A code defect detection method and device based on deep learning

A code defect and deep learning technology, applied in error detection/correction, software testing/debugging, instrumentation, etc., can solve problems that are difficult to judge, affect the efficiency of code detection and review, and false positives

Active Publication Date: 2019-03-01
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF6 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] A large number of code defect detection tools currently exist. Due to the limitation of detection technology, the detection results of these tools usually contain a large number of false positives. Since it is impossible to know

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
  • A code defect detection method and device based on deep learning
  • A code defect detection method and device based on deep learning
  • A code defect detection method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

test Embodiment C1

[0083] S135, the test case C 1 , C 2 ,...C j Convert to the corresponding feature vector as the training data set;

[0084] S136. For defect type D i , train the comparison result as the corresponding data label, and generate the tool T k For defect D i The detection ability evaluation model M(k,i) of .

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 relates to a code defect detection method and device based on deep learning, and the method comprises the steps: selecting a plurality of code defect detection tools, carrying out the detection of detected codes, and correspondingly generating a plurality of detection results; converting the detected code into a feature vector of the detected code through a preset conversion method,wherein the feature vector comprises a structural feature and a semantic feature of the detected code; inputting the feature vectors into evaluation models corresponding to the code defect detection tools respectively, and outputting confidence coefficients of the code defect detection tools for defect detection results of the detected codes respectively; and by combining the detection result of the detection tool on the detected code, whether the code really has a certain defect or not can be effectively judged, the problem of relatively high misinformation in the existing code defect detection can be solved, and the work efficiency of code review is effectively improved.

Description

technical field [0001] The present invention relates to the technical field of detection, in particular to a code defect detection method and device based on deep learning. Background technique [0002] Code defect detection applies code analysis technology and is an important means to ensure software quality and reliability. Analysis methods are usually divided into static analysis and dynamic analysis. Static analysis methods do not need to run the program, and analyze and evaluate the structure and content of the software at the binary or source code level, so that defects in the program code can be found earlier. The dynamic analysis method uses the dynamic analysis method to obtain and analyze the dynamic information generated during the running of the program by running the program to be tested, so as to judge its runtime semantic properties. In the field of static analysis, there are a variety of open source static analysis tools, including FindBugs, JLint, and Infer...

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): G06F11/36
CPCG06F11/3668
Inventor 计卫星高玉金王一拙杨恬石剑君石峰
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap