A text generation system and method based on multi-agent collaboration mechanism MOPAR

Abstract

The present application provides a text generation system and method based on the multi-agent collaboration mechanism MOPAR. The system according to the present application includes: a matching agent, connected to a domain multi-agent system, for obtaining user writing requirements, generating matching prompt words based on the writing requirements, transmitting the matching prompt words to the domain multi-agent system, and performing domain matching with the domain multi-agent system through the matching prompt words, and optimizing based on the feedback information of the reflective agent in the domain multi-agent system; a domain multi-agent system, including multiple agents in different fields, connected to the matching agent, for receiving matching prompt words, and obtaining multiple agents in the corresponding fields based on the matching prompt words, and generating the text content required by the user through the multiple agents in the corresponding fields based on the multi-agent collaboration mechanism MOPAR. The present application provides users with a more efficient, professional and creative text generation service by introducing a collaboration mechanism between multiple agents.

Description

Technical Field

[0001] The present invention relates to the field of text generation technology, and in particular to a text generation system and method based on a multi-agent collaboration mechanism MOPAR. Background Art

[0002] Text generation technology refers to the ability to create natural language text using computer programs. With the development of artificial intelligence, particularly deep learning, text generation technology has made significant progress. Early text generation methods primarily relied on rule-based approaches, which typically used predefined templates or grammatical structures to generate text. However, this approach has limitations when dealing with complex contexts and diverse content requirements. With the advancement of deep learning, deep learning models are able to learn deeper language features, generating more fluent and natural text.

[0003] In recent years, the emergence of large language models (LLMs) has greatly promoted the development of text generation technology. By training on large amounts of text data, these models can learn rich language structures and patterns, thereby generating more natural and fluent text. For example, models based on the Transformer architecture, such as the GPT series of models, have become one of the mainstream technologies in the field of text generation. These models can not only generate general text content, but also complete various language tasks such as translation and question answering.

[0004] An AI agent is a highly intelligent software entity capable of performing a range of complex tasks and making decisions autonomously to a certain extent. AI agents are designed to operate in diverse environments, completing specific tasks or achieving predetermined goals through self-learning and optimization. With the incorporation of large-scale model technology, AI agents have gained enhanced language understanding and generation capabilities, enabling them to interact more naturally with humans and handle more complex and diverse tasks. In the era of large models, AI agents not only passively respond to input or instructions but also proactively plan actions based on set goals to better adapt to the environment and task requirements. Furthermore, AI agents can leverage a variety of tools and services to enhance their capabilities, such as calling external APIs, operating hardware devices, or other software systems. The development of AI agents represents a significant evolution in the field of artificial intelligence: the evolution from simple chatbots to intelligent agents capable of performing complex tasks.

[0005] A multi-agent system (MAS) is a system composed of multiple interacting agents that can collaborate to complete complex tasks. In text generation technology, multi-agent systems can be used to simulate the interactions between different roles, thereby generating richer and more diverse text content.

[0006] While existing deep learning text generation techniques have demonstrated impressive performance in many applications, they still face challenges and issues. For example, traditional deep learning text generation algorithms often require extensive data preparation and model fine-tuning to suit specific tasks or domains. This is not only time-consuming and computationally resource-intensive, but may also fail to fully utilize specialized knowledge. Furthermore, some techniques employ a single-agent architecture, which limits the diversity and expertise of the generated content.

[0007] The main shortcomings of the existing technology include but are not limited to:

[0008] 1. Over-reliance on model training and fine-tuning: Traditional text generation algorithms, especially those based on deep learning, often require model training and fine-tuning for specific application scenarios to achieve satisfactory performance. This process is not only time-consuming and labor-intensive, but also requires a large amount of labeled data, increasing development costs and cycles.

[0009] 2. Limitations of Expertise: While large language models can generate highly natural text, due to a lack of domain-specific training data, general-purpose large models perform poorly when generating highly specialized content. Large models specialized in a particular field are also limited in their cross-domain performance. For example, large models in the medical field struggle to achieve good results in engineering. Therefore, models have limitations in their understanding of expertise and lack flexibility, and may not accurately provide the required information.

