Method and system for generating model essay with format template

Abstract

The invention discloses a method and a system for generating template essays with formats. The method comprises the following steps: presetting template information of a plurality of template essays; obtaining a required template model essay type; according to the required template model essay type and the template information of the preset template model essay, generating a prompt statement instruction and sending the prompt statement instruction to a content generation type AI service platform; the content generation type AI service platform generates a template model essay or a directory framework and content according to the prompt statement instruction requirement, feeds back and displays the template model essay or the directory framework and the content to the user; the scheme has the characteristics of improving content readability, reducing operation difficulty and saving time.

Description

Technical Field

[0001] The present invention relates to the field of content-generating AI, and in particular to a method and system for generating formatted template examples. Background Art

[0002] AI application websites, after integrating content-generating AI services such as ChatGPT and Wenxin Yiyan, can provide answers to specific user questions. Users can use chat windows or Q&A sessions on the website to request AI-generated templates, such as reports, proposals, plans, questionnaires, briefings, notices, minutes, regulations, and speeches, to meet specific requirements. The AI service will then generate text content based on the questions and provide it to the AI application website, which will then present it to the user.

[0003] Typically, AI application websites present users with plain text returned by AI services, which presents the following problems:

[0004] (1) The chapters and content are incomplete, and the paragraphs and formats are not arranged. Reading the text alone is not a good experience and it is easy to miss details.

[0005] (2) It cannot be used as a sample template. If you want to use it, you need to copy and paste it into a Word file, and then adjust the paragraphs and format manually, which is time-consuming.

[0006] Existing content-generating AI applications can generate sample text based on user questions, but they lack precise template type selection, making it difficult for users to obtain accurate templates. They also lack the ability to directly generate and display formatted templates. After obtaining the content, users still need to create the document, edit the content, and set the format. Therefore, there is an urgent need for a method and system for generating formatted templates to address these issues. Summary of the Invention

[0007] To achieve the above object, the inventor provides a method for generating a formatted template sample, comprising the following steps:

[0008] Preset template information of several template examples;

[0009] Get the required template type;

[0010] Generate prompt instructions based on the required template type and the template information of the preset template and send them to the content generation AI service platform;

[0011] The content-generating AI service platform generates template examples or directory frameworks and content according to prompt statement instructions, and displays them to users after feedback.

[0012] As a preferred embodiment of the present invention, the following steps are also included:

[0013] In the database, template information of several template examples is preset;

[0014] The AI application frontend obtains the required template type and sends instructions to the AI application backend;

[0015] The AI application backend obtains the preset template information of the required template type based on the template type, automatically encapsulates the prompt statement instruction, and requires the return of formatted HTML instance content, and sends the prompt statement instruction to the content generation AI service platform;

[0016] The content generation AI service platform generates templates or directory frameworks and content based on prompt instructions. If it is a template, it is directly fed back to the AI application backend. If it is a directory framework and content, it is fed back to the AI application backend after format adjustment.

[0017] The AI application backend feeds the formatted HTML instance content back to the AI application frontend and displays it to the user.

[0018] As a preferred embodiment of the present invention, the automatic packaging of prompt statement instructions includes: when generating content requirements and formatting requirements, specific requirements for content and format are put forward in plain text, all directory frameworks and corresponding format requirements are listed, and HTML example content with good readability is required to be output, and then packaged into prompt statement instructions recognized by the content generation AI service platform;

[0019] Alternatively, when generating content requirements, specific requirements for the content are made in plain text, listing all directory frames. At the same time, requirements for the content and format are made through HTML example content. The directory frames in the HTML example content correspond to the directory frames in the plain text, and the format is agreed upon using HTML and CSS. Readable HTML example content is required to be output, and then encapsulated into prompt statements that can be recognized by the content generation AI service platform.

[0020] Alternatively, when generating content requirements and formatting requirements, specific requirements for the content and format are made through plain text, listing all directory frameworks and corresponding format requirements. At the same time, requirements for the content and format are made through HTML instance content. The format is agreed upon by HTML and CSS, and it is required to output HTML instance content with good readability, and then encapsulate it into prompt statement instructions recognized by the content generation AI service platform.

