Software defect auxiliary dispatching method based on activeness of text and developer

Abstract

The invention discloses a software defect auxiliary dispatching method based on the activeness of a text and a developer. By considering text information of a defect report and the activeness of the developer, on one hand, a two-way circulating network and pooling method is utilized to extract text characteristics of the defect report, on the other hand, a one-way circulating network is utilized to extract developer activeness characteristics at a specific moment, the two-way circulating network and pooling method and the one-way circulating network are blended, a new defect dispatching model based on the activeness of the text of the defect report and the activeness of the developer is given, and therefore the problem that the auxiliary defect dispatching accuracy is low is well solved. An experiment result on four different open-source item data sets of Eclipse and the like shows that, compared with work of the same kind, the defect dispatching prediction accuracy is obviously improved.

Description

technical field [0001] The invention relates to a method for assisting software defect assignment based on text and developer activity, and belongs to the technical field of software assist defect assignment. The invention utilizes the text information including the word order relationship and the developer activity information, and based on the cyclic neural network training model, effectively enhances the ability to assign developers to new defect reports, and improves the recommendation accuracy of the auxiliary defect assignment system. Background technique [0002] In recent years, with the continuous expansion of software scale, large-scale software projects often use defect tracking systems for unified management. When a defect report is submitted to the defect tracking system, managers (senior developers or project leaders) need to browse the defect report and select the appropriate developer for it. This process of assigning developers to bug reports is called bug ...

AI Technical Summary

Problems solved by technology

First of all, natural language texts place more emphasis on the interaction between the preceding and following elements in the text sequence, and the difference in the order of elements will lead to changes in the meaning of the text, while the existing defect assignment methods do not consider word order information

Secondly, most of the existing work ignores the consideration of developer activity, which makes the performance of defect report assignment prediction for developers with similar characteristics poor.

Images