Visual display method of natural language data, electronic equipment and storage medium

Abstract

The invention provides a visual display method of natural language data, electronic equipment and a storage medium, the visual display method of the natural language data comprises the following steps: in response to natural language dialogue information received by a rich text editor, analyzing the natural language dialogue information to obtain a display type and data description information; retrieving a preset database according to the data description information to obtain feedback data information; based on the display type, performing display preprocessing on the feedback data information to obtain display data conforming to the rich text editor display rule; and the rich text editor matches a preset display instruction according to the display type so as to generate rich text content based on the display data. According to the method, the programming capability is not required, a large amount of time and energy can be saved in data preprocessing, chart configuration and interactive design, the working efficiency and the working quality are improved, and the user experience is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method for visualizing natural language data, an electronic device, and a storage medium. Background Art

[0002] The field of visualization technology covers everything from simple static charts (such as Excel charts) to highly interactive and customized dynamic data visualization tools (such as D3.js, Chart.js, Plotly, etc.). In the traditional visualization technology steps, by selecting tools, select appropriate visualization tools or libraries according to project requirements, such as D3.js, Chart.js, Plotly or Highcharts, and then obtain the data to be displayed through API interfaces, database queries or file reading. Clean, transform and aggregate the acquired data to ensure the integrity and correctness of the data. Select the chart type (such as bar chart, line chart, etc.) according to the requirements, and configure the chart style and interaction method. In the image display stage, use the API of the selected tool to render the preprocessed data into a chart, and embed the chart into a web page or application for users to view and interact. If necessary, it is also necessary to check and adjust the chart display effect to ensure consistency on different devices and browsers, and optimize the chart performance to cope with large data volumes. Finally, deploy the generated chart to the production environment, update and maintain the data regularly, ensure that the data displayed in the chart is always up to date, and promptly fix possible problems to ensure stable operation of the chart.

[0003] During the research process of conceiving and forming this application, the applicant has found at least the following problems: traditional visualization technology requires users to have high programming skills and a deep understanding of the tool's API and event handling mechanism, and has a steep learning curve. A large amount of additional code needs to be written to process dynamic data and complex interactions, resulting in poor real-time performance, and the expansion and customization functions are complex and have high maintenance costs. Manual cleaning, conversion, and integration of external data sources are required, and the data preprocessing process is cumbersome. Users are often even required to write additional code to handle errors, and there is a lack of intuitive user feedback, error handling, and insufficient user prompts. In short, traditional visualization technology usually requires users to have high programming skills and spend a lot of time and energy on data preprocessing, chart configuration, and interaction design, resulting in a poor user experience. Summary of the invention

[0004] In order to alleviate the above problems, the present application provides a method for visualizing natural language data, an electronic device, and a storage medium. The method for visualizing natural language data includes: In response to the rich text editor receiving the natural language dialogue information, parsing the natural language dialogue information to obtain the display type and data description information; Searching a preset database according to the data description information to obtain feedback data information; Based on the display type, the feedback data information is subjected to display preprocessing to obtain display data that complies with the display rules of the rich text editor; The rich text editor matches preset presentation instructions according to the presentation type to generate rich text content based on the presentation data.

[0005] Optionally, in response to the rich text editor receiving the natural language dialogue information, the step of parsing the natural language dialogue information to obtain the display type and data description information includes: The rich text editor sends the natural language dialogue information to a preset large model, so that the preset large model parses the natural language dialogue information.

[0006] Optionally, the rich text editor is connected to the preset large model via an API interface to ensure accurate transmission of data and instructions.

[0007] Optionally, before the step of sending the natural language dialogue information to the preset macro model, the rich text editor includes: Set up the initial environment, configure model parameters and environment dependencies to ensure that the preset large model can understand the instruction system and data processing capabilities of the rich text editor.

[0008] Optionally, in response to the rich text editor receiving the natural language dialogue information, the step of parsing the natural language dialogue information to obtain the display type and data description information further includes: The display type and data description information are extracted through the preset prompt, and the data description information is sent to the backend for retrieval.

