System and method for generating official document based on large model

Abstract

The invention discloses an official document generation system and method based on a large model, belongs to the technical field of artificial intelligence, and aims to solve the technical problems of low official document format and content accuracy, poor material failure and poor content innovation in official document generation. Comprising a model training module used for performing model training on an official document generation model based on official document samples in an official document sample library; the model fine tuning module is used for performing layered fine tuning on the trained official document generation model; the cue word optimization module is used for carrying out cue word matching on user input based on a built-in cue word set; the outline generation module is used for calling a final official document generation model to generate an official document outline based on the cue word combination and user input; and the official document generation module is used for calling the final official document generation model to generate and output an official document body based on the user input and the final official document outline, and calling the privacy data shielding module to shield the privacy data in the official document body.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a system and method for generating official documents based on a large model. Background Art

[0002] At present, domestic document generation technology is mainly concentrated on academic research based on deep learning methods. Among them, various large models based on Transformer decoder are pre-trained through massive unsupervised data. The generated texts exceed the performance of other models in contextual coherence and emotional expression, making it one of the main technologies for text generation.

[0003] However, the current generation system has problems such as low accuracy of official document format and content, poor timeliness of materials, and poor content innovation. It is not conducive to the creation of official documents and cannot meet the growing demand for official document writing.

[0004] The low accuracy of official document format and content, poor material validity, and poor content innovation in official document generation are technical problems that need to be solved. Summary of the invention

[0005] The technical task of the present invention is to address the above shortcomings and provide a document generation system and method based on a large model to solve the technical problems of low accuracy of document format and content, poor material invalidity, and poor content innovation in the document generation process.

[0006] In a first aspect, the present invention provides a document generation system based on a large model, comprising:

[0007] A model training module, the model training module is used to regularly update the document sample library, and to train the document generation model based on the document samples in the document sample library. The document generation model is a pre-trained large language model, and is used to generate a document outline based on user input, and to generate a document body based on the user input and the document outline, wherein the user input includes the document title, document type, date of issuance, place of issuance, and keywords, and the keywords include subject, length, and context;

[0008] A model fine-tuning module, wherein the model fine-tuning module is used to perform hierarchical fine-tuning on the trained official document generation model to obtain a final official document generation model;

[0009] A prompt word optimization module, the prompt word optimization module is used to match prompt words input by the user based on a built-in prompt word set and output a prompt word combination;

[0010] An outline generation module, which is used to generate and output an official document outline based on a prompt word combination and user input and by calling a final official document generation model;

[0011] A user interaction editing module, which displays the official document outline through a user interaction interface and supports the user to review and adjust the official document outline to obtain the final official document outline;

[0012] A document generation module, which is used to generate and output the document body based on user input and the final document outline, call the final document generation model, and call the privacy data shielding module to shield the privacy data in the document body;

[0013] A security detection module, which is used to supervise and conduct security audits on the model training module, the model fine-tuning module, the prompt word optimization module, the outline generation module, the user interaction editing module, the official document generation module, and the privacy data shielding module;

[0014] A rewriting extension module, which is used to support users to rewrite and expand the generated official document body;

[0015] An evaluation and optimization module, wherein the evaluation and optimization module is used to receive user feedback and optimize the document generation model and the system based on the user feedback.

[0016] Preferably, the model training module is used to perform the following:

[0017] Collecting official document samples, wherein the official document samples cover various types of official documents;

[0018] Perform data preprocessing on the collected official document samples, and perform data cleaning, denoising, text format standardization, text segmentation and part-of-speech tagging, as well as text expansion and enhancement on the official document samples through data preprocessing to obtain preprocessed official document samples, and regularly update the preprocessed official document samples to the sample library;

[0019] The official document generation model is trained based on the official document samples in the sample library to obtain a trained official document generation model.

[0020] Preferably, the model fine-tuning module is used to perform hierarchical fine-tuning on the trained document generation model as follows:

[0021] According to the document type, fine-tune the structure and language style of the document generation model;

[0022] Fine-tune the document model based on the document format and application industry characteristics to ensure the coherence and logic of the generated document;

[0023] In response to the coherence and logic requirements of long official documents, the official document generation model is fine-tuned in a supervised manner to ensure that long official documents with clear structure and strict logic are generated.

