CN-121996242-A - Techniques for assisting in generating a UI by a generating pre-training transformer code generator

Abstract

In some implementations, the techniques may include accessing a data file containing metadata for various data fields. The technique may include accessing a predefined category list and creating a first request for a generative pre-training transformer to categorize portions of metadata by assigning the portions of metadata to predefined categories of the predefined category list. The technique may include receiving a first output list from a generative pre-training transformer, the first output list including a portion of metadata and an assigned predefined category. The techniques may include using the category list to generate tags, features, and rankings. The techniques may include generating application code using one or more code generation templates and tags and features of the application. The technique may include storing application code. The techniques may be performed by a system or stored as a series of instructions on a computer readable tangible medium.

Inventors

• E. Elliland

Assignees

• SAP欧洲公司

Dates

Publication Date

20260508

Application Date

20250514

Priority Date

20241105

Claims (20)

1. 1. A computer-implemented method, comprising: Accessing a data file containing metadata for various data fields; Accessing a predefined category list; Creating a first request for a generative pre-training transformer to categorize the portion of metadata by assigning the portion of metadata to a predefined category of the predefined category list; receiving a first output list from the generative pre-training transformer, the first output list comprising a portion of the metadata and the assigned predefined categories; Generating tags, features and rankings using the category list; Generating application code using one or more code generation templates and the tags and features of the application, and And storing the application code.
2. 2. The computer-implemented method of claim 1, further comprising: Creating a second request for a generative pre-training transformer to determine a category using the predefined list of categories to filter traffic data from the data file; Receiving a second output list of proposed filters from the generative pre-training transformer; Generating one or more filters based on the second output list of proposed filters; generating application code using one or more code generation templates and one or more filters of the application, and And storing the application code.
3. 3. The computer-implemented method of claim 1, further comprising: creating a third request for a generative pre-training transformer to determine categories using the predetermined list of categories to order business data from the data file; receiving a third output list of proposed ordered items from the generative pre-training transformer; Generating one or more ranking features to rank the metadata based on the third output list of proposed ranking items; generating application code using one or more code generation templates and one or more ordering features of the application, and And storing the application code.
4. 4. The computer-implemented method of claim 1, wherein the data file comprises an extensible markup language file.
5. 5. The computer-implemented method of claim 1, wherein the data file comprises a JavaScript object notation (JSON) formatted structure and object.
6. 6. The computer-implemented method of claim 1, further comprising assigning a color to the data element in the display of the application based at least in part on the list of categories specific to the data element.
7. 7. The computer-implemented method of claim 1, wherein the generating application code comprises: parsing the data file to determine placeholders and elements; Generating a data model containing values to be replaced in the placeholders and the elements; serializing the data model into text, and A transformation is applied to the text for conversion to a code format.
8. 8. A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising: One or more instructions that, when executed by one or more processors of a device, cause the device to perform operations comprising: Accessing a data file containing metadata for various data fields; Accessing a predefined category list; Creating a first request for a generative pre-training transformer to categorize the portion of metadata by assigning the portion of metadata to a predefined category of the predefined category list; receiving a first output list from the generative pre-training transformer, the first output list comprising a portion of the metadata and the assigned predefined categories; Generating tags, features and rankings using the category list; Generating application code using one or more code generation templates and the tags and features of the application, and And storing the application code.
9. 9. The non-transitory computer-readable medium of claim 8, wherein the operations further comprise: Creating a second request for a generative pre-training transformer to determine a category using the predefined list of categories to filter traffic data from the data file; Receiving a second output list of proposed filters from the generative pre-training transformer; Generating one or more filters based on the second output list of proposed filters; generating application code using one or more code generation templates and one or more filters of the application, and And storing the application code.
10. 10. The non-transitory computer-readable medium of claim 8, wherein the operations further comprise: creating a third request for a generative pre-training transformer to determine categories using the predetermined list of categories to order business data from the data file; receiving a third output list of proposed ordered items from the generative pre-training transformer; Generating one or more ranking features to rank the metadata based on the third output list of proposed ranking items; generating application code using one or more code generation templates and one or more ordering features of the application, and And storing the application code.
11. 11. The non-transitory computer-readable medium of claim 8, wherein the data file comprises an extensible markup language file.
12. 12. The non-transitory computer-readable medium of claim 8, wherein the data file comprises JavaScript object notation (JSON) formatted structures and objects.
13. 13. The non-transitory computer-readable medium of claim 8, wherein the operations further comprise assigning a color to a data element in a display of an application based at least in part on the category list specific to the data element.
14. 14. The non-transitory computer-readable medium of claim 8, wherein the generating application code comprises: parsing the data file to determine placeholders and elements; Generating a data model containing values to be replaced in the placeholders and the elements; serializing the data model into text, and A transformation is applied to the text for conversion to a code format.
15. 15. A system, comprising: one or more processors configured to access code stored in memory to perform operations comprising: Accessing a data file containing metadata for various data fields; Accessing a predefined category list; Creating a first request for a generative pre-training transformer to categorize the portion of metadata by assigning the portion of metadata to a predefined category of the predefined category list; receiving a first output list from the generative pre-training transformer, the first output list comprising a portion of the metadata and the assigned predefined categories; Generating tags, features and rankings using the category list; Generating application code using one or more code generation templates and the tags and features of the application, and And storing the application code.
16. 16. The system of claim 15, wherein the operations further comprise: Creating a second request for a generative pre-training transformer to determine a category using the predefined list of categories to filter traffic data from the data file; Receiving a second output list of proposed filters from the generative pre-training transformer; Generating one or more filters based on the second output list of proposed filters; generating application code using one or more code generation templates and one or more filters of the application, and And storing the application code.
17. 17. The system of claim 15, wherein the operations further comprise: creating a third request for a generative pre-training transformer to determine categories using the predetermined list of categories to order business data from the data file; receiving a third output list of proposed ordered items from the generative pre-training transformer; Generating one or more ranking features to rank the metadata based on the third output list of proposed ranking items; generating application code using one or more code generation templates and one or more ordering features of the application, and And storing the application code.
18. 18. The system of claim 15, wherein the data file comprises an extensible markup language file.
19. 19. The system of claim 15, wherein the data file comprises JavaScript object notation (JSON) formatted structures and objects.
20. 20. The system of claim 15, wherein the generating application code comprises: parsing the data file to determine placeholders and elements; Generating a data model containing values to be replaced in the placeholders and the elements; serializing the data model into text, and A transformation is applied to the text for conversion to a code format.