[0010] 3. Uniqueness of generated content: When using traditional deep learning models or a single intelligent agent for text generation, the generated content may have a relatively single perspective and lack diversity. This is an obvious shortcoming in text generation scenarios that require analyzing problems from different angles or creating multi-dimensional content.

[0011] 4. Lack of flexibility: Existing text generation technologies are often limited to a single writing model or scenario, and are unable to quickly adapt to emerging needs or changing environmental conditions. When the application scenario changes, the entire system may need to be redesigned or adjusted, resulting in poor flexibility.

[0012] 5. Lack of reflection mechanism: Most existing text generation methods lack an effective feedback link after generating content. They are unable to automatically evaluate the quality of the generated text and make necessary corrections, which may result in erroneous or inappropriate information being directly output to users.

[0013] In summary, although current text generation methods have greatly improved the effects of natural language processing, there is still much room for improvement in flexibility, professionalism, diversity and self-improvement capabilities. Summary of the Invention

[0014] The purpose of the present invention is to provide a text generation system and method based on a multi-agent collaboration mechanism MOPAR, aiming to solve the above-mentioned problems in the prior art.

[0015] The embodiment of the present invention provides a text generation system based on a multi-agent collaboration mechanism MOPAR, including:

[0016] a matching agent connected to the domain multi-agent system to obtain user writing requirements, generate matching prompt words based on the writing requirements, transmit the matching prompt words to the domain multi-agent system, perform domain matching with the domain multi-agent system using the matching prompt words, and optimize based on feedback information from the reflective agent in the domain multi-agent system;

[0017] The domain multi-agent system includes several multi-agents in different domains, which are connected to the matching agent, and are used to receive the matching prompt words, and obtain the multi-agent in the corresponding domain based on the matching prompt words, and generate the text content required by the user through the multi-agent in the corresponding domain based on the multi-agent collaboration mechanism MOPAR.

[0018] The embodiment of the present invention provides a text generation method based on a multi-agent collaboration mechanism MOPAR, comprising:

[0019] Acquiring user writing requirements through a matching agent, generating matching prompt words based on the writing requirements, transmitting the matching prompt words to a domain multi-agent system, performing domain matching with the domain multi-agent system through the matching prompt words, and optimizing based on feedback information from a reflective agent in the domain multi-agent system;

[0020] The matching prompt word is received through the domain multi-agent system, and the multi-agent of the corresponding domain is obtained according to the matching prompt word, and the text content required by the user is generated by the multi-agent of the corresponding domain based on the multi-agent collaboration mechanism MOPAR.

[0021] An embodiment of the present invention also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the above-mentioned text generation method based on the multi-agent collaboration mechanism MOPAR are implemented.

[0022] An embodiment of the present invention also provides a computer-readable storage medium, on which an implementation program for information transmission is stored. When the program is executed by a processor, the steps of the above-mentioned text generation method based on the multi-agent collaboration mechanism MOPAR are implemented.

[0023] The use of the embodiments of the present invention can include the following beneficial effects: In order to overcome the problems existing in the prior art, the embodiments of the present invention propose a text generation technology based on the MOPAR multi-agent collaboration mechanism in the form of natural language. By introducing a collaboration mechanism among multiple agents, it provides users with more efficient, professional and creative text generation services. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0025] Figure 1 Schematic diagram of a text generation system based on a multi-agent collaboration mechanism MOPAR according to an embodiment of the present invention;

[0026] Figure 2 is a flow chart of the multi-agent based MOPAR collaboration method according to an embodiment of the present invention;

[0027] Figure 3 Schematic diagram of agent relationships in an embodiment of the present invention;

[0028] Figure 4 It is a flow chart of a text generation method based on the multi-agent collaboration mechanism MOPAR according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this document.

