Data generation and display method, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a data generation and display method, electronic equipment, a storage medium and a program product.The data generation method comprises the steps that obtained content uploaded by a user client side is analyzed to obtain a content framework, and the content framework is used for indicating a logic framework of the content of a to-be-generated presentation file; a target demonstration template matched with the content framework is determined in the demonstration templates to be selected, and the target demonstration template comprises a plurality of presentation file pages; generating page elements corresponding to each object in the target presentation template based on the content framework, and obtaining structural data corresponding to the presentation file; and transmitting the structural data to the user client, so that the user client generates the presentation based on the structural data. According to the scheme provided by the embodiment of the invention, the structure data generation and rendering processes of the presentation are separated, so that the working efficiency of the server side is improved, the presentation generation efficiency is further improved, and the problem of content loss caused by server side rendering is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a data generation and display method, electronic device, computer storage medium, and computer program product. Background Technology

[0002] In recent years, AI (Artificial Intelligence) has become a core driving force for productivity transformation. It can extend and expand the boundaries of human intelligence, replace or assist humans in completing complex tasks, and even surpass human capabilities in some areas. For example, the combination of AI and collaborative office work.

[0003] However, AI often has significant limitations when performing complex and creative tasks. For example, when creating PowerPoint presentations using AI, the format is usually based on a custom front-end page, such as HTML rendering technology. Due to the limitations of front-end page rendering and editing capabilities, the PPT file generation efficiency is low, and problems such as missing content are prone to occur, resulting in poor PPT file quality. Summary of the Invention

[0004] In view of this, embodiments of this application provide a data generation method and display scheme to at least partially solve the above problems.

[0005] According to a first aspect of the embodiments of this application, a data generation method is provided. The method includes: parsing acquired content uploaded by a user client to obtain a content framework, wherein the content framework is used to indicate the logical framework of the content of a presentation to be generated; determining a target presentation template that matches the content framework from candidate presentation templates, wherein the target presentation template includes multiple objects, each object corresponding to a presentation page; generating page elements corresponding to each object in the target presentation template based on the content framework to obtain structural data corresponding to the presentation; and transmitting the structural data to the user client so that the user client generates the presentation based on the structural data.

[0006] According to a second aspect of the embodiments of this application, a data display method is provided. The method includes: acquiring structured data transmitted in real time by a server, wherein the structured data includes association information between page elements and element content corresponding to each presentation page in a presentation, element description information for indicating the display mode corresponding to the page elements, and page structure information for indicating the stacking relationship between the page elements; parsing the structured data and rendering the presentation page onto a display interface based on the parsing progress; and adjusting the display effect of the presentation page in response to a user's adjustment operation on the page elements in the presentation page, and synchronizing the adjusted content to the server.

[0007] According to a third aspect of the present application, an electronic device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, wherein the executable instruction causes the processor to perform an operation corresponding to the method described in the first or second aspect.

[0008] According to a fourth aspect of the embodiments of this application, a computer storage medium is provided that stores a computer program thereon, which, when executed by a processor, implements the method as described in the first or second aspect.

[0009] According to a fifth aspect of the embodiments of this application, a computer program product is provided, including computer instructions that instruct a computing device to perform an operation corresponding to the method described in the first or second aspect.

[0010] According to the data generation scheme provided in this application embodiment, the content uploaded by the user client is first parsed to obtain a content framework, which indicates the logical framework of the content of the presentation to be generated. Then, a target presentation template matching the content framework is determined from the candidate presentation templates. This target presentation template includes multiple objects, each corresponding to a presentation page. Next, page elements corresponding to each object in the target presentation template are generated based on the content framework to obtain the structural data corresponding to the presentation, enabling the generation of the structural data on the server side. The structural data can then be transmitted to the user client, allowing the user client to render the presentation based on the structural data, eliminating the need for a rendering process on the server side. This improves server efficiency, thereby increasing the efficiency of presentation file generation and mitigating the problem of content loss caused by server-side rendering. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0012] Figure 1 A schematic diagram of an exemplary system for the data generation and display method applicable to the embodiments of this application; Figure 2 This is a flowchart illustrating the steps of a data generation method according to an embodiment of this application; Figure 3 This is a flowchart illustrating the steps of a data display method according to an embodiment of this application; Figure 4 This is a flowchart illustrating the steps of a presentation document generation method according to an embodiment of this application. Figure 5 This is an architecture diagram of a presentation generation system according to an embodiment of this application; Figure 6 This is a schematic diagram illustrating a data generation method and a data display method according to embodiments of this application. Figure 7 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0013] To enable those skilled in the art to better understand the technical solutions in the embodiments of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art should fall within the protection scope of the embodiments of this application.

[0014] The specific implementation of the embodiments of this application will be further described below with reference to the accompanying drawings.

[0015] Figure 1 An exemplary system applicable to embodiments of this application is shown. For example... Figure 1 As shown, the system 100 may include a cloud server 102, a communication network 104, and / or one or more user devices 106. Figure 1 The example in the text shows multiple user devices.

[0016] The cloud server 102 can be any suitable device for storing information, data, programs, and / or any other suitable type of content, including but not limited to distributed storage system devices, server clusters, computing cloud server clusters, etc. In some embodiments, the cloud server 102 can perform any suitable function. For example, in some embodiments, the cloud server 102 can be used to generate structure data for a presentation. As an optional example, in some embodiments, the cloud server 102 can be used to first parse the content uploaded by the user client (set in the user device) to obtain a content framework, wherein the content framework is used to indicate the logical framework of the content of the presentation to be generated. Then, a target presentation template matching the content framework is determined from the candidate presentation templates, wherein the target presentation template includes multiple objects, each object corresponding to a presentation page. Next, the page elements corresponding to each object in the target presentation template can be generated based on the content framework to obtain the structure data corresponding to the presentation, and the structure data is transmitted to the user client so that the user client can generate a presentation based on the structure data.

[0017] In some embodiments, the communication network 104 can be any suitable combination of one or more wired and / or wireless networks. For example, the communication network 104 can include any one or more of the following: the Internet, an intranet, a wide area network (WAN), a local area network (LAN), a wireless network, a digital subscriber line (DSL) network, a frame relay network, an asynchronous transfer mode (ATM) network, a virtual private network (VPN), and / or any other suitable communication network. The user equipment 106 can be connected to the communication network 104 via one or more communication links (e.g., communication link 112), and the communication network 104 can be linked to the cloud server 102 via one or more communication links (e.g., communication link 114). The communication link can be any communication link suitable for transmitting data between the user equipment 106 and the cloud server 102, such as a network link, a dial-up link, a wireless link, a hardwired link, any other suitable communication link, or any suitable combination of such links.

