Chart display method and device based on artificial intelligence model, electronic equipment and computer program product

Abstract

The invention provides a chart display method and device based on an artificial intelligence model, electronic equipment and a computer program, and is suitable for the technical field of artificial intelligence, and the method comprises the steps: inputting to-be-processed information to the artificial intelligence model, generating target information through the artificial intelligence model, and generating a target chart on a front-end interface of an application of the artificial intelligence model based on the target information, wherein the target chart comprises chart data which is related to the target information and has a man-machine interaction function. When the large language model outputs the target information, the target information can be visually presented in the form of the chart, so that a user can read and understand data more visually and clearly, the user can interact with the chart, and the convenience and efficiency of data interpretation are improved.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and in particular, relates to a chart display method, device, electronic device and computer program product based on an artificial intelligence model. Background Art

[0002] With the advent of Chat Generative Pre-trained Transformer (ChatGPT), AI model technology has developed rapidly in the past two years, and various models have emerged. However, the application of most AI models is still mainly in the form of conversational chat. The front end usually uses Markdown format to display the output of AI models, and improves the response speed through streaming output technology to reduce user waiting time.

[0003] Currently, in some general or vertical field applications, users hope that artificial intelligence models can have a "chart display function" when using them. However, most artificial intelligence model applications in the existing technology do not yet have the ability to generate charts. Summary of the invention

[0004] The embodiments of the present application provide a chart display method, device, electronic device and computer program based on an artificial intelligence model, which can solve the technical problem in the prior art that the application of artificial intelligence models cannot generate charts with human-computer interaction functions.

[0005] In a first aspect, an embodiment of the present application provides a method for displaying a chart based on an artificial intelligence model, the method comprising:

[0006] Inputting the information to be processed into the artificial intelligence model so that the artificial intelligence model generates target information;

[0007] A target chart is generated on the front-end interface of the application of the artificial intelligence model based on the target information, and the target chart includes chart data related to the target information and having a human-computer interaction function.

[0008] In one example, generating a target chart on a front-end interface of an application of the artificial intelligence model based on the target information includes:

[0009] Parse the target information to obtain tabular data, associate the tabular data with a target chart library to obtain chart data, and display a target chart containing the chart data in the front-end interface of the application of the artificial intelligence model, wherein the chart data of the target chart has a human-computer interaction function; wherein the target chart library is an open source chart library that is pre-configured with the front-end interface of the application of the artificial intelligence model.

[0010] In one example, parsing the target information to obtain table data, associating the table data with a target chart library to obtain chart data, and displaying a target chart containing the chart data in a front-end interface of an application of the artificial intelligence model includes:

[0011] A1: Determine whether the format of the target information is a table type;

[0012] A2: when the format of the target information is a table type, determine the table content in the markdown format from the target information, and save the table content in the markdown format to the first storage area;

[0013] A3: Use special characters of code blocks in markdown format to wrap the table content in the first storage area, and add the wrapped table content to the output content;

[0014] A4: Use a specific class name to match the content in the output content, find the code block element corresponding to the special character of the code block, and extract the corresponding target table content in markdown format from the code block element;

[0015] A5: A canvas element of an output box of a front-end interface of an application of the artificial intelligence model, and the code block element is replaced by the canvas element;

[0016] A6: using a specific library to parse the target table content in the markdown format to obtain table data, and saving the table data to the second storage area;

[0017] A7: Fill the table data in the second storage area into a chart of a corresponding type in a target chart library to obtain chart data associated with a chart of a corresponding type in the target chart library, add the chart data to the canvas element, and display the chart data by the canvas element. The chart data of the target chart has a human-computer interaction function.

[0018] In one example, the method further includes:

[0019] In response to a user triggering operation on the chart content of a target chart displayed in the front-end interface of the application of the artificial intelligence model, corresponding descriptive information is displayed in the area position of the chart content triggered by the user.

[0020] In one example, in response to a data filtering instruction, the chart content in the front-end interface of the application of the artificial intelligence model is filtered according to the data filtering instruction, and the filtered chart data is displayed.

[0021] In one example, the method further includes:

[0022] In response to the adjustment instruction, the chart format of the chart data in the front-end interface of the application of the artificial intelligence model is adjusted and displayed according to the adjustment instruction.

[0023] In one example, the method includes:

[0024] Obtain the information to be processed input by the user in the front-end interface of the artificial intelligence model application, and input the information to be processed into the artificial intelligence model.

[0025] In a second aspect, the present application also proposes a chart display device based on an artificial intelligence model, comprising:

[0026] An input module, used to input the information to be processed into the artificial intelligence model so that the artificial intelligence model generates target information;

[0027] A generation module is used to generate a target chart on the front-end interface of the application of the artificial intelligence model based on the target information, and the target chart includes chart data related to the target information and having human-computer interaction function.