[0009] Optionally, in response to the rich text editor receiving the natural language dialogue information, the step of parsing the natural language dialogue information to obtain the display type and data description information further includes: The preset large model uses a ChatGPT language model to detect and correct erroneous instructions input by users, parse the input natural language instructions into specific operation instructions, parse and execute operations in real time, and provide instant feedback to simplify the operation process and improve the fluency and response speed of the interaction.

[0010] Optionally, the rich text editor includes a ProseMirror editor, and the step of performing display preprocessing on the feedback data information based on the display type to obtain display data that complies with the display rules of the rich text editor includes: The front end performs display preprocessing on the feedback data information according to the operation request to ensure that the display data complies with the display rules of the ProseMirror editor.

[0011] Optionally, the step of matching the preset presentation instruction according to the presentation type by the rich text editor to generate rich text content based on the presentation data includes: The ProseMirror editor receives the presentation data, matches the preset presentation instructions according to the presentation type, and generates different rich text contents corresponding to the presentation instructions through different instructions.

[0012] Optionally, after the step of searching a preset database according to the data description information to obtain feedback data information, the following steps are included: By expanding or customizing the instruction set through an open instruction parsing interface, the rich text editor supports a variety of data display and operation requirements, thereby increasing the types of data display and operation and enriching application scenarios.

[0013] The present application also provides an electronic device, including a processor and a storage medium; the storage medium is used to store a computer program; the processor is used to execute the computer program to implement the above-mentioned method for visual display of natural language data.

[0014] The present application also provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for visualizing natural language data as described above are implemented.

[0015] The visualization display method, electronic device and storage medium of natural language data provided by the present application are responsive to a rich text editor receiving natural language dialogue information, parsing the natural language dialogue information to obtain display type and data description information; searching a preset database according to the data description information to obtain feedback data information; based on the display type, pre-processing the feedback data information to obtain display data that conforms to the display rules of the rich text editor; the rich text editor matches the preset display instructions according to the display type to generate rich text content based on the display data. Without the need for programming skills, a lot of time and energy can be saved in data pre-processing, chart configuration and interactive design, improving work efficiency and work quality, and effectively improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor.

[0017] Figure 1 This is a flow chart of a method for visualizing natural language data according to an embodiment of the present application.

[0018] The realization of the purpose, functional features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings have shown clear embodiments of this application, which will be described in more detail later. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0019] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0020] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0021] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0022] First embodiment This application provides a method for visualizing natural language data. Figure 1This is a flow chart of a method for visualizing natural language data according to an embodiment of the present application.

[0023] like Figure 1 As shown, in one embodiment, the method for visualizing natural language data includes: S10: In response to the rich text editor receiving the natural language dialogue information, the natural language dialogue information is parsed to obtain the display type and data description information.

[0024] A rich text editor, Multi-function Text Editor, or MTE for short, is a text editor that can be embedded in a browser and is WYSIWYG. It provides editing functions similar to Microsoft Word, and is easily loved by users who cannot write HTML and need to set various text formats. Its application is becoming more and more widespread. Natural language generally refers to a language that evolves naturally with culture. For example, Chinese and English are examples of natural languages, and this usage can be seen in the term natural language processing. Natural language is the main tool for humans to communicate and think in conversations. Exemplarily, the user's natural language conversation information can be received through a human-computer interaction interface, or the natural language conversation information can be retrieved by actively crawling, and the display type and data description information can be extracted through a preset prompt.

[0025] S20: searching a preset database according to the data description information to obtain feedback data information.

[0026] Exemplarily, the data description information is used to describe the data characteristics of the information data in the natural language dialogue information, such as the number of fields in the statistical data, the number of statistical indicators, and the number of statistics and dimensions, etc., which are not limited here. According to the data description information, a relatively accurate search can be performed to feedback the search results required by the user.

[0027] S30: Based on the display type, the feedback data information is subjected to display preprocessing to obtain display data that complies with the display rules of the rich text editor.

