Form page information supplementing method and device based on large language model

Abstract

The invention discloses a form page information supplementing method and device based on a large language model, electronic equipment and a storage medium. In the method, when a triggering operation for a target component in a surface page is detected, the position of the triggering operation is determined; in order to generate a to-be-supplemented page model for performing preset format representation on the content of the form page and the trigger operation position, actually, the content of the form page is abstracted into the to-be-supplemented page model, and supplement request information exists at the position, corresponding to the trigger operation position, in the to-be-supplemented page model. Therefore, the large language model supplements information to the to-be-supplemented page model based on the supplementation request information, the content of the form page is abstracted into the form page model which actually converts the form page into a text form which is arbitrarily processed by the large language model, and then the information supplemented by the large language model is more accurate and efficient. And the supplementary result prompt information rendered in the form page based on the target supplementary information is more accurate and efficient.

Description

Technical Field

[0001] This application relates to the field of information processing, specifically to a method for supplementing form page information based on a large language model, a device for supplementing form page information based on a large language model, electronic equipment, and computer storage media. Background Technology

[0002] Currently, data entry for forms has become a crucial part of form processing. Due to the large volume of data entry tasks, it is necessary to improve the efficiency of data entry for large numbers of forms.

[0003] With the rapid development of artificial intelligence (AI) technology, applying AI, especially large language models, to form page data entry can obviously improve data entry efficiency. However, data entry on form pages, especially those configured on low-code platforms, mainly focuses on UI interaction. Large language models are good at processing text semantic analysis, but not good at UI-interactive data entry. Therefore, the accuracy of data entry on form pages using AI models is low, resulting in low data entry efficiency. Thus, how to improve the accuracy and efficiency of data entry on form pages has become an urgent technical problem to be solved. Summary of the Invention

[0004] This application provides a method for supplementing information on form pages based on a large language model, so as to improve the accuracy and efficiency of information entry on form pages. This application also provides a device, electronic device and computer storage medium for supplementing information on form pages based on a large language model.

[0005] In a first aspect, this application provides a method for supplementing form page information based on a large language model, applied to a form page processing front-end. The method includes: responding to the detection of a trigger event for a target component in the form page, determining the trigger operation position of the trigger event on the form page; generating a page model to be supplemented based on the content of the form page and the trigger operation position, wherein the page model to be supplemented includes supplementation request information for supplementing the trigger operation of the target component; invoking a large language model to supplement the page model to be supplemented, obtaining a supplemented page model, wherein the supplemented page model includes at least target supplementation information for supplementing the supplementation request information; and rendering supplementation result prompt information for supplementing the trigger operation of the target component on the form page based on the target supplementation information in the supplemented page model.

[0006] Secondly, this application provides a method for supplementing form page information based on a large language model, applied to a large language model processing end. The method includes: obtaining a page model to be supplemented sent by a form page processing front-end, wherein the page model to be supplemented is generated by the form page processing front-end in response to detecting a trigger event for a target component in the form page, determining the trigger operation of the trigger event at the trigger operation position on the form page, and generating a page model in a preset format representing the content of the form page and the trigger operation position based on the content of the form page and the trigger operation position; wherein the page model to be supplemented contains supplementation request information for supplementing the trigger operation of the target component; supplementing the page model to be supplemented to obtain a supplemented page model, wherein the supplemented page model includes at least target supplementation information for supplementing the supplementation request information; and sending the supplemented page model to the form page processing front-end, so that the form page processing front-end renders supplementation result prompt information for supplementing the trigger operation of the target component on the form page based on the target supplementation information in the supplemented page model.

[0007] Thirdly, this application provides a form page information supplementation device based on a large language model, applied to a form page processing front end. The device includes: a trigger operation position determination unit, used to determine the trigger operation position of the trigger event on the form page in response to detecting a trigger event targeting a target component in the form page; a page model to be supplemented generation unit, used to generate a page model to be supplemented in a preset format based on the content of the form page and the trigger operation position, wherein the page model to be supplemented includes supplementation request information that needs to supplement the trigger operation of the target component; a first supplemented page model acquisition unit, used to call the large language model to supplement the page model to be supplemented to obtain a supplemented page model, wherein the supplemented page model includes at least target supplementation information that needs to supplement the supplementation request information; and a supplementation result prompt information rendering unit, used to render supplementation result prompt information for supplementing the trigger operation of the target component on the form page based on the target supplementation information in the supplemented page model.