Description

Techniques for assisting in generating a UI by a generating pre-training transformer code generator Technical Field The software application has the ability to generate other software applications up to and including the generation of specific program code for those applications. However, many of these applications that may be developed using these developer tools produce user interfaces that are not active to the user and are not organized and ordered in a manner that is helpful to the user. User interfaces for these applications may present data in a template fashion or using traditional rules, such as displaying fields alphabetically. The data may be presented in a manner that is not readable or logical to the user. Moreover, editing these applications created using developer tools can be a difficult task for a developer to correct the deficiencies of these developer tools. Background Application developers can use improved tools that utilize artificial intelligence to assist in developing more user-friendly applications, including user interfaces for those applications, customizing those applications with data and in an efficient manner. Disclosure of Invention A system of one or more computers may be configured to perform particular operations or actions by installing software, firmware, hardware, or a combination thereof on the system that, in operation, causes the system to perform the actions. The one or more computer programs may be configured to perform particular operations or actions by including instructions that when executed by data processing apparatus cause the apparatus to perform the actions. In one general aspect, a computer-implemented method may include accessing a data file containing metadata for various data fields. The computer-implemented method may include accessing a predefined category list. The method may include creating a first request for a generative pre-training transformer to categorize the portion of the metadata by assigning the portion of the metadata to a predefined category of a predefined category list. The method may include receiving a first output list from a generative pre-training transformer, the first output list including a portion of metadata and an assigned predefined category. Further, the method may include generating tags, features, and rankings using the category list. The method may also include generating application code using one or more code generation templates and tags and features of the application. The method may also include storing the application code. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each configured to perform the actions of the methods. Implementations may include one or more of the following features. In various embodiments, a computer-implemented method may include creating a second request for a generative pre-training transformer to determine a category using a predefined category list to filter traffic data from a data file. The computer-implemented method may include receiving a second output list of proposed filters from the generative pre-training transformer. The computer-implemented method may include generating one or more filters based on the second output list of proposed filters. The computer-implemented method may include generating application code using one or more code generation templates and one or more filters of an application. The computer-implemented method may include generating application code. The computer-implemented method may include storing application code. The computer-implemented method may include creating a third request for the generative pretraining transformer to determine categories using the predetermined category list to order the business data from the data file. The computer-implemented method may include receiving a third output list of proposed ordering items (sorting terms) from the generative pre-training transformer. The computer-implemented method may include generating one or more ranking features to rank the metadata based on the third output list of proposed ranking terms. The computer-implemented method may include generating application code using one or more code generation templates and one or more ordering features of the application. The computer-implemented method may include storing application code. In various embodiments, the data file may comprise an extensible markup language file. In various embodiments, the data file may include structures and objects in JavaScript object notation (JSON) format. In various embodiments, a computer-implemented method may include assigning colors to data elements in a display of an application based at least in part on a category list specific to the data elements. In various embodiments, the process of generating application code may include parsing a data file to determine placeholders and elements. The process may i