[0018] User device 106 may include any one or more user devices that parse structured data and render presentations. Specifically, the user device first acquires structured data transmitted in real time from cloud server 102. This structured data includes association information between page elements and their content corresponding to each presentation page, element description information indicating the display method of each page element, and page structure information indicating the stacking relationship between page elements. Then, the user device parses the structured data and renders the presentation pages onto the display interface based on the parsing progress. Next, in response to user adjustments to page elements on the presentation pages, the user device adjusts the display effect of the presentation pages and synchronizes the adjusted content to cloud server 102. In some embodiments, user device 106 may include any suitable type of device. For example, in some embodiments, user device 106 may include mobile devices, tablets, laptops, desktop computers, wearable computers, game consoles, media players, and / or any other suitable type of user device.

[0019] Based on the above system, the solutions provided in the embodiments of this application will be described below through multiple examples.

[0020] This embodiment provides a data generation method that can be used on a server-side, such as a cloud server. Figure 2 This is a flowchart of a data generation method according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps: Step S101: Parse the content uploaded by the user client to obtain a content framework, wherein the content framework is used to indicate the logical framework of the content of the presentation to be generated.

[0021] In this embodiment, the user client is located on the user's device. Uploaded content can be data such as keywords, documents, text, and images related to the content of the presentation to be generated (hereinafter referred to as PPT). The presentation can be a dynamic display medium combining text, images, charts, animations, and multimedia elements, and includes at least one slide. The content framework is used to indicate the logical framework of each page in the presentation to be generated. Through the content framework, the content logic of the presentation can be planned, information hierarchy organized, and design direction guided, thereby ensuring that the entire PPT has both a clear narrative structure and efficiently conveys core viewpoints. Specifically, the content framework can include the structure of different parts of the presentation, such as the cover, table of contents, core content, and summary, as well as the specific content layout within each presentation page.

[0022] In one alternative approach, after the server obtains the content uploaded by the user's client, it can call a generative model to parse the uploaded content in order to obtain the content framework of the presentation to be generated. Here, the generative model is a type of AI model with good semantic understanding and the ability to reason and generate new content. For example, generative models can include Large Language Models (LLMs).

[0023] For example, the uploaded content can first be preprocessed and cleaned to obtain content with uniform format and noise reduction. Then, logical paragraphs can be re-divided based on a combination of rules and machine learning. For example, the semantic coherence between sentences can be judged by the BERT (Bidirectional Encoder Representations from Transformers) model, and adjacent paragraphs with strong semantic relevance can be merged. For example, adjacent paragraphs with a semantic relevance of more than 80% can be merged to obtain the division result.

[0024] Then, the partitioning results can be input into a generative model such as LLM, so that the generative model can perform deep semantic parsing and information extraction based on the partitioning results to obtain the above content framework. The specific method of determining the content framework depends on the actual generative model used, and no specific limitation is made here.

[0025] Step S103: Determine the target presentation template that matches the content framework from the candidate presentation templates. The target presentation template includes multiple objects, each of which corresponds to a presentation page.

[0026] In this embodiment, the candidate presentation template can be a pre-stored presentation template in a template library. The template library can categorize candidate presentation templates according to presentation type, where the presentation type indicates the corresponding style, such as business style, educational style, or technological style. In this case, style analysis can be performed on the content framework to obtain the presentation type. Then, candidate presentation templates matching the presentation type can be determined from the template library, and the target presentation template can be selected from these candidate templates.

[0027] Step S105: Generate page elements corresponding to each object in the target presentation template based on the content framework to obtain the structural data corresponding to the presentation.

[0028] In this embodiment, page elements may include, but are not limited to, text elements, graphic elements, table elements, chart elements, animation elements, and multimedia elements. Text elements may include title bars, body paragraphs, notes, and footnotes; graphic elements may include rectangles, circles, and other shapes or images; table elements may include tables with several rows and columns; chart elements may include various statistical charts such as bar charts and line charts; animation elements may include dynamic images; and multimedia elements may include audio and video. Structured data is data with a predefined structure, format, or organization. For example, it may include, but is not limited to, structured JSON data. Structured data is used to describe the content, style, and layout information contained in the page elements of the target presentation template. For example, structured data can be organized in the form of key-value pairs, saving the content, style, and layout information corresponding to the page elements in the PPT for subsequent processing.

[0029] In one alternative approach, after determining the target presentation template, the generative model can be instructed to generate various types of page elements within the template and determine the attributes of each element. For example, text content can be generated for text elements, and the font style (e.g., name, size, bold, italic, etc.), color, and alignment can be determined. For text boxes, the generative model can specify their position, size, fill color, border style, and internal text paragraphs and runtime information. Similarly, the specific shapes of graphic elements, such as rectangles and circles, can be determined, along with their position, size, rotation angle, fill color, and border style. When an image element is filled with an image, the image path or URL can be recorded. Furthermore, the number of rows and columns of a table element can be determined, along with the content and span information of each cell. Finally, based on data series, labels, legends, and other information, various statistical charts such as bar charts and line charts can be generated for icon elements.

[0030] Next, we can establish the relationships between page elements and their corresponding content and attributes in each slide of the PowerPoint presentation, thereby generating an array corresponding to the presentation. This array can then be converted into structured data, such as structured JSON data. It should be understood that other forms of structured data are also possible, depending on the specific use case; no specific limitations are made here.

[0031] Step S107: Transmit the structure data to the user client so that the user client can generate a presentation based on the structure data.

[0032] As can be seen from the above, in this embodiment of the application, the structure data is generated in units of demo pages. Therefore, the structure data can be streamed to the user client in units of demo pages, thereby realizing the real-time transmission of structure data. Streaming allows the server to continuously and in chunks push data to the client on a persistent connection.

[0033] For example, whenever the structure data corresponding to a presentation page is ready, the structure data can be pushed to the user client in real time using long-connection technologies such as Server-Sent Events (SSE), without waiting for the structure data of the entire PPT to be prepared. It should be understood that other long-connection technologies can also be used to achieve real-time transmission of structure data in this application embodiment, depending on what is feasible, and this application embodiment will not elaborate on them.