[0008] Fourthly, this application provides a form page information supplementation device based on a large language model, applied to a large language model processing end. The device includes: a page model to be supplemented acquisition unit, used to acquire a page model to be supplemented sent by a form page processing front-end. The page model to be supplemented is generated by the form page processing front-end in response to detecting a trigger event for a target component in the form page, determining the trigger operation position of the trigger event on the form page, and generating a page model in a preset format based on the content of the form page and the trigger operation position. The page model to be supplemented includes supplementation request information that needs to supplement the trigger operation of the target component; a supplemented page model second acquisition unit, used to supplement the page model to be supplemented to obtain a supplemented page model, the supplemented page model including at least target supplementation information for supplementing the supplementation request information; and a supplemented page model sending unit, used to send the supplemented page model to the form page processing front-end, so that the form page processing front-end renders supplementation result prompt information for supplementing the trigger operation of the target component on the form page based on the target supplementation information in the supplemented page model.

[0009] Fifthly, this application provides an electronic device, including: a processor; and a memory for storing a computer program. After the electronic device is powered on and runs the computer program through the processor, it executes the above-described method for supplementing form page information based on a large language model.

[0010] Sixthly, this application provides a computer storage medium storing computer execution instructions, which are executed by a processor to perform the above-described method for supplementing form page information based on a large language model.

[0011] Compared with the prior art, this application has the following advantages: The form page information supplementation method based on a large language model provided in this application embodiment is applied to the form page processing front end. The method includes: responding to the detection of a trigger event for a target component in the form page, determining the trigger operation position of the trigger event on the form page; generating a page model to be supplemented based on the content and trigger operation position of the form page in a preset format, wherein the page model to be supplemented includes supplementation request information that needs to supplement the trigger operation of the target component; calling the large language model to supplement the page model to be supplemented to obtain a supplemented page model, wherein the supplemented page model includes at least target supplementation information that supplements the supplementation request information; and rendering supplementation result prompt information for supplementing the trigger operation of the target component on the form page based on the target supplementation information in the supplemented page model. In this method, when a trigger operation is detected targeting a component on the form page, the trigger operation location is determined to generate a supplementary page model that represents the form page content and the trigger operation location in a preset format. Essentially, the form page content is abstracted into a supplementary page model, and supplementary request information exists at the corresponding trigger operation location within this model. This allows the large language model to supplement information into the supplementary page model based on this request. Abstracting the form page content into a supplementary page model effectively converts the form page into a text format that the large language model is adept at processing. This makes the supplementary information provided by the large language model more accurate and efficient. Consequently, the supplementary result prompts rendered on the form page based on the target supplementary information are more accurate and efficient, facilitating user selection of supplementary result prompts and improving the form page processing efficiency. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0013] Figure 1 A flowchart of the form page information supplementation method based on a large language model provided in the first embodiment of this application.

[0014] Figure 2 This is a schematic diagram of a first scenario for the form page information supplementation method based on a large language model provided in the first embodiment of this application.

[0015] Figure 3 This is a schematic diagram of a second scenario for the form page information supplementation method based on a large language model provided in the first embodiment of this application.

[0016] Figure 4 A flowchart of a method for supplementing form page information based on a large language model, provided in the second embodiment of this application.

[0017] Figure 5 A schematic diagram of a form page information supplementation device based on a large language model provided in the third embodiment of this application.

[0018] Figure 6 A schematic diagram of a form page information supplementation device based on a large language model provided in the fourth embodiment of this application.

[0019] Figure 7 A schematic diagram of an electronic device provided in the fifth embodiment of this application. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solutions of this application, the application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. However, this application can be implemented in many other ways different from those described below. Therefore, based on the embodiments provided in this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0021] It should be noted that the terms "first," "second," "third," etc., in the claims, specification, and drawings of this application are used to distinguish similar objects and are not used to describe a specific order or sequence. Such data are interchangeable where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that shown or described in this application. Furthermore, the terms "comprising," "having," and their variations are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0022] It should be understood that in the embodiments of this application, "at least one" means one or more, and "more than one" means two or more. "And / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. The character " / " generally indicates that the related objects before and after it are in an "or" relationship. "Contains A, B and / or C" means containing any one, two, or three of A, B, and C.

[0023] It should be understood that in the embodiments of this application, "B corresponding to A", "B corresponding to A", "A corresponds to B" or "B corresponds to A" means that B is associated with A, and B can be determined based on A. Determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0024] This application provides a method, apparatus, electronic device, and computer storage medium for supplementing form page information based on a large language model. The following specific embodiments illustrate the method, apparatus, electronic device, and computer storage medium for supplementing form page information based on a large language model.

[0025] First Embodiment This embodiment provides a method for supplementing information on a form page based on a large language model. The execution entity of this embodiment is the form page processing front-end. Please refer to the following for details. Figure 1 This is a flowchart of the method for supplementing form page information based on a large language model provided in the first embodiment of this application.

