Editable manuscript generation method and device, electronic equipment and storage medium

Abstract

This application provides an editable document generation method, apparatus, electronic device, and storage medium, belonging to the field of computer software technology and applicable to the financial sector. The method includes: generating a hypertext markup page based on a fine-tuned large model of the presentation generation scenario and presentation generation information, obtaining a basic markup page for presentation generation; parsing the basic markup page to obtain page structure information including a list of content modules, a list of style rules, and pagination identifiers; locating the content modules in the list to obtain a content module location information table; converting the basic markup page based on the style rule list and content module location information table to obtain editable document elements; and arranging the editable document elements based on the pagination identifiers to obtain an editable presentation. This application embodiment can improve the efficiency of editing document generation.

Description

Technical Field

[0001] This application relates to the field of computer software technology, and is applicable to the financial field, particularly to an editable document generation method and apparatus, electronic device and storage medium. Background Technology

[0002] Editable document generation is used to generate editable presentations using large language models. Taking the financial sector as an example, by generating editable documents from credit reports, editable loan review reports can be created, facilitating online modifications by credit personnel. For instance, this allows for adjustments to assessment conclusions, supplementary risk point explanations, and modifications to loan amount recommendations.

[0003] Currently, the method for generating editable documents usually involves manually copying and pasting the document content from a hypertext markup page, followed by manual formatting adjustments to obtain an editable presentation. However, this method is time-consuming due to the manual copying and pasting process and the difficulty in determining the position of content modules within the hypertext markup page, resulting in low efficiency in generating editable documents. Therefore, improving the efficiency of generating editable documents has become an urgent technical problem to be solved. Summary of the Invention

[0004] The main objective of this application is to provide an editable document generation method, apparatus, electronic device, and storage medium, which aims to improve the efficiency of editing document generation.

[0005] To achieve the above objectives, a first aspect of this application proposes a method for generating an editable document, the method comprising: Get presentation generation information and fine-tune the large model of the presentation generation scene; Based on the fine-tuning model of the presentation generation scenario and the presentation generation information, a hypertext markup page is generated to obtain the basic markup page for presentation generation. The basic markup page of the presentation is parsed to obtain page structure information, which includes a list of content modules, a list of style rules, and pagination identifier information. The content module list is located to obtain a content module location information table; Based on the style rule list and the content module location information table, the basic markup page of the presentation is converted into content modules to obtain editable elements of the presentation. Based on the pagination identifier information, the editable elements of the document are arranged to obtain an editable presentation document.

[0006] In some embodiments, based on the content module list, the basic markup page of the presentation is scanned for content modules to obtain the position coordinates of the content modules; Based on the location coordinates of the content module, the geometric parameters of the module are calculated to obtain the geometric parameters of the content module; Based on the location coordinates and geometric parameters of the content modules, the list of content modules is transformed into a table to obtain the content module location information table.

[0007] In some embodiments, the style rule list includes a text conversion rule list, a table conversion rule list, and a chart conversion rule list. Based on the style rule list and the content module location information table, the presentation's basic markup page is converted into content modules to obtain editable elements, including: The content module location information table is categorized into three tables: text module location information table, table module location information table, and chart module location information table. The text content of the text module location information table is extracted to obtain the module text, and the module text is converted into a text box based on the text conversion rule list to obtain the editable text box element of the document; The table content of the table module location information table is extracted to obtain the module table structure and module table data. Based on the table conversion rule list and the module table structure, the module table data is converted to obtain editable table elements of the document. The chart content is extracted from the chart module location information table to obtain the module chart type and module chart data. Based on the chart conversion rule list and the module chart type, the module chart data is converted to obtain editable chart elements for the document. The editable text box element, the editable table element, and the editable chart element of the document are merged to obtain the editable document element.

[0008] In some embodiments, the step of parsing the basic markup page generated from the presentation to obtain page structure information includes: The style rules of the basic markup page of the presentation are extracted to obtain a set of style rules, and the elements of the set of style rules are classified to obtain a list of style rules; The basic marked pages of the presentation are generated by identifying pagination tags to obtain the pagination identification information; The basic markup page of the presentation is split into page content modules. Based on the pagination identifier information, the pagination content modules are integrated to obtain the content module list; The page structure information is obtained by merging the style rule list, the pagination identifier information, and the content module list.

[0009] In some embodiments, obtaining the large model for fine-tuning the presentation generation scene includes: Obtain a presentation sample, and obtain the hypertext markup page generation data and format specification sample of the presentation sample; Obtain the initial large language model; The format specification samples are classified and organized to obtain a style specification dataset, an element label dataset, and a pagination rule dataset. Based on the presentation sample, the hypertext markup page generation data, the style specification dataset, the element tag dataset, and the pagination rule dataset, the initial large language model is trained under supervision to obtain the fine-tuned large model for the presentation generation scenario.

[0010] In some embodiments, the step of arranging the editable elements of the document based on the pagination identifier information to obtain an editable presentation document includes: Based on the pagination identifier information, construct a presentation page set; Based on the content module location information table and the presentation page set, the editable elements of the presentation are laid out to obtain the presentation element page set. The presentation element page set is assembled to obtain the editable presentation.

[0011] In some embodiments, after arranging the editable elements of the document based on the pagination identifier information to obtain an editable presentation, the method further includes: Based on preset presentation editing instructions, the editable presentation is edited to obtain an updated presentation document; Save the updated presentation document to obtain an editable updated presentation document.

[0012] To achieve the above objectives, a second aspect of this application provides an editable document generation apparatus, the apparatus comprising: The basic information acquisition module is used to acquire presentation generation information and to obtain a large model for fine-tuning the presentation generation scenario. The page generation module is used to generate hypertext markup pages based on the fine-tuning of the large model in the presentation generation scenario and the presentation generation information, so as to obtain the basic markup page for presentation generation. The page parsing module is used to parse the basic markup page of the presentation to obtain page structure information, wherein the page structure information includes a list of content modules, a list of style rules, and pagination identifier information; The content location module is used to locate the content module list and obtain a content module location information table. The content conversion module is used to convert the basic markup page of the presentation document into editable elements based on the style rule list and the content module location information table. The element arrangement module is used to arrange the editable elements of the document based on the pagination identifier information to obtain an editable presentation document.