[0028] In a third aspect, the present application further proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect above when executing the computer program.

[0029] In a fourth aspect, the present application further proposes a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method described in the first aspect above is implemented.

[0030] The beneficial effects of the present application are as follows: the present application inputs the information to be processed into the artificial intelligence model, the artificial intelligence model generates the target information, and generates the target chart based on the target information in the front-end interface of the application of the artificial intelligence model, wherein the target chart includes chart data related to the target information and having a human-computer interaction function. When the large language model is output, the present invention can intuitively present the tabular data in the form of a chart, making it more intuitive and clear for users to read and understand the data, and users can interact with the chart, which improves the convenience and efficiency of data interpretation. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0032] Figure 1 A flowchart of an embodiment of a diagram display method based on an artificial intelligence model provided by the present application;

[0033] Figure 2 A flowchart of another embodiment of a diagram display method based on an artificial intelligence model provided by the present application;

[0034] Figure 3 A schematic diagram of an embodiment of generating a target chart in the front-end interface of the application of the artificial intelligence model provided in the present application;

[0035] Figure 4 A schematic diagram of an embodiment of the human-computer interaction function of the target chart provided by the present application;

[0036] Figure 5 A schematic diagram of another embodiment of the human-computer interaction function of the target chart provided by the present application;

[0037] Figure 6 A schematic diagram of the structure of an embodiment of an electronic device for executing a chart display method based on an artificial intelligence model provided by the present application;

[0038] Figure 7 A structural block diagram of a chart display device based on an artificial intelligence model provided in this application. DETAILED DESCRIPTION

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0040] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0041] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0042] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0043] In the description of the embodiments of the present application, the term "plurality" refers to more than two (including two), unless otherwise clearly and specifically defined.

[0044] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0045] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0046] The applicant of the present invention has noticed that with the advent of ChatGPT, artificial intelligence model technology has developed rapidly in the past two years, and various models have emerged. However, at present, the application of most artificial intelligence models is still mainly carried out in the form of conversational chat. The front end usually uses Markdown format to display the output of the artificial intelligence model, and improves the response speed through streaming output technology to reduce the user's waiting time.

[0047] In some general or vertical applications of the prior art, the output of the AI ​​model sometimes involves tables to display relevant data. However, tables are less intuitive than charts, which can more intuitively show the differences and changing trends between data.

[0048] Most AI model applications in existing technologies do not yet have the ability to generate charts. Even if they can generate charts, they are often presented in the form of pictures through the "text-based chart" method. The chart generation speed is slow and cannot interact with users.

[0049] Embodiment 1

[0050] In order to solve the above-mentioned technical problems, this application provides a chart display method based on an artificial intelligence model, please refer to Figure 1 The chart display method in the embodiment of the present application can be applied to the application programs (Application, APP) of artificial intelligence models in various vertical fields, including at least education and training application APP, marketing APP, medical health APP, scientific research APP and other application programs. The specific method includes:

[0051] Step S10, inputting the information to be processed into the artificial intelligence model so that the artificial intelligence model generates target information.

[0052] In a specific implementation, when a user uses an APP based on an artificial intelligence model, the user can input the information to be processed in the front-end interface of the artificial intelligence model APP, input the information to be processed into the artificial intelligence model, and then generate the target information by the artificial intelligence model. Among them, the information to be processed may at least include a text description information of the user (such as a question-like text information), or it may be a voice message, and the artificial intelligence model generates a target information for answering the information to be processed. In this process, if the user chooses to display the target information generated by the artificial intelligence model in the form of a chart, the following step S20 is executed.

[0053] Step S20, generating a target chart on the front-end interface of the application of the artificial intelligence model based on the target information, wherein the target chart includes chart data related to the target information and having a human-computer interaction function.

[0054] It is understandable that the application of the artificial intelligence model itself does not have the ability to generate functional charts, and some artificial intelligence models can output tables, but the intuitiveness of tables is poor compared to charts. In specific implementations, the embodiments of the present application can use the open source chart library (such as chart.js) pre-configured in the front-end interface of the artificial intelligence model application to assist the artificial intelligence model in realizing the function of chart display, including:

[0055] The front end receives the target information from the back end, and obtains the table data by parsing the target information (the table data can be displayed on the front end interface or not. Figure 3The table data is an example effect diagram displayed on the front-end interface), the table data is associated with a target chart library (such as chart.js) pre-configured on the front-end interface of the application of the artificial intelligence model to obtain chart data, and a target chart containing the chart data is displayed in the front-end interface of the application of the artificial intelligence model through some specific processing methods, so that the chart data of the target chart has a human-computer interaction function, which may specifically include the following steps A1 to A7:

[0056] A1: Determine whether the format of the target information is a table type, if it is a table type, execute step A2;