[0026] The method for supplementing form page information based on a large language model according to this application includes the following steps.

[0027] Step S101: In response to detecting a trigger event for a target component on the form page, determine the trigger operation position of the trigger event on the form page.

[0028] In this embodiment, the method is executed by the form page processing front-end. In fact, the form page processing front-end displays a form page containing the form and can interact with the user.

[0029] When a user triggers a component on a form page, that triggered component becomes the target component, and its event is triggered. In fact, all components on the form page can be monitored, and when a component is triggered, that component becomes the target component. Generally, triggering an operation on a component on a form page most likely involves populating its attribute values, i.e., filling information into the target component. The information filled into the target component is that component's attribute value.

[0030] Specifically, the actions that trigger the operation include at least one of the following: focus action, hover action, and click action on the target component. A focus action is when the target component is selected; a hover action is when the cursor or mouse pointer hovers over the target component; and a click action is when a click is performed on the target component.

[0031] After detecting that the target component has been triggered, the triggering operation's location on the form page can be determined. This involves determining the target component's position on the form page and then confirming the triggering operation's position within that component. This ensures the triggering operation's location is included in the subsequently generated supplementary page model (the triggering operation location is essentially the position where information needs to be supplemented or completed to serve as the target component's attribute value). Specifically, the triggering operation's location in the supplementary page model can be represented by the cursor position. For example, suppose a text input box requires "name". If the user has already entered the first character "surname", the cursor position is after "surname". It's necessary to predict what information needs to be entered after "surname". Alternatively, the cursor position can be manually adjusted. For instance, if a text input box requires "contact number", and the user has already entered "electricity", the cursor position is after "electricity". It's necessary to predict what information needs to be entered after "electricity". Alternatively, the cursor position can be manually adjusted to be before "electricity". In this case, it's necessary to predict what information needs to be entered before "electricity" (e.g., predicting "contact").

[0032] Step S102: Based on the content and trigger operation location in the form page, generate a supplementary page model that represents the content and trigger operation location in a preset format. The supplementary page model contains supplementary request information that needs to supplement the trigger operation of the target component.

[0033] In this embodiment, code corresponding to the content of the form page can be generated. This code can represent the content of the form page. Specifically, the content of the form page can refer to the objects (such as components) and their structures (such as component structures) contained on the form page. In this embodiment, the code to be supplemented is mainly used as an example of a page model to be supplemented. In fact, the page model to be supplemented can also be in other forms, as long as it can express the content of the form page in text form. In essence, it is to convert the content of the form page into a form that is easy for artificial intelligence models (AI), especially large language models, to analyze. The supplement request information can be information about the parts of the code that need to be supplemented. In the code method, it is presented in the form of a code editor, that is, the large language model is used to supplement or complete the code in the code editor.

[0034] In this embodiment, the trigger operation position is used to divide the content of the form page into first form page content and second form page content. Based on the content of the form page and the trigger operation position, a supplementary page model is generated that represents the content of the form page and the trigger operation position in a preset format. This can be achieved by: converting the first form page content and the second form page content according to a preset format to obtain first preset format information and second preset format information; then, obtaining the supplementary position information based on the trigger operation position, generating supplementary request information containing the supplementary position information; and finally, setting the supplementary request information between the first preset format information and the second preset format information to generate the supplementary page model.

[0035] The location information to be supplemented can be indicated by the cursor. The first and second preset format information are actually form page context information that is easy for the Large Language Model (LLM) to understand.

[0036] In this embodiment, based on the content and trigger operation positions in the form page, a supplementary page model is generated that represents the content and trigger operation positions in a preset format. This can be done as follows: obtain form page content protocol data for describing the content in the form page; generate the supplementary page model based on the form page content protocol data, the content in the form page, and the trigger operation positions.

[0037] Since form pages can generally be configured using low-code platforms, the content of the form page corresponds to low-code, such as JSON-formatted protocol data. Therefore, the JSON-formatted protocol data of the corresponding form page content can be obtained. This JSON-formatted protocol data can then be referenced when generating the supplementary code, which will be in the form of plain code. JavaScript or TypeScript can be used. However, some information may be missing during the conversion of the JSON-formatted protocol data into the supplementary code, such as the type of the target component's attribute values ​​(to help determine the type of supplementary information later, such as text or number). Therefore, the missing information can be inserted as comments into the supplementary code (such as React code) to prompt the large language model for better generation of the supplemented code. For example, component type and component title can be used as comments.