[0013] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect.

[0014] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0015] The editable document generation method, apparatus, electronic device, and storage medium proposed in this application, through the acquisition of presentation document generation information, can ensure that the basic markup page of the presentation document generation generated by fine-tuning the large model in the presentation document generation scenario is adapted to the user application scenario and user style requirements, providing a precise reference standard for the generation of editable documents. Furthermore, by parsing the basic markup page of the presentation document generation, page structure information is obtained, which facilitates the identification of the content module list, style rule list, and pagination identifier information in the basic markup page of the presentation document generation, thereby improving the accuracy of editable document generation. Secondly, the content module list is positioned to obtain a content module location information table, making the location information of each module in the content module list clearer, thereby further improving the accuracy of generating editable documents. Finally, based on the style rule list and the content module location information table, the basic markup page for presentation generation is converted into content modules to obtain editable elements of the document. Based on the pagination identifier information, the editable elements of the document are arranged to obtain an editable presentation. This reduces the manual conversion of presentations, makes the presentation editable, and thus improves the efficiency of generating editable presentations. Attached Figure Description

[0016] Figure 1 This is a flowchart of the editable document generation method provided in the embodiments of this application; Figure 2 yes Figure 1 The flowchart of step S101 in the text; Figure 3 yes Figure 1 The flowchart of step S103 in the process; Figure 4 yes Figure 1 The flowchart of step S104 in the process; Figure 5 yes Figure 1 The flowchart of step S105 in the process; Figure 6 yes Figure 1 The flowchart of step S106 in the process; Figure 7 This is a flowchart of an editable document generation method provided in another embodiment of this application; Figure 8 This is a schematic diagram of the structure of the editable document generation device provided in the embodiments of this application; Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0020] First, let's analyze some of the terms used in this application: Hypertext markup pages: Hypertext markup pages are digital information carriers organized around tags. They define the structure, layout, and relationships of content units such as text, tables, charts, and images through preset tag rules. They can also carry additional information such as content styles, pagination markers, and hyperlinks. They can be directly rendered and displayed in a browser or serve as an intermediate medium for information transmission and conversion. In scenarios where editable documents are generated, they often serve as an intermediate product of AI large models or system outputs, integrating original content and format specifications to provide a structured data foundation for subsequent parsing and extraction of module information, conversion of editable elements, and construction of presentations.

[0021] Artificial Intelligence (AI) is a technological field that integrates multiple disciplines such as computer science, psychology, philosophy, and cognitive science. AI aims to develop systems and machines capable of performing tasks that typically require human intelligence. These tasks include, but are not limited to, language understanding, learning, reasoning, perception, pattern recognition, problem-solving, and planning. AI systems simulate human cognitive functions through algorithms and statistical models, enabling computers to recognize language and images, understand natural language, and even make complex decisions and predictions.

[0022] Editable document generation is used to generate editable presentations using large language models. Taking the financial sector as an example, by generating editable documents from credit reports, editable loan review reports can be created, facilitating online modifications by credit personnel. For instance, this allows for adjustments to assessment conclusions, supplementary risk point explanations, and modifications to loan amount recommendations.

[0023] Currently, the method for generating editable documents usually involves manually copying and pasting the document content from a hypertext markup page, followed by manual formatting adjustments to obtain an editable presentation. However, this method is time-consuming due to the manual copying and pasting process and the difficulty in determining the position of content modules within the hypertext markup page, resulting in low efficiency in generating editable documents. Therefore, improving the efficiency of generating editable documents has become an urgent technical problem to be solved.

[0024] Based on this, embodiments of this application provide an editable document generation method and apparatus, electronic device and storage medium, aiming to improve the efficiency of editing document generation.

[0025] The editable document generation method, apparatus, electronic device, and storage medium provided in this application are specifically described through the following embodiments. First, the editable document generation method in this application is described.

[0026] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0027] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0028] The editable document generation method provided in this application relates to the field of computer software technology and is applicable to the financial sector. The editable document generation method provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the editable document generation method, but is not limited to the above forms.

[0029] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0030] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0031] Figure 1 This is an optional flowchart of an editable document generation method provided in this application embodiment. This method can be used in an editable document generation system. Figure 1 The method may include, but is not limited to, steps S101 to S106.

[0032] Step S101: Obtain presentation generation information and obtain the large model for fine-tuning the presentation generation scene; Step S102: Based on the presentation generation scenario, fine-tune the large model and the presentation generation information, generate the hypertext markup page to obtain the basic markup page for presentation generation. Step S103: Perform page parsing on the basic markup page of the presentation to obtain page structure information, including a list of content modules, a list of style rules, and pagination identifier information; Step S104: Locate the content module list to obtain a content module location information table; Step S105: Based on the style rule list and content module location information table, perform content module conversion on the basic markup page of the presentation to obtain editable elements of the presentation; Step S106: Based on the pagination identifier information, the editable elements of the document are arranged to obtain an editable presentation document.

[0033] Steps S101 to S106 as illustrated in this embodiment of the application, by obtaining the presentation generation information, ensure that the basic markup page for presentation generation generated using the fine-tuned large model of the presentation generation scenario is adapted to the user application scenario and user style requirements, providing a precise reference standard for the generation of editable documents. Furthermore, page parsing is performed on the basic markup page for presentation generation to obtain page structure information, facilitating the identification of the content module list, style rule list, and pagination identifier information within the basic markup page, thereby improving the accuracy of editable document generation. The process involves locating content modules in the list to obtain a content module location information table. This clarifies the position of each module, further improving the accuracy of generating editable presentations. Finally, based on the style rule list and the content module location information table, the basic markup pages for presentation generation are transformed into content modules to obtain editable elements. These editable elements are then arranged based on pagination information to create an editable presentation. This reduces manual presentation conversion and streamlines the editing process, thereby improving the efficiency of generating editable presentations.

