Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Severity prediction method based on part-of-speech information in defect report abstract

A defect reporting and severity technology, applied in instruments, biological neural network models, electrical digital data processing, etc., can solve problems affecting the performance of prediction models, uneven data set quality, and difficulty in ensuring data set scale, etc. Prediction effect, easy principle, small data volume requirement

Pending Publication Date: 2021-06-22
NANTONG UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in actual application scenarios, problems such as uneven data set quality and difficulty in ensuring the size of the data set have affected the further improvement of the performance of the prediction model.

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
  • Severity prediction method based on part-of-speech information in defect report abstract
  • Severity prediction method based on part-of-speech information in defect report abstract
  • Severity prediction method based on part-of-speech information in defect report abstract

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] See Figure 1 to 6 The present invention provides a technical solution as a severity prediction method of the morbid information based on the defect report summary:

[0038] Step (1) From the Defect Report Tracking System, the defect report that has been marked severity and severity is Blocker, critical, major, minor, trivial, and enhancement, which will be severely reported by Block, critical, and Major's defect report corresponding to The degree unified is set to "severe" type, and the severity of minor, trivial, and enhancement corresponds to the "non-severe" type, which is a summary of the collection of defect reports, including: word, The pause word removal is restored to the word shape, resulting in the word root form; due to the large amount of total data, the top 5 display is selected, as shown in Table 1:

[0039] Table 1 Some of the words (top 5)

[0040]

[0041] Step (2) Based on the ONTONOTES 5 corpus, the Glove Common crawl corpus, and the spocuous neural net...

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 severity prediction method based on part-of-speech information in a defect report abstract, which realizes similar or better prediction performance by using a small amount of data, and further utilizes a software defect report to track a defect report contained in a large project stored on a system platform, and performs rapid and high-accuracy prediction of the severity of the software defect report. The invention has the beneficial effects that firstly, text preprocessing is performed on abstract attributes in the defect report to obtain segmented words in a root form; based on a large-scale text corpus, a convolutional neural network model is used for training, a Spacy model containing part-of-speech of each segmented word and a similarity adjacent matrix between words is obtained, the segmented words are further screened and randomly extracted, a similar data expansion data set is generated, and finally, the severity of a defect report is predicted. And compared with other prediction methods, better performance is realized by using less data.

Description

Technical field [0001] The present invention relates to the field of software quality assurance, and more particularly to a severity prediction method of the morbid information based on the defect report summary. Background technique [0002] Developers are impossible to develop projects that have not been defective. As developers are not possible to find out what it exists before discovering a defect. Because of this, we must fully guarantee the code quality and user experience of the project. Developers must invest enough human resources to ensure that each defect that affects code quality or user experience can be fixed in time. In order to more efficiently track and repair project defects, the current practice in the industry is to establish a defect report tracking system. The user will write the defects that the defects are reported to the defect report tracking system, and the severity of the defect is required to mark the severity of the defect to determine the priority o...

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): G06F40/284G06F40/237G06N3/04
CPCG06F40/284G06F40/237G06N3/045Y02P90/30
Inventor 田丹陈雪娇林浩陈翔贾焱鑫葛骅
Owner NANTONG UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com