[0024] Preferably, for the prompt word optimization module, the prompt word set includes basic official document elements and covers data and professional vocabulary of various industries;

[0025] The prompt word optimization module is used to adjust the weight combination of matching prompt words based on the context specified in the user input through a pre-configured context-aware strategy, and output a prompt word combination that meets the specified context.

[0026] Preferably, the user interaction module is configured with a template library, editing tools and editing services, which support users to edit and optimize the official document outline, and adjust the font and paragraph settings of the official document outline through editing and optimization.

[0027] Preferably, the document generation module is used to generate multimodal content including recommended charts and cited documents according to the document type and keywords specified in the user input.

[0028] Preferably, the security detection module is used to encrypt and perform access control on data transmission between the model training module, the model fine-tuning module, the prompt word optimization module, the outline generation module, the user interaction editing module, the official document generation module and the privacy data shielding module based on a preconfigured encryption method and access control policy, and the data involved in the model training module, the model fine-tuning module, the prompt word optimization module, the outline generation module, the user interaction editing module, the official document generation module and the privacy data shielding module are stored in a high-security server with a firewall, intrusion detection service and data backup service.

[0029] Preferably, the privacy data masking module is used to identify the privacy data in the body of the document through entity recognition technology and replace the privacy data with pre-configured special symbols.

[0030] Preferably, the rewriting extension module is configured with a rewriting extension strategy for supporting users to optimize and expand specific paragraphs or the entire text of the document, and for adjusting the rewriting extension strategy based on user feedback and user input.

[0031] In a second aspect, the present invention provides a method for generating official documents based on a large model, which is used to generate the main body of an official document by using an official document generation system based on a large model as described in any one of the first aspects, and comprises the following steps:

[0032] Model training: Update the document sample library through the model training module, and train the document generation model based on the document samples in the document sample library to obtain the trained document generation model;

[0033] Model fine-tuning: The trained document generation model is fine-tuned in layers through the model fine-tuning module to obtain the final document generation model;

[0034] Prompt word optimization: Based on user input, the prompt word optimization module is called to output the prompt word combination;

[0035] Outline generation: taking the user input and prompt word combination as input, calling the final document generation model to generate and output the document outline;

[0036] Outline adjustment: Users review and adjust the document outline based on the user interactive editing module to obtain the final document outline;

[0037] Official document generation: Based on user input and the final official document outline, the official document generation module calls the final official document generation model to generate and output the official document body, and calls the privacy data masking module to mask the privacy data in the official document body;

[0038] Security audit: supervise and conduct security audits on model training, model fine-tuning, prompt word optimization, outline generation, outline adjustment, official document generation, and privacy data shielding;

[0039] Rewrite and expand: Users can rewrite and expand the generated official document text through the rewrite extension module;

[0040] Evaluation and Optimization: Receive user feedback through the evaluation and optimization module, and optimize the document generation model and document generation system based on user feedback.

[0041] The document generation system and method based on the large model of the present invention has the following advantages:

[0042] 1. Improve efficiency: significantly shorten the document writing cycle and reduce the burden on staff;

[0043] 2. Enhance accuracy: ensure that the format of official documents is standardized and the content is accurate, reducing human errors;

[0044] 3. Enhance innovation and personalization: Improve the innovation and personalized expression of official documents through specific optimization and user interaction;

[0045] 4. Real-time and flexibility: Quickly respond to the latest policy changes and information updates to ensure the timeliness of official document content. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] The present invention is further described below in conjunction with the accompanying drawings.

[0048] Figure 1 This is a flowchart of Example 1, in which a document generation system based on a large model generates an official document. DETAILED DESCRIPTION

[0049] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it. However, the embodiments are not intended to limit the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments may be combined with each other.

[0050] The embodiments of the present invention provide a system and method for generating official documents based on a large model, which are used to solve the technical problems of low accuracy of official document format and content, poor material expiration, and poor content innovation in official document generation.

[0051] Embodiment 1:

[0052] The invention discloses a document generation system based on a large model, comprising a model training module, a model fine-tuning module, a prompt word optimization module, an outline generation module, a user interactive editing module, a document generation module, a privacy data shielding module, a security detection module, a rewriting expansion module and an evaluation optimization module.

[0053] The model training module is used to regularly update the official document sample library, and to train the official document generation model based on the official document samples in the official document sample library. The official document generation model is a pre-trained large language model, which is used to generate an official document outline based on user input, and to generate the official document body based on user input and the official document outline, wherein the user input includes the official document title, official document type, date of issuance, place of issuance and keywords, and the keywords include subject, length and context.