[0030] System Example

[0031] According to an embodiment of the present invention, a text generation system based on a multi-agent collaboration mechanism MOPAR is provided. Figure 1 Schematic diagram of a text generation system based on a multi-agent collaborative mechanism MOPAR according to an embodiment of the present invention. Figure 1 As shown, the text generation system based on the multi-agent collaboration mechanism MOPAR according to an embodiment of the present invention specifically includes:

[0032] The matching agent 10 is connected to the domain multi-agent system and is used to obtain the user's writing requirements, generate matching prompt words based on the writing requirements, transmit the matching prompt words to the domain multi-agent system, perform domain matching with the domain multi-agent system using the matching prompt words, and optimize based on feedback information from the reflective agent in the domain multi-agent system;

[0033] The writing requirements include the writing topic, target audience and content requirements;

[0034] The matching prompt words include the writing requirements and relevant information of multiple agents in various fields;

[0035] The domain multi-agent system 12 includes multiple multi-agents in different domains, connected to the matching agent, and configured to receive the matching prompt word, obtain a multi-agent in the corresponding domain based on the matching prompt word, and generate the text content required by the user through the multi-agent in the corresponding domain based on the multi-agent collaboration mechanism MOPAR, specifically including:

[0036] an outline agent, connected to the matching agent, the perspective agent, and the reflection agent, configured to receive the writing requirements, generate a writing body structure based on the writing requirements, transmit the writing requirements and the writing body structure to the perspective agent, and optimize the writing body structure based on feedback from the reflection agent; wherein the writing body structure includes several levels of writing outlines;

[0037] a perspective agent, connected to the outline agent, the retrieval agent, and the reflection agent, configured to receive the writing requirements and the writing subject structure, generate a plurality of writing perspectives for each level of the writing outline based on the writing requirements, transmit the writing subject structure and the plurality of writing perspectives to the retrieval agent, and optimize the writing based on feedback from the reflection agent;

[0038] a retrieval agent, connected to the perspective agent, the summary agent, and the reflection agent, for receiving the writing subject structure and the multiple types of writing perspectives, generating corresponding search statements for each writing perspective of each level of the writing outline based on the writing subject structure and the multiple types of writing perspectives, calling a search engine to retrieve professional knowledge in related fields using the search statements to obtain search results, transmitting the writing subject structure, the multiple types of writing perspectives, and the search results to the summary agent, and performing optimization based on feedback from the reflection agent;

[0039] a summarizing agent, connected to the retrieval agent and the generation agent, configured to receive the writing subject structure, the multiple types of writing perspectives, and the search results, summarize each writing perspective and its corresponding professional knowledge in each level of the writing outline, eliminate redundant content, obtain a comprehensive summary, and transmit the comprehensive summary to the generation agent;

[0040] a generating agent connected to the summarizing agent and the reflecting agent, configured to receive the comprehensive summary content, generate text based on the comprehensive summary content to obtain initial text content, transmit the initial text content to the reflecting agent, and optimize the text based on feedback information from the reflecting agent;

[0041] a reflective agent, connected to the matching agent, outline agent, perspective agent, retrieval agent, and generation agent, for receiving the writing requirements and the initial text content, reviewing the initial text content according to the writing requirements, forming corresponding feedback information based on the review results, and transmitting the feedback information to the matching agent, outline agent, perspective agent, retrieval agent, and generation agent to generate the final text content required by the user;

[0042] The review result is whether the initial text content meets the user's writing needs or whether the initial text content does not meet the user's writing needs.

[0043] The following is a specific example of a text generation system based on a multi-agent collaborative mechanism MOPAR according to an embodiment of the present invention. Figure 2 As shown, the above technical solution of the embodiment of the present invention is described in detail.

[0044] In order to address the many limitations of existing text generation technologies, the embodiments of the present invention propose a multi-agent collaborative mechanism MOPAR (Match-Outline-Perspective-Action-Reflect). Among them, Match: automatically matches domain agents according to the user's writing requirements. Outline: The outline generation agent first writes an outline for the user's writing requirements. Perspective: The perspective generation agent generates a variety of writing perspectives based on the results of the outline generation agent and the user's writing requirements. Action: In the Action stage, it can be divided into three agents, responsible for retrieval (Search), summary (Summary) and generation (Generation), and these three agents jointly perform the task (Take Action). The retrieval agent is responsible for retrieving professional domain knowledge related to the output of the outline agent and the perspective generation agent from the knowledge base, and then handing the results to the summary agent. The summary agent integrates all perspectives of all outlines and the retrieved knowledge, summarizes them, and then passes the message to the generation agent to generate the initial text. Reflect: The reflection agent reviews and modifies according to the results of the Action stage, and the user finally obtains the modified and optimized text content.