[0028] Exemplarily, the display types configured based on the rules include announcement components, pop-up components, and area components, which can be displayed in the form of tables, pictures, texts, etc., but are not limited thereto.

[0029] S40: The rich text editor matches a preset presentation instruction according to the presentation type to generate rich text content based on the presentation data.

[0030] In this embodiment, in response to the rich text editor receiving natural language dialogue information, the natural language dialogue information is parsed to obtain the display type and data description information; a preset database is retrieved according to the data description information to obtain feedback data information; based on the display type, the feedback data information is pre-processed to obtain display data that conforms to the display rules of the rich text editor; the rich text editor matches the preset display instructions according to the display type to generate rich text content based on the display data. Users do not need to have programming skills, and can save a lot of time and energy in data pre-processing, chart configuration and interactive design, improve work efficiency and work quality, and effectively improve user experience.

[0031] Optionally, in response to the rich text editor receiving the natural language dialogue information, the step of parsing the natural language dialogue information to obtain the display type and data description information includes: The rich text editor sends the natural language dialogue information to a preset large model, so that the preset large model parses the natural language dialogue information.

[0032] A large model refers to a machine learning model with large-scale parameters and complex computational structures. These models are usually built with deep neural networks and have billions or even hundreds of billions of parameters. The purpose of designing a large model is to improve the expressiveness and predictive performance of the model and to be able to handle more complex tasks and data. Large models are widely used in various fields, including natural language processing, computer vision, speech recognition, and recommendation systems. Large models learn complex patterns and features by training massive data, have stronger generalization capabilities, and can make accurate predictions on unseen data. For example, ChatGPT's explanation of large models is more easy to understand and more human-like induction and thinking abilities. The large model is essentially a deep neural network model trained with massive data. Its huge data and parameter scale realizes the emergence of intelligence and shows human-like intelligence. By presetting a large model to parse natural language conversation information, it is possible to more accurately extract the display type requirements and data description information in natural language conversation information in a human-like way of understanding.

[0033] Optionally, the rich text editor is connected to the preset large model via an API interface to ensure accurate transmission of data and instructions.

[0034] In recent years, the scale of software has become increasingly large, and it is often necessary to divide complex systems into small components. The design of programming interfaces is very important. In the practice of programming, the design of programming interfaces must first make the responsibilities of the software system reasonably divided. Good interface design can reduce the interdependence of various parts of the system, improve the cohesion of the components, and reduce the degree of coupling between the components, thereby improving the maintainability and scalability of the system. Application Programming Interface (API) is a set of predefined functions that aims to provide applications and developers with the ability to access a set of routines based on certain software or hardware without having to access the source code or understand the details of the internal working mechanism.

[0035] Optionally, before the step of sending the natural language dialogue information to the preset macro model, the rich text editor includes: Set up the initial environment, configure model parameters and environment dependencies to ensure that the preset large model can understand the instruction system and data processing capabilities of the rich text editor.

[0036] The parameters of the big model are the core components of the deep learning model. They directly determine the model's representation learning of the input data and the final prediction or decision-making capabilities. The parameters of the big model are parameters built based on the neural network model. The neural network model has many layers, each layer has many neurons, and each layer needs to be connected. The parameters of the big model, such as weights and biases, are parameters that each neuron has. In general, the parameters of the big model are set when the network architecture is built, and the number of parameters generally does not change; but there are exceptions, such as the dynamic neural network 4 will dynamically adjust the number of parameters. Exemplarily, setting matching parameters for the preset big model and the rich text editor according to the interface type can enable the big model to accurately interact with the rich text editor.

[0037] Optionally, in response to the rich text editor receiving the natural language dialogue information, the step of parsing the natural language dialogue information to obtain the display type and data description information further includes: The display type and data description information are extracted through the preset prompt, and the data description information is sent to the backend for retrieval.

[0038] Actually, developing the part of a web application that is not visible to the user is called the web backend, which is the backend work. In simple terms, everything that is not visible on the screen of the application or website is the backend of the frontend. Such as: core business logic, database, etc. The backend is the "soul" of web applications. The backend affects all aspects of the web frontend. In addition to business logic, it also needs to consider security, stability, maintainability, scalability, and scaling issues. The backend includes server configuration, database management, and program writing and execution. Its purpose is to ensure that the frontend requests can obtain correct data and services.