[0038] In this embodiment, the form page is a form page for a single form; the trigger event is a filling trigger event for filling the attribute value of the target component; the page model to be supplemented is the code to be supplemented; the supplementary request information is the supplementary request code; generating a page model to be supplemented that represents the content of the form page and the trigger operation position in a preset format based on the content in the form page and the trigger operation position may refer to: generating a declaration code for describing the form content of a single form based on the form content of a single form; generating form creation code for a single form based on the components in a single form and the trigger operation position; generating the code to be supplemented based on the declaration code and the form creation code; the code to be supplemented includes at least the supplementary request code.

[0039] For the convenience of understanding the form page of a single form, please refer to Figure 2 , which is the first scenario schematic diagram of the form page information supplementation method based on the large language model provided in the first embodiment of the present application; Figure 2 The page of Figure 2 is the form page of a single form. When filling in the address information in

[0040] , some address information has been filled: Putuo, Shanghai. The cursor is located after the character 'Tuo'. The displayed supplementary result prompt information is 'No. 1111, Jinshajiang Road, Putuo District, Shanghai', and the cursor in the supplementary result prompt information is aligned with the cursor of the target component. Of course, the displayed supplementary result prompt information can also be 'Jinshajiang Road, No. 1111', and the cursor is before the character 'District', that is, 'Putuo, Shanghai' is not displayed. 1 interface Data { 2 name: string / Name / ; 3 age: number / [[ID=2 forty]]Age, >= / ; 4 address?: string / Address / ; 5 hobby?: string / Hobby, length <= 50 / ; 6} 7 class Form { 8 static title = 'New User'; 9 data: Data; 10 constructor(data: Data) { 11 this.data = data; 12} 13 submit() {} 14} 16 const form = new Form({ 17 name: '张三', 18 age: 18, 19 address: 'Putuo District, Shanghai Lane 1111, Jinshajiang Road, District ', 20 hobby: '', 21}); 22 form.submit(); 23 The declaration code is lines 1 to 15 of the above code, and the form creation code is lines 16 to 23 of the above code. Meanwhile, in fact, near line 19, the acceptance options of the code editor can be shown to accept the completion prompt information (the completed part is in italics Lane 1111, Jinshajiang Road, District ), so as to generate the code corresponding to line 19. It should be noted that in this example, the difference between the code to be supplemented and the supplemented code is only that in the code to be supplemented, what is shown in line 19 is address: 'Putuo District, Shanghai| / ', so as to know that this place needs to be completed. The form creation code represents the code currently filling out this form.

[0041] In this embodiment, the form page includes a preview form interface and a form configuration interface; the trigger event is a filling trigger event for filling the attribute values of the target component in the form configuration interface; the page model to be supplemented is the code to be supplemented; the supplementary request information is the supplementary request code; generating a page model to be supplemented in a preset format for the content and trigger operation position of the form page based on the content and trigger operation position in the form page may mean: generating a declaration code for describing the preview form interface as the code to be supplemented based on the content and trigger operation position of the preview form interface; the code to be supplemented contains at least the supplementary request code.

[0042] For the convenience of understanding the preview form interface, the form configuration interface, and the processing flow, please refer to Figure 3 , which is the second scenario schematic diagram of the form page information supplementation method based on the large language model provided by the first embodiment of this application; in Figure 3 , the left side is the preview form interface and the right side is the form configuration interface.

[0043] After clicking "Last Name" in the form preview interface, the form configuration interface will be displayed. This is actually an example of modifying the "Last Name" field. After entering "Last Name" in the form configuration interface, the generated code to be supplemented is as follows (only a part is shown): export default LowcodeComponent { css = 'body {\ncolor: red;\n}' dataSourceMap = [] state = 0 componentDidMount() {} handleSearch() {} render() { return <page> <SearchForm columns={[ { dataindex: "name", title: "Surname|" / Text type / } ]} / > <page> In the code above, title: "Last Name|" / Text type The slash " / " serves as a comment and also as part of the supplementary request information. In the form configuration interface, the "Last Name" field is being configured. During configuration, if "Last Name" is entered in the text box on the right, and the cursor is positioned after "Last Name," the displayed supplementary result prompt will be "Last Name|First Name," with the cursor in the supplementary result prompt aligned with the cursor of the target component. Of course, the displayed supplementary result prompt can also be "|First Name." Figure 2 and Figure 3 All components in this document are content-type components.

[0044] Step S103: Call the large language model to supplement the page model to be supplemented, and obtain the supplemented page model. The supplemented page model includes at least the target supplement information supplemented in response to the supplement request information.

[0045] In this embodiment, invoking the large language model to supplement the page model to be supplemented and obtaining the supplemented page model includes: sending the page model to be supplemented to the application programming interface (API) used to invoke the large language model, so that the API provides the page model to be supplemented to the large language model while taking the supplementation request information as an input parameter; and obtaining the supplemented page model provided by the large language model and sent by the API, wherein the target supplementation information is used as an output parameter of the input parameter.