[0045] The implementation steps of the embodiment of the present invention specifically include:

[0046] S1. User demand reception and multi-agent matching

[0047] S1.1 The algorithm of the embodiment of the present invention takes user requirements in natural language as input, including writing topics, target audiences, content requirements, etc. The algorithm of the embodiment of the present invention has good natural language understanding capabilities and can accurately interpret user intent.

[0048] S1.2 Based on user needs, a matching prompt word p_match is combined and input into a large language model (the embodiment of the present invention is not limited to a specific large language model, such as GPT-4, Tongyi Qianwen, etc.), to form an intelligent matching agent (Match agent). In addition to the user needs, p_match also contains relevant information such as the functional description of agents in various fields, which is used to achieve multi-agent matching.

[0049] The S1.3 Match agent categorizes and selects user needs, identifying a multi-agent set (e.g., legal or medical) that meets these requirements. This multi-agent set consists of an Outline agent, a Perspective agent, a Search agent, a Summary agent, a Generation agent, and a Reflection agent. These agents execute sequentially in a pipelined manner to generate text for users with deep expertise and broad content coverage.

[0050] S2. Outline Generation

[0051] S2.1 Construct the outline generation prompt word p_outline, combine it with user needs and input it into the big model to build the outline generation agent (Outline agent).

[0052] S2.2 The Outline agent generates a writing outline o based on the user's needs, including the outline title and writing theme, and breaks down the user's needs to form the main structure of the writing.

[0053] S3. Multi-dimensional perspective generation

[0054] S3.1 Construct the perspective generation prompt word p_perspective, combine user needs and the output o of the Outline agent into the large language model, and construct the perspective generation agent (Perspective agent).

[0055] The S3.2 Perspective agent leverages the outline and user needs to generate diverse writing perspectives p for each level of the outline, improving the diversity of generated text. This agent can consider different writing perspectives to ensure diverse details in the generated text.

[0056] S4. Information Retrieval

[0057] S4.1 Construct the search prompt word p_search, combine the output o of the Outline agent and the output p of the perspective generation agent, and construct the retrieval agent (Search agent).

[0058] The S4.2 Search agent can generate a search statement q for each writing perspective at each level of the outline. The agent then calls an internal knowledge base or an internet search engine to retrieve relevant domain knowledge. Using this knowledge, the agent generates a response to the search statement q as the search result a. The search agent in this embodiment of the present invention ensures the accuracy and relevance of the search results, ensuring that subsequent text generation is based on reliable information.

[0059] S5. Information Summary

[0060] S5.1 Construct the summary prompt word p_summary, combine the output o of the Outline agent, the output p of the Perspective agent and the output a of the Search agent to construct the Summary agent.

[0061] The S5.2 Summary agent summarizes each writing perspective and the corresponding knowledge a in each level of the outline, extracting key information and outputting a comprehensive summary of knowledge s, eliminating redundant information. The agent's primary task is to ensure the accuracy and conciseness of this information, so that subsequent text generation can be based on high-quality information.

[0062] S6. Text Generation

[0063] S6.1 Text generation agent construction: The algorithm combines the text generation prompt word p_generation based on the output of the Outline agent, the output of the Perspective agent, and the output of the Summary agent, inputs it into the large language model, and constructs a text generation agent.

[0064] S6.2 First Draft Generation: The Generation agent generates a first draft text g based on the text generation prompt word p_generation. This agent's goal is to combine the output of the Outline, Perspective, and Summary agents to generate text, ensuring its coherence and naturalness, increasing the depth and breadth of knowledge contained in the text, and enabling users to obtain higher-quality text.

[0065] S7. Reflection and Optimization

[0066] S7.1 Construction of reflection prompt words: The algorithm combines the reflection prompt word p_reflection according to the output of the Generation agent and the needs of the user, inputs it into the large model, and constructs the reflection agent.