[0039] Optionally, in response to the rich text editor receiving the natural language dialogue information, the step of parsing the natural language dialogue information to obtain the display type and data description information further includes: The preset large model uses a ChatGPT language model to detect and correct erroneous instructions input by users, parse the input natural language instructions into specific operation instructions, parse and execute operations in real time, and provide instant feedback to simplify the operation process and improve the fluency and response speed of the interaction.

[0040] For example, ChatGPT's explanation of the big model is more understandable and more human-like inductive and thinking abilities. The big model is essentially a deep neural network model trained with massive data. Its huge data and parameter scale enable the emergence of intelligence and demonstrate human-like intelligence. By presetting the big model to parse natural language conversation information, it is possible to more accurately extract the display type requirements and data description information in the natural language conversation information in a human-like way of understanding, and can parse and perform operations on natural language conversation information in real time, provide instant feedback, simplify the operation process, and improve the fluency and response speed of interaction.

[0041] Optionally, the rich text editor includes a ProseMirror editor, and the step of performing display preprocessing on the feedback data information based on the display type to obtain display data that complies with the display rules of the rich text editor includes: The front end performs display preprocessing on the feedback data information according to the operation request to ensure that the display data complies with the display rules of the ProseMirror editor.

[0042] ProseMirror Editor is a powerful JavaScript rich text editor library that provides powerful text editing capabilities and flexible extensibility. For example, the front end includes web design, website architecture, and web interaction implementation. Front-end developers need to ensure that the appearance of the web page conforms to the design and that user operations are as smooth as possible. They usually use languages ​​such as HTML, CSS, and JavaScript to build the part of the website that users can see and interact with. ProseMirror Editor can cooperate with the front-end page to display the required rich text.

[0043] Optionally, the step of matching the preset presentation instruction according to the presentation type by the rich text editor to generate rich text content based on the presentation data includes: The ProseMirror editor receives the presentation data, matches the preset presentation instructions according to the presentation type, and generates different rich text contents corresponding to the presentation instructions through different instructions.

[0044] Exemplarily, the ProseMirror editor receives preprocessed presentation data, matches preset presentation instructions according to presentation types, and generates rich text contents such as tables, images, and texts from the preprocessed presentation data through different instructions.

[0045] Optionally, after the step of searching a preset database according to the data description information to obtain feedback data information, the following steps are included: By expanding or customizing the instruction set through an open instruction parsing interface, the rich text editor supports a variety of data display and operation requirements, thereby increasing the types of data display and operation and enriching application scenarios.

[0046] The command parsing interface is mainly used to implement functions such as sending commands and waiting for responses. For example, through the open command parsing interface, a variety of data display and operations are supported. By extending the command set, a variety of data display and operation requirements can be supported, such as table insertion, style modification, content search, etc., with high flexibility and scalability to increase the types of data display and operations and enrich application scenarios.

[0047] In this embodiment, ChatGPT is used in natural language processing to generate and understand natural language and realize intelligent text generation and interaction.

[0048] In this embodiment, an API interface is developed in terms of API integration and design to achieve seamless connection and data exchange between ChatGPT and the ProseMirror editor.

[0049] In this embodiment, in terms of rich text editing and customization, ProseMirror is used to implement the rich text editing function and customize the interface to enhance user experience and visual effects.

[0050] In this embodiment, in terms of data preprocessing and optimization, user input and external data are preprocessed to improve the quality of generated text and the system response speed.

[0051] Second embodiment The present application also provides an electronic device, including a processor and a storage medium; the storage medium is used to store a computer program; the processor is used to execute the computer program to implement the above-mentioned method for visual display of natural language data.