[0034] As described above, in this embodiment, the content uploaded by the user client is first parsed to obtain a content framework, which indicates the logical framework of the content of the presentation to be generated. Then, a target presentation template matching the content framework is determined from the candidate presentation templates. This target presentation template includes multiple objects, each corresponding to a presentation page. Next, page elements corresponding to each object in the target presentation template are generated based on the content framework to obtain the structural data corresponding to the presentation, enabling the generation of the structural data on the server side. The structural data can then be transmitted to the user client, allowing the user client to render the presentation based on the structural data, eliminating the need for a rendering process on the server side. This improves server efficiency, thereby increasing the efficiency of presentation file generation and mitigating the problem of content loss caused by server-side rendering.

[0035] In some optional implementations, the content uploaded by the user client includes at least one of the following: topic keywords, documents, and text content. Step S101 above parses the obtained content uploaded by the user client to obtain a content framework, including: Step S1011: Parse the uploaded content based on the generative model to obtain the presentation outline.

[0036] Step S1012: Determine the layout of each object in the presentation based on the presentation outline to obtain the content framework.

[0037] In this embodiment, the presentation outline may include key points such as the theme and content to be expressed in the presentation. The content frame, on the other hand, is used to indicate the more specific logical framework of each page in the presentation.

[0038] In determining the presentation outline, the generative model can first determine the type of data contained in the uploaded content, adopt different parsing strategies according to the type, and determine the presentation outline based on the parsing results.

[0039] For example, topic keywords describe the theme of the presentation to be generated. When the uploaded content includes topic keywords, the generative model can parse and generate a presentation outline. Alternatively, LLM can be used for parsing and generation. Here, Retrieval Augmentation (RAG) can be performed first based on the topic keywords to obtain information related to those keywords from a knowledge base. Then, based on the topic keywords and the information obtained from the RAG retrieval, prompts are generated to instruct the LLM to generate the presentation outline. For example, when the topic keywords include "artificial intelligence" and "algorithmic bias," the prompt generated based on these keywords and the information obtained from the RAG retrieval could be: "Based on the following background information, design a logically rigorous presentation outline for 'Artificial Intelligence Ethics,' including an introduction, core issues (such as personal information protection and algorithmic bias), typical cases, suggested solutions, and conclusions." The presentation outline generated by the LLM based on the above prompts could be: "Topic: Challenges and Responses to Artificial Intelligence Ethics, Core Ethical Issues, and Typical Case Analysis."

[0040] After obtaining the presentation outline, a second RAG (Research and Argumentation) can be performed based on the outline and key themes to obtain matching auxiliary information that can be used to generate the content framework. Here, the presentation outline can be used to determine the various chapters within the presentation, as well as the logical framework of the corresponding presentation pages within each chapter. The auxiliary information can include detailed information retrieved from searches of each chapter in the presentation outline. For example, using the presentation outline and original key themes as input, a knowledge base can be further searched to supplement detailed information matching each chapter, such as searching for specific research reports or regulatory clauses related to "algorithmic bias."

[0041] Next, a new prompt can be generated based on this auxiliary information, presentation outline, and topic keywords, and a content framework can be generated using LLM based on this prompt. For example, the content framework generated by LLM based on the prompt may include: 1. Introduction; 2. Core ethical issues: (1) Data privacy and abuse, (2) Algorithmic bias and social fairness; 3. Typical case analysis: facial recognition misjudgment incidents and liability attribution for autonomous driving accidents; 4. Governance framework recommendations; 5. Conclusion and future outlook. Here, taking the typical case analysis in Chapter 3 as an example, the logical framework of a one-page presentation page corresponding to this chapter can be: Chapter 3: Typical Case Analysis - **Case 1: Facial Recognition Misjudgment Incident** • Time / Location: Wrongfully identifying a suspect by law enforcement in a U.S. state in 2020; • Reason: Bias in the training dataset leads to differences in recognition accuracy; • Impact: Raises public concerns about the impartiality of AI in the judicial process; • Data cited: MIT research shows that the error rate of commercial facial recognition is as high as 35% (in certain populations); - **Countermeasures:** Require high-risk systems to undergo third-party audits.

[0042] For example, when uploading content including documents, generative models such as LLM can parse the document and generate a presentation outline; further, they can generate a content framework based on this presentation outline. Because documents contain relatively rich information that can represent the content to be displayed in the presentation, LLM can directly parse the document and generate a presentation outline based on the parsing results. Then, based on the presentation outline, a Representational Aggregator (RAG) can be performed to obtain matching auxiliary information that can be used to generate the content framework; a new prompt can then be generated based on this auxiliary information, the presentation outline, and the content of the aforementioned document; and the content framework can be generated by LLM based on this prompt.

[0043] For example, when uploading text content, if the text content contains information such as core content, chapter hierarchy, and relationships, a generative model like LLM can directly generate a corresponding presentation outline based on the text content. If the text content only provides simple summary information, a Representational Analysis (RAG) can be performed on the text content to obtain matching auxiliary information, while summarizing the key themes of the text content. Then, a prompt can be generated based on the auxiliary information and key themes, instructing the LLM to generate a presentation outline. The specific method of generating a prompt based on auxiliary information and key themes, and instructing the LLM to generate a presentation outline, is as described above and will not be repeated here. Furthermore, a RAG can be performed again on the presentation outline to obtain matching auxiliary information that can be used to generate a content framework. Then, a new prompt can be generated based on this auxiliary information, the presentation outline, and the aforementioned key themes, and the LLM can generate a content framework based on this prompt. The specific method of generating a content framework is as described above and will not be repeated here.

[0044] By using generative models, we can not only generate more comprehensive and rational presentation outlines and content frameworks, but also simplify the implementation of solutions.

[0045] In some optional implementations, step S103 above, which involves determining a target presentation template that matches the content framework from the candidate presentation templates, includes: The content framework and / or uploaded content are analyzed based on a generative model to obtain the presentation type, and a target presentation template that matches the presentation type is determined from the candidate presentation templates; or the target presentation template that matches the content framework is determined by the user through the user client from the candidate presentation templates.

[0046] In this embodiment of the application, candidate demonstration templates in the template library can be displayed in the user client, and in response to the user's selection operation in the user client, the candidate demonstration template selected by the user client can be determined as the target demonstration template.

