Article 4224

Title of the article

A methodology for assessing the quality of software products that include artificial intelligence in the tasks of document classification and recognition 

Authors

Aleksandr N. Milovanov, Candidate of engineering sciences, systems analyst, “Logstrim” LLC (building 1, 15 Krzhizhanovsky street, Moscow, Russia), E-mail: amilovanov@logstream.ru
Aleksey A. Mistyukov, engineering director, “Logstrim” LLC (building 1, 15 Krzhizhanovsky street, Moscow, Russia), E-mail: amistyukov@logstream.ru
Dmitriy A. Trusov, chief executive, “Logstrim” LLC (building 1, 15 Krzhizhanovsky street, Moscow, Russia), E-mail: dtrusov@logstream.ru
Aleksey A. Korshunov, testing specialist, “Logstrim” LLC (building 1, 15 Krzhizhanovsky street, Moscow, Russia), E-mail: akorshunov@logstream.ru 

Abstract

The article presents the results of research conducted by the Russian IT company “Logstrim” to assess the quality of software products that include artificial intelligence in document classification and recognition tasks. During the research, a methodology was developed that allows us to evaluate the quality of software products that include artificial intelligence in document classification and recognition tasks. The developed methodology was used to evaluate the quality of the “ECO-DOC” software package, which includes the YOLO v5 neural network service, in document classification and recognition tasks. The results of testing and quality assessment of the ECO-DOC software package are presented. 

Key words

methodology, software package quality assessment, neural network, artificial intelligence system, “ECO-DOC” software package, quality characteristics, quality indicators, quality indicator elements, functional correctness metrics 

Download PDF
For citation:

Milovanov A.N., Mistyukov A.A., Trusov D.A., Korshunov A.A. A methodology for assessing the quality of software products that in-clude artificial intelligence in the tasks of document classification and recognition. Povolzhskiy region. Tekhnicheskie nauki = University proceedings. Volga region. Engineering sciences. 2024;(2):58–72. (In Russ.). doi: 10.21685/2072-3059-2024-2-4

 

Дата создания: 04.10.2024 11:13
Дата обновления: 17.10.2024 14:33
Сайт использует сервис аналитики MyTracker, оставаясь на сайте, вы соглашаетесь на размещение файлов cookie на вашем устройстве. Продолжая посещать сайт, вы соглашаетесь с политикой "обработки персональных данных" для согласия нажмите:   Согласен!