[0021] As a preferred embodiment of the present invention, the AI application background is used to classify and grade templates used in the workplace, and provide them to users in different job roles for selective use. Template information for each type of template is pre-made in the database, and the AI application background obtains the pre-made template information from the database and caches it.

[0022] As a preferred method of the present invention, the AI application foreground obtains the required template example type and sends instructions to the AI application background, which also includes the following steps: the user enters the template example page, selects the first-level category of the template example according to user needs, and enters the details page corresponding to the template example category. The template example details page presents a list of template example types under the first-level category of the template example selected by the user. The user selects the required template example type according to the usage scenario in the template example type list. The AI application foreground will send the template example generation instruction to the AI application background based on the template example type selected by the user.

[0023] As a preferred embodiment of the present invention, the content generation AI service platform generates results according to prompt statement instructions and returns them to the AI application background, including: generating results that meet the chapter requirements, content requirements and formatted HTML instance content of the required template type.

[0024] As a preferred embodiment of the present invention, the AI application backend feeds back the formatted HTML instance content to the AI application frontend and displays it to the user, including the steps of: the AI application frontend parses the HTML instance content and displays the formatted template sample to the user.

[0025] As a preferred method of the present invention, it also includes a download step: if the user needs to download a generated and formatted template sample, by clicking the download option, the AI application foreground converts the HTML instance content into a word document through a third-party plug-in and downloads it to the user's local computer.

[0026] As a preferred embodiment of the present invention, the following steps are also included: when the content generation AI service platform generates template examples, the template examples are also stored in the template example instance library; when the number of examples corresponding to the same template example type accumulates to a preset level, the content quality is evaluated according to the algorithm and the score is calculated; if the preset score is reached, the AI application background directly selects the template example from the template example instance library and provides it to the user.

[0027] To achieve the above-mentioned purpose, the inventors also provide a system for generating a formatted template sample text, comprising:

[0028] Template sample display module, used to display information and / or provide user operation selection;

[0029] The template article category acquisition module is used to obtain the first-level category of template articles from the database and send it to the template article display module for display and / or for user selection;

[0030] The template sample type acquisition module is used to receive the template sample category selected by the user, obtain the subcategories and template sample types under the template sample category, and send them to the template sample display module for display and / or for user selection;

[0031] A template sample content generation module is configured to receive a template sample type selected by a user, retrieve preset information from a database, automatically encapsulate prompt statement instructions, generate formatted HTML instance content, and send it to the content generation AI service platform; and receive and parse the template sample content generated by the content generation AI service platform and send it to the template sample presentation module for display and / or user selection.

[0032] The content generation AI service platform is used to generate template sample content according to prompt statement instructions and return it to the template sample content generation module.

[0033] Different from the existing technology, the above technical solution has the following beneficial effects:

[0034] (1) The present invention is aimed at websites or apps of AI application type. When providing template model services to users, the present invention can quickly utilize the content returned by the content generation AI service platform to generate standard content and formatted template models that conform to different template model types. While solving the problems of poor readability of the original text and incomplete chapters and content, the present invention can enable users to directly view and download template models in a WYSIWYG manner.

[0035] (2) The present invention implements a method for guiding users to quickly find the template type they need in the form of classification and grading;

[0036] (3) The present invention provides a complete solution for users to search and find templates that meet their needs on AI application websites or apps;

[0037] (4) The present invention solves the problem of poor reading experience of pure text templates provided by large-scale AI services on AI application websites or apps, and effectively improves the readability of the content;

[0038] (5) The present invention solves the problem that AI application websites or APPs cannot download the plain text templates provided by large-scale AI services as Word documents that meet the content and format requirements and can be used directly, effectively reducing the user's operating difficulty and saving time. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flow chart of the method described in the specific embodiment;

[0040] Figure 2 The system flow described in the specific implementation method Figure 1 ;

[0041] Figure 3 This is a connection diagram of the functional modules in the system described in the specific implementation method;

[0042] Figure 4 The system flow described in the specific implementation method Figure 2 . DETAILED DESCRIPTION

[0043] In order to explain the technical content, structural features, achieved objectives and effects of the technical solution in detail, the following is a detailed description in conjunction with specific embodiments and accompanying drawings.