[0047] Additionally, if the user client does not select a target presentation template, the generative model can first perform analysis based on the above content framework, such as style analysis, to obtain the presentation type. For example, the presentation type may include business style, education style, technology style, etc. Then, a target presentation template that matches the presentation type can be determined from the template library.

[0048] Here, the correlation between each candidate presentation template and the content frame corresponding to the presentation type can be calculated, and the candidate presentation template with the highest correlation can be determined as the target presentation template. Alternatively, a generative model can be used to analyze the correlation between uploaded content and the content frame, and based on this, the candidate presentation template with the highest correlation can be determined as the target presentation template.

[0049] Taking LLM as an example, in the previous example, the content framework can be determined based on the presentation outline. In this case, the presentation outline is also part of the content framework. LLM can determine the target presentation template based on the information of the presentation outline and the candidate presentation templates, and select the candidate presentation template with the highest relevance to the outline.

[0050] For example, LLM can parse the core keywords and topic sentences in the outline based on the prompt and semantically align them with the preset structural tags of the candidate presentation templates. If the outline contains a comparison of technical parameters, it will prioritize matching candidate presentation templates that contain tables or charts.

[0051] For example, LLM can also analyze the space distribution reserved in candidate presentation templates, such as the position of text boxes and the proportion of image placeholders, to determine whether they can accommodate the presentation requirements of the outline content. Candidate presentation templates that can meet the presentation requirements of the outline content are identified as target presentation templates. For example, long paragraphs need to be matched with candidate presentation templates with scrolling text areas, while short sentence lists are more suitable for candidate presentation templates with icon-assisted bullet points pages.

[0052] In this embodiment of the application, the content framework and / or uploaded content can be analyzed based on a generative model to obtain the presentation type, and a target presentation template that matches the presentation type can be determined from the candidate presentation templates, or the target presentation template determined by the user client can be obtained, so that the determined target presentation template can better meet the user's usage needs.

[0053] In some optional implementations, step S103 above further includes: Based on the target presentation template and content framework, generate a presentation preview image and send the presentation preview image back to the user's client; Obtain prompts from user input based on presentation preview images, and adjust the corresponding structural data of the presentation based on the prompts and instructions of the generative model.

[0054] In this embodiment, the presentation preview image is used to give users a general idea of ​​the final generated PPT presentation. Therefore, before generating the structural data of the presentation, a presentation preview image can be generated based on the target presentation template and content framework. Specifically, the generative model can be instructed to fill in the page elements in the target presentation template based on the content framework to obtain a presentation for preview. Next, the presentation can be captured by taking a screenshot or other means to generate a presentation preview image, which is then sent back to the user's client.

[0055] After receiving the presentation preview image, the user client can use it to understand the final presentation's appearance. If the user is not satisfied with the presentation, they can input a prompt, which will be transmitted to the server to instruct the generative model to adjust the presentation's structural data to meet the user's desired presentation effect.

[0056] In this embodiment of the application, a presentation preview image can be generated based on the target presentation template and content framework, and the presentation preview image can be sent back to the user's client, so that the user can understand the presentation effect of the PPT, so that the user can instruct the generative model to correct the PPT generation process and improve the accuracy of the final generated PPT.

[0057] In some optional implementations, step S105 above, which generates page elements corresponding to each object in the target presentation template based on the content framework, to obtain the structural data corresponding to the presentation, includes: The content framework is input into the generative model, which then generates supplementary content corresponding to the page elements in the target presentation template based on the content framework, and generates element description information that matches the supplementary content, thus obtaining the structural data corresponding to the presentation. The element description information is used to indicate the display method of the page elements.

[0058] In this embodiment, the supplementary content can be dynamic data automatically populated into page elements by the generative model based on the content framework. Element description information can include the attributes of the aforementioned page elements, such as visual style, interaction methods, spatial layout constraints, multimedia adaptation, etc., wherein visual style can include font size, color, animation effects, etc., interaction methods can include clicking to expand details, floating tips, etc., spatial layout constraints can include left alignment, center alignment, cross-column display, etc., and multimedia adaptation rules can include image ratio, video autoplay settings, etc.

[0059] Here, we take a generative model, LLM, as an example. In the process of determining supplementary content, LLM can transform abstract textual descriptions within the content framework into visual materials. For instance, LLM can convert abstract descriptions such as keywords within the content framework into visual materials. For example, for chart elements, if the chart element is used to describe content related to core competencies, supplementary content such as a list of charts can be inserted to visualize key advantages.

[0060] Furthermore, when determining element descriptions that match supplementary content, LLM can match the page element with a corresponding display method based on the criticality of the supplementary content within the page element, thereby generating element description information based on the display effect. For example, when "important data indicators" are detected, the display method for marking this paragraph can be highlighted using bold red font combined with an upward arrow animation.

[0061] After determining the supplementary content and element description information, LLM can generate the data structure corresponding to the presentation according to a preset standardized data format. For example, the data structure may include structured JSON data, which may include key-value pairs between page elements and supplementary content and element description information.

[0062] In this embodiment, the generative model can determine the supplementary content corresponding to the page elements in the target presentation template based on the content framework, and determine the element description information that matches the supplementary content. Based on the supplementary content and element description information, the structural data corresponding to the presentation can be determined, so that the core responsibility of the server can return to its strengths in data processing and AI capability scheduling. It no longer needs to run a heavyweight rendering program for each user, so that users do not have to wait for the server to generate the entire PPT, reducing the time users spend waiting for PPT generation.

[0063] In some optional implementations, the above-mentioned structured data includes the data nesting structure corresponding to each presentation page in the presentation, and step S105 further includes: Step S21: Obtain the page structure information corresponding to the target demo template, wherein the page structure information is used to indicate the hierarchical relationship between page elements in the target demo template.

[0064] In this embodiment of the application, the page structure information may include the DOM (Document Object Model Tree) structure of the target demo template. The DOM structure follows the "root-leaf-look" node model, where each page element is both a child node of a parent page element and may also have its own child page elements.

[0065] It should be understood that, in this embodiment of the application, the DOM structure corresponding to each candidate demo template in the template library can be preset. Therefore, after determining the target demo template from the candidate demo templates, the DOM structure corresponding to the target demo template can be directly called to obtain the page structure information. For example, determining the page structure information corresponding to the candidate demo template may include the following process: Step a1: Obtain the candidate demo template.

