SIA OpenIR  > 工业控制网络与系统研究室
Alternative TitleStatic analysis and neural network based software failure prediction technique construction method
杨顺昆; 苟晓冬; 黄婷婷; 郑征; 于海斌; 徐皑冬; 王锴; 吴玉美; 李国旗; 路云峰; 姜博; 李大庆
Rights Holder北京航空航天大学 ; 中国科学院沈阳自动化研究所
Patent Agent北京慧泉知识产权代理有限公司 11232
Other AbstractThe invention provides a static analysis and neural network based software failure prediction technique construction method. The construction method includes the following steps: 1, collecting valid failures of diagnosed software, adding the valid failures into a created failure case library; 2, counting the frequency of historical versions of valid failures of the software; 3, using a static analysis tool to scan a software source code, and outputting a complexity metric; 4, performing correlation analysis, and calculating the significance level of the failure frequency and the metric; 5, selecting a complexity metric having significant correlation with the failure frequency; 6, constructing a network training input output matrix and a prediction input matrix; 7, constructing a BP neuralnetwork; 8, completing network training, and constructing a failure prediction system; and 9, performing neural network prediction, and predicting the number of a new version of failures. Constructionof the static analysis and BP neural network based software failure prediction technique can be completed through the above steps. The construction method can help a developer to predict possible software failures, and has practical value.
PCT Attributes
Application Date2017-11-13
Date Available2020-08-25
Application NumberCN201711113909.8
Open (Notice) NumberCN107832219A
Contribution Rank2
Document Type专利
Recommended Citation
GB/T 7714
杨顺昆,苟晓冬,黄婷婷,等. 基于静态分析和神经网络的软件故障预测技术的构建方法[P]. 2018-03-23.
Files in This Item:
File Name/Size DocType Version Access License
CN201711113909.8.pdf(1121KB)专利 开放获取CC BY-NC-SAView Application Full Text
CN201711113909.8授权.p(1068KB)专利 开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[杨顺昆]'s Articles
[苟晓冬]'s Articles
[黄婷婷]'s Articles
Baidu academic
Similar articles in Baidu academic
[杨顺昆]'s Articles
[苟晓冬]'s Articles
[黄婷婷]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[杨顺昆]'s Articles
[苟晓冬]'s Articles
[黄婷婷]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: CN201711113909.8.pdf
Format: Adobe PDF
File name: CN201711113909.8授权.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.