[0034] In step S101 of some embodiments, the presentation generation information refers to a set of information on the generation requirements and format specifications of the presentation. The generation requirements may be the theme, number of pages, core content elements of each page, etc., and the format specifications may be content style standards, element type requirements, etc. For example, in the scenario of generating a financial management report, the presentation generation information may be the theme of the quarterly income report of the financial management report, the number of report pages, the income line chart and income table. In addition, the presentation generation information may also include information such as title, font size and color, and table background color.

[0035] The fine-tuned large model for presentation generation scenarios refers to a large model adapted to editable presentation generation scenarios after being trained under supervision using datasets such as presentation samples, hypertext markup page generation data, style specifications, element tags, and pagination rules.

[0036] In this embodiment, presentation generation information can be obtained by collecting user-inputted presentation generation requirements and format specifications. It's important to note that when collecting user input, the user must be prompted that the input completely covers the presentation generation requirements and format specifications. For example, the generation requirements should include the theme, target page number, and core content elements of each page, while the format specifications should include content style standards, element type requirements, and pagination rules. Simultaneously, pre-prepared presentation samples, hypertext markup page generation data, and information such as style specifications, element tags, and pagination rules from the presentation samples can be used to perform supervised learning model training on an untrained large language model. This yields a large language model suitable for presentation generation scenarios—a fine-tuned large model for presentation generation.

[0037] For details, please refer to Figure 2 In some embodiments, step S101, obtaining the large model for fine-tuning the presentation generation scene, may include, but is not limited to, steps S201 to S204: Step S201: Obtain a presentation sample, including the hypertext markup page generation data and format specification sample of the presentation sample; Step S202: Obtain the initial large language model; Step S203: Classify and organize the format specification samples to obtain the style specification dataset, element label dataset, and pagination rule dataset; Step S204: Based on presentation samples, hypertext markup page generation data, style specification dataset, element tag dataset, and pagination rule dataset, supervised training is performed on the initial large language model to obtain a fine-tuned large model for the presentation generation scenario.

[0038] In step S201 of some embodiments, a presentation sample refers to a finished presentation containing different themes, structures and content elements. For example, in the scenario of generating a financial report, a presentation sample can be a PPT file corresponding to multiple historical personal financial return reports.

[0039] Hypertext markup page generation data refers to the data related to the hypertext markup page corresponding to the presentation sample. Hypertext markup page generation data usually includes data such as page structure, content layout and style configuration.

[0040] A format specification sample refers to a data set formed by compiling and summarizing the format requirements of presentation sample.

[0041] In this embodiment, presentation samples with different themes and structures can be collected from internal enterprise document libraries, historical project materials, or publicly available compliant presentation resources. It should be noted that the presentation samples need to cover core content elements such as text, tables, and charts to ensure the diversity of training data. HTML generation tools can be used to generate hypertext markup pages that correspond one-to-one with each presentation sample, and the HTML code, page structure, content layout, and style configuration of these hypertext markup pages can be extracted to form hypertext markup page generation data. In addition, by organizing the content and format information of the presentation samples, format specification samples can be obtained.

[0042] In step S202 of some embodiments, the initial large language model refers to a general large language model that has basic natural language understanding and text generation capabilities but has not undergone specific training for presentation generation scenarios.

[0043] In this embodiment of the application, an initial large language model with basic natural language understanding and text generation capabilities can be obtained by calling commonly available large language models on the market.

[0044] In step S203 of some embodiments, the element label dataset refers to a data set formed by organizing the exclusive tags of various content elements in the presentation sample. The element label dataset usually includes label rules corresponding to elements such as text, tables, and charts.

[0045] A pagination rule dataset is a collection of data that organizes the pagination logic and identification methods of presentation samples. Pagination rule datasets typically include rules such as the number of pages, pagination order, and pagination label format.

[0046] In this embodiment of the application, the information in the format specification sample can be classified according to a pre-defined classification dimension to obtain a style specification dataset, an element label dataset, and a pagination rule dataset. Specifically, the format requirements of elements such as text, tables, and charts can be classified into a style specification dataset, the exclusive tagging rules corresponding to text modules, table modules, and chart modules can be classified into an element label dataset, and the rules such as the number of pages, page order logic, and page label naming format of the presentation can be classified into a pagination rule dataset.

[0047] In step S204 of some embodiments, by dividing the aforementioned presentation sample, hypertext markup page generation data, style specification dataset, element label dataset, and pagination rule dataset into training and validation sets in a proportional manner, supervised training can be implemented to train the initial large language model. Specifically, the generation requirements of the presentation sample in the training set are used as input, and the hypertext markup page generation data, style specification dataset, element label dataset, and pagination rule dataset corresponding to the presentation sample in the training set are used as labeled output. This guides the initial large language model to learn the mapping relationship between requirements, specifications, and hypertext markup pages, thereby achieving model training for the initial large language model. Furthermore, the accuracy of the output results of the initial large language model can be verified through the validation set. In detail, if the hypertext markup pages generated by the initial large language model do not meet the requirements of the style specification dataset, element label dataset, or pagination rule dataset, the output results can be fed back to the initial large language model for parameter optimization. The initial large language model is iterated repeatedly until the accuracy of the initial large language model on the validation set reaches a preset threshold, which can then be transformed into a fine-tuned large model for the presentation generation scenario.

[0048] Steps S201 to S204, as illustrated in this embodiment, involve obtaining presentation samples, hypertext markup page generation data and format specification samples from the presentation samples, and acquiring an initial large language model. This provides basic data support and a model foundation for the initial large language model's training. The diversity of presentation samples ensures the effectiveness of the initial large language model's training. Secondly, the format specification samples are classified and organized to form a structured style specification dataset, element label dataset, and pagination rule dataset. This makes the rules for training the initial large language model clearer and improves the dimensionality and relevance of the model training. Finally, based on the presentation samples, hypertext markup page generation data, style specification dataset, element label dataset, and pagination rule dataset, the initial large language model is subjected to supervised training. This yields a fine-tuned large model for the presentation generation scenario that can accurately understand the presentation generation requirements and output hypertext markup pages that conform to the specifications, improving the accuracy and standardization of intermediate carrier generation during the presentation generation process.