[0067] S7.2 First Draft Review: The Reflect agent reviews and evaluates the first draft text based on the reflection prompt p_reflect, generating review comments or revision suggestions. The core goal of the Reflect agent is to consider the accuracy, coherence, and compliance with user needs of the text during the review process, and to generate high-quality review comments.

[0068] S7.3 Feedback and Revision: The Generation agent rewrites the text based on the feedback from the Reflect agent, which then reviews it, forming a feedback mechanism. This feedback mechanism allows for multiple iterations to achieve optimal results, ultimately generating high-quality text.

[0069] S7.4 Requirements Satisfaction Judgment: The Reflect agent also determines whether the current content meets the user's needs. If not, it provides feedback to the Match agent or other agents for regeneration or additional information. Specifically, feedback is fed back to the Match agent for matching multiple agents in other fields (to meet the user's cross-domain writing needs), or to the Outline agent, Perspective agent, Search agent, and Generation agent for regeneration or supplementation of outlines, perspectives, and knowledge.

[0070] S8. Final text output

[0071] After the final review by the Reflect agent, users obtain the optimized final text content.

[0072] like Figure 3 As shown, the intelligent agent of the embodiment of the present invention specifically includes the following contents:

[0073] 1. Multi-agent collaborative mechanism (MOPAR):

[0074] The MOPAR mechanism includes five stages: Match, Outline, Perspective, Action (Search, Summary, Generation) and Reflect. Through division of labor and cooperation among intelligent agents, efficient and professional text generation is achieved.

[0075] The collaboration between agents, including how agents dynamically combine and perform tasks based on user needs.

[0076] 2. Dynamic matching of agents (Match):

[0077] Automatically identify user needs and match them with appropriate domain agents, reducing the need for fine-tuning models for specific scenarios.

[0078] 3. Outline and Multi-dimensional Perspective Generation (Outline & Perspective):

[0079] Automatically generate a writing outline to provide a structured framework for user needs.

[0080] Generate diverse writing perspectives based on the outline to increase the diversity and professionalism of the text.

[0081] 4. Information retrieval and summary (Search & Summary):

[0082] Intelligently retrieve professional information in related fields and ensure the accuracy and relevance of the information.

[0083] Summarize the retrieved information, eliminate redundant information, and improve information quality.

[0084] 5. High-quality text generation (Generation):

[0085] Combine the results of the previous stages to generate a coherent and natural first draft text, ensuring the professionalism and breadth of the content.

[0086] 6. Feedback and optimization mechanism (Reflect):

[0087] Review the generated text and provide modification suggestions to form an iterative optimization feedback mechanism to ensure the quality of the final text generation.

[0088] In summary, the problem to be solved by the embodiments of the present invention is to improve the quality of text generation, enhance the knowledge expertise and content richness of the text. Specifically, the purposes of the embodiments of the present invention include:

[0089] (1) Improving the professionalism of generated content: In order to address the limitations of large language models in professional domain knowledge, the embodiment of the present invention proposes a multi-agent-based MOPAR collaboration method, in which the agents can automatically match, retrieve and integrate professional knowledge in related fields according to the user's specific domain needs, ensuring that the generated text is highly professional.

[0090] (2) Increase the diversity of generated content: The “Perspective” agent in the MOPAR mechanism can generate text content from multiple perspectives according to user requirements, while the agent in the “Action” stage further enriches text details from different dimensions, thereby ensuring that the final generated text not only meets user needs but also has diverse perspectives.

[0091] (3) Improved system flexibility: Unlike traditional fixed models and single-scenario applications, the present invention enables rapid adaptation to diverse application scenarios through flexible collaboration among multiple agents. Whether in medicine, law, or engineering, MOPAR can rapidly adjust its strategies to meet evolving needs.

[0092] (4) Establishing an effective feedback and optimization mechanism: In order to solve the problem of lack of effective feedback in the prior art, the embodiment of the present invention introduces a "Reflect" intelligent agent, which is responsible for reviewing the generated content and optimizing and correcting it as needed to ensure the quality of the output text.