[0044] Example 1:

[0045] like Figure 1 As shown, this embodiment provides a method for generating a formatted template sample, comprising the following steps:

[0046] Preset template information of several template examples;

[0047] Get the required template type;

[0048] Generate prompt instructions based on the required template type and the template information of the preset template and send them to the content generation AI service platform;

[0049] The content-generating AI service platform generates template examples or directory frameworks and content according to prompt statement instructions, and displays them to users after feedback.

[0050] The specific implementation process of this embodiment includes the following steps:

[0051] In the database, template information of several template examples is preset, and the template information includes content requirements, formatting requirements, etc.

[0052] The AI application frontend obtains the required template type and sends instructions to the AI application backend;

[0053] The AI application backend obtains the preset template information of the required template type according to the type of template, automatically encapsulates the prompt statement instruction, and requires the return of formatted HTML instance content, and sends the prompt statement instruction to the content generation AI service platform; in this embodiment, the full name of HTML is Hypertext Markup Language, which is a markup language. It includes a series of tags. Through these tags, the document format on the network can be unified, and scattered Internet resources can be connected into a logical whole. HTML text is a descriptive text composed of HTML commands. HTML commands can describe text, graphics, animations, sounds, tables, links, etc.; the content generation AI service platform can be ChatGPT, Wenxin Yiyan, etc.

[0054] The content-generating AI service platform generates a template text or a directory framework and content according to the prompt statement instructions. If it is a template text, it is directly fed back to the AI application background. If it is a directory framework and content, it is fed back to the AI application background after format adjustment. In this embodiment, the content-generating AI service platform directly generates a template text with complete content and good format according to the prompt statement instructions; it can also be carried out in two steps, namely: first generate the directory framework and content of the template text to ensure the completeness of the content, and then adjust the content and format, which is carried out in two steps.

[0055] The AI application backend feeds formatted content, such as HTML instance content, to the AI application frontend and displays it to the user.

[0056] In the above embodiment, there are three ways to automatically encapsulate prompt statement instructions, specifically:

[0057] Method 1: When generating prompt statements, specify the content and formatting requirements in plain text, including listing all directory frameworks and corresponding formatting requirements. For example, the title format is bold, centered, Songti, size 3, and 2em line spacing; the summary format is bold, centered, Songti, size 4, and 2em line spacing. Readable HTML example content is then required to be output and then encapsulated into prompt statements that can be recognized by the content generation AI service platform.

[0058] Method 2: When generating prompt statement instructions, when the content is required to be generated, specific requirements are put forward for the content through plain text, including listing all directory frames, such as: title, abstract, etc., and at the same time, requirements are put forward for the content and format through HTML samples. The directory frame in the HTML reference case corresponds to the directory frame in the plain text, and the format is agreed upon through HTML and CSS, such as: the title uses tags such as H1, H2, the paragraph format is set with div, the font is set with font style, etc., and it is required to output HTML instance content with good readability, and then encapsulate it into prompt statement instructions that can be recognized by the content generation AI service platform; in this embodiment, CSS refers to Cascading Style Sheets, the full English name: Cascading Style Sheets, which is a computer language used to express the style of files such as HTML or XML.

[0059] Method 3: When generating prompt statement instructions, when generating content requirements and formatting requirements, specific requirements for content and format are put forward in plain text, including listing all directory frames and corresponding format requirements. For example, title format: bold, centered, Songti, size 3, line spacing 2em, summary format: bold, centered, Songti, size 4, line spacing 2em, etc. At the same time, requirements for content and format are put forward through HTML reference cases. The format is based on HTML and CSS conventions, such as using tags such as H1 and H2 for titles, setting paragraph formats with div, and setting fonts with font styles, etc., and it is required to output HTML instance content with good readability, and then encapsulate it into prompt statement instructions that can be recognized by the content generation AI service platform.

[0060] In the above embodiment, the AI application background is used to classify and grade various templates used in the workplace, and provide them to users in different job roles for selective use. Among them, each type of template has pre-made content requirements and formatting requirements in the database, such as: content requirements include title, abstract, name, time, precautions, etc., and formatting requirements include font, position, indentation, etc. The AI application background obtains the above pre-made template information from the database and caches it.