[0054] In this embodiment, the model training module is used to perform the following:

[0055] (1) collecting official document samples, wherein the official document samples cover various types of official documents;

[0056] (2) Performing data preprocessing on the collected official document samples, including data cleaning, denoising, text format standardization, text segmentation and part-of-speech tagging, and text expansion and enhancement, to obtain preprocessed official document samples, and regularly updating the preprocessed official document samples to the sample library;

[0057] (3) The official document generation model is trained based on the official document samples in the sample library to obtain a trained official document generation model.

[0058] In this embodiment, the work of the model training module includes three stages: data collection, data preprocessing and basic model training.

[0059] During the data collection phase, a large number of different types of official document samples need to be collected and sorted. These samples should cover 15 types of official documents, such as reports, notices, requests for instructions, and replies, to ensure the diversity and representativeness of the samples, so as to cover various industries and fields. In order to improve the model's ability to generate official documents for specific industries, it is necessary to collect special samples for specific industries. For example, when collecting official documents from government departments, special attention should be paid to policy documents, regulatory documents, etc.; when collecting corporate documents, attention should be paid to contracts, reports, and other types. Collect representative and timely official documents. Update the sample library regularly to include the latest policy documents, industry reports, etc., to ensure that the model can keep up with the times and generate official documents that keep pace with the times.

[0060] In the data preprocessing stage, the collected samples need to be cleaned, irrelevant information and noise data need to be removed, the text format needs to be standardized, and the standardization and consistency of the data need to be ensured; the text needs to be processed by word segmentation and part-of-speech tagging to better extract key information from the text. In addition, in order to ensure the generalization ability of the model, the text is expanded and enhanced, and the diversity of the text is increased through synonym replacement and sentence reorganization. This prevents the training effect of the model from being affected by data problems.

[0061] In the basic model training phase, a pre-trained large language model, such as BERT or GPT, is used as the basic model, and the model is trained through a large number of official document samples so that it can better adapt to the unique language style and structure of official documents. This process not only improves the accuracy of the model, but also enhances its flexibility and adaptability in practical applications.

[0062] The model fine-tuning module is used to perform hierarchical fine-tuning on the trained document generation model to obtain the final document generation model.

[0063] As a specific implementation of the model fine-tuning module, this module is used to perform the following hierarchical fine-tuning on the trained document generation model:

[0064] (1) Fine-tune the structure and language style of the document generation model according to the document type;

[0065] (2) Fine-tune the document model based on the document format and application industry characteristics to ensure the coherence and logic of the generated document;

[0066] (3) In response to the coherence and logic requirements of long official documents, the official document generation model is fine-tuned in a supervised manner to ensure that long official documents with clear structure and strict logic are generated.

[0067] The model fine-tuning module of this embodiment first fine-tunes the macro structure and language style of the official document type, and then makes micro-detail adjustments based on the specific official document format and industry characteristics, gradually refining the performance of the model in specific scenarios to ensure the coherence and logic of the generated official documents. In response to the coherence and logic requirements of long official documents, the model is carefully fine-tuned in a supervised manner to ensure that the model can generate long articles with clear organization and strict logic. Improve the overall quality of official documents and ensure the fluency and readability of document content.

[0068] The prompt word optimization module is used to match prompt words input by the user based on the built-in prompt word set and output a prompt word combination.

[0069] For the prompt word optimization module, the prompt word set includes basic official document elements and covers data and professional vocabulary of various industries. The prompt word optimization module is used to adjust the weight combination of matching prompt words based on the context specified in the user input and through the pre-configured context-aware strategy, and output a prompt word combination that meets the specified context. Among them, when matching prompt words through the prompt word set, the matching query method disclosed in the prior art can be selected, and this embodiment does not limit the specific method.

[0070] In order to improve the pertinence and professionalism of official documents, the prompt word optimization module of the present embodiment has designed a richer and more detailed prompt word set for 15 types of national standard official documents (such as minutes, notices, announcements, etc.). These prompt word sets not only contain basic official document elements, but also cover industry terms, professional vocabulary, etc., to ensure that the generated official documents are both in line with standards and professional. The prompt word optimization module also provides a context-aware prompt strategy, which can dynamically adjust the weight and combination of prompt words according to the official document background information (such as industry, theme, urgency, etc.) input by the user, so that the official documents generated by the model are more suitable for specific situations. These prompt word sets are intended to optimize the starting point of the model when generating specific types of official documents, thereby enhancing the relevance and innovation of the content. In this way, it can be ensured that each official document can accurately meet the needs of users.