[0046] In fact, before calling the large language model, it is necessary to break down the content before the cursor (prefix) and the content after the cursor (suffix) based on the form page context and cursor position. After calling the API, the completion suggestions are obtained. API stands for Application Programming Interface.

[0047] by Figure 3 As an example, the input parameters (in) and output parameters (out) are as follows: enter: { "prefix":"export default ...", "suffix":" / text type / \n\n..." } out: { "choice": "name" } The above only shows a portion of the input and output parameters.

[0048] Step S104: Based on the target supplementary information in the supplemented page model, render supplementary result prompt information in the form page to supplement the trigger operation of the target component.

[0049] In this embodiment, rendering supplementary result prompt information for supplementing the triggering operation of the target component in the form page includes: rendering supplementary result prompt information in a floating layer above the target component; the method further includes: in response to detecting an acceptance operation for the supplementary result prompt information, setting the attribute value of the target component based on the supplementary result prompt information and displaying it.

[0050] Please see details. Figure 2 or Figure 3 The AI ​​completion overview shown is an example of rendering the completion result prompt information. Clicking the "Accept" button or pressing the "Tab" key actually accepts the operation; at this time, the completed information can be displayed in the target component, such as in... Figure 3 The text box displays "Name". Of course, if you choose not to accept, you can close the supplementary result prompt message, such as by closing the top pop-up. In fact, you can also close it after accepting. The acceptance rate can be calculated later. In reality, the supplementary result prompt message can be inserted into or replace the component value. Generally, content-type components have a cursor and are therefore suitable for insertion, while enumeration-type components / click-type components do not have a cursor and are suitable for replacement. Click-type components, such as... Figure 3 The enabled component in the form configuration interface is currently open. If this component is triggered and the large language model determines that it needs to be closed, the AI ​​completion overview will display the closed state of the enabled component, and the closed state will be the completion result prompt information. The content type component is actually the component that requires the insertion or filling in of specific content.

[0051] In this embodiment, the method further includes: determining the type of the target component; and rendering supplementary result prompts on the form page to supplement the triggering operation of the target component, including: rendering supplementary result prompts on the form page based on the type of the target component. Different types of components use different forms of rendering supplementary result prompts. The types of target components include content type components, enumeration type components, and collection type components. Figure 2 and Figure 3 The examples shown are for content-type components. Enumeration-type components can be components with dropdown menus. When the target component is an enumeration-type component, the overlay rendering the supplementary result information also includes a dropdown indicator. To facilitate understanding how the supplementary result information is displayed, when "Gender" is displayed in an enumeration-type component, the overlay AI completion overview can display "Male" or "Female" as the supplementary result information. An example of a collection-type component could be a component for entering contact information, with one component for entering +86 and another for entering an eleven-digit phone number, thus forming a complete collection-type component.

[0052] For content-type components, the message indicating the completion result will change if the cursor position or input content changes; for enumeration-type components, the message indicating the completion result will change if the content changes; for collection-type components (i.e., collection class - array type), the message indicating the completion result will change if a row is added.

[0053] For example, regarding content-type components, as mentioned earlier, when "contact number" needs to be entered in a text input box, assuming the user has already entered "electricity," the cursor position is after "electricity." In reality, it's necessary to predict what information needs to be entered after "electricity." Of course, the cursor position can be manually adjusted, moving it before the word "electricity." In this case, it's necessary to predict what information needs to be entered before "electricity" (e.g., predicting "contact"). This corresponds to a change in cursor position. If "contact" is entered in the text input box, the cursor is after "contact," so it's necessary to predict what information needs to be entered after "contact." This corresponds to a change in input content.

[0054] For collection-type components, such as those with two rows for entering name and age, if a new row is added, the cursor will automatically be placed in the text box for entering the specific name in the new row. In this case, it's necessary to predict the supplementary information for the new row. It should be noted that this is different from... Figure 3 The examples are different. Figure 3 This is a solution to change the field from "Last Name" to "First Name," and it's a supplementary result prompt message for the target component in the configuration process, ultimately enabling... Figure 3 In the preview form interface, "surname" is changed to "full name"; and the text box for entering the specific name can be filled with detailed names such as "Zhang San".

[0055] In this embodiment, the method further includes: determining whether the number of items in the supplementary result prompt information is multiple; if the number of items in the supplementary result prompt information is multiple, then the supplementary result prompt information is decomposed according to the number of items to obtain the decomposed supplementary result prompt information; rendering the supplementary result prompt information used to supplement the trigger operation of the target component on the form page, including: rendering the decomposed supplementary result prompt information on the form page. In fact, this part refers to the fact that there are multiple schemes for the supplementary result prompt information, so different supplementary result prompt information schemes need to be displayed separately, such as displaying multiple AI completion overview overlays.