[0061] In the above embodiment, the AI application frontend obtains the required template example type and sends instructions to the AI application backend, further comprising the following steps: the user enters the template example page, selects a first-level category for the template example based on the user's needs, and then enters the details page corresponding to the template example category. The template example details page presents a list of template example types under the first-level category selected by the user, and the template example type list is grouped by application scenario and user role. The user selects the required template example type based on the usage scenario in the template example type list, and the AI application frontend sends the template example generation instruction to the AI application backend based on the template example type selected by the user.

[0062] The AI application backend obtains the preset information of the template type selected by the user, including content requirements and formatting requirements, automatically encapsulates prompt statement instructions, and requires the output of readable HTML example content, and then sends the prompt statement instructions to the content generation AI service platform. There are three ways to implement the automatic encapsulation of prompt statement instructions, namely: making specific requirements for content and format through plain text; making specific requirements for content through plain text and making requirements for content and format through HTML reference cases; making specific requirements for content and format through plain text and making requirements for content and format through HTML reference cases. In addition, when automatically encapsulating prompt statement instructions, in order to make the content returned by the content generation AI service platform more accurate, prompt word information such as background, role, and task can also be included.

[0063] In the above embodiment, the content-generating AI service platform generates results according to prompt statement instructions and returns them to the AI application backend. The generated results are tested by code and meet the chapter requirements, content requirements, and formatted HTML instance content of this type of template.

[0064] The AI application backend feeds back the formatted HTML instance content to the AI application frontend and displays it to the user, including the following steps: the AI application frontend parses the HTML instance content and displays the formatted template sample to the user.

[0065] In some embodiments, a download step is also included: that is, if the user needs to download a generated and formatted template sample, by clicking the download option, that is, clicking the "Download" button on the page, the AI application foreground converts the HTML instance content into a word document, such as: doc, docx, through third-party plug-ins and other services, and supports downloading to the user's local computer.

[0066] In different embodiments, an auxiliary method is also provided to provide users with preferred document solutions: that is, when the AI application background generates a template example, it also stores the template example in the template example instance library. When the number of examples corresponding to the same template example type accumulates to a preset level, the content quality is evaluated according to the algorithm and a certain score is calculated. If the content quality of the template example reaches the preset score, the AI application background directly selects the template example from the template example instance library, provides it to the user and presents it on the front-end page.

[0067] Example 2:

[0068] like Figure 2 and Figure 3 As shown, this embodiment provides a system for generating a formatted template sample text, including:

[0069] Template sample display module, used to display information and / or provide user operation selection;

[0070] The template article category acquisition module is used to obtain the first-level category of template articles from the database and send it to the template article display module for display and / or for user selection;

[0071] The template sample type acquisition module is used to receive the template sample category selected by the user, obtain the subcategories and template sample types under the template sample category, and send them to the template sample display module for display and / or for user selection;

[0072] A template sample content generation module is configured to receive a template sample type selected by a user, retrieve preset information from a database, automatically encapsulate prompt statement instructions, generate formatted HTML instance content, and send it to the content generation AI service platform; and receive and parse the template sample content generated by the content generation AI service platform and send it to the template sample presentation module for display and / or user selection.

[0073] The content generation AI service platform is used to generate template sample content according to prompt statement instructions and return it to the template sample content generation module.

[0074] The specific implementation of this system includes the following processes:

[0075] The user enters the template sample page, and the template sample display module requests the template sample category acquisition module to obtain the template sample first-level category.

[0076] The template sample category acquisition module obtains the first-level categories of template samples from the database, such as report category, program category, plan category, questionnaire category, etc., and sends them to the template sample display module for display and user selection.

[0077] The user selects a report category and is immediately directed to the report template details page. The report template details page requests template templates, including the subcategories of the report category and the report template types required by each department. For example, the subcategories of reports include 11 categories, such as research reports, survey reports, summary reports, and work reports. From a departmental perspective, these include 11 departments, including the Human Resources Department, the Administration Department, and the Customer Service Department. Users can view a list of corresponding report template types based on the report categories and departments they require. For example, the Human Resources Department's summary report includes performance appraisal summary reports, talent introduction summary reports, and compensation analysis summary reports. Users select a specific report template type, such as a performance appraisal summary report.

