Intelligent report generation system and method for business intelligent platform

Abstract

The invention provides an intelligent report generation system and method for a business intelligent platform, and the system comprises a report title module which is used for extracting an intelligent assistant name or an instrument panel name in a data source to generate a report title; the report content module is used for extracting report components in the data source and chapter names corresponding to the report components to generate report content; the intelligent analysis module is used for selecting a large model to be subjected to intelligent analysis from the integrated large models, configuring cue words for the selected large model, and returning an analysis result according to the report content and the cue words; and the report editing module is used for carrying out online editing on the report title, the report content and the analysis result based on an integrated rich text editor to generate a final intelligent report. According to the system and the method, the problem of insufficient support for an intelligent report online editing function in similar products is solved, report analysis is generated by means of a large model, and the report editing efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent report generation technology, and more specifically, to an intelligent report generation system and method for a business intelligence platform. Background Technology

[0002] Business Intelligence (BI) is the process of collecting, managing, and analyzing enterprise information. It involves extracting, transforming, and storing business data, and then showcasing and mining its potential value through visualization and data analysis techniques. A complete BI system typically includes data processing, data warehouse modeling, data visualization, and analysis. The tools and systems involved include ETL, data warehousing, data visualization, and data analysis. Through BI, business data can be standardized. During ETL, data from different business systems is collected and integrated into a data warehouse. In data visualization systems, business personnel and managers can view data in the form of reports (tables, charts) to quickly and intuitively grasp the business operation status. Data analysts can also perform data mining and analysis through more professional programming environments, providing a basis for business personnel and managers to make enterprise decisions.

[0003] Intelligent BI is a practical application of business intelligence (BI) and artificial intelligence (AI). Currently, the application of AI in BI mainly focuses on intelligent question answering, which involves endowing BI systems with natural language understanding capabilities through large models. Users can send query commands to the intelligent BI system in natural language, and the intelligent BI system uses large models to convert the natural language into SQL, then presents the queried data to the user in the form of visual tables and charts. Most existing intelligent BI products are based on this model, focusing on solving problems such as the accuracy of natural language to SQL conversion and the diversity of report presentation. However, users of intelligent BI often also have the need to edit and analyze reports. For the data returned by the intelligent BI, it is necessary to manually copy it into Word documents, and for tables and charts, screenshots need to be taken one by one, which is inconvenient. Summary of the Invention

[0004] To address the technical problem that existing technologies using intelligent BI cannot meet the needs of users to edit and analyze reports online, this invention provides an intelligent report generation system and method for business intelligence platforms.

[0005] According to one aspect of the present invention, an intelligent report generation system for a business intelligence platform is provided, the system comprising:

[0006] The report title module is used to extract the smart assistant name or dashboard name from the data source to generate the report title in response to the smart report generation request;

[0007] The report content module is used to extract report components from the data source and the corresponding chapter names of the report components to generate report content;

[0008] The intelligent analysis module is used to respond to the analysis request for intelligent analysis of the report content, select the large model to be intelligently analyzed from the integrated large models, configure prompt words for the selected large model, and return the analysis results based on the report content and prompt words;

[0009] The report editing module is used to edit the report title, report content and analysis results online based on the integrated rich text editor, and generate the final intelligent report.

[0010] According to another aspect of the present invention, the present invention provides a method for generating intelligent reports for a business intelligence platform, the method comprising:

[0011] In response to a smart report generation request, extract the smart assistant name or dashboard name from the data source to generate the report title;

[0012] Extract report components from the data source and the corresponding chapter names of the report components to generate report content;

[0013] In response to an analysis request to perform intelligent analysis on the report content, a large model to be intelligently analyzed is selected from the integrated large models, prompt words are configured for the selected large model, and analysis results are returned based on the report content and prompt words;

[0014] Based on the integrated rich text editor, the report title, report content, and analysis results can be edited online to generate the final intelligent report.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, the storage medium storing a computer program that, when executed by a processor, implements the methods described in any of the above aspects of the present invention.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method described in any of the preceding aspects of the present invention.

