Methods of synthesizing a program code using the artificial intelligence

Authors: Chuvashov V.A.
Published in issue: #5(94)/2024
DOI:
Category: Informatics, Computer Engineering and Control | Chapter: Information Technology. Computer techologies. Theory of computers and systems
Keywords: artificial intelligence, software, program code, software development, automation, neural networks
Published: 18.11.2024

The paper is devoted to the methods of synthesizing a software code using the artificial intelligence (AI). It summarizes the current research methods aimed at automating creation of a software code and provides an overview of advantages, relevance and scientific novelty in this area. The paper highlights the importance of using AI to accelerate the development process, improve the programs quality and solve the problem of shortage of the qualified specialists in software development. Modern trends are also considered, and a comprehensive analysis of current approaches is presented. The paper notes their significance and prospects for further development in software creation using the AI.

References

[1] Korablev A.Yu., Bulatov R.B. Machine learning in business. Azimuth of Scientific Research: Economics and Management, 2018, No. 2, pp. 68–72. (In Russ.).

[2] Bevzenko S.A. Application of artificial intelligence and machine learning in software development. Innovations and Investments, 2023, No. 8, pp. 187–191. (In Russ.).

[3] Sakib F.A., Khan S.H., Karim A.H.M. Extending the frontier of chatGPT:Code generation and debugging. arXiv preprint arXiv:2307.08260, 2023.

[4] Becker B.A. et al. Programming is hard-or at least it used to be: educational opportunities and challenges of ai code generation. Proceedings of the 54th ACM Technical Symposium on Computer Science Education, 2023, vol. 1, pp. 500–506. https://doi.org/10.1145/3545945.3569759

[5] Bembenek A. Combining Datalog and SAT-Based Solving in Code-Reasoning Tools. Diss. Dr. of Philosophy. Harvard, Harvard University, 2023.

[6] Gaev L.V., Krasikov I.A., Simonov I.N. Application of artificial intelligence in software development. Innovative Science, 2023, No. 3, pp. 45–46. (In Russ.).

[7] Petrov V.N. Web development: fundamentals and modern technologies. St. Petersburg, BHV-Petersburg Publ., 2019, 760 p. (In Russ.).

[8] Bozdai A.S., Artamonov D.V., Evseeva Yu.I. The use of machine learning with reinforcement in the creation of self-adaptive software. News of higher educational institutions. The Volga region. Technical Sciences, 2019, No. 3, pp. 58–68. (In Russ.). https://doi.org/10.21685/2072-3059-2019-3-5

[9] Sotnikov O.O. A paradigm shift in software product development with the transition from human labor to artificial intelligence. Alley of Science, 2020, vol. 2, No. 5 (44), pp. 967–975. (In Russ.).

[10] Kozlov A.I., Mikhailova E.P. Programming web applications in PHP and JavaScript. St. Petersburg, Piter Publ., 2019, 922 p. (In Russ.).

[11] Sawant N., Sengamedu S.H. Learning-based identification of coding best practices from software documentation. IEEE International Conference on Software Maintenance and Evolution (ICSME), IEEE, 2022, pp. 533–542. https://doi.org/10.1109/ICSME55016.2022.00073

[12] Tseplyaev A.F. The use of AI language models for the study of programming. Symbol of Science, 2023, No. 5–2, pp. 58–60. (In Russ.).

[13] Wermelinger M. Using GitHub Copilot to solve simple programming problems. Proceedings of the 54th ACM Technical Symposium on Computer Science Education, 2023, vol. 1, 2023, pp. 172–178. https://doi.org/10.1145/3545945.3569830

[14] Abadi M., Barham P., Chen J. et al. TensorFlow: A System for Large-Scale Machine Learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, 2016, vol. 16, pp. 265–283.

[15] Wang Y. et al. GypSum: learning hybrid representations for code summarization. Proceedings of the 30th IEEE/ACM International Conference on Program Comprehension, 2022, pp. 12–23. https://doi.org/10.48550/arXiv.2204.12916

[16] Jiang J. et al. APP-Miner: Detecting API Misuses via Automatically Mining API Path Patterns. 2024 IEEE Symposium on Security and Privacy (SP), IEEE, 2024, pp. 4034–4052. https://doi.org/10.1109/SP54263.2024.00043

[17] Barke S., James M.B., Polikarpova N. Grounded copilot: How programmers interact with code-generating models. CoRR arXiv, 2022, vol. 2206. https://doi.org/10.48550/arXiv.2206.15000

[18] Pengcheng Y., Graham N. A syntactic neural model for general-purpose code generation. arXiv preprint arXiv:1704.0169, 2017. https://doi.org/10.48550/arXiv.1704.01696

[19] Campbell M. Automated coding: The quest to develop programs that write programs. Computer, 2020, vol. 53, no. 2, pp. 80–82. https://doi.org/10.1109/MC.2019.2957958

[20] Owasp Top 10. URL: https://owasp.org/www-project-top-ten/ (accessed May 15, 2024).