[0056] In this method, when a trigger operation is detected targeting a component on the form page, the trigger operation location is determined to generate a supplementary page model that represents the form page content and the trigger operation location in a preset format. Essentially, the form page content is abstracted into a supplementary page model, and supplementary request information exists at the corresponding trigger operation location within this model. This allows the large language model to supplement information into the supplementary page model based on this request. Abstracting the form page content into a supplementary page model effectively converts the form page into a text format that the large language model is adept at processing. This makes the supplementary information provided by the large language model more accurate and efficient. Consequently, the supplementary result prompts rendered on the form page based on the target supplementary information are more accurate and efficient, facilitating user selection of supplementary result prompts and improving the form page processing efficiency.

[0057] Second Embodiment Corresponding to the first embodiment, the second embodiment of this application provides another method for supplementing form page information based on a large language model. The execution entity of this embodiment is the large language model processing terminal. The parts in the second embodiment that are the same as those in the first embodiment will not be described again; please refer to the relevant parts of the first embodiment for details.

[0058] Please refer to Figure 4 This is a flowchart of the method for supplementing form page information based on a large language model provided in the second embodiment of this application.

[0059] The method for supplementing form page information based on a large language model according to this application includes the following steps.

[0060] Step S401: Obtain the supplementary page model sent by the form page processing front-end.

[0061] The page model to be supplemented is the response of the front-end of the form page processing to detect the trigger event for the target component in the form page, determine the trigger operation position of the trigger operation on the form page, and generate a page model that represents the content and trigger operation position of the form page in a preset format based on the content and trigger operation position of the form page; wherein, the page model to be supplemented contains supplementary request information that needs to supplement the trigger operation of the target component.

[0062] Step S402: Supplement the page model to be supplemented to obtain the supplemented page model. The supplemented page model includes at least the target supplementary information supplemented in response to the supplementary request information.

[0063] Step S403: Send the supplemented page model to the form page processing frontend so that the form page processing frontend can render supplementary result prompt information in the form page to supplement the trigger operation of the target component based on the target supplementary information in the supplemented page model.

[0064] In this embodiment, the page model to be supplemented is received through an application programming interface, with the supplementation request information as the input parameter; the target supplementation information is the output parameter of the input parameter.

[0065] In this method, after obtaining the page model to be supplemented sent by the form page processing frontend, the page model to be supplemented is supplemented to obtain a supplemented page model. The supplemented page model includes at least the target supplementary information to be supplemented in response to the supplementary request information. Then, the supplemented page model is sent to the form page processing frontend so that the form page processing frontend can render supplementary result prompt information in the form page to supplement the trigger operation of the target component based on the target supplementary information in the supplemented page model. In fact, the content of the form page is abstracted into the page model to be supplemented, and the page model to be supplemented contains supplementary request information at the corresponding trigger operation position. This allows the large language model to supplement information to the page model to be supplemented based on the supplementary request information. Abstracting the content of the form page into the page model to be supplemented actually converts the form page into a text form that the large language model is good at processing. This makes the information supplemented by the large language model more accurate and efficient, and the supplementary result prompt information rendered in the form page based on the target supplementary information more accurate and efficient, so that users can select supplementary result prompt information and improve the efficiency of form page processing.

[0066] Third Embodiment Corresponding to the form page information supplementation method based on a large language model provided in the first embodiment of this application, the third embodiment of this application also provides a form page information supplementation device based on a large language model. Since the device embodiment is basically similar to the first embodiment, it is described simply; relevant details can be found in the description of the first embodiment. The device embodiments described below are merely illustrative.

[0067] Please refer to Figure 5 This is a schematic diagram of a form page information supplementation device based on a large language model provided in the third embodiment of this application.

[0068] The form page information supplementation device 500 based on a large language model is applied to the form page processing front end. The device includes: a trigger operation position determination unit 501, used to determine the trigger operation position of the trigger event on the form page in response to detecting a trigger event for a target component in the form page; a page model to be supplemented generation unit 502, used to generate a page model to be supplemented based on the content in the form page and the trigger operation position, representing the content of the form page and the trigger operation position in a preset format, wherein the page model to be supplemented includes supplementation request information that needs to supplement the trigger operation of the target component; a supplemented page model first acquisition unit 503, used to call the large language model to supplement the page model to be supplemented to obtain a supplemented page model, wherein the supplemented page model includes at least target supplementation information that needs to be supplemented in response to the supplementation request information; and a supplementation result prompt information rendering unit 504, used to render supplementation result prompt information for supplementing the trigger operation of the target component on the form page based on the target supplementation information in the supplemented page model.