[0049] In step S102 of some embodiments, the presentation generation base markup page refers to the intermediate carrier of the presentation generation scene fine-tuning model based on the presentation generation information output.

[0050] In this embodiment, the collected presentation generation information can be input into the presentation generation scenario fine-tuning model. This model, using natural language understanding technology, can parse important information regarding generation requirements and format specifications from the presentation generation information. Combined with the mapping relationships between requirements, specifications, and hypertext markup pages learned during model training, this important information can be transformed into the basic markup page for presentation generation. It's important to note that the basic markup page for presentation generation, as an intermediate carrier in the editable document generation process, must ensure that the style area defined in the page header, along with different types of content such as text, tables, and charts, are each carried by dedicated tags or containers. Chart data is stored separately in the page's script area for easy subsequent retrieval. Simultaneously, corresponding pagination tags are set according to the page number in the generation requirements to ensure that each pagination tag accurately corresponds to a page of content in the presentation.

[0051] In step S103 of some embodiments, the page structure information includes a list of content modules, a list of style rules, and pagination identifier information. For example, in the scenario of generating an insurance industry data briefing, the page structure information may be a list of split insurance text modules and insurance table modules, style rules for titles and tables, and pagination identifiers for the corresponding 5 pages of briefing content.

[0052] A content module list refers to a collection of various content units formed by further integrating the basic marked pages of a presentation according to pagination identifiers. The content module list includes content modules such as text, tables, and charts. For example, in the scenario of generating a property insurance project report presentation, the content module list can be an ordered collection containing a property insurance project background text module, a progress table module, and a result chart module.

[0053] A style rule list is a collection of formatting standards extracted from the basic markup pages of a presentation and categorized by element type. The style rule list includes style requirements for text, tables, charts, etc. For example, in the scenario of generating a property insurance project report presentation, the style rule list could be a summary of rules such as bold 32-point font for titles, black borders for tables, and blue fill color for charts.

[0054] Pagination identifiers are unique markers used to distinguish different pages in a presentation within the basic marker page of the presentation. Pagination identifiers typically include the page number and page order of the presentation. For example, in the scenario of generating a monthly work summary presentation for an insurance company, the pagination identifiers could be labeled page1, page2, and page3, corresponding to the three pages of the summary cover, work data, and next month's plan, respectively.

[0055] In this embodiment of the application, the basic markup page of the presentation can be generated by sequentially extracting and classifying style rules, identifying pagination tags, splitting page content, and integrating pagination content modules, and then merging the resulting list of style rules, pagination identification information, and content module list to obtain page structure information.

[0056] For details, please refer to Figure 3 In some embodiments, step S103 may include, but is not limited to, steps S301 to S305: Step S301: Extract style rules from the basic markup page of the presentation to obtain a style rule set, and classify the style rule set into elements to obtain a style rule list; Step S302: Perform pagination tag recognition on the basic marked pages of the presentation to obtain pagination identifier information; Step S303: Split the basic markup page of the presentation into page content modules to obtain paginated content modules; Step S304: Based on the pagination identifier information, integrate the pagination content modules to obtain a list of content modules; Step S305: Merge the style rule list, pagination identifier information, and content module list to obtain page structure information.

[0057] In step S301 of some embodiments, the style rule set refers to the set of all formatting rules for each element type obtained after style rule extraction. The style rule set usually includes style requirements for various content elements such as text, tables, and charts.

[0058] In this embodiment, a publicly available HTML parsing tool can be called to load the presentation and generate a basic markup page. Then, the style definition area in the header of the basic markup page can be located, and all rules containing format requirements for elements such as text, tables, and charts within the style definition area can be extracted to obtain a set of style rules. Subsequently, the set of style rules can be systematically categorized according to the content element type to form a list of style rules. Specifically, rules related to text, such as font size, color, and alignment, can be grouped into one category; rules related to tables, such as borders, background colors, and cell spacing, can be grouped into another category; and rules related to charts, such as fill colors, axis styles, and data label formats, can be grouped into another category.

[0059] In step S302 of some embodiments, the complete code of the basic markup page of the presentation can be scanned by a publicly available HTML parsing tool, and the exclusive pagination tag code used to distinguish different pages of the presentation can be selected. Then, the name, position in the page code and corresponding page order of each exclusive pagination tag code are recorded. Finally, the above information is integrated to form pagination identification information.

[0060] In step S303 of some embodiments, the pagination content module refers to an independent collection of content for a single page of a presentation. The pagination content module includes all content elements of the single page, such as text, tables, and charts. For example, in a customer financial planning presentation scenario, the pagination content module for the second page can be a collection of the text module and the product revenue table module for the second page's revenue data.

[0061] In this embodiment, the pagination tags identified in the basic markup page for generating the presentation are used as the split boundaries. The overall content of the basic markup page for generating the presentation is divided according to the split boundaries using a publicly available HTML parsing tool. This allows all the content between the starting point of each pagination tag and the starting point of the next pagination tag to form an independent pagination content module. Each pagination content module contains all the content elements required for the corresponding single page of the presentation, such as text, tables, and charts.

[0062] In step S304 of some embodiments, the pagination content modules are arranged in order according to the pagination order recorded in the pagination identification information. Each pagination content module is labeled with its corresponding pagination number and content type, and then organized into a structured list, thereby forming a content module list containing all pagination content modules.

[0063] In step S305 of some embodiments, the above-mentioned style rule list, pagination identifier information and content module list are associated and matched so that each pagination content module corresponds to a specific page number in the pagination identifier information, and the elements in each pagination content module are associated with the corresponding format standards in the style rule list. Furthermore, the associated and matched data are summarized in order to form a complete structured data set containing the presentation pagination logic, all content units and corresponding format rules, i.e., page structure information. For example, in the scenario of generating a financial management report presentation, the page structure information may include the cover module of page1 corresponding to the style rule of "title bold 32-point font", the data table module of page2 corresponding to the style rule of "table black border", and all modules are arranged in pagination order with consistent data logic.