[0066] Step a2: Based on the generative model, the candidate demo template is parsed to obtain the page elements to be supplemented, and based on the hierarchical relationship between the page elements, the page structure information corresponding to the candidate demo template is determined.

[0067] In this embodiment, the generative model can perform semantic and structural analysis on the selected presentation template to obtain the page elements to be added. For example, semantic analysis can include placeholder annotation analysis, specifically, the editable areas in the selected presentation template, such as title boxes, body paragraphs, footnotes, etc. For instance, if a text box is labeled "Click here to add a chart," the LLM will classify it as a "data visualization slot" and identify it as a page element to be added. Additionally, structural analysis can include spatial partitioning analysis. Specifically, the LLM can divide the page in the selected presentation template into different functional modules based on the page structure, such as a left navigation bar, a central main display area, a right notes bar, etc., and analyze each functional module to obtain the page elements to be added.

[0068] After identifying the page elements to be added, a standard DOM structure can be recursively generated based on the hierarchical nesting relationships and spatial location information between page elements. Specifically, each page element can be converted into a DOM node object, and the parent-child relationship of the DOM node objects can be determined. The basis for determining the parent-child relationship can include physical containment relationships, logical subordination relationships, etc. Physical containment relationships indicate that one page element is completely within the boundary of another page element. Logical subordination relationships can be page elements with pre-defined subordination relationships, such as bulleted list items belonging to corresponding numbered headings. It should be understood that when handling overlap conflicts, the principle of "last-in, first-out" can be used, such as the last added element being displayed on top.

[0069] In this embodiment, the selected presentation template can be parsed based on a generative model to obtain page structure information, which can then be converted into structure data to be filled. This allows incremental writing to supplement the content when generating a PPT based on the selected presentation template, thereby further improving the PPT generation efficiency.

[0070] Step S22: Based on the page structure information, nest the page elements in the presentation page to obtain a data nesting structure.

[0071] In this embodiment, when nesting page elements in a presentation page, a depth-first search algorithm is first used to traverse the page structure information corresponding to each page of the presentation, thereby transforming the parent-child relationship in the DOM structure into a data nesting structure. For example, this data nesting structure may include structured JSON sub-data. Then, structural data can be determined based on this data nesting structure, facilitating automated processing of the PPT directly based on this structural data.

[0072] In some optional implementations, step S107 above, transmitting the structure data to the user client, includes: The structural data corresponding to each page of the presentation is sequentially transmitted to the user client.

[0073] In this embodiment, whenever the structure data corresponding to a presentation page is ready, the structure data can be immediately pushed to the user client using the aforementioned long-connection technology such as SSE, without waiting for the structure data of the entire PPT to be prepared. It should be understood that other long-connection technologies can also be used to achieve real-time transmission of structure data; the specific implementation depends on what is feasible, and this application will not elaborate on these.

[0074] In this embodiment of the application, whenever the structural data corresponding to a presentation page is ready, it can be immediately transmitted to the user client through long connection technology, thereby shortening the time for the user client to render the homepage content to the second level, so that the user can start browsing almost immediately and reduce the user's waiting time.

[0075] In summary, in this embodiment, the content uploaded by the user client is first parsed to obtain a content framework, which indicates the logical framework of the content of the presentation to be generated. Then, a target presentation template matching the content framework is determined from the candidate presentation templates. This target presentation template includes multiple objects, each corresponding to a presentation page. Next, page elements corresponding to each object in the target presentation template are generated based on the content framework to obtain the structural data corresponding to the presentation, enabling the generation of the structural data on the server side. The structural data can then be transmitted to the user client, allowing the user client to render the presentation based on the structural data, eliminating the need for a rendering process on the server side. This improves server efficiency, thereby increasing the efficiency of presentation file generation and mitigating the problem of content loss caused by server-side rendering.

[0076] This embodiment provides a data display method that can be used on a user client. Figure 3 This is a flowchart of a data display method according to an embodiment of this application, such as... Figure 3 As shown, the process includes the following steps: Step S201: Obtain the structure data transmitted in real time from the server. The structure data includes the data nesting structure between page elements corresponding to each presentation page in the presentation.

[0077] In this embodiment, the structured data transmitted in real time by the server can be streamed in units of presentation pages, such as structured JSON data. The specific method for determining the structured data is as described above. Figure 2 The corresponding embodiments are described herein and will not be repeated here.

[0078] Step S203: Parse the structural data and render the presentation page onto the display interface based on the parsing progress.

[0079] In this embodiment of the application, an HTML5 page to be rendered can be displayed on the display interface, and the data stream from the server can be listened to, the structured JSON data corresponding to the presentation page can be received and parsed in real time, and then the parsed page elements can be rendered into the HTML5 page according to their hierarchical relationship based on the parsing progress.

[0080] Step S205: In response to the user's adjustment operation on the page elements in the presentation page, adjust the display effect of the presentation page and synchronize the adjusted content to the server.

[0081] In the embodiments of this application, adjustment operations may include dragging, deleting, adding, scaling, etc., of page elements. The client can capture the user's adjustment operations through the interaction layer. For example, a mask can be set in advance in the HTML5 page, and the object operated on and the specific operation content can be detected through the mask. It should be understood that other methods can also be used to capture the user's adjustment operations, depending on what can be implemented. This application does not make specific limitations on this.

[0082] It should be understood that user clients can synchronize changes to the PowerPoint presentation to the server, achieving data synchronization between the client and server, thereby ensuring consistency between the backup data on the server and the PowerPoint data on the user's client. Here, after the user confirms the generation of the PowerPoint presentation, the PowerPoint file can be exported, and user permissions can be verified so that the PowerPoint file can be downloaded to the local machine after the permission verification is successful.

[0083] As described above, in this embodiment, the system first acquires the structured data transmitted in real-time from the server. This structured data includes the nested data structure between page elements corresponding to each presentation page. Then, the structured data is parsed, and the presentation pages are rendered onto the display interface based on the parsing progress. Next, in response to user adjustments to page elements within the presentation pages, the system adjusts the display effect of the presentation pages and synchronizes the adjusted content to the server. This eliminates the need for server-side rendering of the presentation, improving the quality of the presentation and mitigating the problem of content loss caused by server-side rendering.