[0057] A2: determining table content in markdown format from the target information, and saving the table content in markdown format to a first storage area;

[0058] A3: Use special characters of code blocks in markdown format to wrap the table content in the first storage area, and add the wrapped table content to the output content;

[0059] A4: After receiving the output end signal, use the specific class name to match the content in the output content, find the code block element corresponding to the special character of the code block, and extract the corresponding target table content in markdown format from the code block element;

[0060] A5: A canvas element of an output box of a front-end interface of an application of the artificial intelligence model, and the code block element is replaced by the canvas element;

[0061] A6: Use a specific library (such as a markdown parsing library) to parse the target table content in the markdown format to obtain table data, and save the table data to the second storage area;

[0062] A7: Fill the table data in the second storage area into a chart of a corresponding type in a target chart library to obtain chart data associated with the chart of a corresponding type in the target chart library, and add the chart data to the canvas element so that the canvas element displays the chart data, and the chart data of the target chart has a human-computer interaction function.

[0063] The method of the embodiment of the present application can be directly integrated into the application of artificial intelligence models, which can be large language models or intelligent assistants, so that these artificial intelligence model apps can not only generate text and tables, but also display complex data in the form of charts. When generating tables, the tabular data generated by the large language model can be displayed in the form of charts, and users can interact with the charts. Users can generate charts in different formats through simple voice or text commands to better understand the data.

[0064] Embodiment 2

[0065] It is understandable that compared with the prior art, the present invention can intuitively present the target information generated by the artificial intelligence model in the form of a chart when the large language model is output, so that users can read and understand the data more intuitively and clearly. Especially when facing multiple sets of data, users can flexibly change the chart format through interaction, so as to more conveniently analyze the trend changes between different data. The methods related to the human-computer interaction function at least include:

[0066] Interaction method one: responding to a user's triggering operation on the chart content of a target chart displayed in the front-end interface of the application of the artificial intelligence model, and displaying corresponding description information in the area position of the chart content triggered by the user.

[0067] It is understandable that if there are multiple data in the chart, the user can use the mouse to view the data information, and then change the display effect of the data by clicking the legend, which can help the user to conduct a deeper analysis and interpretation of the data. Figure 3 When the user clicks on the "Water Supply" chart in the chart displayed in the front-end interface, the corresponding text description information will be displayed in the area of ​​the "Water Supply" chart after being triggered.

[0068] Interaction mode two: respond to data filtering instructions, filter the chart content in the front-end interface of the application of the artificial intelligence model according to the data filtering instructions, and display the filtered chart data.

[0069] It is understandable that through chart visualization, users can quickly capture data trends, compare different data sets, and adjust chart formats through interactive functions to view data changes from different perspectives, thereby improving the accuracy of data analysis and decision support capabilities. This integration method not only makes the large language model in vertical fields more intelligent, but also enhances the user's interactive experience with data, making the presentation and understanding of complex data more intuitive and efficient. Figure 4 As shown, the user operates the "water supply" chart content in the chart displayed in the front-end interface in a certain preset way to realize the filtering function of the chart content. Figure 4If you remove the "Water Supply" chart content option from the chart, the chart data below will change accordingly, that is, the chart data related to "Water Supply" will be removed from the chart, and the chart data after removing the "Water Supply" chart content will be displayed.

[0070] Interaction mode three: responding to adjustment instructions, adjusting and displaying the chart format of the chart data in the front-end interface of the application of the artificial intelligence model according to the adjustment instructions.

[0071] It is understandable that the embodiments of the present application can also be applied to reporting and briefing generation scenarios in daily work. Through the artificial intelligence model, users can input raw data into the system and automatically generate concise and easy-to-understand charts to present the report content in an intuitive way. The system can adjust the chart format according to user needs, display the core trends and key comparisons of the data, so that leaders and colleagues can quickly understand the key information in the report. This automatically generated chart not only improves reporting efficiency, but also enhances the visualization of information, making the cumbersome data analysis process simple and efficient, and is suitable for daily work scenarios such as business meetings, project progress reports, and financial audits.

[0072] Embodiment 3

[0073] See also Figure 6 , Figure 6 A schematic diagram of the structure of an embodiment of an electronic device for executing a chart display method based on an artificial intelligence model provided in the present application is shown in FIG. Figure 6 As shown, the electronic device of this embodiment includes: at least one processor 10, a memory 11, and a computer program 12 stored in the memory 11 and executable on the at least one processor 10. When the processor 10 executes the computer program 12, the steps in the embodiment of the chart display method based on the artificial intelligence model of the present application are implemented.

[0074] The electronic device may be a computing device such as a desktop computer, notebook, smart phone, PDA, etc. loaded with an application program of an artificial intelligence model. The APP application of the artificial intelligence model includes at least education and training application APP, marketing APP, medical health APP, scientific research APP and other application programs.

