Method for web code generation based on generative confrontation and convolutional neural network UI

A convolutional neural network and code technology, applied in the field of software development, can solve the problems of unfavorable use by developers, cannot be applied on a large scale, and high threshold for use, and achieve the effect of low cost of use, high accuracy, and improved accuracy.

Active Publication Date: 2021-08-17
YANGZHOU UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, there are many technologies for automatic code generation, including template-based Freemarker, XSLT, velocity, model-driven MDA, MDD, object-relational mapping-based ORM, MVC, document annotation-based Annotation, XDoclet, and proxy dynamic class-based AOP, PROXY, ASM, these automatic code generation methods only play a partial auxiliary role in the software development process, and cannot replace a certain link of software development, and have a very limited effect on improving the speed of software development
In addition, these automatic code generation methods need to be studied in related fields first, and then they can be applied in actual development after mastering these methods. The threshold for use is high, which is not conducive to the use of most developers, so the universality is poor , cannot be applied on a large scale in actual development

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for web code generation based on generative confrontation and convolutional neural network UI
  • Method for web code generation based on generative confrontation and convolutional neural network UI
  • Method for web code generation based on generative confrontation and convolutional neural network UI

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0066] The present invention generates the method for Web code based on the UI of generation confrontation and convolutional neural network, comprises the following contents:

[0067] 1. Construct the mapping relationship between the display effect of HTML elements and their source codes, specifically: use CNN to extract the feature maps of HTML elements, and make a one-to-one correspondence between the feature maps of HTML elements and HTML codes.

[0068] Common HTML elements include Elements (Button, Container, Divider, Flag, Header, Icon, Image, Input, Label, List, Loader, Placeholder, Rail, Reveal, Segment, Step), Collections (Breadcrumb, Form, Grid, Menu, Message, Table), Views (Advertisement, Card, Comment, Feed, Item, Statistic), Modules (Accordion, Checkbox, Dimmer, Dropdown, Embed, Modal, Popup, Progress, Rating, Search, Shape, Sidebar, Sticky, Tab, Transition).

[0069] In this embodiment, the input web design diagram demo1.png is as follows figure 2 shown. In t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method for generating Web codes based on generating confrontation and convolutional neural network UI. Code; Find the similarity Sim between the manually written HTML code and the generated HTML code 1 ; Find the picture I and the picture I generated by the generated HTML code 1 The similarity Sim 2 ; will Sim 1 and Sim 2 Balanced as a Sim 0 , discriminant Sim 0 The relationship with the threshold t, if Sim 0 If it is less than t, repeat the above process, otherwise, go to the next step; after the training in the previous step, obtain the image-to-HTML code generation model M, and input the UI image to be processed into the model M to obtain the corresponding HTML code. The method of the present invention can obtain a generation model M from pictures to HTML codes, and input the UI pictures to be processed to M to generate corresponding HTML codes, which is more universal and versatile, and can replace some links in actual development, so that The actual use cost is lower and the application field is wider.

Description

technical field [0001] The invention belongs to the field of software development, in particular to a method for generating Web codes based on generating confrontation and convolutional neural network UI. Background technique [0002] Due to the explosive growth of the scale and complexity of software products, rapid software development has become more and more challenging, especially in the early stages of software development, the designer designs the prototype diagram and realizes the prototype diagram with code. Very heavy and extremely inefficient. By studying the automatic generation of software codes, developers can speed up their own development progress during the development process, realize software functions more quickly, and finally launch their own software products quickly. Therefore, the research on automatic software code generation is more and more important. [0003] At present, there are many technologies for automatic code generation, including templa...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F8/38G06F16/958G06N3/04G06N3/08
CPCG06F8/38G06F16/986G06N3/08G06N3/044G06N3/045G06V10/25G06V10/7715G06V10/82G06N3/088G06N3/047G06T7/73G06F40/143G06V10/761G06T2207/20084G06T2207/30176G06N3/048
Inventor 孙小兵徐勇李斌
Owner YANGZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products