Supercharge Your Innovation With Domain-Expert AI Agents!

Software defect report classification method fusing multivariate text information and report intention

A technology for text information and software defects, applied in text database clustering/classification, software testing/debugging, unstructured text data retrieval, etc. Intent, low performance, etc.

Pending Publication Date: 2022-04-08
NORTHEAST DIANLI UNIVERSITY
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, some scholars are concerned about the quality of defect reports and the imbalance of categories of data sets.
[0004] However, a large number of existing studies have not considered the reporting intent when classifying defect reports, which leads to the low performance of their methods.

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 report classification method fusing multivariate text information and report intention
  • Software defect report classification method fusing multivariate text information and report intention
  • Software defect report classification method fusing multivariate text information and report intention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to make the object, technical solution and advantages of the present invention clearer, the present invention 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 invention, not to limit the present invention.

[0044] The method frame that the present invention proposes is as figure 2shown. The framework considers both the textual information of the defect report and the intent of the report. First, after the software defect report is submitted, the method will store information such as summary, project, component, reporter, intent, etc. in CSV file format; Preprocess the data in CSV format; on this basis, use BERT to extract the text information of the report summary, and then use the TF-IDF method to extract other features of the report, including the intent of the report, and then generate a feature...

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 software defect report classification method fusing multivariate text information and report intention, which comprises the following steps of: after a software defect report is submitted, storing information such as abstract, project, component, reporter and intention in a CSV file format; preprocessing the data in the CSV format through methods of standardization, marking, stop word removal and word drying; extracting text information features of the report abstract by using BERT, extracting other features of the report by using a TF-IDF method, including the intention of the report, and further generating a feature matrix; the feature matrix is normalized to form a training set, and the training set is respectively input into five classifiers, including K-NN, NB, LR, SVM and RF, for establishing a classification model; and selecting one classification model with the best performance from the five classification models to realize classification of defect reports. According to the method, text mining, natural language processing and machine learning technologies are combined, and reports are divided into error reports and non-error reports.

Description

technical field [0001] The invention relates to defect report classification technology, in particular to a software defect report classification method that combines multivariate text information and report intent. Background technique [0002] At present, as the main activity in the later maintenance stage of software engineering, defect repair has an important impact on software quality assurance. In recent years, with the vigorous development of the software engineering industry, the complexity of the architecture of the software system and the capacity of the code have reached a level that is difficult for developers to understand and manage. This trend has inevitably led to a large number of defects in the software system development process. In order for the system to run normally, it is very necessary to fix these defects. The most common aid that developers use when fixing bugs is the bug report. The defect report describes the defects in the software system in th...

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): G06F16/35G06F11/36G06F40/289
Inventor 孟凡奇王雪松王敬东成文莹季王鑫
Owner NORTHEAST DIANLI UNIVERSITY
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