[0078] Based on the performance appraisal summary report template type selected by the user, the template display module will send a performance appraisal summary report request to the template content generation module. The template content generation module retrieves the preset information of the report type from the database, including content requirements and formatting requirements, automatically encapsulates prompt statement instructions, and generates formatted HTML example content. There are three ways to implement the automatic encapsulation prompt statement instruction:

[0079] Implementation method 1: When generating prompt statement instructions, when generating content requirements and formatting requirements, specific requirements for content and format are put forward in plain text, including listing all directory frameworks and corresponding format requirements, and requiring the output of readable HTML instance content, and then encapsulating it into a prompt statement instruction that can be recognized by the content generation AI service, which can contain one or more prompt words. For example: The content of a report must include the following parts: the title part format: bold, centered, Songti, size 3; the ending part format: left-aligned, not bold, the first line is indented to 2 words, and it also includes notes, prospects, acknowledgments, etc. Output readable HTML instance content, and encapsulate the prompt statement instruction through the above text description.

[0080] Implementation method 2: When generating prompt statement instructions, when generating content requirements, specific requirements for the content are put forward in plain text, including listing all directory frameworks, such as: title, abstract, etc. At the same time, requirements for content and format are put forward through HTML reference cases. The format is based on HTML and CSS conventions. For example, the content of a report must include the following parts: title part, notes, etc. The content is filled in the corresponding HTML section below, and the HTML content is returned, such as: <style>.center{font-size:15px；margin-bottom:30px；}...< / style> <divcl ass="center"> <h2> Performance Appraisal Summary Report< / h2> <div class＝"abstract"> summary <div class＝"content"> ... . Encapsulate the prompt statement instructions through the above content.

[0081] Implementation method 3: When generating prompt statement instructions, when generating content requirements and formatting requirements, specific requirements for content and format are put forward in plain text, including listing all directory frameworks and corresponding format requirements. At the same time, requirements for content and format are put forward through HTML reference cases. The format is based on HTML and CSS conventions. For example, the content of a report must include the following parts: Title part format: bold, centered, Songti, size 3; Ending part format: left-aligned, no bold, first line indented to 2 characters, also includes notes, outlook, acknowledgments, etc. The content is filled in the corresponding HTML chapter below, and the HTML content is returned, such as: <style>.center{text-align:center；font-size:15px；margin-bottom:30px；}...< / style> <divclass="center"> <h2> Performance Appraisal Summary Report< / h2> <div class＝"abstract"> summary <div class＝"content"> .... Encapsulate the prompt statement instructions through the above content.

[0082] The template content generation module sends the organized prompt statement instructions to the content generation AI service platform. The service platform generates the performance appraisal summary report result content according to the prompt statement instructions of the performance appraisal summary report and returns it to the template content generation module: <style>.center{text-align:center；font-size:15px；...< / style> <div class＝"center"> <h2> Performance Appraisal Summary Report< / h2> <div class＝"abstract">Title: Performance Appraisal Summary Report….

[0083] The template sample content generation module parses the received data and obtains the result content, such as the HTML instance content of the performance appraisal summary report, and feeds it back to the template sample display module. The template sample display module parses the HTML instance content and presents it to the user in a formatted form.

[0084] When the user clicks the download button, the template sample display module converts the HTML instance content into a Word document, such as performance appraisal summary report.doc, through third-party plug-ins and other services, and prompts the user to download it locally.

[0085] Example 3:

[0086] In the specific implementation of this system, Figure 3 and Figure 4 As shown, the following process can also be performed:

[0087] The user enters the template sample page, and the template sample display module requests the template sample category acquisition module to obtain the template sample first-level category.

[0088] The template sample category acquisition module obtains the first-level categories of template samples from the database, such as: report category, program category, plan category, questionnaire category, etc., and sends them to the template sample page to display them for user selection.

[0089] The user selects a report category and then enters the template details page of the report category. The template details page of the report category requests the template sample type to obtain the template, obtain the sub-categories of the report category, and the report sample types required by each department. For example, the sub-categories of the report include 11 categories such as research reports, investigation reports, summary reports, and work reports. From the perspective of the department, it includes 11 departments such as the Human Resources Department, the Administration Department, and the Customer Service Department. Users can view the corresponding list of report sample types according to the report categories and departments they need. For example, the summary report of the Human Resources Department includes the performance appraisal summary report, the talent introduction summary report, the salary analysis summary report, etc. The user selects a specific report sample type, such as the performance appraisal summary report.

