Two-stage discrimination defect report severity prediction method based on Spacy word vector

Abstract

The invention provides a two-stage discrimination defect report severity prediction method based on a Spacy word vector, and the method comprises the following steps of: firstly, searching a historical defect report from a defect tracking system where a project is located, extracting corresponding contents of a description information summery attribute and a severity degree severity attribute to obtain a defect report training data set, and then performing preprocessing and generating a corresponding vector; and finally, executing a two-stage discrimination process to construct a severity prediction model. The method has the advantages that: the Naive Bayes algorithm is adopted in the two-stage discrimination process, the algorithm is easy to implement and good in effect, and the accuracyof the prediction model can be guaranteed; according to the severity prediction model, the same data is applied twice, so that on the one hand, secondary utilization of the same batch of data is realized, and the performance of the model is improved; and on the other hand, two-stage discrimination is realized, so that the pressure of the multi-classification Naive Bayes prediction model can be reduced under the condition of correct large-class classification, and the accuracy of the prediction model is further improved.

Description

technical field [0001] The invention relates to the technical field of software quality assurance, in particular to a two-stage discrimination defect report severity prediction method based on Spacy word vectors. Background technique [0002] Software defects and software development are inseparable like twins, which will affect software quality to a greater or lesser extent, and need to be repaired by technicians in a timely manner, and software defect repair operations run through the entire software development life cycle. Therefore, in order to ensure the quality of the developed software, how to improve the efficiency of software defect repair is a very critical issue. [0003] At present, in order to solve this problem, that is, to quickly locate and repair defects in the software development process, many large-scale projects use a software defect report tracking system to record defect information. The severity of software defect reports in the defect report trackin...

AI Technical Summary

Problems solved by technology

When further classifying defect reports, the traditional classification method represented by manual qualitative classification by developers has the disadvantages of being greatly affected by personal subjective factors, time-consuming, low efficiency, and high cost of time and energy. Therefore, it has become a challenge to find an automated alternative top priority

[0004] In recent years, in the field of software defect report severity prediction, most researchers have used classification or regression methods to predict the severity of software defect reports at one time. This method only uses the training set once to build a corresponding severity prediction model. , there is a result that the predictive model does not perform well

Images