Software defect predication method based on cost sensitivity and semi-supervision

Abstract

The invention relates to a software defect predication method based on cost sensitivity and semi-supervision. The software defect predication method comprises the following steps: S1, collecting a source code file of software to be predicated through a version control tool; S2, extracting a measurement element value from the source code file, wherein the source code file obtained by S1 is composed of I modules; S3, obtaining a sampling result set through a measurement element value selecting module in a sampling manner; S4, constructing a training set by a labeled sampling result set and a label-free sampling result set; S5, extracting a target function and solving a classification function enabling the target function to be minimum; and S6, predicating a module to be predicated through the classification function and outputting a predicated result. The method provided by the invention fuses semi-supervision and cost sensitivity thoughts to construct a software defect predication model and two problems in software defect predication that defect data is difficult to obtain and types are not balanced are solved; and the accuracy of the predicated result is extremely improved.

Description

technical field [0001] The invention relates to software prediction, in particular to a software defect prediction method based on cost-sensitive semi-supervision. Background technique [0002] However, with the increasing scale and complexity of software, and the market's demand for shortening the software development cycle as much as possible, the difficulty of predicting and controlling software quality is gradually increasing, and the cost is also increasing. Moreover, with the development of software technology so far, whether it is a small program or a large system, defects in software have become an indispensable by-product in the software development process, and there is no inspection or verification method that can find and eliminate all defects. Defects. Worse, the later a software defect is discovered, the more expensive it is to fix. Therefore, how to effectively and fully test the software and find the defects in the software as comprehensively as possible un...

AI Technical Summary

Problems solved by technology

[0005] 1) Relying on a large amount of historical defect information, it is difficult or even impossible to obtain a certain amount of label data for learning in practical applications, and the prediction accuracy is not high without enough learning samples

[0006] 2) Defect data has obvious class imbalance characteristics, which makes the recall rate of traditional machine learning methods not high on the problem of defect prediction

[0007] 3) More and more software metrics are introduced into the field of defect prediction, which can easily cause the disaster of dimensionality

Images