[0090] According to the performance appraisal summary report template type selected by the user, the template display module will send a performance appraisal summary report request to the template content generation module. The template content generation module obtains the preset information of the report type from the database, including: content requirements and formatting requirements, etc., and is divided into two steps to generate formatted HTML instance content.

[0091] Step 1: Encapsulate prompt statement instructions. The content requirements include the directory framework that needs to be generated, such as title, summary, etc., and send it to the content generation AI service platform. The service platform generates the performance appraisal summary report result content based on the prompt statement instructions of the performance appraisal summary report, such as: Title: Performance Appraisal Summary Report; Summary: All employees actively engaged in work and completed various tasks, etc.

[0092] Step 2: Based on the result content generated in Step 1, encapsulate prompt statements and add format requirements such as text requirements and HTML reference cases, requiring the content generation AI service platform to output readable HTML example content. This process can be implemented in the following three ways:

[0093] Implementation method 1: When generating prompt statements, use plain text to request the content generation AI service platform to output readable HTML examples based on the content generated in step 1 according to specified requirements. For example, please return the performance review summary report you just generated for me in HTML format according to the following requirements: Title format: bold, centered, Songti, size 3; Summary format: bold, centered, Songti, size 14.

[0094] Implementation method 2: When generating prompt statements, ask the content generation AI service platform to output readable HTML examples based on the content generated in the first step, referring to the provided HTML examples. For example: Please fill the performance review summary report you just generated for me into the corresponding HTML section I will give you below, and then return the filled HTML to me: <style>.center{text-align:center；font-size:15px；margin-bottom:30px；}...< / style> <div class＝"center"> <h2> Performance Appraisal Summary Report< / h2> <divclass="abstract"> summary <div class＝"content"> ... .

[0095] Implementation method 3: When generating prompt statements, the content generation AI service platform is required to provide requirements in plain text for the content generated in the first step, and to output readable HTML examples based on the provided HTML examples. For example: Please fill in the content of the performance review summary report you just generated for me with the following text description requirements: Title format: bold, centered, Songti, size 3; Summary format: bold, centered, Songti, size 4. Fill in the content into the corresponding HTML section below, and then return the filled HTML to me: <style>.center{text-align:center；font-size:15px；margin-bottom:30px；}...< / style> <divclass="center"> <h2> Performance Appraisal Summary Report< / h2> <divclass="abstract"> summary <div class＝"content"> ... .

[0096] Content generation AI services (such as ChatGPT and Wenxinyiyan) receive prompt instructions for formatting content and return a performance appraisal summary report in readable HTML format, for example: <style>.center{text-align:center；font-size:15px；......< / style> <div class＝"center"> <h2> Performance Appraisal Summary Report< / h2> <div class＝"abstract">Title: Performance Appraisal Summary Report......

[0097] The template sample content generation module parses the received data and obtains the result content, such as the HTML instance content of the performance appraisal summary report, and feeds it back to the template sample display module. The template sample display module parses the HTML instance content and presents it to the user in a formatted form.

[0098] When the user clicks the download button, the template sample display module converts the HTML instance content into a Word document, such as performance appraisal summary report.doc, through plug-ins and other services, and prompts the user to download it locally.

[0099] It should be noted that although the above embodiments have been described herein, this does not limit the scope of patent protection of the present invention. Therefore, based on the innovative concept of the present invention, changes and modifications to the embodiments described herein, or equivalent structural or equivalent process transformations made using the contents of the present invention's specification and drawings, and direct or indirect application of the above technical solutions to other related technical fields, are all included in the scope of patent protection of the present invention.

Claims

1. A method for generating a formatted template sample, characterized in that: The following steps are involved: Preset template information of several template examples; Get the required template type; Generate prompt instructions based on the required template type and the template information of the preset template and send them to the content generation AI service platform; The content-generating AI service platform generates template examples or directory frameworks and content according to prompt statement instructions, and displays them to users after feedback.