[0084] In some optional implementations, step S203 above, parsing the structure data and rendering the presentation page onto the display interface based on the parsing progress, includes: The structural data is parsed to obtain page structure information. Based on the page structure information, the parsed page elements are rendered into the display interface according to the parsing progress. The page structure information is used to indicate the hierarchical relationship between page elements in the target demo template.

[0085] As can be seen from the above, the page structure information defines the hierarchical relationship between page elements in the presentation page. Therefore, the parsed page elements can be rendered onto the display interface based on the DOM structure in the page structure information.

[0086] For example, the coordinate parameters of page elements in the structured JSON data can first be converted into screen pixel positions, and the stacking order of page elements can be determined based on the DOM structure to handle the occlusion relationship between page elements according to this stacking order. Then, SVG can be used to add real-time outlines to page elements and fill shapes. Finally, a text layout engine can be used to achieve advanced text processing such as automatic line wrapping and character spacing adjustment.

[0087] The process of rendering the parsed page elements onto the display interface can be done dynamically. Specifically, a basic framework, such as the outline of the title box, can be drawn first, and then text, images, and other materials can be displayed gradually, with entrance animations played according to the timeline of the parsing progress.

[0088] In this embodiment, based on the page structure information of the presentation, the parsed page elements can be rendered onto the display interface according to the parsing progress, thereby making the page rendering process visible. Users are no longer facing an unknown and lengthy PPT generation process, thus making the entire construction process transparent and visible. Users can clearly perceive the progress and output of AI, improving the user experience.

[0089] In some optional implementations, step S205 above, in response to a user's adjustment operation on page elements in the presentation page, adjusts the display effect of the presentation page, including: Step S2051: During the rendering of the presentation page, capture adjustment operations and pause the rendering process when an adjustment operation is captured.

[0090] Step S2052: Based on the page structure information, determine the adjustable page elements in the presentation page.

[0091] Step S2053: Display the adjustable page elements and adjust the presentation page display in response to adjustment operations on the adjustable page elements.

[0092] In this embodiment, during or after the rendering of a slide in a PowerPoint presentation, the user can make adjustments. It should be understood that after the user's client engine detects an adjustment operation, it can pause the rendering process and determine the currently adjustable page elements based on the rendering progress of the presentation slide.

[0093] For example, step S2052 above, based on page structure information, determines adjustable page elements in the presentation page, including: Step S31: Based on the parsing progress of the structural data information corresponding to the presentation page and the page structure information, determine the target page elements whose correlation between unparsed page elements meets the adjustment requirements.

[0094] Step S32: Based on the target page elements, determine the adjustable page elements.

[0095] In this embodiment of the application, the parsing progress is used to indicate whether the rendering of the current presentation page has ended. If so, the unparsed page elements can be determined based on the page structure information, and the adjustable target page element can be determined among the unparsed page elements. For example, the target page element can be a page element among the unparsed page elements that does not have any relationship with other unparsed page elements or parsed page elements. That is, adjusting the target page element will not cause the other page elements to be adjusted.

[0096] For example, it can be determined whether the unparsed page element corresponding to the current parsing progress contains child nodes. If not, the page element is identified as an adjustable page element. If so, it can be determined whether the current adjustment operation will affect the page elements in the child nodes. If so, the page element can be identified as an unadjustable item; otherwise, it is an adjustable item. Additionally, it can be determined whether the page element corresponding to the current parsing progress is associated with other page elements. If so, the page element can be identified as an unadjustable item; otherwise, it is an adjustable item.

[0097] Additionally, if the parsing progress indicates that the current presentation page has finished rendering, then all page elements on that presentation page can be identified as adjustable.

[0098] In this embodiment, the interaction layer can capture the user's adjustment operations in real time to achieve partial redrawing of the presentation page being rendered, without waiting for the entire PPT presentation page to finish rendering, thereby achieving zero-latency WYSIWYG editing.

[0099] In summary, in this embodiment, the structural data transmitted in real time by the server can be obtained first. This structural data includes the nested data structure between page elements corresponding to each presentation page in the presentation. Then, the structural data can be parsed, and the presentation pages can be rendered onto the display interface based on the parsing progress. Next, in response to user adjustments to page elements within the presentation pages, the display effect of the presentation pages can be adjusted, and the adjusted content can be synchronized to the server. This separates the generation and rendering processes of the presentation's structural data, improving the problem of content loss caused by server-side rendering and enhancing the quality of the presentation.

[0100] This embodiment provides a method for generating presentations. Figure 4 This is a flowchart of a presentation document generation method according to an embodiment of this application, such as... Figure 4 As shown, the process includes the following steps: Step S301: Obtain the content uploaded by the user's client.

[0101] Step S302: Determine the input type of the data included in the uploaded content. If the uploaded content includes topic keywords, proceed to step S303 based on the topic keywords; if the uploaded content includes documents, proceed to step S304 based on the documents; if the uploaded content includes text content, proceed to step S305 based on the text content.

[0102] Step S303: Perform topic keyword analysis based on LLM.

[0103] Step S304: Perform document content parsing based on LLM.

[0104] Step S305: Perform text content parsing based on LLM.

[0105] Step S306: Based on the parsing results determined in steps S303-S305 above, instruct the LLM to generate a content framework.

[0106] In this embodiment, the method of obtaining the uploaded content from the user client and parsing the uploaded content based on the generative model to obtain the content framework is as described in the embodiment corresponding to step S101 above, and will not be repeated here.

[0107] Step S307: Based on the content framework, determine the target presentation template from the candidate presentation templates.

[0108] In this application embodiment, the style of the presentation can be determined based on the content framework to obtain the presentation type. The specific method for determining the presentation type is as described in the embodiment corresponding to step S101 above, and will not be repeated here.

[0109] Step S308: Detect the target demo template selected by the user client and perform template preloading.

[0110] Step S309: Generate and intelligently format content based on the target presentation template.

[0111] In this embodiment, the method for generating content to fill the target presentation template is as described in the embodiment of step S105 above, which states that "the content framework is input into the generative model so that the generative model determines the supplementary content corresponding to the page elements in the target presentation template based on the content framework," and will not be repeated here. Furthermore, when filling the target presentation template, the LLM can dynamically adjust the size and spacing of the filled page elements based on the principle of information density balance. For example, the title area is allocated more space according to visual weight, while data visualization components preferentially occupy the central focus position.

[0112] Step S310: Intelligent image matching with legend.