[0093] In summary, the embodiments of this invention aim to provide a more flexible, professional, and diverse text generation solution through the MOPAR multi-agent collaborative mechanism, overcoming the key shortcomings of existing technologies and providing users with high-quality text generation methods and services. The goal of these embodiments is to build a text generation platform that can adapt to different scenarios and possess self-optimization capabilities, thereby advancing the development of text generation technology to a new level.

[0094] Method Example

[0095] According to an embodiment of the present invention, a text generation method based on a multi-agent collaboration mechanism MOPAR is provided. Figure 4 This is a flow chart of a text generation method based on a multi-agent collaborative mechanism MOPAR according to an embodiment of the present invention. Figure 4 As shown, the text generation method based on the multi-agent collaboration mechanism MOPAR according to an embodiment of the present invention specifically includes:

[0096] Step S401: obtaining user writing requirements through a matching agent, generating matching prompt words based on the writing requirements, transmitting the matching prompt words to a domain multi-agent system, performing domain matching with the domain multi-agent system using the matching prompt words, and optimizing based on feedback from a reflective agent in the domain multi-agent system;

[0097] The writing requirements include the writing topic, target audience and content requirements;

[0098] The matching prompt words include the writing requirements and relevant information of multiple agents in various fields;

[0099] Step S402: receiving the matching prompt word through the domain multi-agent system, obtaining a multi-agent in the corresponding domain based on the matching prompt word, and generating the text content required by the user through the multi-agent in the corresponding domain based on the multi-agent collaboration mechanism MOPAR, specifically including:

[0100] The outline agent in the multi-agent receives the writing requirement, generates a writing body structure according to the writing requirement, transmits the writing requirement and the writing body structure to the perspective agent, and optimizes the writing body structure according to the feedback information of the reflection agent; wherein the writing body structure includes several levels of writing outlines;

[0101] receiving the writing requirements and the writing subject structure through a perspective agent, generating a plurality of writing perspectives for each level of the writing outline based on the writing requirements, transmitting the writing subject structure and the plurality of writing perspectives to a retrieval agent, and optimizing the writing based on feedback from the reflection agent;

[0102] The writing subject structure and the multiple types of writing perspectives are received by a retrieval agent, and corresponding search statements are generated for each writing perspective of each level of the writing outline based on the writing subject structure and the multiple types of writing perspectives. A search engine is called to retrieve professional knowledge in related fields using the search statements to obtain search results. The writing subject structure, the multiple types of writing perspectives, and the search results are transmitted to a summarizing agent, and optimization is performed based on feedback information from the reflecting agent.

[0103] The summarizing agent receives the writing subject structure, the multiple types of writing perspectives, and the search results, summarizes each writing perspective and its corresponding professional knowledge in each level of the writing outline, eliminates redundant content, obtains comprehensive summary content, and transmits the comprehensive summary content to the generating agent;

[0104] The generating agent receives the comprehensive summary content, generates text based on the comprehensive summary content to obtain initial text content, transmits the initial text content to the reflecting agent, and optimizes the text based on feedback information from the reflecting agent;

[0105] The reflection agent receives the writing requirement and the initial text content, reviews the initial text content according to the writing requirement, generates corresponding feedback information based on the review results, and transmits the feedback information to the matching agent, outline agent, perspective agent, retrieval agent and generation agent to generate the final text content required by the user;

[0106] The review result is that the initial text content meets the user's writing needs or the initial text content does not meet the user's writing needs.

[0107] The embodiment of the present invention is a method embodiment corresponding to the above-mentioned system embodiment. The specific operation of each step can be understood by referring to the description of the system embodiment, and will not be repeated here.

[0108] In summary, the beneficial effects of the embodiments of the present invention include:

[0109] 1. Reduced reliance on model training and fine-tuning: By designing a novel multi-agent collaboration mechanism, MOPAR, this embodiment of the present invention strives to significantly reduce or even eliminate the need for model fine-tuning in specific scenarios without sacrificing generation quality. This approach utilizes intelligent matching of agents (Match) and multiple agents in the Action phase to dynamically combine agents based on specific user needs, adapting to different application scenarios without changing the underlying model.