[0069] Fourth embodiment Corresponding to the form page information supplementation method based on a large language model provided in the second embodiment of this application, the fourth embodiment of this application also provides a form page information supplementation device based on a large language model. Since the device embodiment is basically similar to the second embodiment, the description is relatively simple; relevant details can be found in the description of the second embodiment. The device embodiments described below are merely illustrative.

[0070] Please refer to Figure 6 This is a schematic diagram of the form page information supplementation device based on a large language model provided in the fourth embodiment of this application.

[0071] The form page information supplementation device 600 based on a large language model is applied to a large language model processing end. The device includes: a page model acquisition unit 601, used to acquire a page model to be supplemented sent by the form page processing front-end. The page model to be supplemented is generated by the form page processing front-end in response to detecting a trigger event targeting a target component in the form page, determining the trigger operation position of the trigger event on the form page, and generating a page model in a preset format representing the content of the form page and the trigger operation position based on the content of the form page and the trigger operation position. The page model to be supplemented... The page model contains supplementary request information that needs to supplement the triggering operation of the target component; the supplemented page model second obtaining unit 602 is used to supplement the page model to be supplemented to obtain the supplemented page model, the supplemented page model includes at least target supplementary information supplemented in response to the supplementary request information; the supplemented page model sending unit 603 is used to send the supplemented page model to the form page processing front end, so that the form page processing front end renders supplementary result prompt information for supplementing the triggering operation of the target component in the form page based on the target supplementary information in the supplemented page model.

[0072] Fifth embodiment Corresponding to the methods of the first to second embodiments of this application, the fifth embodiment of this application also provides an electronic device.

[0073] The electronic device includes: a processor; and a memory for storing a computer program. After the electronic device is powered on and runs the computer program through the processor, it executes the methods of the first to second embodiments. Figure 7 As shown, Figure 7 This is a schematic diagram of an electronic device provided according to the fifth embodiment of this application. The electronic device specifically includes: at least one processor 701, at least one communication interface 702, at least one memory 703, and at least one communication bus 704. Optionally, the communication interface 702 can be an interface for a communication module, such as the interface for a GSM module. The processor 701 may be a CPU, an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The memory 703 may include high-speed RAM and may also include non-volatile memory, such as at least one disk storage device. The memory 703 stores a program, and the processor 701 calls the program stored in the memory 703 to execute the methods of the first to second embodiments.

[0074] Sixth Embodiment Corresponding to the methods of the first to second embodiments of this application, the sixth embodiment of this application also provides a computer storage medium storing computer execution instructions, which are executed by a processor to perform the methods of the first to second embodiments of this application.

[0075] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0076] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0077] 1. Computer-readable media includes both permanent and non-permanent, removable and non-removable media, which can store information by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined in this application, computer-readable media does not include non-transitory computer-readable media, such as modulated data signals and carrier waves.

[0078] 2. Those skilled in the art will understand that embodiments of this application can provide methods, systems, or computer program products. Therefore, embodiments of this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] 3. This application embodiment may involve the use of user data. In practical applications, user-specific personal data may be used within the scope permitted by applicable laws and regulations of the country in which the application is located (e.g., with the user's explicit consent and effective notification to the user, etc.). Furthermore, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. The collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0080] Although this application discloses preferred embodiments as described above, it is not intended to limit this application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of this application. Therefore, the scope of protection of this application should be determined by the scope defined in the claims of this application.< / page> < / page>

Claims

1. A method for supplementing form page information based on a large language model, characterized in that, The method, applied to the front-end of form page processing, includes: In response to detecting a trigger event targeting a target component on a form page, the triggering operation of the trigger event is determined to be located at the triggering operation position on the form page; Based on the content of the form page and the trigger operation location, a supplementary page model is generated, which represents the content of the form page and the trigger operation location in a preset format. The supplementary page model contains supplementary request information that needs to supplement the trigger operation of the target component. The large language model is invoked to supplement the page model to be supplemented, and a supplemented page model is obtained. The supplemented page model includes at least the target supplementary information that is supplemented in response to the supplementary request information. Based on the target supplementary information in the supplemented page model, supplementary result prompt information for supplementing the trigger operation of the target component is rendered on the form page.