2. The method for generating a formatted template sample according to claim 1, wherein: The following steps are also included: In the database, template information of several template examples is preset; The AI application frontend obtains the required template type and sends instructions to the AI application backend; The AI application backend obtains the preset template information of the required template type based on the template type, automatically encapsulates the prompt statement instruction, and requires the return of formatted HTML instance content, and sends the prompt statement instruction to the content generation AI service platform; The content generation AI service platform generates templates or directory frameworks and content based on prompt instructions. If it is a template, it is directly fed back to the AI application backend. If it is a directory framework and content, it is fed back to the AI application backend after format adjustment. The AI application backend feeds the formatted HTML instance content back to the AI application frontend and displays it to the user.

3. The method for generating a formatted template essay according to claim 2, wherein: Automatically encapsulating prompt statement instructions includes: when generating content requirements and formatting requirements, providing specific requirements for content and format in plain text, listing all directory frameworks and corresponding format requirements, and requiring the output of readable HTML example content, which is then encapsulated into prompt statement instructions that can be recognized by the content generation AI service platform; Alternatively, when generating content requirements, specific requirements for the content are made in plain text, listing all directory frames. At the same time, requirements for the content and format are made through HTML example content. The directory frames in the HTML example content correspond to the directory frames in the plain text, and the format is agreed upon using HTML and CSS. Readable HTML example content is required to be output, and then encapsulated into prompt statements that can be recognized by the content generation AI service platform. Alternatively, when generating content requirements and formatting requirements, specific requirements for the content and format are made through plain text, listing all directory frameworks and corresponding format requirements. At the same time, requirements for the content and format are made through HTML instance content. The format is agreed upon by HTML and CSS, and it is required to output HTML instance content with good readability, and then encapsulate it into prompt statement instructions recognized by the content generation AI service platform.

4. The method for generating a formatted template sample according to claim 2, wherein: The AI application background is used to classify and grade template examples used in the workplace, and provide them to users in different job roles for selective use. Among them, template information for each type of template example is pre-made in the database, and the AI application background obtains the pre-made template information from the database and caches it.

5. The method for generating a formatted template sample according to claim 2, wherein: The AI application front-end obtains the required template example type and sends instructions to the AI application back-end, which also includes the following steps: the user enters the template example page, selects the first-level category of the template example according to the user's needs, and enters the details page corresponding to the template example category. The template example details page presents a list of template example types under the first-level category of the template example selected by the user. The user selects the required template example type based on the usage scenario in the template example type list. The AI application front-end will send the template example generation instruction to the AI application back-end based on the template example type selected by the user.

6. The method for generating a formatted template sample according to claim 2, wherein: The content generation AI service platform generates results according to prompt statement instructions and returns them to the AI application background, including: generating chapter requirements, content requirements and formatted HTML instance content that meet the required template type.

7. The method for generating a formatted template essay according to claim 2, wherein: The AI application backend feeds back the formatted HTML instance content to the AI application frontend and displays it to the user, including the following steps: the AI application frontend parses the HTML instance content and displays the formatted template sample to the user.

8. The method for generating a formatted template sample according to claim 1 or 2, characterized in that: It also includes a download step: if the user needs to download a generated and formatted template sample, he can click the download option to download the Word document converted by the AI application front-end through a third-party plug-in to the user's local computer.

9. The method for generating a formatted template sample according to claim 1 or 2, characterized in that: It also includes the following steps: when the content generation AI service platform generates template examples, it also stores the template examples in the template example library. When the number of examples corresponding to the same template example type accumulates to a preset level, the content quality is evaluated according to the algorithm and the score is calculated. If the preset score is reached, the AI application background directly selects the template example from the template example library and provides it to the user.

10. A system for generating formatted template sample texts, characterized in that: include: Template sample display module, used to display information and / or provide user operation selection; The template article category acquisition module is used to obtain the first-level category of template articles from the database and send it to the template article display module for display and / or for user selection; The template sample type acquisition module is used to receive the template sample category selected by the user, obtain the subcategories and template sample types under the template sample category, and send them to the template sample display module for display and / or for user selection; The template content generation module is used to receive the template type selected by the user, obtain preset information from the database, automatically encapsulate prompt statement instructions, generate formatted HTML instance content, and send it to the content generation AI service platform; Also, it is used to receive and parse the template sample content generated by the content generation AI service platform, and send it to the template sample display module for display and / or for user selection; The content generation AI service platform is used to generate template sample content according to prompt statement instructions and return it to the template sample content generation module.

Images