Article 1321

Title of the article

The concept of a virtual programmer in a self-adaptive organization management system 

Authors

Aleksandr S. Bozhday, Doctor of engineering sciences, associate professor, professor of the sub-department of computer-aided design system, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: bozhday@yandex.ru
Yuliya I. Evseeva, Candidate of engineering sciences, associate professor of the sub-department of computer-aided design system, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: shymoda@mail.ru
Aleksey A. Gudkov, Candidate of engineering sciences, associate professor, associate professor of the sub-department of computer-aided design system, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: alexei-ag@yandex.ru 

Index UDK

004.4 

DOI

10.21685/2072-3059-2021-3-1 

Abstract

Background. The article is devoted to the problem of creating a specialized component of an organization’s management system, capable of solving the following tasks associated with automated revision and maintenance of such a system: generate program modifications based on a technical specification drawn up in a natural language; automatically transfer the source code of the system and custom modifications created for it to new versions of programming languages, libraries and application programming interfaces; endow the generated software components with the property of self-adaptability - that is, the ability to flexibly adjust to the needs of each category of users. Since the functions that this component should implement are currently performed by programmers, the authors of the article decided to call the concept of its development the concept of a virtual programmer. Materials and methods. Methods of intelligent text recognition and program code generation based on neural network technologies are used as the main methods. Results. The main results of the work should include: review and classification of existing software management systems of the organization; the concept of a virtual programmer, the main purpose of which is to determine exactly what functions and how a specialized component of artificial intelligence of a software system should be performed, designed for its automatic completion; description of the learning process of a component (virtual programmer) of automatic code generation based on a technical assignment written in a natural language. Conclusions. The practical implementation of the concept proposed by the authors will reduce the resource costs for modifying the organization’s management systems and improve the quality of their functioning. 

Key words

self-adaptive software, virtual programmer, software engineering, neural networks, artificial Intelligence, automatic code generation 

Download PDF
References

1. Abramova E.A., Voynova M.E. CRM system as a factor in the successful implementation of business processes in a modern company. Problemy ekonomiki, finansov i upravleniya proizvodstvom = Issues of economics, finance and production management. 2019;(44):42–46. (In Russ.)
2. Nechaeva M.A., Zimina L.V. The features of customer relationship management information systems. Ekonomicheskaya sreda = Economic environment. 2016;(1):59–64. (In Russ.)
3. Magomedov R.M. Analysis of the possibilities of using the Saleforze CRM platform in the Russian market. Samoupravlenie = Self-government. 2021;(1):312–314. (In Russ.)
4. Pashaeva S.S., Kochetkova N.V. Comparative analysis of domestic and foreign programs used in management. Sovremennye nauchnye issledovaniya v sfere ekonomiki: sb. rezul'tatov nauch. Issledovaniy = Modern scientific research in the field of economics: collection of scientific research’s results. Kirov, 2018:821–824. (In Russ.)
5. Naumova O.G., Elistratova O.V., Gerasimenko N.A. Bitrix24 as an innovation and convenient service for students’ scientific activities. Sistema menedzhmenta kachestva: opyt i perspektivy = Quality management system: experience and perspectives. 2016;(5):262–265. (In Russ.)
6. Shin R., Brocksshmidt M., Allamanis M., Polozov O. Program Synthesis with Learned Code Idioms. ICLR 2019 Conference Withdrawn Submission. 2019;(4):1–12.
7. Allamanis M., Sutton C. Mining idioms from source code. FSE 2014: Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering. Guimaraes, 2014:472–483
8. Gelman A., Carlin J.B. [et al.]. Bayesian data analysis. London: CRC Press, 2013:676.
9. Gershman S.J., Blei D.M. A tutorial on Bayesian non-parametric models. Journal of Mathematical Psychology. 2012;(56):1–12.
10. Neelakantan A., Le Q.V., Abadi M. [et al.]. Learning a natural language interface with neural programmer. Proceedings of the 5th International Conference on Learning Representations (ICLR). 2017:1332–1342.
11. Bozhday A.S., Evseeva Yu.I. The method of reflexive self-adaptation of software systems. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki = University proceedings. Volga region. Engineering sciences. 2018;(2):74–86. (In Russ.)
12. Bershadskiy A.M., Bozhday A.S., Evseeva Yu.I., Gudkov A.A. Self-adaptation of training software systems based on monitoring the information environment. Otkrytoe obrazovanie = Open education. 2019;(3):33–41. (In Russ.)
13. Bozhday A.S., Evseeva Yu.I., Artamonov D.V. Using reinforcement learning to build self-adaptive software. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki = University proceedings. Volga region. Engineering sciences. 2019;(3):56–68. (In Russ.)

 

Дата создания: 09.12.2021 08:41
Дата обновления: 09.12.2021 09:19