M.A. Panov1, D.T. Imranova2, S.A. Krasilov3

1–3 Ural State Economic University (Ekaterinburg, Russia)

1 panov79@ya.ru, 2 imranovadt@gmail.com, 3 sergey.krasilov.dev@gmail.com

The problem posed in this study is the need to assess the prospects for using fully automated methods for developing code testing tools and their relationship with traditional approaches based on developer participation. This is caused by a number of issues and problems, such as efficiency, cost, speed of development and reliability of the final software product. The purpose of the study was to evaluate the prospects for using fully automated methods for developing code testing tools and their relationship with traditional approaches based on developer participation. During the work, a reference result of a request to a neural network was generated using the competencies of an experienced Java developer. An experiment was conducted, the data obtained from which was sufficient to form an average result of code coverage with unit tests using neural network queries. Comparisons were made and the average results of the developer and the neural network were calculated, and conclusions were drawn. The results of this study can help developers determine the most effective methods for testing and implementing automation, which will speed up the software development process. Using more reliable and efficient testing methods can improve the quality of the final product and reduce the number of errors and defects.

Panov M.A., Imranova D.T., Krasilov S.A. Research and development of methods for assessing and optimizing information processes based on the exchange of information between the user and the neural network when writing Unit tests. Neurocomputers. 2024. V. 26. № 3. Р. 22-35. DOI: https://doi.org/10.18127/j19998554-202403-03 (In Russian)