[0052] In one embodiment, when implementing the above-mentioned method for visualizing natural language data, the electronic device connects the big model with the ProseMirror editor through an API to ensure that data and instructions can be transmitted between the two. The initial environment of the electronic device is set, and necessary dependencies and parameters are configured to ensure that the big model can understand the instruction system and data processing capabilities of the ProseMirror editor.

[0053] When the electronic device receives the user's natural language input, it uses the large model to parse the user's input, extracts the display type and data description information through the preset prompt, and sends it to the backend of the electronic device.

[0054] Receive the parsed content of the large model, retrieve the data required by the user according to the data description information, and return it to the front end of the electronic device. The front end pre-processes the data according to the operation request to ensure that the displayed data meets the display rules of the ProseMirror editor.

[0055] Finally, the electronic device receives the preprocessed display data through the ProseMirror editor, matches the preset display instructions according to the display type, and generates rich text content such as tables, pictures, and texts from the preprocessed display data through different instructions.

[0056] In this embodiment, the electronic device can intelligently parse and, using the powerful natural language processing capabilities of ChatGPT, parse the natural language instructions input by the user into specific operation instructions, greatly simplifying the user's operation process.

[0057] In this embodiment, the electronic device can automatically execute and automatically pass the parsed instructions to ProseMirror for execution, thereby realizing a fully automated process from instruction input to operation execution and reducing user intervention.

[0058] In this embodiment, the electronic device can integrate natural language processing and rich text editing, closely combining natural language processing technology with the rich text editor ProseMirror to provide an integrated solution, thereby enhancing the intelligence of the system and user experience.

[0059] In this embodiment, the electronic device can support multiple data displays and operations. By extending the instruction set, it can support multiple data display and operation requirements, such as table insertion, style modification, content search, etc. It has high flexibility and scalability to increase the types of data displays and operations and enrich application scenarios.

[0060] In this embodiment, the electronic device can provide real-time feedback. After the user inputs a natural language instruction, the system can parse and execute the operation in real time, provide instant feedback, and improve the smoothness and response speed of the interaction.

[0061] In this embodiment, the electronic device can be highly customizable, and the system can customize the instruction set and operation process according to the needs of different users to meet the needs of various specific scenarios.

[0062] In this embodiment, the electronic device is capable of error detection and correction. Using the language understanding ability of ChatGPT, the system can detect and correct erroneous instructions input by the user, providing a more intelligent and friendly user experience.

[0063] In this embodiment, the electronic device can provide prompts and suggestions. When the user inputs vague or unclear instructions, the system can provide prompts and suggestions to help the user improve the instructions and improve the accuracy and effectiveness of the operation.

[0064] In this embodiment, the electronic device can expand the instruction set. Through the open instruction parsing interface, the developer can expand and customize the instruction set according to specific needs to increase the functions and application scenarios of the system.

[0065] Third embodiment The present application also provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for visualizing natural language data as described above are implemented.

[0066] The visualization display method, electronic device and storage medium of natural language data provided by the present application, in response to the rich text editor receiving natural language dialogue information, parse the natural language dialogue information to obtain the display type and data description information; search the preset database according to the data description information to obtain feedback data information; based on the display type, perform display preprocessing on the feedback data information to obtain display data that conforms to the display rules of the rich text editor; the rich text editor matches the preset display instructions according to the display type to generate rich text content based on the display data. Without the need for programming skills, a lot of time and energy can be saved in data preprocessing, chart configuration and interactive design, which improves work efficiency and work quality and effectively improves user experience. Intelligent parsing uses ChatGPT's powerful natural language processing capabilities to parse the natural language instructions input by the user into specific operation instructions, greatly simplifying the user's operation process.

[0067] It should be noted that in the present application, step codes such as S10, S20, etc. are used for the purpose of expressing the corresponding content more clearly and concisely, and do not constitute a substantial limitation on the sequence. When implementing the step, those skilled in the art may execute S20 first and then S10, etc., but these should all be within the scope of protection of the present application.

[0068] In the embodiments of the system and storage medium provided in the present application, all technical features of any of the above-mentioned method embodiments may be included, and the expanded and explained contents of the specification are basically the same as those of the above-mentioned method embodiments, and will not be repeated here.