2. The method according to claim 1, characterized in that, The trigger operation position is used to divide the content of the form page into the content of the first form page and the content of the second form page; The step of generating a supplementary page model based on the content of the form page and the trigger operation location, representing the content of the form page and the trigger operation location in a preset format, includes: The content of the first form page and the content of the second form page are converted according to the preset format to obtain the first preset format information and the second preset format information; Based on the location of the trigger operation, obtain the location information to be supplemented, and generate supplementary request information containing the location information to be supplemented; The supplementary request information is set between the first preset format information and the second preset format information to generate the page model to be supplemented.

3. The method according to claim 1, characterized in that, The step of generating a supplementary page model based on the content of the form page and the trigger operation location, representing the content of the form page and the trigger operation location in a preset format, includes: Obtain form page content protocol data used to describe the content in the form page; The page model to be supplemented is generated based on the form page content protocol data, the content in the form page, and the trigger operation location.

4. The method according to claim 1, characterized in that, The step of calling the large language model to supplement the page model to be supplemented, and obtaining the supplemented page model, includes: Send the page model to be supplemented to the application programming interface (API) used to invoke the large language model, so that the API provides the page model to be supplemented to the large language model while taking the supplementation request information as an input parameter. Obtain the supplemented page model provided by the large language model and sent by the application programming interface, wherein the target supplementary information is used as the output parameter of the input parameter.

5. The method according to claim 1, characterized in that, The form page is a single form page; the triggering event is a fill triggering event that fills in the attribute values ​​of the target component; the page model to be supplemented is the code to be supplemented; the supplementation request information is the supplementation request code; The step of generating a supplementary page model based on the content of the form page and the trigger operation location, representing the content of the form page and the trigger operation location in a preset format, includes: Based on the form content of the single form, generate declaration code to describe the form content of the single form; Based on the components in the single form and the location of the triggering operation, generate form creation code for the single form; Based on the declaration code and the form creation code, the code to be supplemented is generated; the code to be supplemented includes at least the supplement request code.

6. A method for supplementing form page information based on a large language model, characterized in that, Applied to large language model processing, the method includes: The form page processing frontend receives a supplementary page model sent by the frontend. This supplementary page model is generated in response to the frontend detecting a trigger event for a target component on the form page, determining the trigger operation's location on the form page, and generating a page model representing the form page content and trigger operation location in a preset format based on the form page content and the trigger operation location. The supplementary page model includes supplementary request information requiring the supplementation of the trigger operation for the target component. The page model to be supplemented is supplemented to obtain a supplemented page model, wherein the supplemented page model includes at least target supplementary information that is supplemented in response to the supplementary request information; The supplemented page model is sent to the form page processing front-end, so that the form page processing front-end renders supplementary result prompt information in the form page to supplement the trigger operation of the target component based on the target supplementary information in the supplemented page model.

7. A form page information supplementation device based on a large language model, characterized in that, The device, used in the front-end of form page processing, includes: A trigger operation location determination unit is used to determine the trigger operation location of the trigger event on the form page in response to detecting a trigger event targeting a target component in the form page. The supplementary page model generation unit is used to generate a supplementary page model based on the content of the form page and the trigger operation position, which is represented in a preset format for the content of the form page and the trigger operation position. The supplementary page model includes supplementary request information that needs to supplement the trigger operation of the target component. The first unit for obtaining the supplemented page model is used to call the large language model to supplement the page model to be supplemented, and obtain the supplemented page model. The supplemented page model includes at least the target supplementary information for supplementing the supplementary request information. The supplementary result prompt information rendering unit is used to render supplementary result prompt information on the form page, based on the target supplementary information in the supplemented page model, to supplement the trigger operation of the target component.

8. A form page information supplementation device based on a large language model, characterized in that, The device, applied to large language model processing, includes: The supplementary page model acquisition unit is used to acquire the supplementary page model sent by the form page processing front-end. The supplementary page model is generated by the form page processing front-end in response to detecting a trigger event for a target component in the form page, determining the trigger operation position of the trigger event on the form page, and generating a page model in a preset format based on the content of the form page and the trigger operation position. The supplementary page model includes supplementary request information that needs to supplement the trigger operation of the target component. The second unit for obtaining the supplemented page model is used to supplement the page model to be supplemented to obtain the supplemented page model. The supplemented page model includes at least target supplementary information for supplementing the supplementary request information. The supplemented page model sending unit is used to send the supplemented page model to the form page processing front end, so that the form page processing front end renders supplementary result prompt information in the form page to supplement the trigger operation of the target component based on the target supplementary information in the supplemented page model.

9. An electronic device, characterized in that, include: processor; And a memory for storing a computer program, wherein after the electronic device is powered on and the computer program is run by the processor, it performs the method according to any one of claims 1-6.

10. A computer storage medium, characterized in that, The computer storage medium stores computer execution instructions, which are executed by a processor to perform the method described in any one of claims 1-6.

Images