[0113] In this embodiment, LLM can further analyze the page elements that can be illustrated in the target presentation template and determine the legends that match the page elements in the material library. For example, when the page element includes the phrase "Example of Future City Transportation", a cyberpunk-style transportation scene illustration can be matched in the material library.

[0114] Step S311, text typesetting and layout.

[0115] In this embodiment, LLM can automatically adjust the font size according to the text length of each page element. For example, long paragraphs can use a 10pt font size for compact layout, and short headings can use a 14pt font size for emphasis, which improves the aesthetics of the layout while reducing the risk of text overflow.

[0116] Step S312: Generate a PPT preview image.

[0117] In this embodiment of the application, the method of generating PPT is as described in steps S103-107 above, and will not be repeated here.

[0118] Step S313: Render the PPT page through the front-end rendering container, which includes a data parsing module, a graphics rendering module, a text rendering module, and an image rendering module.

[0119] Step S314: Detect the user's adjustment operation.

[0120] Step S315: Determine the adjustment operation type, which includes text editing, image processing, template replacement, and AI retouching.

[0121] In this embodiment, text editing is used to instruct adjustments to the font, size, color, alignment, etc. of text using a text editor. Image processing is used to instruct adjustments such as uploading, cropping, scaling, and replacing images using an image editor. Template changing is used to instruct switching to a target demo template based on a template library. AI polishing is used to instruct content optimization based on a large model, such as text polishing, rewriting, abbreviation, and expansion.

[0122] Step S316: Based on the results of the adjustment operation, preview the PPT update in real time.

[0123] Step S317: Determine whether a user confirmation operation on the PPT has been detected. If yes, proceed to step S318; otherwise, proceed to step S314.

[0124] Step S318: Export the PPT.

[0125] Step S319: Verify user permissions. If successful, send the PPT file to the user.

[0126] Step S320: Download the PPT file to your local computer.

[0127] Reference Figure 5 The diagram shows a schematic of a presentation generation system according to this application. The presentation generation system is used to execute the above-mentioned data generation method and data display method. The presentation generation system includes: a user interaction layer, a user client, an infrastructure layer, and a server.

[0128] The user interaction layer is used to capture user client interaction operations, such as uploading content before generating a presentation, and adjusting the presentation after it is generated.

[0129] The server-side includes a data processing module, an AI service module, and a PPT processing module. The data processing module is used to paginate the selected presentation template to obtain each presentation page. The AI ​​service module is used to perform content understanding based on the above content framework and match it with the target presentation template during the presentation generation process. The PPT processing module is used to generate structured JSON data corresponding to the presentation.

[0130] The user client includes an interaction layer, a canvas layer, a plugin layer, an element component layer, a middleware layer, and a data layer. The interaction layer is used to listen for captured interactive operations, such as the upload and adjustment operations mentioned above. The canvas layer is used to render the presentation based on the structured JSON data mentioned above. The plugin layer is used to adjust the layout of page elements in each presentation page. The middleware layer is used to manage the editing status of page elements. The data layer is used to parse the structured JSON data of the presentation.

[0131] The infrastructure layer includes storage units and a network layer. The storage units are used to store candidate presentation templates, user data, material resources, and generated presentation files. The network layer is used to provide streaming and persistent connection channels to enable data transmission of presentation files between user clients and servers.

[0132] The following uses the scenario corresponding to the aforementioned presentation generation system as an example, combined with... Figure 6 The data generation and data display methods of this application are illustrated with scenario examples.

[0133] exist Figure 6In the process, users can upload relevant content, such as Document 1 and Document 2, on the AI ​​assistant page of the user client, and enter the prompt header "Generate a PPT on the theme of XX with the uploaded content" in the input area, so as to instruct LLM to generate a presentation based on the prompt header.

[0134] After receiving the prompt header, the server-side LLM can parse the uploaded content entered by the user client to obtain a content framework including the presentation outline, match the target presentation template for the outline, and populate the target presentation template according to the layout indicated by the outline and content framework to obtain the structured JSON data corresponding to each page of the presentation.

[0135] It should be understood that whenever the structured JSON data corresponding to a presentation page is ready, the structured data can be immediately pushed to the user's client using the aforementioned SSE long-lived connection technology, without waiting for the structured data of the entire PPT to be prepared.

[0136] The user client listens to the data stream from the server, receives and parses the structured JSON data corresponding to the presentation page in real time, and then dynamically renders the parsed page elements into the HTML5 page according to their hierarchical relationship based on the parsing progress.

[0137] When rendering a presentation page, the user client can detect the user's adjustment operations through the interaction layer. These adjustment operations can include dragging, deleting, adding, scaling, etc., of page elements. The client can capture the user's adjustment operations through the interaction layer. For example, a mask can be set in advance in the HTML5 page, and the object being adjusted and the specific content of the operation can be detected through the mask.

[0138] After obtaining the adjustment details, the user client can adjust the display effect of the presentation page and synchronize the adjustment to the server. The server will then adjust the backup data based on the adjustment and perform permission verification on the user after rendering all presentations. If the verification is successful, the server will send the presentation file to the user.

[0139] Reference Figure 7 The diagram shows a structural schematic of an electronic device according to Embodiment 5 of this application. The specific embodiments of this application do not limit the specific implementation of the electronic device.

[0140] like Figure 7 As shown, the electronic device may include: a processor 502, a communications interface 504, a memory 506, and a communications bus 508.

[0141] in: The processor 502, communication interface 504, and memory 506 communicate with each other via communication bus 508.

[0142] Communication interface 504 is used to communicate with other electronic devices or servers.

[0143] The processor 502 is used to execute program 510, which can specifically execute the relevant steps in the above-described verification code generation method embodiment.

[0144] Specifically, program 510 may include program code that includes computer operation instructions.

[0145] The processor 502 may be a CPU, a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The electronic device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs.

[0146] Memory 506 is used to store program 510. Memory 506 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0147] Program 510 may include multiple computer instructions. Specifically, program 510 may use multiple computer instructions to cause processor 502 to perform the operations corresponding to the data generation method and data display method described in any of the foregoing multiple method embodiments.

[0148] The specific implementation of each step in program 510 can be found in the corresponding steps and units described in the above method embodiments, and has corresponding beneficial effects, which will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the devices and modules described above can be referred to the corresponding process descriptions in the foregoing method embodiments, and will not be repeated here.