[0110] 2. Improved professionalism of generated content: Through collaboration between agents, embodiments of the present invention can automatically match, retrieve, and integrate relevant domain expertise based on the user's specific domain needs, ensuring the generated text is highly professional. This mechanism overcomes the limitations of a single model in a specific domain and improves the accuracy and credibility of generated content.

[0111] 3. Increased diversity of generated content: The "Perspective" agent can generate a variety of writing perspectives, while the "Action" stage agent further enriches the text details, so that the final generated text not only meets user needs but also has a multi-dimensional perspective, enhancing the richness and attractiveness of the text.

[0112] 4. Improved flexibility of text generation algorithms: Through flexible collaboration among multiple agents, this embodiment of the present invention enables rapid adaptation to diverse application scenarios. Whether facing specialized needs in fields such as medicine, law, or engineering, the system can quickly adjust its strategies to meet evolving requirements.

[0113] 5. An effective feedback and optimization mechanism has been established: The introduction of the "Reflect" intelligent agent solves the problem of lack of effective feedback in existing technologies. It is responsible for reviewing the generated content and optimizing and correcting it as needed to ensure the quality of the output text. This mechanism improves the accuracy and reliability of text generation.

[0114] 6. High degree of automation: From demand reception, intelligent agent matching, outline generation to final text output, the entire process is highly automated, which greatly reduces the need for manual intervention and improves work efficiency.

[0115] 7. Support cross-domain applications: Through collaboration between intelligent agents, the embodiments of the present invention can easily cope with complex cross-domain tasks, achieve seamless switching between different fields, and provide users with a unified text generation solution.

[0116] 8. Improved text generation: The method established by the embodiment of the present invention provides a more intelligent, flexible and efficient text generation technology, enabling users to obtain higher quality and more targeted service experience, and through continuous self-optimization, better meeting the personalized needs of users.

[0117] Device Example 1

[0118] An embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps described in the method embodiment when executed by the processor.

[0119] Device Example 2

[0120] An embodiment of the present invention provides a computer-readable storage medium, on which a program for implementing information transmission is stored. When the program is executed by a processor, the steps described in the method embodiment are implemented.

[0121] The computer-readable storage medium in this embodiment includes but is not limited to: ROM, RAM, magnetic disk or optical disk, etc.

[0122] 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 above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A text generation system based on multi-agent collaboration mechanism MOPAR, characterized by include: a matching agent connected to the domain multi-agent system to obtain user writing requirements, generate matching prompt words based on the writing requirements, transmit the matching prompt words to the domain multi-agent system, perform domain matching with the domain multi-agent system using the matching prompt words, and optimize based on feedback information from the reflective agent in the domain multi-agent system; The domain multi-agent system includes multiple multi-agents in different domains, connected to the matching agent, configured to receive the matching prompt word, obtain a multi-agent in the corresponding domain based on the matching prompt word, and generate the text content required by the user through the multi-agent in the corresponding domain based on the multi-agent collaboration mechanism MOPAR. The domain multi-agent system specifically includes: an outline agent, connected to the matching agent, the perspective agent, and the reflection agent, configured to receive the writing requirements, generate a writing body structure based on the writing requirements, transmit the writing requirements and the writing body structure to the perspective agent, and optimize the writing body structure based on feedback from the reflection agent; wherein the writing body structure includes several levels of writing outlines; a perspective agent, connected to the outline agent, the retrieval agent, and the reflection agent, configured to receive the writing requirements and the writing subject structure, generate a plurality of writing perspectives for each level of the writing outline based on the writing requirements, transmit the writing subject structure and the plurality of writing perspectives to the retrieval agent, and optimize the writing based on feedback from the reflection agent; a retrieval agent, connected to the perspective agent, the summary agent, and the reflection agent, for receiving the writing subject structure and the multiple types of writing perspectives, generating corresponding search statements for each writing perspective of each level of the writing outline based on the writing subject structure and the multiple types of writing perspectives, calling a search engine to retrieve professional knowledge in related fields using the search statements to obtain search results, transmitting the writing subject structure, the multiple types of writing perspectives, and the search results to the summary agent, and performing optimization based on feedback from the reflection agent; a summarizing agent, connected to the retrieval agent and the generation agent, configured to receive the writing subject structure, the multiple types of writing perspectives, and the search results, summarize each writing perspective and its corresponding professional knowledge in each level of the writing outline, eliminate redundant content, obtain a comprehensive summary, and transmit the comprehensive summary to the generation agent; a generating agent connected to the summarizing agent and the reflecting agent, configured to receive the comprehensive summary content, generate text based on the comprehensive summary content to obtain initial text content, transmit the initial text content to the reflecting agent, and optimize the text based on feedback information from the reflecting agent; a reflective agent, connected to the matching agent, outline agent, perspective agent, retrieval agent, and generation agent, for receiving the writing requirements and the initial text content, reviewing the initial text content according to the writing requirements, forming corresponding feedback information based on the review results, and transmitting the feedback information to the matching agent, outline agent, perspective agent, retrieval agent, and generation agent to generate the final text content required by the user; The review result is whether the initial text content meets the user's writing needs or whether the initial text content does not meet the user's writing needs.

