073] Table 1

[0074] Model Name Model Address Model Access Key gpt-3.5-turbo http: / / gpt3.5 / v1 key1 GPT-4 http: / / gpt4 / v1 key2 chatglm3 http: / / glm3 / v1 key3 …… …… ……

[0075] Optionally, the tool list includes at least the name of the tool, description information of the tool, a parameter set corresponding to the tool, function information of the tool, and performance information of the tool.

[0076] Optionally, the tool list information format is as follows:

[0077]

[0078]

[0079] From the above content, it can be seen that the intelligent processing system can select the most appropriate language model according to the task requirements, thereby improving the accuracy and efficiency of processing. Different tools can be used to handle different operations, so that the system can cover a wider range of business needs. The parameter set corresponding to each tool ensures that the tool can flexibly adapt to various operational requirements, and the system can add new models and tools, with good scalability.

[0080] According to another aspect of the embodiments of the present application, an embodiment of an information processing device is also provided. Figure 3 is a schematic diagram of an optional information processing device according to an embodiment of the present application, such as Figure 3As shown, the information processing device includes: an acquisition unit 301, a creation unit 302, a setting unit 303 and a determination unit 304.

[0081] Optionally, an acquisition unit 301 is used to obtain the user's target input information; a creation unit 302 is used to create a large model configuration list and a tool list, wherein the large model configuration list is used to provide a variety of different language models, and the tool list is used to provide the tools and parameters required for performing business work, wherein the tool is a software application, plug-in or module; a setting unit 303 is used to set N intelligent agent systems, wherein N is an integer greater than 1, and the intelligent agent system is a software system that realizes autonomous execution of tasks, makes decisions and interacts with other entities, and different intelligent agent systems are used to handle different tasks, wherein other entities refer to external systems, hardware devices or data sources that the intelligent agent system needs to interact with when performing tasks and making decisions; a determination unit 304 is used to process the target input information according to the large model configuration list, the tool list and the intelligent agent system to obtain the target result.

[0082] Optionally, setting unit 303 includes: a first intelligent agent system, wherein the first intelligent agent system is used to receive target input information from the user; a second intelligent agent system, wherein the second intelligent agent system is used to analyze the target input information; a third intelligent agent system, wherein the third intelligent agent system is used to determine the tasks involved in the target input information; a fourth intelligent agent system, wherein the fourth intelligent agent system is used to execute the tasks corresponding to the target input information; and a fifth intelligent agent system, wherein the fifth intelligent agent system is used to process tasks that do not belong to the second intelligent agent system, the third intelligent agent system and the fourth intelligent agent system.

[0083] Optionally, the determination unit 304 includes: a first determination subunit, a second determination subunit, and a third determination subunit. The first determination subunit is used to determine the user requirements corresponding to the target input information according to the large model configuration list and the second intelligent agent system, wherein the user requirements are used to characterize the problems to be solved expressed in the target input information; the second determination subunit is used to determine the process content of the target business process and the working parameters required to execute the target business process according to the tool list and the third intelligent agent system when the user requirements are the requirements for executing the target business process; the third determination subunit is used to determine the target result according to the fourth intelligent agent system, the process content of the target business process, and the working parameters required to execute the target business process.

[0084] Optionally, the first determination subunit includes: a first acquisition module and a first processing module. The first acquisition module is used to acquire the fifth intelligent agent system when the user demand is irrelevant to the execution of the business process; the first processing module is used to process the user demand according to the fifth intelligent agent system.

[0085] Optionally, the third determination subunit includes: a first judgment module, a second acquisition module and a first determination module. The first judgment module is used to judge whether the working parameters meet the preset parameter conditions for executing the target working content, wherein the preset parameter conditions are all parameter information required for executing the target working content; the second acquisition module is used to generate an information feedback request when the working parameters do not meet the preset parameter conditions, and obtain the feedback result of the user's reply to the information feedback request; the first determination module is used to determine the target result according to the fourth intelligent agent system, the process content of the target business process, the working parameters required for executing the target business process, and the feedback result.

[0086] Optionally, the setting unit 303 includes: a management subunit, which is used to supervise and manage N intelligent agent systems through a target management component, wherein the target management component is connected to the N intelligent agent systems.

[0087] Optionally, the creation unit 302 includes: a first creation subunit and a second creation subunit. The first creation subunit is used to create a large model configuration list according to the names of M language models, the access addresses of M language models, and the access keys of M language models, where M is an integer greater than 1; the second creation subunit is used to create a tool list according to the names of K tools, the description information of K tools, and the parameter sets corresponding to the K tools, where K is an integer greater than 1, different tools are used to process different operations, and the parameter set is used to provide at least one parameter required when using the tool to perform the corresponding operation, and the parameter set at least includes parameter name, parameter type, and parameter attribute.