[0064] Steps S301 to S305, as illustrated in this embodiment, involve extracting style rules from the basic markup page for presentation generation to obtain a set of style rules, classifying the style rule set into elements to obtain a list of style rules, thus clarifying the format standards for various element contents. Next, pagination tags are identified on the basic markup page for presentation generation to obtain pagination identifier information. The page content is then split into pagination content modules. Based on the pagination identifier information, these modules are integrated to obtain a list of content modules. Finally, the style rule list, pagination identifier information, and content module list are merged to obtain page structure information. This ensures that the page structure information covers the three core dimensions of style, pagination, and content, providing accurate data support for module positioning and content conversion, reducing operational errors caused by fragmented information, and thereby improving the accuracy and efficiency of generating editable presentations.

[0065] In step S104 of some embodiments, the content module location information table refers to the structured table formed by associating and matching the location coordinates and geometric parameters of the content modules with the content module list. For example, in the scenario of generating an insurance product launch presentation, the content module location information table may be a detailed table containing the location coordinates and size parameters of the insurance product text description module, as well as the corresponding module name.

[0066] In this embodiment, the location coordinates of the content modules are obtained by scanning the presentation based on the content module list to generate a basic marked page. After calculating the geometric parameters of the modules, the content module list is converted into a content module location information table by combining the location coordinates and geometric parameters.

[0067] Please see Figure 4 In some embodiments, step S104 may include, but is not limited to, steps S401 to S403: Step S401: Based on the content module list, scan the basic markup page of the presentation to obtain the content module location coordinates; Step S402: Based on the position coordinates of the content module, calculate the geometric parameters of the module to obtain the geometric parameters of the content module; Step S403: Based on the location coordinates and geometric parameters of the content modules, the content module list is converted into a table to obtain the content module location information table.

[0068] In step S401 of some embodiments, the content module position coordinates refer to the numerical information of the specific position of the content module in the basic markup page of the presentation generation. It is usually represented by the pixel value of the top left corner of the module from the left side and the top of the page. For example, in the scenario of generating a financial management project report presentation, the content module position coordinates may be the numerical information of the top left corner of a financial data table module being 150 pixels from the left side of the page and 200 pixels from the top.

[0069] In this embodiment, the identification features of various independent content units such as text, tables, and charts included in the content module list are first identified. Then, based on the identification features, the corresponding content modules are searched and matched one by one in the basic markup page for presentation generation. The specific position of each content module in the basic markup page for presentation generation is captured and recorded in numerical form to obtain the position coordinates of the content module.

[0070] In step S402 of some embodiments, the geometric parameters of the content module refer to the size of the content module, which mainly includes the width and height of the content module.

[0071] In this embodiment of the application, the width and height of the content module can be obtained by capturing the position coordinates of the upper right and lower left corners of the content module and calculating the difference between the position coordinates of the upper right and lower left corners and the position coordinates of the upper left corner of the content module, thereby forming the geometric parameters of the content module.

[0072] In step S403 of some embodiments, each content module in the content module list is associated and matched with the corresponding content module location coordinates and content module geometric parameters one by one, clarifying key information such as the name, type, location coordinate value, and geometric parameter value of each content module. Then, according to the preset table format, these associated information are systematically organized into a structured table form, and finally a content module location information table is formed.

[0073] Steps S401 to S403, as illustrated in this embodiment, involve scanning the basic marker page for presentation generation based on the content module list. This accurately captures the specific location of each content module within the basic marker page and records it as content module position coordinates, laying the foundation for obtaining spatial information of the content modules. Next, based on the content module position coordinates, geometric parameters are calculated to obtain dimensional data such as the width and height of the content modules, thus improving the spatial feature information of the content modules and forming complete geometric parameters. Finally, the content module position coordinates and geometric parameters are associated and bound to each content module in the content module list, transforming the content module list into a content module position information table. This effectively avoids presentation layout errors caused by position or size information deviations, improving the accuracy and standardization of editable presentation generation.

[0074] In step S105 of some embodiments, editable document elements refer to presentation components in the basic markup page for generating presentations that can be modified a second time. Editable document elements typically include elements such as text boxes, tables, and charts. For example, in the scenario of generating a presentation for a customized financial plan for a client, editable document elements may be text boxes that allow modification of the client's name, tables that allow adjustment of the holding amount, and line charts that allow updating of return data.

[0075] In this embodiment, the content module location information table is classified into three types: text, table, and chart. The text, table structure and data, and chart type and data of the corresponding content module are extracted respectively. Then, the conversion is completed according to the corresponding conversion rule list. Finally, all editable elements are merged to obtain the editable elements of the document.

[0076] For details, please refer to Figure 5 In some embodiments, the style rule list includes a text conversion rule list, a table conversion rule list, and a chart conversion rule list. Step S105 may include, but is not limited to, steps S501 to S505: Step S501: Classify the content module location information table into tables to obtain the text module location information table, the table module location information table, and the chart module location information table. Step S502: Extract the text content from the text module location information table to obtain the module text, and convert the module text into a text box based on the text conversion rule list to obtain the editable text box element of the document; Step S503: Extract the table content from the table module location information table to obtain the module table structure and module table data. Based on the table conversion rule list and the module table structure, perform table conversion on the module table data to obtain editable table elements of the document. Step S504: Extract the chart content from the chart module location information table to obtain the module chart type and module chart data. Based on the chart conversion rule list and the module chart type, convert the module chart data to obtain editable chart elements of the document. Step S505: Merge the editable text box element, editable table element, and editable chart element of the document to obtain the editable elements of the document.

[0077] In step S501 of some embodiments, the text conversion rule list refers to the set of format conversion rules specifically for the text module in the style rule list. The text conversion rule list usually includes requirements for dimensions such as text font size, color, and alignment.

[0078] The table conversion rule list refers to the set of format conversion rules specifically for the table module in the style rule list. The table conversion rule list usually includes requirements for table borders, background colors, cell spacing, and other dimensions.

[0079] The chart conversion rule list refers to the set of format conversion rules specifically for the chart module in the style rule list. The table conversion rule list usually includes requirements for chart fill color, axis style, data label format, and other dimensions.

[0080] The text module location information table is a structured table obtained after table classification, which specifically records the location coordinates, geometric parameters and related information of text content modules.

