Topic model-based software defect detection method and system

A software defect, topic model technology, applied in the field of security detection, to achieve the effect of enhancing security and reliability, and improving quality

Pending Publication Date: 2019-11-29
EAST CHINA INST OF COMPUTING TECH
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, the core idea of ​​the mainstream static source code defect detection method is to search and match, whether it is lexical, grammatical or semantic level, it is a matching process at different levels, so that it is impossible to make similar but not identical defects was detected

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
  • Topic model-based software defect detection method and system
  • Topic model-based software defect detection method and system
  • Topic model-based software defect detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0036] A method for software defect detection based on a topic model provided by the present invention includes:

[0037] Space construction step: make the static source code generate the corresponding abstract syntax tree, map the abstract syntax tree to the digital feature vector space, and construct the original matrix;

[0038] Semantic analysis step: build a defect pattern library, perform singular matrix decomposition on the defect pattern library to reduce dimensionality, form a reconstruction ma...

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 provides a topic model-based software defect detection method and system. The topic model-based software defect detection method comprises the steps: enabling a static source code to generate a corresponding abstract syntax tree in space construction, enabling the abstract syntax tree to be mapped to a digitalized feature vector space, and constructing an original matrix; in semanticanalysis, constructing a defect mode library, carrying out singular matrix decomposition dimensionality reduction on the defect mode library to form a reconstructed matrix, carrying out cosine similarity calculation on the reconstructed matrix, and obtaining a defect detection result; and adding a machine learning algorithm for processing a natural language into software defect detection, and detecting hidden defects from semantic-level detection codes, so that the means of high-security software code defect detection is enriched, and whether a given code has defects similar to known defectsin a defect mode library or not is automatically detected, and the quality of software is further improved.

Description

technical field [0001] The invention relates to the technical field of security detection, in particular to a method and system for software defect detection based on a topic model. Background technique [0002] At present, the core idea of ​​the mainstream static source code defect detection method is to search and match, whether it is lexical, grammatical or semantic level, it is a matching process at different levels, so that it is impossible to make similar but not identical defects was detected. It has become a new idea to use machine learning methods in static source code defect detection. Due to the innate intelligence factors of the topic model algorithm in machine learning, it has the potential semantic understanding ability, so it has good development potential from semantics. [0003] The prior art related to this application is the patent document CN 105204997B, which discloses a software defect detection method and device. Based on the specified error type, a ...

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 Applications(China)
IPC IPC(8): G06F11/36G06F8/41G06N20/00
CPCG06F11/3684G06F11/3688G06F8/42G06F8/425G06N20/00
Inventor 张俊博高元钧徐冬晨陆平
Owner EAST CHINA INST OF COMPUTING TECH
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