[0017] The present invention discloses an intelligent report generation system and method for a business intelligence platform. The system includes a report title module, used to extract the name of the intelligent assistant or dashboard from the data source to generate a report title in response to an intelligent report generation request; a report content module, used to extract report components from the data source and the corresponding chapter names of the report components to generate report content; an intelligent analysis module, used to select a large model from an integrated large model for intelligent analysis in response to an analysis request to perform intelligent analysis on the report content, configure prompts for the selected large model, and return analysis results based on the report content and prompts; and a report editing module, used to edit the report title, report content, and analysis results online using an integrated rich text editor to generate the final intelligent report. The system and method address the shortcomings of similar products in supporting online intelligent report editing functions and improve report editing efficiency by leveraging large models to generate report analysis. Attached Figure Description

[0018] Exemplary embodiments of the present invention can be more fully understood by referring to the following figures:

[0019] Figure 1 This is a schematic diagram of the structure of an intelligent report generation system for a business intelligence platform according to a preferred embodiment of the present invention;

[0020] Figure 2 This is a schematic diagram of a report editing module according to a preferred embodiment of the present invention;

[0021] Figure 3 A flowchart of a method for generating intelligent reports for a business intelligence platform according to a preferred embodiment of the present invention;

[0022] Figure 4 This is a schematic diagram of the structure of an electronic device according to a preferred embodiment of the present invention. Detailed Implementation

[0023] Exemplary embodiments of the invention will now be described with reference to the accompanying drawings. However, the invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to fully and completely disclose the invention and to fully convey its scope to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the drawings is not intended to limit the invention. In the drawings, the same units / elements are referred to by the same reference numerals.

[0024] Unless otherwise stated, the terms used herein (including technical terms) have their common meaning as understood by one of ordinary skill in the art. Furthermore, it is understood that terms defined in commonly used dictionaries should be understood to have a meaning consistent with the context of their relevant field, and not to be interpreted as having an idealized or overly formal meaning.

[0025] Exemplary System

[0026] Figure 1 This is a schematic diagram of the structure of an intelligent report generation system for a business intelligence platform according to a preferred embodiment of the present invention. Figure 1 As shown, the intelligent report generation system 100 for a business intelligence platform according to this preferred embodiment includes:

[0027] The report title module 101 is used to extract the smart assistant name or dashboard name from the data source in response to the smart report generation request to generate the report title.

[0028] Preferably, the system further includes a data source, wherein the data source is an intelligent problem module or a dashboard module, specifically:

[0029] The intelligent question-and-answer module includes an intelligent assistant list and a conversation window, which is used to switch between intelligent assistants in the intelligent assistant list to conduct topic conversations and generate conversation records in the conversation window. Different intelligent assistants are bound to different large models, and the response information returned by the intelligent assistants in the conversation records includes at least one report component.

[0030] The dashboard module includes a dashboard list and a display window, used to switch dashboards in the dashboard list to display at least one report component corresponding to the switched dashboard in the display window.

[0031] In this preferred embodiment, the conversation window of the intelligent question-and-answer module can display the current or historical conversation records. Each reply returned by the large model contains a report component, which can display tables or charts. Different display methods can be switched according to the characteristics of the report data, such as the number of indicators, the number of grouping fields, and the number of data entries. Below each conversation message is an "Import Report" button. Clicking "Import Report" triggers an intelligent report generation request, which pops up a report configuration page. Users can enter the chapter name corresponding to the current report (defaulting to the user's question for that report) and select the target report to import. If no target report is selected, a new report is generated, named as the currently used intelligent assistant name + "Intelligent Report". Below the conversation window are a dialogue input box and an intelligent report generation button. Clicking the "Generate Report" button at the bottom of the page generates a report for all reports in the current conversation. Users can also choose to import a target report or generate a new report.

[0032] In this preferred embodiment, the dashboard display window contains multiple report components. Each report component has an "Import Report" button on its right. Clicking this button will bring up a report selection page; otherwise, a new report will be created. A "Report Generation" button is located in the upper right corner of the dashboard display window. Clicking this button triggers an intelligent report generation request, which can generate reports for all reports in the current dashboard. Again, users can choose to import a target report or generate a new report.

[0033] It should also be noted that in traditional BI, in addition to dashboards, there are also data screens for displaying report components. This implementation uses dashboards for explanation and does not constitute a limitation on other forms of displaying report components in traditional BI.

[0034] The report content module 102 is used to extract report components from the data source and the chapter names corresponding to the report components to generate report content;

[0035] Preferably, the report content module 102 extracts report components from the data source and the chapter names corresponding to the report components to generate report content, including:

[0036] Call the report rendering submodule to load each report individually;

[0037] The scheduled task module periodically checks whether the data extraction request and rendering process have ended.