[0071] The outline generation module is used to generate and output the official document outline based on the prompt word combination and user input and call the final official document generation model.

[0072] The outline generation module of this embodiment automatically constructs a preliminary document outline framework based on the parameters input by the user (such as length requirements, title, keywords, time, location, etc.) through the final document production model. This framework provides structural guidance for subsequent content generation, ensuring that the document's organizational structure is reasonable and efficient.

[0073] The user interactive editing module displays the official document outline through the user interactive interface, and supports users to review and adjust the official document outline to obtain the final official document outline.

[0074] As a specific implementation of the user interaction module, the module is configured with a template library, editing tools and editing services. The template library, editing tools and editing services support users to edit and optimize the official document outline, and adjust the font and paragraph settings of the official document outline through editing optimization.

[0075] The user interactive editing module of this embodiment provides a user interface that allows users to review and adjust the automatically generated outline. In addition, it also provides a wealth of editing tools and functions, such as font adjustment, paragraph setting, etc., so that users can edit and optimize official documents more conveniently. It ensures that the content can fully meet the specific needs and preferences of users. In this way, users can participate in every link of official document creation, thereby ensuring that the final output of official documents is both professional and personalized. And the template library technology is introduced to provide users with a wealth of official document templates for selection and use.

[0076] The official document generation module is used to generate and output the official document body based on user input and the final official document outline, calling the final official document generation model, and calling the privacy data masking module to mask the privacy data in the official document body.

[0077] As a specific implementation of the official document generation module, the module is used to generate multimodal content including recommended charts and references according to the official document type and keywords specified in the user input.

[0078] The document generation module of this embodiment uses a streaming output method to generate the document content according to the final confirmed outline. This method can ensure that the generated document content is smooth and coherent, and can quickly respond to user input and editing operations. The generated document is polished and optimized through natural language generation technology to make it more in line with the language style and expression habits of the document. In addition to the text content, the document generation module can also automatically generate multimodal content such as recommended charts and references according to the document type and user needs, thereby enhancing the information richness and persuasiveness of the document.

[0079] The privacy data shielding module of this embodiment is used to identify the privacy data in the body of the official document through entity recognition technology and replace the privacy data with pre-configured special symbols. These privacy data include sensitive information such as names, telephone numbers, and email addresses. Once these privacy data are identified, they are replaced with specific symbols (such as "xxx") to prevent the leakage of privacy data. In addition, the privacy data shielding module provides a service for users to customize shielding rules. Users can customize shielding rules and shield the identified privacy data based on the user-defined shielding rules to meet the special needs of users.

[0080] The security detection module is used to supervise and conduct security audits on the model training module, model fine-tuning module, prompt word optimization module, outline generation module, user interaction editing module, official document generation module and privacy data masking module.

[0081] As a specific implementation of the security detection module, this module is used to encrypt and control access to data transmission between the model training module, the model fine-tuning module, the prompt word optimization module, the outline generation module, the user interaction editing module, the official document generation module and the privacy data shielding module based on preconfigured encryption methods and access control policies. The data involved in the model training module, the model fine-tuning module, the prompt word optimization module, the outline generation module, the user interaction editing module, the official document generation module and the privacy data shielding module are stored in a high-security server with a firewall, intrusion detection service and data backup service.

[0082] The security detection module of this embodiment adopts strict data protection measures and implements a full-link security audit mechanism from data collection to official document output to ensure that data processing at each link meets the most stringent security standards and prevents potential data leakage risks. The security and privacy of user data are ensured by strictly supervising and auditing the data collection and processing process of the system. Encryption technology and access control policies are used to prevent unauthorized access and data leakage. Security audits and vulnerability scans are also performed on the system regularly to ensure the stability and security of the system. The official document data is stored on a server with higher security, and it is ensured that the server has security measures such as firewalls, intrusion detection, and data backup.

[0083] The rewrite extension module is used to support users to rewrite and expand the generated official document text.

[0084] As a specific implementation of the rewrite extension module, the module is configured with a rewrite extension strategy for supporting users to optimize and expand specific paragraphs or the entire text of the document, and for adjusting the rewrite extension strategy based on user feedback and user input.