[0069] The embodiment of the present application further provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer executes the methods in the above various possible implementation modes.

[0070] An embodiment of the present application also provides a chip, including a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that a device equipped with the chip executes the methods in various possible implementation modes as described above.

[0071] It is understood that the above scenarios are only examples and do not constitute a limitation on the application scenarios of the technical solutions provided in the embodiments of the present application. The technical solutions of the present application can also be applied to other scenarios. For example, it is known to those skilled in the art that with the evolution of the system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0072] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0073] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs.

[0074] The units in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0075] In the present application, the same or similar terminology concepts, technical solutions and / or application scenario descriptions are generally described in detail only the first time they appear. When they appear again later, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of the present application, for the same or similar terminology concepts, technical solutions and / or application scenario descriptions that are not described in detail later, reference can be made to the previous related detailed descriptions.

[0076] In the present application, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0077] The various technical features of the technical solution of the present application can be arbitrarily combined. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present application.

[0078] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for visualizing natural language data, characterized in that: include: In response to the rich text editor receiving the natural language dialogue information, parsing the natural language dialogue information to obtain the display type and data description information; Searching a preset database according to the data description information to obtain feedback data information; Based on the display type, the feedback data information is subjected to display preprocessing to obtain display data that complies with the display rules of the rich text editor; The rich text editor matches preset presentation instructions according to the presentation type to generate rich text content based on the presentation data.

2. A method for visualizing natural language data according to claim 1, characterized in that: The method for visualizing natural language data further includes: The rich text editor sends the natural language dialogue information to a preset large model, so that the preset large model parses the natural language dialogue information; and / or, The rich text editor is connected to the preset large model through an API interface to ensure accurate transmission of data and instructions.

3. A method for visualizing natural language data according to claim 2, characterized in that: Before the step of sending the natural language dialogue information to the preset macro model, the rich text editor includes: Set up the initial environment, configure model parameters and environment dependencies to ensure that the preset large model can understand the instruction system and data processing capabilities of the rich text editor.

4. A method for visualizing natural language data according to claim 3, characterized in that: The step of parsing the natural language dialogue information to obtain the display type and data description information in response to the rich text editor receiving the natural language dialogue information also includes: The display type and data description information are extracted through the preset prompt, and the data description information is sent to the backend for retrieval.

5. A method for visualizing natural language data according to claim 4, characterized in that: In response to the rich text editor receiving the natural language dialogue information, the step of parsing the natural language dialogue information to obtain the display type and data description information further includes: The preset large model uses a ChatGPT language model to detect and correct erroneous instructions input by users, parse the input natural language instructions into specific operation instructions, parse and execute operations in real time, and provide instant feedback to simplify the operation process and improve the fluency and response speed of the interaction.

6. A method for visualizing natural language data according to claim 5, characterized in that: The rich text editor includes a ProseMirror editor, and the step of performing display preprocessing on the feedback data information based on the display type to obtain display data that complies with the display rules of the rich text editor includes: The front end performs display preprocessing on the feedback data information according to the operation request to ensure that the display data complies with the display rules of the ProseMirror editor.

7. A method for visualizing natural language data according to claim 6, characterized in that: The step of matching the preset display instruction according to the display type by the rich text editor to generate rich text content based on the display data includes: The ProseMirror editor receives the presentation data, matches the preset presentation instructions according to the presentation type, and generates different rich text contents corresponding to the presentation instructions through different instructions.

8. A method for visualizing natural language data according to any one of claims 1 to 7, characterized in that: After the step of searching a preset database according to the data description information to obtain feedback data information, the following steps are included: By expanding or customizing the instruction set through an open instruction parsing interface, the rich text editor supports a variety of data display and operation requirements, thereby increasing the types of data display and operation and enriching application scenarios.

9. An electronic device, characterized in that: It comprises a processor and a storage medium; the storage medium is used to store a computer program; the processor is used to execute the computer program to implement the method for visual display of natural language data as described in any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for visualizing natural language data as described in any one of claims 1 to 8.

Images