[0038] After rendering is complete, generate chapter names for the report component. If the data source is the intelligent question-and-answer module, use the question in the topic dialogue corresponding to the report component as the chapter name. If the data source is the dashboard module, use the title of the report component as the chapter name.

[0039] Based on the type of the report component, the corresponding report content is generated using a preset generation method.

[0040] Preferably, the report content module generates corresponding report content according to the type of the report component using a preset generation method, including:

[0041] When the report component is of type table, the first tag code block is dynamically generated based on the table data;

[0042] When the report component is of type chart, the screenshot module is called to take a screenshot of the report and encode it, generating a second tag code block;

[0043] Report content is generated based on the first tag code block or the second tag code block, wherein the first tag code block and the second tag code block are respectively added with attribute fields reflecting the custom attributes of the first tag and the second tag, and the attribute fields are used to store the report component ID and the report component data.

[0044] In this preferred embodiment, when generating a smart report, a report title is generated based on the name of the smart dialogue assistant or the name of the dashboard / data screen; each report is loaded separately by calling the report rendering module, and the report rendering module is controlled by CSS z-index to make it invisible on the page; the scheduled task module periodically checks whether the data request and rendering process have ended; after rendering is completed, a chapter name is generated for the current report. If the source is a smart dialogue, the chapter name is the question asked by the user corresponding to the current report; if the source is a dashboard / data screen, the chapter name is the title of the report component; different methods are used to insert the report according to the report type. If it is a table, an HTML table tag code block is dynamically generated based on the table data; if it is a chart, the screenshot module is called to take a screenshot of the report, convert it to base64 encoding, and generate an HTML img tag; the table tag and img tag are given custom attributes data-report-id and data-report-data to store the report ID and report data, respectively.

[0045] The intelligent analysis module 103 is used to respond to an analysis request to perform intelligent analysis on the report content, select a large model to be intelligently analyzed from the integrated large models, configure prompt words for the selected large model, and return the analysis results based on the report content and prompt words.

[0046] The report editing module 104 is used to edit the report title, report content and analysis results online based on the integrated rich text editor, and generate the final intelligent report.

[0047] In this preferred embodiment, by integrating a rich text editor, online text editing and report format adjustment are supported, avoiding repetitive operations such as screenshotting and copying and pasting, and improving the efficiency of users in writing analysis reports.

[0048] Preferably, the system further includes an intelligent update module, which is used to traverse the attribute fields of the first tag and the second tag in the generated final intelligent report, load the report components corresponding to the attribute fields, query the latest data, and regenerate the first tag code block and the second tag code block to update the report content.

[0049] Figure 2 This is a schematic diagram of a report editing module according to a preferred embodiment of the present invention. Figure 2 As shown, the report editing module has save, share, update, and print buttons at the top. Clicking the corresponding button will trigger the corresponding operation. The middle toolbar integrates a rich text editor for online editing of the report in the report editing window on the lower right, while the window on the lower left is used to display the report's table of contents.

[0050] In this preferred embodiment, such as Figure 2 As shown, clicking the update button triggers a report update. This process iterates through all table and img tags in the report, checks the data-report-id attribute, and if the attribute exists, loads the corresponding report component, queries the latest data, and regenerates the table or img tag code block. Alternatively, an update can be performed on a single report. Clicking on a report will bring up the corresponding report component, which is interactive. Users can drill down on the data within the report component and take a new screenshot.

[0051] Furthermore, clicking the "Intelligent Analysis" button triggers a request for intelligent analysis of the report content, which then pops up the analysis configuration page. Users can switch between different large models, configure analysis requirements (hints), and select saved hints. After configuration, the large model returns analysis results based on the report content and analysis requirements. The front-end primarily communicates with the business intelligence platform's back-end server via the SSE (Server-Sent Events) protocol. The back-end acts as an intermediary, forwarding communication data between the front-end and the large model, mainly using the Flux interface for responsive data stream processing. The front-end uses a markdown-html conversion module to convert the markdown returned by the large model into HTML, and adjusts the HTML according to the rich text editor's requirements for the input content, such as handling nested lists and adding closing tags in real time.

[0052] By integrating a large model into the report editing module, it can read report data and other text content from reports and automatically generate summary analyses; it can identify and correct formatting errors in the generated content through hard coding; it supports prompt word templates, which can be edited and saved for convenient reuse.