[0085] The rewriting and extension module of this embodiment provides users with intelligent rewriting, expansion, and continuation tools. These tools can not only help users optimize and expand specific paragraphs or the entire text, but also automatically adjust the strategies and methods of rewriting and expansion based on user input and feedback. In this way, it can ensure that every official document meets the highest standards.

[0086] The evaluation and optimization module is used to receive user feedback and optimize the document generation model and the system based on the user feedback.

[0087] The evaluation and optimization module of this embodiment regularly evaluates and optimizes the system. By collecting user feedback and evaluation indicators (such as the quality of generated documents, user satisfaction, system stability, etc.), it can promptly discover problems and make improvements. This continuous improvement method enables the system to always maintain the best performance and user experience, and uses machine learning technology to automatically analyze and optimize user behavior and system performance. For example, the system's recommendation algorithm and interface design can be optimized by analyzing user usage habits and preferences, thereby improving user experience and satisfaction.

[0088] After the system of this embodiment trains and fine-tunes the document generation model, Figure 1 The following execution is shown to generate an official document: based on user input, a prompt word combination is matched through a prompt word set, based on the user input and the prompt word combination, an official document outline is output through an official document generation model, after the user adjusts the official document outline, the official document body is generated and output through the official document generation model based on the user input and the official document outline, and the user adjusts the official document body output by the model to obtain the final official document body.

[0089] Embodiment 2:

[0090] The present invention provides a method for generating official documents based on a large model, which generates the official document body through the system disclosed in Example 1, and includes the following steps:

[0091] S100 model training: The document sample library is updated through the model training module, and the document generation model is trained based on the document samples in the document sample library to obtain the trained document generation model;

[0092] S200 model fine-tuning: The model fine-tuning module is used to perform layered fine-tuning on the trained document generation model to obtain the final document generation model.

[0093] S300 prompt word optimization: based on user input, call the prompt word optimization module to output prompt word combinations;

[0094] S400 outline generation: taking the user input and prompt word combination as input, calling the final document generation model to generate and output the document outline;

[0095] S500 outline adjustment: The user reviews and adjusts the document outline based on the user interactive editing module to obtain the final document outline;

[0096] S600 Official document generation: Based on user input and the final official document outline, the official document generation module calls the final official document generation model to generate and output the official document body, and calls the privacy data masking module to mask the privacy data in the official document body;

[0097] S700 security audit: supervision and security audit of model training, model fine-tuning, prompt word optimization, outline generation, outline adjustment, official document generation, and privacy data shielding;

[0098] S800 rewrite and expand: users rewrite and expand the generated official document body through the rewrite expansion module;

[0099] S900 Evaluation and Optimization: Receive user feedback through the evaluation and optimization module, and optimize the document generation model and document generation system based on user feedback.

[0100] The method of this embodiment can automatically generate the body of an official document, and can optimize and update the core sample library and the official document generation model, thereby improving accuracy and real-time performance.

[0101] The present invention has been shown and described in detail above through the accompanying drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above multiple embodiments, those skilled in the art can know that the means in the above different embodiments can be combined to obtain more embodiments of the present invention, and these embodiments are also within the protection scope of the present invention.

Claims

1. A document generation system based on a large model, characterized in that: include: A model training module, the model training module is used to regularly update the document sample library, and to train the document generation model based on the document samples in the document sample library. The document generation model is a pre-trained large language model, and is used to generate a document outline based on user input, and to generate a document body based on the user input and the document outline, wherein the user input includes the document title, document type, date of issuance, place of issuance, and keywords, and the keywords include subject, length, and context; A model fine-tuning module, wherein the model fine-tuning module is used to perform hierarchical fine-tuning on the trained official document generation model to obtain a final official document generation model; A prompt word optimization module, the prompt word optimization module is used to match prompt words input by the user based on a built-in prompt word set and output a prompt word combination; An outline generation module, which is used to generate and output an official document outline based on a prompt word combination and user input and by calling a final official document generation model; A user interaction editing module, which displays the official document outline through a user interaction interface and supports the user to review and adjust the official document outline to obtain the final official document outline; A document generation module, which is used to generate and output the document body based on user input and the final document outline, call the final document generation model, and call the privacy data shielding module to shield the privacy data in the document body; A security detection module, which is used to supervise and conduct security audits on the model training module, the model fine-tuning module, the prompt word optimization module, the outline generation module, the user interaction editing module, the official document generation module, and the privacy data shielding module; A rewriting extension module, which is used to support users to rewrite and expand the generated official document body; An evaluation and optimization module, wherein the evaluation and optimization module is used to receive user feedback and optimize the document generation model and the system based on the user feedback.