[0149] This application also provides a computer storage medium storing a computer program thereon, which, when executed by a processor, implements the method described in any of the foregoing method embodiments. The computer storage medium includes, but is not limited to, compact disc read-only memory (CD-ROM), random access memory (RAM), floppy disk, hard disk, or magneto-optical disk.

[0150] This application also provides a computer program product, including computer instructions that instruct a computing device to perform operations corresponding to any of the data generation and data display methods in the above-described multiple method embodiments.

[0151] Furthermore, it should be noted that the user-related information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to sample data used for training the model, data used for analysis, stored data, displayed data, etc.) involved in the embodiments of this application are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0152] It should be noted that, depending on the implementation needs, the various components / steps described in the embodiments of this application can be broken down into more components / steps, or two or more components / steps or parts of the operation of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of this application.

[0153] The methods described in the embodiments of this application can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD-ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code downloaded over a network that is originally stored in a remote recording medium or a non-transitory machine-readable medium and will be stored in a local recording medium. Thus, the methods described herein can be stored on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an Application Specific Integrated Circuit (ASIC) or a Field Programmable Gate Array (FPGA)). It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components (e.g., Random Access Memory (RAM), Read-Only Memory (ROM), Flash Memory, etc.) capable of storing or receiving software or computer code, implementing the methods described herein when the software or computer code is accessed and executed by the computer, processor, or hardware. Furthermore, when a general-purpose computer accesses code used to implement the methods shown herein, the execution of the code transforms the general-purpose computer into a dedicated computer for executing the methods shown herein.

[0154] Those skilled in the art will recognize that the units and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this application.

[0155] The above embodiments are only used to illustrate the embodiments of this application, and are not intended to limit the embodiments of this application. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the embodiments of this application. Therefore, all equivalent technical solutions also fall within the scope of the embodiments of this application, and the patent protection scope of the embodiments of this application should be defined by the claims.

Claims

1. A data generation method, the method comprising: parsing uploaded content of a user client to obtain a content framework, wherein the content framework is used to indicate a logical framework of content of a presentation to be generated; determining a target presentation template matching the content framework from candidate presentation templates, wherein the target presentation template comprises a plurality of objects, each object corresponding to a page of the presentation; generating page elements corresponding to the objects in the target presentation template based on the content framework to obtain structural data of the presentation; transmitting the structural data to the user client to enable the user client to generate the presentation based on the structural data.

2. The method of claim 1, wherein, The generating page elements corresponding to the objects in the target presentation template based on the content framework to obtain structural data of the presentation comprises: inputting the content framework into a generative model to enable the generative model to generate supplementary content corresponding to the page elements in the target presentation template based on the content framework, and generate element description information matching the supplementary content to obtain the structural data of the presentation, wherein the element description information is used to indicate a display mode corresponding to the page elements.

3. The method of claim 2, wherein, The structural data comprises a data nesting structure corresponding to each page of the presentation. The method further comprises: obtaining page structure information corresponding to the target presentation template, wherein the page structure information is used to indicate a hierarchical relationship between page elements in the target presentation template; nesting the page elements in the pages of the presentation based on the page structure information to obtain the data nesting structure.

4. The method of claim 3, wherein, The method further comprises: obtaining a candidate presentation template before obtaining the page structure information corresponding to the target presentation template; analyzing the candidate presentation template based on a generative model to obtain page elements to be supplemented, and determining the page structure information corresponding to the candidate presentation template based on a hierarchical relationship between the page elements.

5. The method of claim 1, wherein, The uploaded content of the user client comprises at least one of the following: a theme keyword, a document, and text content used to generate a presentation; The parsing the uploaded content of the user client to obtain a content framework comprises: analyzing the uploaded content of the user client based on a generative model to obtain a presentation outline; determining a layout of each object in the presentation based on the presentation outline to obtain the content framework.

6. The method of claim 1, wherein, The determining a target presentation template matching the content framework from candidate presentation templates comprises: analyzing the content framework and / or the uploaded content based on a generative model to obtain a presentation type, and determining a target presentation template matching the presentation type from the candidate presentation templates; or obtaining a target presentation template matching the content framework from the candidate presentation templates determined by a user through the user client.

7. The method of claim 6, wherein, The method further comprises: generating a preview image of the presentation based on the target presentation template and the content framework, and returning the preview image of the presentation to the user client; obtain a prompt word input by the user based on the presentation preview image, to instruct the generative model to adjust the structural data corresponding to the presentation based on the prompt word.

8. The method of claim 1, wherein, The transmitting the structural data to the user client comprises: transmitting the structural data corresponding to each page of the presentation to the user client in sequence.

9. A data display method, the method comprising: obtaining structural data transmitted by a server in real time, wherein the structural data comprises a data nesting structure between page elements corresponding to each page of a presentation; parsing the structural data and rendering the presentation page into a display interface based on a parsing progress; in response to an adjustment operation of a user on a page element in the presentation page, adjusting the display effect of the presentation page and synchronizing the adjustment content to the server.

10. The method of claim 9, wherein, The parsing the structural data and rendering the presentation page into a display interface based on a parsing progress comprises: parsing the structural data to obtain the page structure information, and based on the page structure information, rendering the parsed page elements into the display interface according to the parsing progress, wherein the page structure information is used to indicate the hierarchical relationship between the page elements in the target presentation template.

11. The method of claim 10, wherein, The response to the adjustment operation of the user on the page element in the presentation page to adjust the display effect of the presentation page comprises: capturing the adjustment operation during the rendering of the presentation page, and pausing the rendering process when the adjustment operation is captured; determining the adjustable page element in the presentation page based on the page structure information; displaying the adjustable page element and adjusting the display effect of the presentation page in response to the adjustment operation on the adjustable page element.

12. The method of claim 11, wherein, The determination of the adjustable page element in the presentation page based on the page structure information comprises: determining a target page element whose correlation between un-parsed page elements meets the adjustment requirement based on the parsing progress of the structural data corresponding to the presentation page and the page structure information; determining the adjustable page element based on the target page element.

13. An electronic device comprising: a processor, a memory, a communication interface, and a communication bus, the processor, the memory, and the communication interface communicate with each other through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform the operation corresponding to the method in any one of claims 1-12.

14. A computer storage medium having a computer program stored thereon, the program being executed by a processor to implement the method of any one of claims 1-12.

15. A computer program product comprising computer instructions, the computer instructions instructing a computing device to perform operations corresponding to the method of any one of claims 1-12.

Images