[0053] In summary, this preferred implementation addresses the issue that existing products, when integrating large models, primarily focus on returning report data to users for visualization, with most unable to generate analysis reports. A few products can generate analysis reports, but only for single-question queries within intelligent BI, lacking support for dashboards / data screens and typically not allowing online editing. This solution introduces a rich text editor and large models into the business intelligence platform. The rich text editor provides online report editing capabilities, supports question-and-answer dialogues, and allows importing reports from dashboards / data screens, reducing the need for manual report editing through screenshots and copy-pasting, thus simplifying the workflow. It also supports report data updates, facilitating regularly scheduled report writing tasks. Furthermore, the large model summarizes and analyzes the report data, providing insights and assisting users in writing analysis reports.

[0054] Exemplary methods

[0055] Figure 3This is a flowchart of a method for generating intelligent reports for a business intelligence platform according to a preferred embodiment of the present invention. Figure 3 As shown, the intelligent report generation method for a business intelligence platform described in this preferred embodiment begins at step 301.

[0056] In step 301, in response to the smart report generation request, the smart assistant name or dashboard name is extracted from the data source to generate the report title.

[0057] In step 302, the report components and the corresponding chapter names of the report components are extracted from the data source to generate report content.

[0058] In step 303, in response to the analysis request for intelligent analysis of the report content, a large model to be intelligently analyzed is selected from the integrated large models, prompt words are configured for the selected large model, and analysis results are returned based on the report content and prompt words.

[0059] In step 204, the report title, report content, and analysis results are edited online using an integrated rich text editor to generate the final intelligent report.

[0060] Preferably, in response to the intelligent report generation request, the intelligent assistant name or dashboard name is extracted from the data source to generate the report title, wherein the data source is the intelligent question module or dashboard module, specifically:

[0061] The intelligent question-and-answer module includes an intelligent assistant list and a conversation window, which is used to switch between intelligent assistants in the intelligent assistant list to conduct topic conversations and generate conversation records in the conversation window. Different intelligent assistants are bound to different large models, and the response information returned by the intelligent assistants in the conversation records includes at least one report component.

[0062] The dashboard module includes a dashboard list and a display window, used to switch dashboards in the dashboard list to display at least one report component corresponding to the switched dashboard in the display window.

[0063] Preferably, the step of extracting report components from the data source and generating report content from the corresponding chapter names of the report components includes:

[0064] Call the report rendering submodule to load each report individually;

[0065] The scheduled task module periodically checks whether the data extraction request and rendering process have ended.

[0066] After rendering is complete, generate chapter names for the report component. If the data source is the intelligent question-and-answer module, use the question in the topic dialogue corresponding to the report component as the chapter name. If the data source is the dashboard module, use the title of the report component as the chapter name.

[0067] Based on the type of the report component, the corresponding report content is generated using a preset generation method.

[0068] The intelligent report generation method for business intelligence platforms described in this preferred embodiment uses an intelligent report generation system to generate intelligent reports. The steps are the same, and the technical effects achieved are also the same, so they will not be repeated here.

[0069] Exemplary electronic devices

[0070] Figure 4 This is a schematic diagram of the structure of an electronic device according to a preferred embodiment of the present invention. Figure 4 As shown, the electronic device includes one or more processors 401 and memory 402.

[0071] The processor 401 may be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0072] Memory 402 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and processor 401 may execute the program instructions to implement the intelligent report generation method for a business intelligence platform and / or other desired functions as described in the various embodiments disclosed above. In one example, the electronic device may also include an input device 403 and an output device 404, these components being interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0073] In addition, the input device 403 may also include, for example, a keyboard, a mouse, etc.

[0074] The output device 404 can output various information to the outside. The output device 404 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0075] Of course, for the sake of simplicity, Figure 4 Only some of the components of the electronic device relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0076] Exemplary computer program products and computer-readable storage media

[0077] In addition to the methods and apparatus described above, embodiments of this disclosure may also be computer program products comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the intelligent report generation method for a business intelligence platform according to various embodiments of this disclosure as described in the "Exemplary Methods" section above.

[0078] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0079] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform the steps in the intelligent report generation method for a business intelligence platform according to various embodiments of this disclosure as described in the "Exemplary Methods" section above.