1. Dobrovolskaya E.A., Yakhin I.E. Cognitive modeling and neural networks. Materials of the II International Scientific the forum "Step into the future: artificial intelligence and the digital economy. Revolution in management: a new digital economy or a new world of machines." M.: State University of Management. 2018. V. 3. P. 135–141. (In Russian)
2. Knyazeva E.G., Kurbakova S.N., Murog I.A. Specific character of linguistic imagineering in advertising. Questions of psycholinguistics. 2018. № 37. P. 36–49. DOI 10.30982/2077-5911-2018-37-3-36-49. (In Russian)
3. Panov M.A. The impact of big data on the global stock market. Collection of materials of the national scientific forum of undergraduates, graduate students and young scientists "Life-changing science". Vladivostok: Vladivostok State University. 2023. P. 239–243. (In Russian)
4. Dobrina M.V. Methods of data analysis using artificial neural networks. Neurocomputers. 2023. V. 25. № 4. Р. 45–53. DOI 10.18127/j19998554-202304-06 (In Russian)
5. Gokul Y., Ramalingam M., Chemmalar S.G., Supriya Y., Gautam S., Praveen K.R.M., Deepti R.G., Rutvij H.J., Prabadevi B., Weizheng W., Athanasios V.V., Thippa R.G. GPT (Generative Pre-trained Transformer) – A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions. [Electronic resource] – Access mode: https://arxiv.org/pdf/2305.10435, date of reference 16.12.2023.
6. Kumratova A.M., Morozova N.V., Vasilenko A.I., Kogai I.E. Analysis of possibilities of the GPT-3 neural network model and ways of its application in production. Bulletin of the Adygea State University. Series 4: Natural, mathematical and Technical sciences. 2023. № 1(316). P. 80–85. DOI 10.53598/2410-3225-2023-1-316-80-85. (In Russian)
7. Galassi A., Lippi M., Torroni P. Attention in Natural Language Processing. IEEE Transactions on Neural Networks and Learning Systems. 2021. V. 32. № 10. P. 4291–4308. DOI 10.1109/TNNLS.2020.3019893.
8. Chou J.-S., Chong P.-L., Liu C.-Y. Deep learning-based chatbot by natural language processing for supportive risk management in river dredging projects. Engineering Applications of Artificial Intelligence. 2024. V. 131. P. 107744. DOI 10.1016/j.engappai.2023.107744.
9. Otter D.W., Medina J.R., Kalita J.K. A Survey of the Usages of Deep Learning for Natural Language Processing. IEEE Transactions on Neural Networks and Learning Systems. 2021. V. 32. № 2. P. 604–624. DOI 10.1109/TNNLS.2020.2979670.
10. Sirbiladze K.K. ChatGPT and its possibilities for promoting companies' products. Practical marketing. 2023. № 7(313). P. 47–52. DOI 10.24412/2071-3762-2023-7313-47-52. (In Russian)
11. JDK 17 Documentation. [Electronic resource] – Access mode: https://docs.oracle.com/en/java/javase/17/, date of reference 16.12.2023.
12. GitHub – spring-projects/spring-petclinic: A sample Spring-based application. [Electronic resource] – Access mode: https://github.com/spring-projects/spring-petclinic, date of reference16.12.2023.
13. Brown T.B., Mann B., Ryder N., Subbiah M., Kaplan J., Dhariwal P., Neelakantan A., Shyam P., Sastry G., Askell A., Agarwal S., Herbert-Voss A., Krueger G., Henighan T., Child R., Ramesh A., Ziegler D.M., Wu J., Winter C., Hesse C., Chen M., Sigler E., Litwin M., Gray S., Chess B., Clark J., Berner C., McCandlish S., Radford A., Sutskever I., Amodei D. Language models are few-shot learners. [Electronic resource] – Access mode: https://arxiv.org/pdf/2005.14165, date of reference 16.12.2023.
14. Ziegler D.M., Stiennon N., Wu J., Brown T.B., Radford A., Amodei D., Christiano P., Irving G. Fine-Tuning Language Models from Human Preferences. [Electronic resource] – Access mode: https://arxiv.org/pdf/1909.08593v1, date of reference 16.12.2023.
15. Keskar N.S., McCann B., Varshney L.R., Xiong C., Socher R. Ctrl: A Conditional Transformer Language Model for Controllable Generation. [Electronic resource] – Access mode: https://arxiv.org/pdf/1909.05858, date of reference 16.12.2023.
16. Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., Kaiser L., Polosukhin I. Attention Is All You Need. [Electronic resource] – Access mode: https://arxiv.org/pdf/1706.03762, date of reference 16.12.2023.
17. Shidaeva R.Z., Magomedov I.A. ChatGPT: applications from the possibility. Materials of the III All-Russian Scientific and Practical conference "Digital Era". Grozny: A.A. Kadyrov Chechen State University. 2023. P. 235–237. DOI 10.36684/93-1-2023-235-237. (In Russian)
18. Jaimovitch-López G., Ferri C., Hernández-Orallo J., Martínez-Plumed F., Ramírez-Quintana M.J. Can language models automate data wrangling? Machine Learning. 2023. V. 112. № 6. P. 2053–2082. DOI 10.1007/s10994-022-06259-9.
19. Krasochkin S.G. How ChatGPT differs from current neural networks. Eurasian Union of Scientists. Series: technical and physical and mathematical sciences. 2023. № 4(107). P. 30–35. DOI 10.31618/ESU.2413-9335.2023.1.107.1798. (In Russian)
20. Lyubimova T.V., Evseenko I.N., Rymar A.N. ChatGPT technology. University science. 2023. № 2(16). P. 174–177. (In Russian)
21. Namiot D.E., Zubareva E.V. About the work of the AI Red Team. International Journal of Open Information Technologies. 2023. V. 11. №10. P. 130–139. (In Russian)
22. Ayupov R.H., Baltabaeva G.R. Application directions of artificial intelligence methods and tools in education. Internauka. 2023.
    № 13-5(283). P. 44–47. DOI 10.32743/26870142.2023.13.283.354779.
23. Nasirov E.F., Kirillov D.S., Mertins G.R., Molostov D.D. UNIT testing. Collection of articles XXVI International scientific and practical Conference. "Science and Innovation in the 21st century: current issues, discoveries and achievements". Penza: Science and Education. 2021. P. 96–98. (In Russian)
24. Spring Boot. [Electronic resource] – Access mode: https://spring.io/projects/spring-boot, date of reference 16.12.2023.
25. JUnit 5 User Guide. [Electronic resource] – Access mode: https://junit.org/junit5/docs/current/user-guide/, date of reference 16.12.2023.
26. Mockito framework site. [Electronic resource] – Access mode: https://site.mockito.org/, date of reference 16.12.2023. 
27. Spadini D., Aniche M., Bruntink M., Bacchelli A. Mock objects for testing java systems. Empirical Software Engineering. 2019. V. 24. № 3. P. 1461–1498. DOI 10.1007/s10664-018-9663-0.
28. API Reference – OpenAI API. [Electronic resource] – Access mode: https://platform.openai.com/docs/api-reference/introduction, date of reference 16.12.2023.