[0088] According to another aspect of the present application, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program is executed, the device where the computer-readable storage medium is located executes the above-mentioned information processing method.

[0089] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned information processing method.

[0090] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0091] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0092] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0093] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0094] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0095] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0096] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An information processing method, characterized in that: include: Get the user's target input information; Creating a large model configuration list and a tool list, wherein the large model configuration list is used to provide a plurality of different language models, and the tool list is used to provide tools and parameters required for performing business work, wherein the tool is a software application, plug-in or module; Setting N intelligent agent systems, where N is an integer greater than 1, and the intelligent agent systems are software systems that can autonomously perform tasks, make decisions, and interact with other entities, and different intelligent agent systems are used to handle different tasks, where the other entities refer to external systems, hardware devices, or data sources that the intelligent agent systems need to interact with when performing tasks and making decisions; The target input information is processed according to the large model configuration list, the tool list and the intelligent agent system to obtain a target result.

2. The information processing method according to claim 1, characterized in that: The N intelligent agent systems include the following intelligent agent systems: A first intelligent agent system, wherein the first intelligent agent system is used to receive target input information of the user; A second intelligent agent system, wherein the second intelligent agent system is used to analyze the target input information; A third intelligent agent system, wherein the third intelligent agent system is used to determine the task involved in the target input information; A fourth intelligent agent system, wherein the fourth intelligent agent system is used to execute the task corresponding to the target input information; A fifth intelligent agent system, wherein the fifth intelligent agent system is used to process tasks that are not related to the second intelligent agent system, the third intelligent agent system and the fourth intelligent agent system.

3. The information processing method according to claim 2, characterized in that: Processing the target input information according to the large model configuration list, the tool list and the intelligent agent system to obtain a target result includes: Determining user requirements corresponding to the target input information according to the large model configuration list and the second intelligent agent system, wherein the user requirements are used to characterize the problems to be solved expressed in the target input information; When the user demand is a demand for executing a target business process, determining the process content of the target business process and the work parameters required for executing the target business process according to the tool list and the third intelligent agent system; The target result is determined based on the fourth intelligent agent system, the process content of the target business process, and the working parameters required to execute the target business process.

4. The information processing method according to claim 3, characterized in that: Determining the target result according to the fourth intelligent agent system, the process content of the target business process, and the work parameters required to execute the target business process includes: Determine whether the working parameters meet the preset parameter conditions for executing the target working content, wherein the preset parameter conditions are all parameter information required for executing the target working content; In the case where the working parameter does not satisfy the preset parameter condition, generating an information feedback request, and obtaining a feedback result of the user's reply to the information feedback request; The target result is determined based on the fourth intelligent agent system, the process content of the target business process, the working parameters required to execute the target business process and the feedback result.

5. The information processing method according to claim 3, characterized in that: After determining the user demand corresponding to the target input information according to the large model configuration list and the second intelligent agent system, the information processing method further includes: When the user demand is a demand unrelated to the execution of the business process, obtaining the fifth intelligent agent system; The user demand is processed according to the fifth intelligent agent system.

6. The information processing method according to claim 1, characterized in that: After setting N intelligent agent systems, the information processing method further includes: The N intelligent agent systems are supervised and managed by a target management component, wherein the target management component is connected to the N intelligent agent systems.

7. The information processing method according to claim 1, characterized in that: Create large model configuration lists and tool lists, including: Creating the large model configuration list according to the names of the M language models, the access addresses of the M language models, and the access keys of the M language models, where M is an integer greater than 1; The tool list is created according to the names of K tools, the description information of K tools, and the parameter sets corresponding to the K tools, wherein K is an integer greater than 1, different tools are used to process different operations, and the parameter set is used to provide at least one parameter required when using the tool to perform the corresponding operation, and the parameter set includes at least parameter name, parameter type, and parameter attribute.

8. An information processing device, characterized in that: include: An acquisition unit, which acquires target input information of a user; A creation unit, which creates a large model configuration list and a tool list, wherein the large model configuration list is used to provide a plurality of different language models, and the tool list is used to provide tools and parameters required for performing business work, wherein the tool is a software application, plug-in or module; A setting unit is configured to set N intelligent agent systems, wherein N is an integer greater than 1, and the intelligent agent system is a software system that can autonomously execute tasks, make decisions, and interact with other entities. Different intelligent agent systems are used to process different tasks, and the other entities refer to external systems, hardware devices, or data sources that the intelligent agent system needs to interact with when executing tasks and making decisions. The determination unit processes the target input information according to the large model configuration list, the tool list and the intelligent agent system to obtain a target result.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located executes the information processing method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the information processing method described in any one of claims 1 to 7.

Images