[0080] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0081] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0082] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0083] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0084] The apparatus and methods of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0085] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps are decomposable and / or recombinable. Such decomposition and / or recombination should be considered equivalent to the present disclosure. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0086] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. An intelligent report generation system for a business intelligence platform, characterized in that, The system includes: The report title module is used to extract the smart assistant name or dashboard name from the data source to generate the report title in response to the smart report generation request; The report content module is used to extract report components from the data source and the corresponding chapter names of the report components to generate report content; The intelligent analysis module is used to respond to the analysis request for intelligent analysis of the report content, select the large model to be intelligently analyzed from the integrated large models, configure prompt words for the selected large model, and return the analysis results based on the report content and prompt words; The report editing module is used to edit the report title, report content and analysis results online based on the integrated rich text editor, and generate the final intelligent report.

2. The system according to claim 1, characterized in that, The system also includes a data source, wherein the data source is an intelligent problem module or a dashboard module, specifically: The intelligent question-and-answer module includes an intelligent assistant list and a conversation window, which is used to switch between intelligent assistants in the intelligent assistant list to conduct topic conversations and generate conversation records in the conversation window. Different intelligent assistants are bound to different large models, and the response information returned by the intelligent assistants in the conversation records includes at least one report component. The dashboard module includes a dashboard list and a display window, used to switch dashboards in the dashboard list to display at least one report component corresponding to the switched dashboard in the display window.

3. The system according to claim 2, characterized in that, The report content module extracts report components from the data source and the corresponding chapter names of the report components to generate report content, including: Call the report rendering submodule to load each report individually; The scheduled task module periodically checks whether the data extraction request and rendering process have ended. After rendering is complete, generate chapter names for the report component. If the data source is the intelligent question-and-answer module, use the question in the topic dialogue corresponding to the report component as the chapter name. If the data source is the dashboard module, use the title of the report component as the chapter name. Based on the type of the report component, the corresponding report content is generated using a preset generation method.

4. The system according to claim 3, characterized in that, The report content module generates corresponding report content according to the type of the report component using a preset generation method, including: When the report component is of type table, the first tag code block is dynamically generated based on the table data; When the report component is of type chart, the screenshot module is called to take a screenshot of the report and encode it, generating a second tag code block; Report content is generated based on the first tag code block or the second tag code block, wherein the first tag code block and the second tag code block are respectively added with attribute fields reflecting the custom attributes of the first tag and the second tag, and the attribute fields are used to store the report component ID and the report component data.

5. The system according to claim 4, characterized in that, The system also includes an intelligent update module, which is used to traverse the attribute fields of the first and second tags in the generated final intelligent report, load the report components corresponding to the attribute fields, query the latest data, and regenerate the first and second tag code blocks to update the report content.

6. A method for generating intelligent reports for a business intelligence platform, characterized in that, The method includes: In response to a smart report generation request, extract the smart assistant name or dashboard name from the data source to generate the report title; Extract report components from the data source and the corresponding chapter names of the report components to generate report content; In response to an analysis request to perform intelligent analysis on the report content, a large model to be intelligently analyzed is selected from the integrated large models, prompt words are configured for the selected large model, and analysis results are returned based on the report content and prompt words; Based on the integrated rich text editor, the report title, report content, and analysis results can be edited online to generate the final intelligent report.

7. The method according to claim 6, characterized in that, In response to the intelligent report generation request, the intelligent assistant name or dashboard name is extracted from the data source to generate the report title, wherein the data source is the intelligent question module or dashboard module, specifically: The intelligent question-and-answer module includes an intelligent assistant list and a conversation window, which is used to switch between intelligent assistants in the intelligent assistant list to conduct topic conversations and generate conversation records in the conversation window. Different intelligent assistants are bound to different large models, and the response information returned by the intelligent assistants in the conversation records includes at least one report component. The dashboard module includes a dashboard list and a display window, used to switch dashboards in the dashboard list to display at least one report component corresponding to the switched dashboard in the display window.

8. The method according to claim 7, characterized in that, The step of extracting report components from the data source and generating report content based on the corresponding chapter names of the report components includes: Call the report rendering submodule to load each report individually; The scheduled task module periodically checks whether the data extraction request and rendering process have ended. After rendering is complete, generate chapter names for the report component. If the data source is the intelligent question-and-answer module, use the question in the topic dialogue corresponding to the report component as the chapter name. If the data source is the dashboard module, use the title of the report component as the chapter name. Based on the type of the report component, the corresponding report content is generated using a preset generation method.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 5 to 8.

10. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the steps of the method of any one of claims 5 to 8.

Images