Software defect prediction method and device based on multi-model selection and storage medium

A software defect prediction and multi-model technology, applied in software testing/debugging, computer components, error detection/correction, etc., can solve problems affecting software reliability and stability, affecting software development, etc.

Pending Publication Date: 2022-05-27
HANGZHOU QULIAN TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Software defects will seriously affect the development of software. If not detected and corrected in time, software defects will be further accumulated or transmitted, thus affecting the reliability and stability of the software.

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
  • Software defect prediction method and device based on multi-model selection and storage medium
  • Software defect prediction method and device based on multi-model selection and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention mainly comprises the following steps:

[0028] Step 1) Use the first data collection mechanism to collect software module flow data, update the confusion matrix and sample mean statistic at the same time, and incrementally train the random forest model M0 using each newly arrived software module flow data. Compared with the single classifier model, the random forest model has better generalization ability by retaining multiple decision trees. Among them, software module flow data has the characteristics of concept drift and category imbalance.

[0029] Step 2) The updated sample mean statistic is used in the concept drift detection of the flow data of the software module, thereby obtaining the data blocks D1 and D2. Concept drift detection using ADWIN method. First, if the mean value of the software module flow data reaches a warning level, the first data collection mechanism stops collecting the software module flow data. And at the same time c...

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 software defect prediction method and equipment based on multi-model selection and a storage medium. The method comprises the following steps: training one by one in an incremental learning mode to obtain a random forest model M0; then, detecting the dynamism of a sample mean value by using an ADWIN concept drift detection mechanism, and obtaining data blocks D1 and D2 by using a data collection mechanism; thirdly, the SMOTE algorithm is used for balancing category distribution in the D1 and the D2, and a data block D1'and a data block D2 'are obtained respectively; and for the obtained data blocks D1, D2, D1 'and D2', respectively establishing four classification models M1, M2, M3 and M4 based on a random forest model, and selecting a model with the best performance from five software defect flow data classification models M0, M1, M2, M3 and M4 as a final software defect prediction model M. And finally, predicting the category of the software defect data based on the M classification model of the random forest so as to realize software defect prediction.

Description

technical field [0001] The invention relates to a software defect prediction method, equipment and storage medium based on multi-model selection. Background technique [0002] With the rapid development of technologies such as big data, cloud computing, and parallel computing, the corresponding application scenarios are becoming more and more abundant, such as transportation, commerce, and medical care. At the same time, the development of high technology has also accelerated the emergence and development of various software. In the process of software development, it is necessary to strictly follow user requirements, otherwise the software development process is prone to errors. Such problems that affect the normal operation of software or programs are called software defects. Software defects will seriously affect the development of software. If not detected and corrected in time, software defects will be further accumulated or transmitted, thereby affecting the reliabili...

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): G06F11/36G06K9/62
CPCG06F11/3684G06F11/3688G06F11/3692G06F18/24323Y02D10/00
Inventor 邵羽詹士潇曾磊匡立中张帅
Owner HANGZHOU QULIAN TECH CO LTD
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