2. The system according to claim 1, wherein: The writing requirements include the writing topic, target audience, and content requirements; The matching prompt words include the writing requirements and relevant information of multiple agents in various fields.

3. A text generation method based on multi-agent collaboration mechanism MOPAR, characterized by include: Acquiring user writing requirements through a matching agent, generating matching prompt words based on the writing requirements, transmitting the matching prompt words to a domain multi-agent system, performing domain matching with the domain multi-agent system through the matching prompt words, and optimizing based on feedback information from a reflective agent in the domain multi-agent system; The domain multi-agent system receives the matching prompt word, obtains a multi-agent in the corresponding domain according to the matching prompt word, and generates the text content required by the user based on the multi-agent collaboration mechanism MOPAR by the multi-agent in the corresponding domain. Specifically, the process includes: The outline agent in the multi-agent receives the writing requirement, generates a writing body structure according to the writing requirement, transmits the writing requirement and the writing body structure to the perspective agent, and optimizes the writing body structure according to the feedback information of the reflection agent; wherein the writing body structure includes several levels of writing outlines; receiving the writing requirements and the writing subject structure through a perspective agent, generating a plurality of writing perspectives for each level of the writing outline based on the writing requirements, transmitting the writing subject structure and the plurality of writing perspectives to a retrieval agent, and optimizing the writing based on feedback from the reflection agent; The writing subject structure and the multiple types of writing perspectives are received by a retrieval agent, and corresponding search statements are generated for each writing perspective of each level of the writing outline based on the writing subject structure and the multiple types of writing perspectives. A search engine is called to retrieve professional knowledge in related fields using the search statements to obtain search results. The writing subject structure, the multiple types of writing perspectives, and the search results are transmitted to a summarizing agent, and optimization is performed based on feedback information from the reflecting agent. The summarizing agent receives the writing subject structure, the multiple types of writing perspectives, and the search results, summarizes each writing perspective and its corresponding professional knowledge in each level of the writing outline, eliminates redundant content, obtains comprehensive summary content, and transmits the comprehensive summary content to the generating agent; The generating agent receives the comprehensive summary content, generates text based on the comprehensive summary content to obtain initial text content, transmits the initial text content to the reflecting agent, and optimizes the text based on feedback information from the reflecting agent; The reflection agent receives the writing requirement and the initial text content, reviews the initial text content according to the writing requirement, generates corresponding feedback information based on the review results, and transmits the feedback information to the matching agent, outline agent, perspective agent, retrieval agent and generation agent to generate the final text content required by the user; The review result is whether the initial text content meets the user's writing needs or whether the initial text content does not meet the user's writing needs.

4. The method according to claim 3, characterized in that The writing requirements include the writing topic, target audience, and content requirements; The matching prompt words include the writing requirements and relevant information of multiple agents in various fields.

5. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the text generation method based on the multi-agent collaboration mechanism MOPAR as described in any one of claims 3-4.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by the processor, the steps of the text generation method based on the multi-agent collaboration mechanism MOPAR as described in any one of claims 3 to 4 are implemented.

Images