[0075] Figure 6 The electronic device shown may include, but is not limited to, a processor 10 and a memory 11. Those skilled in the art will appreciate that Figure 5 These are merely examples of electronic devices and do not constitute a limitation on the electronic devices. The electronic devices may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, the electronic devices may also include input and output devices, network access devices, etc.

[0076] The processor 10 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0077] In some embodiments, the memory 11 may be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device. In other embodiments, the memory 11 may also be an external storage device of the computer device 1, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 may also include both an internal storage unit of the electronic device and an external storage device. The memory 11 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 11 may also be used to temporarily store data that has been output or is to be output.

[0078] Further, in one embodiment, if Figure 7 As shown, the present invention also provides a chart display device based on an artificial intelligence model, comprising:

[0079] An input module 10, used to input the information to be processed into the artificial intelligence model so that the artificial intelligence model generates target information;

[0080] The generation module 20 is used to generate a target chart on the front-end interface of the application of the artificial intelligence model based on the target information, and the target chart includes chart data related to the target information and having a human-computer interaction function.

[0081] It should be noted that the chart display device based on the artificial intelligence model can be understood as a virtual device, which can be loaded into the electronic device of the aforementioned embodiment. The electronic device calls the chart display based on the artificial intelligence model through the processor, and then runs the specific implementation plan in the above-mentioned chart display method embodiment based on the artificial intelligence model.

[0082] Since the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application, their specific functions and technical effects can be found in the method embodiment section.

[0083] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0084] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0085] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0086] In the above embodiments, 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.

[0087] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A chart display method based on an artificial intelligence model, characterized in that: The method comprises: Inputting the information to be processed into the artificial intelligence model so that the artificial intelligence model generates target information; A target chart is generated on the front-end interface of the application of the artificial intelligence model based on the target information, and the target chart includes chart data related to the target information and having a human-computer interaction function.

2. The method according to claim 1, characterized in that The generating a target chart on the front-end interface of the application of the artificial intelligence model based on the target information includes: Parse the target information to obtain tabular data, associate the tabular data with a target chart library to obtain chart data, and display a target chart containing the chart data in the front-end interface of the application of the artificial intelligence model, wherein the chart data of the target chart has a human-computer interaction function; wherein the target chart library is an open source chart library that is pre-configured with the front-end interface of the application of the artificial intelligence model.

3. The method according to claim 2, characterized in that The step of parsing the target information to obtain table data, associating the table data with a target chart library to obtain chart data, and displaying a target chart containing the chart data in a front-end interface of an application of the artificial intelligence model includes: A1: Determine whether the format of the target information is a table type; A2: when the format of the target information is a table type, determine the table content in the markdown format from the target information, and save the table content in the markdown format to the first storage area; A3: Use special characters of code blocks in markdown format to wrap the table content in the first storage area, and add the wrapped table content to the output content; A4: Use a specific class name to match the content in the output content, find the code block element corresponding to the special character of the code block, and extract the corresponding target table content in markdown format from the code block element; A5: Create a canvas element for the output box of the front-end interface of the application of the artificial intelligence model, and replace the code block element with the canvas element; A6: using a specific library to parse the target table content in the markdown format to obtain table data, and saving the table data to the second storage area; A7: Fill the table data in the second storage area into a chart of a corresponding type in a target chart library to obtain chart data associated with a chart of a corresponding type in the target chart library, add the chart data to the canvas element, and display the chart data by the canvas element. The chart data of the target chart has a human-computer interaction function.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: In response to a user triggering operation on the chart content of a target chart displayed in the front-end interface of the application of the artificial intelligence model, corresponding descriptive information is displayed in the area position of the chart content triggered by the user.

5. The method according to any one of claims 1 to 3, characterized in that: In response to the data filtering instruction, the chart content in the front-end interface of the application of the artificial intelligence model is filtered according to the data filtering instruction, and the filtered chart data is displayed.

6. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: In response to the adjustment instruction, the chart format of the chart data in the front-end interface of the application of the artificial intelligence model is adjusted and displayed according to the adjustment instruction.

7. The method according to any one of claims 1 to 3, characterized in that: The method comprises: Obtain the information to be processed input by the user in the front-end interface of the artificial intelligence model application, and input the information to be processed into the artificial intelligence model.

8. A chart display device based on an artificial intelligence model, characterized in that: include: An input module, used to input the information to be processed into the artificial intelligence model so that the artificial intelligence model generates target information; A generation module is used to generate a target chart on the front-end interface of the application of the artificial intelligence model based on the target information, and the target chart includes chart data related to the target information and having human-computer interaction function.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that The method comprises a computer program, which implements the steps of the method according to any one of claims 1 to 7 when the computer program is executed by a processor.

Images