[0081] The table module location information table is a structured table obtained after classifying tables, which specifically records the location coordinates, geometric parameters and related information of table-type content modules.

[0082] The chart module location information table is a structured table obtained after table classification, which specifically records the location coordinates, geometric parameters and related information of chart content modules.

[0083] In this embodiment, the content module type corresponding to each entry in the content module location information table is first determined. Then, the content module location information table is classified and filtered according to the content module type. The location coordinates, geometric parameters and other information corresponding to all text-type content modules are separately organized into structured tables to form the text module location information table. At the same time, the location and size data corresponding to table-type content modules and chart-type content modules are classified and organized separately to generate table module location information tables and chart module location information tables in sequence, ensuring that the three types of module location information tables only contain the complete spatial data of the corresponding type of module.

[0084] In step S502 of some embodiments, module text refers to the text content within a text-type content module.

[0085] Editable text box elements refer to native text box components in presentations that support modification of text content and formatting. For example, in a financial report generation scenario, an editable text box element could be a text box that allows modification of the customer's name and adjustment of font size and color.

[0086] In this embodiment, each text module is precisely located in the presentation document generation basic markup page based on the position coordinates and geometric parameters in the text module position information table. Furthermore, text recognition is performed on the text modules to extract the original text content within the text modules, i.e., the module text. Subsequently, a text box that can be filled with text information is constructed according to the coordinates and geometric parameters in the text module position information table. Then, referring to the format requirements in the text conversion rule list, the corresponding font size, color, alignment and other attributes are configured for the module text. The module text with the configured attributes is then filled into the created text box, thereby obtaining the document editable text box element.

[0087] In step S503 of some embodiments, the module table structure refers to the frame information of the table in the table module, which includes the number of rows, the number of columns, the table header settings, etc.

[0088] Module table data refers to the raw data within a table module. For example, in a data briefing scenario in the financial and insurance industry, module table data can be specific values ​​such as the first quarter sales of 1 million, 1.5 million, or 800,000 for each region.

[0089] Editable table elements in presentations refer to native table components that support adding or deleting rows / columns, modifying cell data and formatting. For example, in the scenario of quarterly performance of insurance companies, editable table elements in presentations can be tables that allow adjustment of insurance product sales data and modification of table header styles.

[0090] In this embodiment, based on the spatial data in the table module location information table, the table module is located in the presentation generation basic markup page, and the table module is parsed to obtain information such as the number of rows, columns, and header settings, thereby obtaining the module table structure. At the same time, the original numerical or text information of each cell in the table module is extracted to obtain the module table data. Then, according to the coordinates and geometric parameters in the table module location information table and the above-mentioned module table structure, a blank table is constructed. Then, according to the requirements in the table conversion rule list, the module table data is imported into the blank table to generate editable table elements for the presentation.

[0091] In step S504 of some embodiments, the module chart type refers to the specific presentation form of the chart module. It should be noted that the specific presentation form of the chart module can be a line chart, bar chart, pie chart, etc. For example, in the scenario of financial project progress demonstration, the module chart type can be a bar chart used to display the completion rate of each stage of the financial project.

[0092] Module chart data refers to the raw numerical data that supports the generation of charts.

[0093] Editable chart elements in presentations refer to native chart components that allow users to adjust chart types, update data, and modify styles. For example, in a financial return presentation scenario, editable chart elements could be replaced with bar charts or line charts that allow modification of quarterly return data.

[0094] In this embodiment, the corresponding chart module can be found in the presentation document generation basic mark page by referring to the position coordinates and geometric parameters in the chart module position information table. Further, the presentation type of the chart module is determined to obtain the module chart type. At the same time, the data, text and other information in the chart module are identified and extracted to obtain the module chart data. Then, a blank chart is constructed according to the coordinates and geometric parameters in the chart module position information table and the above-mentioned module chart type. Then, according to the style requirements in the chart conversion rule list, the module chart data is imported into the blank chart, thereby converting the blank chart into an editable chart element in the document.

[0095] In step S505 of some embodiments, the above-mentioned editable text box elements, editable table elements, and editable chart elements are sorted according to the order of their original modules in the content module list, and the page and module name to which each editable element belongs are marked, thus forming a complete set containing all types of editable components, namely, editable document elements.

[0096] Steps S501 to S505, as illustrated in this application example, categorize the content module location information table by module type to obtain text module location information tables, table module location information tables, and chart module location information tables. This provides an information foundation for the accurate processing of various elements. Then, core content corresponding to different module types is extracted, and targeted conversion is performed based on the specific conversion rule list corresponding to each module type. This ensures that the format and style rule list of text boxes, tables, and charts match, thereby improving the conversion accuracy of various editable elements. Finally, the editable text box elements, editable table elements, and editable chart elements are integrated to form complete editable elements, achieving efficient conversion of various content modules into editable presentation elements. This ensures both the uniformity and standardization of different element formats and the integrity and flexible modification characteristics of editable elements, reducing the cost of secondary adjustments due to non-standard element conversion and improving the generation quality and efficiency of editable presentations.

[0097] In step S106 of some embodiments, an editable presentation refers to a finished presentation that supports multiple modifications to elements such as text, tables, and charts.

[0098] In this embodiment, a presentation page set is constructed based on pagination identifier information, and the editable elements of the presentation are laid out in combination with the content module location information table to obtain a presentation element page set. After page assembly, an editable presentation can be obtained.

[0099] For details, please refer to Figure 6 In some embodiments, step S106 may include, but is not limited to, steps S601 to S603: Step S601: Based on the pagination identifier information, construct the presentation page set; Step S602: Based on the content module location information table and the presentation page set, perform element layout on the editable elements of the presentation to obtain the presentation element page set; Step S603: Assemble the presentation element page set to obtain an editable presentation.

[0100] In step S601 of some embodiments, the presentation page set refers to a collection of blank pages that are consistent with the presentation page number in the pagination identification information and are arranged in order.

[0101] In this embodiment, by extracting information from the pagination identifiers, the number of pages, page order, and core function definition of each page in the presentation can be obtained. Subsequently, a corresponding number of blank pages are created according to the number of pages, and the blank pages are numbered and sorted according to the order of the pagination identifiers. At the same time, each blank page is assigned basic attributes corresponding to the pagination function according to the core function definition of each page. Finally, the presentation page set can be obtained.

