Supercharge Your Innovation With Domain-Expert AI Agents!

Graph-based end-to-end program repair method

A repair method and program technology, applied in the direction of non-redundancy-based fault handling, response error generation, instruments, etc., can solve the problems of inability to learn enough program defect characteristic information, low repair ability, low efficiency and subjectivity

Active Publication Date: 2021-03-09
YANGZHOU UNIV
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among the three types of methods, the first and second methods mostly use manual extraction of defect features or patterns, but the manual extraction of features and patterns by experts is inefficient and highly subjective, and lacks generalization ability; while the third Although the class method avoids a large amount of manual intervention, because a more suitable code representation method has not been found, the model it uses cannot learn enough feature information of program defects, resulting in low repair ability

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
  • Graph-based end-to-end program repair method
  • Graph-based end-to-end program repair method
  • Graph-based end-to-end program repair method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.

[0070] In one embodiment, combined with figure 1 , the present invention proposes a graph-based end-to-end program repair method, the method comprising the following steps:

[0071] Step 1, construct defect data set;

[0072] Step 2, perform defect program slicing, and extract the context related to the defect statement;

[0073] Step 3, embedding the defect code graph, transforming the defect statement and its context into a graph structure that can be learned;

[0074] Step 4, build and train the Graph2Seq model;

[0075] Step 5, use the trained Graph2Seq model to generate repair pat...

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 graph-based end-to-end program repair method, which belongs to the field of software debugging, and comprises the following steps: constructing a defect data set; slicing a defect program; embedding a defect code graph; building and training a Graph2Seq model; and generating a repair patch by using the trained Graph2Seq model and verifying the correctness of the patch. According to the method provided by the invention, the graph is used for representing the code, the grammar and semantic association between the code defect statement and the context thereof can be fully mined, and the characteristics of the defect can be better learned, so that the repair patch with higher quality and higher readability is generated, the purpose of automatically repairing the program defect is achieved, and the efficiency of automatic program repair can be greatly improved.

Description

technical field [0001] The invention belongs to the field of software debugging, in particular to a graph-based end-to-end program repair method. Background technique [0002] During the software development process, program defects (bugs) are inevitable due to the comprehensive effects of each stage, and historical data shows that 45% of software development costs are consumed in the process of positioning and repairing. After software developers and maintainers determine the location of the defect, it often takes a lot of effort to manually repair the found defect. Therefore, in order to reduce the cost of the repair process, the field of industrial production and academic research began to study the method of automatic program repair. [0003] At present, automatic program repair is still in the development stage, and the mainstream program repair method is the repair method based on the test set. The inpainting methods based on the test set are mainly divided into thre...

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
IPC IPC(8): G06F11/07G06F8/70G06K9/62G06N20/00
CPCG06F11/0793G06F8/70G06N20/00G06F18/214
Inventor 李斌唐奔孙小兵倪珍
Owner YANGZHOU UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com