2. The document generation system based on a large model according to claim 1 is characterized in that: The model training module is used to perform the following: Collecting official document samples, wherein the official document samples cover various types of official documents; Perform data preprocessing on the collected official document samples, and perform data cleaning, denoising, text format standardization, text segmentation and part-of-speech tagging, as well as text expansion and enhancement on the official document samples through data preprocessing to obtain preprocessed official document samples, and regularly update the preprocessed official document samples to the sample library; The official document generation model is trained based on the official document samples in the sample library to obtain a trained official document generation model.

3. The document generation system based on a large model according to claim 1 is characterized in that: The model fine-tuning module is used to perform the following layered fine-tuning on the trained document generation model: According to the document type, fine-tune the structure and language style of the document generation model; Fine-tune the document model based on the document format and application industry characteristics to ensure the coherence and logic of the generated document; In response to the coherence and logic requirements of long official documents, the official document generation model is fine-tuned in a supervised manner to ensure that long official documents with clear structure and strict logic are generated.

4. The document generation system based on a large model according to claim 1 is characterized in that: For the prompt word optimization module, the prompt word set includes basic official document elements and covers data and professional vocabulary of various industries; The prompt word optimization module is used to adjust the weight combination of matching prompt words based on the context specified in the user input through a pre-configured context-aware strategy, and output a prompt word combination that meets the specified context.

5. The document generation system based on a large model according to claim 1 is characterized in that: The user interaction module is configured with a template library, editing tools and editing services, and supports users in editing and optimizing the official document outline through the template library, editing tools and editing services, and adjusts the font and paragraph settings of the official document outline through editing and optimization.

6. The document generation system based on a large model according to claim 1 is characterized in that: The document generation module is used to generate multimodal content including recommended charts and references according to the document type and keywords specified in the user input.

7. The document generation system based on a large model according to claim 1 is characterized in that: The security detection module is used to encrypt and control access to data transmission between the model training module, the model fine-tuning module, the prompt word optimization module, the outline generation module, the user interaction editing module, the official document generation module and the privacy data shielding module based on a preconfigured encryption method and access control strategy. The data involved in the model training module, the model fine-tuning module, the prompt word optimization module, the outline generation module, the user interaction editing module, the official document generation module and the privacy data shielding module are stored in a high-security server with a firewall, intrusion detection service and data backup service.

8. The document generation system based on a large model according to claim 1 is characterized in that: The privacy data shielding module is used to identify the privacy data in the body of the document through entity recognition technology and replace the privacy data with pre-configured special symbols.

9. The document generation system based on a large model according to claim 1 is characterized in that: The rewriting extension module is configured with a rewriting extension strategy for supporting users to optimize and expand specific paragraphs or the entire text of the document, and for adjusting the rewriting extension strategy based on user feedback and user input.

10. A method for generating official documents based on a large model, characterized in that: The method is used to generate the body of an official document by using an official document generation system based on a large model as described in any one of claims 1 to 9, comprising the following steps: Model training: The document sample library is updated through the model training module, and the document generation model is trained based on the document samples in the document sample library to obtain the trained document generation model; Model fine-tuning: The model fine-tuning module is used to perform layered fine-tuning on the trained document generation model to obtain the final document generation model; Prompt word optimization: Based on user input, the prompt word optimization module is called to output the prompt word combination; Outline generation: taking the user input and prompt word combination as input, calling the final document generation model to generate and output the document outline; Outline adjustment: Users review and adjust the document outline based on the user interactive editing module to obtain the final document outline; Official document generation: Based on user input and the final official document outline, the official document generation module calls the final official document generation model to generate and output the official document body, and calls the privacy data masking module to mask the privacy data in the official document body; Security audit: supervise and conduct security audits on model training, model fine-tuning, prompt word optimization, outline generation, outline adjustment, official document generation, and privacy data shielding; Rewrite and expand: Users can rewrite and expand the generated official document text through the rewrite extension module; Evaluation and Optimization: Receive user feedback through the evaluation and optimization module, and optimize the document generation model and document generation system based on user feedback.

Images