[0102] In step S602 of some embodiments, the presentation element page set refers to a set in which each blank page contains corresponding editable elements and is arranged in order.

[0103] In this embodiment, the basic information of each editable element in the content module location information table can be extracted one by one to obtain the page to which the editable element belongs, its position coordinates, and geometric parameters. Further, the page to which the editable element belongs, its position coordinates, and geometric parameters are associated with the corresponding blank pages in the presentation page set. Each editable element is placed in the designated area of ​​the corresponding blank page according to the associated position coordinates. At the same time, the size of the editable element is adjusted according to the geometric parameters to ensure that the position and size of the editable element on the page are consistent with the basic markup page for presentation generation. Finally, after completing the layout of all editable elements, an ordered set in which each page contains the corresponding editable element can be obtained, i.e., the presentation element page set.

[0104] In step S603 of some embodiments, after obtaining the presentation element page set, the page logic of the generated editable presentation can be ensured by checking whether the order of each page in the presentation element page set is consistent with the pagination identifier information. Then, the basic layout of each page is unified, including headers, footers, page backgrounds, and margins, to ensure the format uniformity of the editable presentation. Next, the spacing and hierarchy of the editable elements within the page are optimized to avoid overlapping or layout chaos. At the same time, the functional integrity of the editable elements is verified to ensure their normal display. After completing the above verification work, an optimized presentation element page set can be obtained. Furthermore, by integrating the optimized presentation element page set into a standard presentation file format and outputting the presentation file, an editable presentation that supports multiple modifications and optimizations by the user is obtained.

[0105] Steps S601 to S603, as illustrated in this embodiment, construct a presentation page set based on pagination identifier information. This provides a document framework for the orderly layout of editable elements. Furthermore, by combining the content module location information table, each editable element is laid out into the presentation page set, resulting in a presentation element page set. This ensures that the position and size of each editable element are consistent with the requirements in the presentation generation information, achieving accuracy and standardization in element layout. Finally, the presentation element page set is compiled to form an editable presentation. This ensures both the logical coherence and format consistency of the editable presentation's pages, as well as the functional integrity of each editable element. It avoids problems such as layout errors or inconsistent formats in the editable presentation, thereby improving the generation quality and delivery efficiency of the editable presentation and reducing the time cost for users to make secondary adjustments to the presentation.

[0106] In this embodiment of the application, after obtaining an editable presentation, the editable presentation can be edited according to the preset presentation editing instructions to obtain an updated presentation. The updated presentation can then be saved to obtain an editable updated presentation.

[0107] For details, please refer to Figure 7 In some embodiments, the editable document generation method may also include, but is not limited to, steps S701 to S702: Step S701: Based on preset presentation editing instructions, edit the editable presentation to obtain an updated presentation document; Step S702: Save the presentation update document to obtain an editable presentation update document.

[0108] In step S701 of some embodiments, presentation editing instructions refer to operation instructions used to modify the content, format or structure of an editable presentation. For example, in a financial report scenario, presentation editing instructions may be a set of instructions for modifying customer earnings data, adjusting chart types, and changing text font sizes.

[0109] An updated presentation document refers to an intermediate version of a presentation that includes revised content but has not yet been saved.

[0110] In this embodiment, the editing object, operation type and specific parameters corresponding to the editing instruction can be clarified by parsing the presentation editing instruction. Then, the editing operation can be performed on the editable presentation according to the editing object, operation type and specific parameters, thereby realizing the editing of the editable presentation and obtaining the updated presentation.

[0111] In step S702 of some embodiments, an editable updated presentation refers to the final version of a presentation that includes the latest modifications and still supports further editing.

[0112] In this embodiment of the application, after confirming that the modified content in the presentation update document meets the requirements of the presentation editing instructions, a pre-set save format and storage path can be selected to solidify the temporary modified content in the presentation update document into an official file, and ensure that the modified text, tables, charts and other element information are completely stored, and the document still retains the editable attributes. It should be noted that after the presentation update document is saved, an editable presentation update document can be generated.

[0113] Steps S701 to S702, as illustrated in this embodiment, modify the editable elements in the editable presentation based on preset presentation editing instructions to obtain an updated presentation. This avoids the need for users to create new presentations due to content adjustments, thereby improving the efficiency of content modification. Furthermore, saving the updated presentation to obtain an editable updated presentation enables rapid updates and iterations of presentation content, ensuring the flexible reusability of the editable updated presentation and reducing the time cost of repetitive editing.

[0114] The presentation generation information obtained in this application ensures that the basic markup page for presentation generation, generated using a fine-tuned large model of the presentation generation scenario, is adapted to the user's application scenario and style requirements. This provides a precise reference standard for the generation of editable presentations. Furthermore, page parsing of the basic markup page yields page structure information, facilitating the identification of the content module list, style rule list, and pagination identifier information within the basic markup page, thereby improving the accuracy of editable presentation generation. Secondly, module positioning is performed on the content module list to obtain a content module location information table, making the location information of each module in the content module list clearer, further improving the accuracy of editable presentation generation. Finally, based on the style rule list and content module location information table, the basic markup page for presentation generation is converted into content modules to obtain editable elements. Based on the pagination identifier information, these editable elements are arranged to obtain an editable presentation. This reduces manual conversion of presentations, streamlines the presentation editing process, and improves the efficiency of generating editable presentations.

[0115] Please see Figure 8 This application also provides an editable document generation apparatus that can implement the above-described editable document generation method. The apparatus includes: The basic information acquisition module 801 is used to acquire presentation generation information and to acquire the large model for fine-tuning the presentation generation scenario. The page generation module 802 is used to fine-tune the large model and presentation generation information based on the presentation generation scenario, generate hypertext markup pages, and obtain the basic markup pages for presentation generation. The page parsing module 803 is used to parse the basic markup pages of the presentation to obtain page structure information, including a list of content modules, a list of style rules, and pagination identifier information. Content positioning module 804 is used to locate the content module list and obtain a content module location information table. Content conversion module 805 is used to convert the basic markup page of the presentation into content modules based on the style rule list and the content module location information table, so as to obtain editable elements of the presentation. The element arrangement module 806 is used to arrange the editable elements of the document based on the pagination identifier information to obtain an editable presentation document.

