Software defect priority prediction method based on improved support vector machine

Abstract

A software defect priority prediction method based on an improved support vector machine is mainly characterized in that an improved support vector machine model is used for modeling defect priority prediction and judging and predicting defect report processing priority. The software defect priority prediction method includes the steps: firstly, selecting solved, closed and determined error report as training data; secondly, extracting needed characteristics; thirdly, giving a sampling weight to each sample and training a classifier to classify the samples by the aid of the support vector machine on the samples; fourthly, redistributing weight vectors by the aid of obtained error rate in the manner of distributing larger weights to mistakenly classified samples and distributing smaller weights to correctly classified samples; and fifthly, sequentially iterating in the manner to finally obtain a strong classifier equal to the weighted sum of a plurality of weak classifiers. The classifiers are trained by means of machine learning, so that defect priority is automatically determined, and consumption of staff and cost is reduced.

Description

technical field [0001] The invention relates to a defect report priority prediction method, which mainly adopts an improved support vector machine model as the defect priority prediction model to judge and predict the defect report processing priority, and belongs to the field of software testing. Background technique [0002] We are already in the digital age. For more than half a century, with the rapid development of computer technology, information technology has penetrated into all fields of human activities. The popularization of database, data warehouse and Internet technology makes the scale of data we need to process more and more huge. These data are very valuable resources. However, while possessing massive amounts of data, our extraction of data knowledge still largely remains at the level of query and simple retrieval in the past. The carrier of information is data, but data itself is not equal to information. There are a lot of "treasures" behind the surge o...

AI Technical Summary

Problems solved by technology

However, there are not many methods for predicting the priority of errors. Most of them are aimed at predicting the number of errors and locating errors in the code [4], and some are predicting the severity of errors.

However, the priority of the error is also very important and cannot be ignored. It directly determines the order of repairing the error. Delaying the repair of the error will cause a loss that cannot be underestimated.

Images