Software test task assignment in agile development based on deep learning algorithms

ChenZhi Lu; Xiaoqiang Liu; Hui Guo

doi:10.1117/12.2656479

20 October 2022 Software test task assignment in agile development based on deep learning algorithms

ChenZhi Lu, Xiaoqiang Liu, Hui Guo

Proceedings Volume 12451, 5th International Conference on Computer Information Science and Application Technology (CISAT 2022); 124514C (2022) https://doi.org/10.1117/12.2656479
Event: 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 2022, Chongqing, China

Abstract

Agile development is an efficient development mode, which has a short iteration cycle and high iteration frequency. To maintain the stability and quality of software in the high-frequency iterations, test engineers require to assign and perform many test tasks while it is hard to design an accurate and efficient test assignment. In order to mitigate the problem, we designed a BERT-based test task assignment prediction model, which uses the software requirement description text and testing records as dataset to train out an accurate task assignment model. For each iteration, this model assigns the case design tasks to different testers and automatically dispatches regression test cases to the appropriate testers. As a result, it accelerates the test management process, and improves the test efficiency and quality.

Citation Download Citation

ChenZhi Lu, Xiaoqiang Liu, and Hui Guo "Software test task assignment in agile development based on deep learning algorithms", Proc. SPIE 12451, 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 124514C (20 October 2022); https://doi.org/10.1117/12.2656479

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available