[0116] The specific implementation of the editable document generation device is basically the same as the specific embodiment of the editable document generation method described above, and will not be repeated here.

[0117] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method for generating editable documents. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0118] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 using the editable document generation method of the embodiments of this application. The input / output interface 903 is used to implement information input and output; The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0119] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for generating editable documents.

[0120] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0121] The editable document generation method, editable document generation device, electronic device, and storage medium provided in this application embodiment acquire presentation document generation information, acquire a large-scale model for fine-tuning the presentation document generation scenario, generate hypertext markup pages based on the large-scale model and the presentation document generation information, obtain a basic markup page for presentation document generation, parse the basic markup page for presentation document generation to obtain page structure information, wherein the page structure information includes a list of content modules, a list of style rules, and pagination identifier information, locate the content module list to obtain a content module position information table, perform content module conversion on the basic markup page for presentation document generation based on the list of style rules and the content module position information table, obtain editable document elements, and arrange the editable document elements based on the pagination identifier information to obtain an editable presentation document.

[0122] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0123] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0124] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0125] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0126] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0127] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. The coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, or indirect coupling or communication connection between the apparatus or units, and may be electrical, mechanical, or other forms.

[0129] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0130] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0131] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0132] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for generating an editable document, characterized in that, The method includes: Get presentation generation information and fine-tune the large model of the presentation generation scene; Based on the fine-tuning model of the presentation generation scenario and the presentation generation information, a hypertext markup page is generated to obtain the basic markup page for presentation generation. The basic markup page of the presentation is parsed to obtain page structure information, which includes a list of content modules, a list of style rules, and pagination identifier information. The content module list is located to obtain a content module location information table; Based on the style rule list and the content module location information table, the basic markup page of the presentation is converted into content modules to obtain editable elements of the presentation. Based on the pagination identifier information, the editable elements of the document are arranged to obtain an editable presentation document.

2. The method according to claim 1, characterized in that, The step of locating the content module list to obtain a content module location information table includes: Based on the content module list, the basic markup page of the presentation is scanned for content modules to obtain the position coordinates of the content modules; Based on the location coordinates of the content module, the geometric parameters of the module are calculated to obtain the geometric parameters of the content module; Based on the location coordinates and geometric parameters of the content modules, the list of content modules is transformed into a table to obtain the content module location information table.

3. The method according to claim 1, characterized in that, The style rule list includes a text conversion rule list, a table conversion rule list, and a chart conversion rule list. Based on the style rule list and the content module location information table, the basic markup page of the presentation is converted into content modules to obtain editable elements, including: The content module location information table is categorized into three tables: text module location information table, table module location information table, and chart module location information table. The text content of the text module location information table is extracted to obtain the module text, and the module text is converted into a text box based on the text conversion rule list to obtain the editable text box element of the document; The table content of the table module location information table is extracted to obtain the module table structure and module table data. Based on the table conversion rule list and the module table structure, the module table data is converted to obtain editable table elements of the document. The chart content is extracted from the chart module location information table to obtain the module chart type and module chart data. Based on the chart conversion rule list and the module chart type, the module chart data is converted to obtain editable chart elements for the document. The editable text box element, the editable table element, and the editable chart element of the document are merged to obtain the editable document element.

4. The method according to claim 1, characterized in that, The step of generating a basic markup page for the presentation and obtaining page structure information includes: The style rules of the basic markup page of the presentation are extracted to obtain a set of style rules, and the elements of the set of style rules are classified to obtain a list of style rules; The basic marked pages of the presentation are generated by identifying pagination tags to obtain the pagination identification information; The basic markup page of the presentation is split into page content modules. Based on the pagination identifier information, the pagination content modules are integrated to obtain the content module list; The page structure information is obtained by merging the style rule list, the pagination identifier information, and the content module list.

5. The method according to claim 1, characterized in that, The process of obtaining the large model for fine-tuning the scene generated from the presentation includes: Obtain a presentation sample, and obtain the hypertext markup page generation data and format specification sample of the presentation sample; Obtain the initial large language model; The format specification samples are classified and organized to obtain a style specification dataset, an element label dataset, and a pagination rule dataset. Based on the presentation sample, the hypertext markup page generation data, the style specification dataset, the element tag dataset, and the pagination rule dataset, the initial large language model is trained under supervision to obtain the fine-tuned large model for the presentation generation scenario.

6. The method according to any one of claims 1-5, characterized in that, The step of arranging the editable elements of the document based on the pagination identifier information to obtain an editable presentation document includes: Based on the pagination identifier information, construct a presentation page set; Based on the content module location information table and the presentation page set, the editable elements of the presentation are laid out to obtain the presentation element page set. The presentation element page set is assembled to obtain the editable presentation.

7. The method according to claim 6, characterized in that, After arranging the editable elements of the document based on the pagination identifier information to obtain an editable presentation, the process further includes: Based on preset presentation editing instructions, the editable presentation is edited to obtain an updated presentation document; Save the updated presentation document to obtain an editable updated presentation document.

8. An editable document generation device, characterized in that, The device includes: The basic information acquisition module is used to acquire presentation generation information and to obtain a large model for fine-tuning the presentation generation scenario. The page generation module is used to generate hypertext markup pages based on the fine-tuning of the large model in the presentation generation scenario and the presentation generation information, so as to obtain the basic markup page for presentation generation. The page parsing module is used to parse the basic markup page of the presentation to obtain page structure information, wherein the page structure information includes a list of content modules, a list of style rules, and pagination identifier information; The content location module is used to locate the content module list and obtain a content module location information table. The content conversion module is used to convert the basic markup page of the presentation document into editable elements based on the style rule list and the content module location information table. The element arrangement module is used to arrange the editable elements of the document based on the pagination identifier information to obtain an editable presentation document.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the editable document generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the editable document generation method according to any one of claims 1 to 7.

Images