DOI: 10.17587/prin.17.497-509

Towards the Development of a Module for Automated Construction of an Individual Educational Trajectory for IT Specialist Training using Artificial Intelligence Technologies

A. V. Samokhvalov, Cand. Sc. (Ped.), Head of Department of Mathematical Modeling and Information Technologies, samohvalov@gmail.com, D. S. Solovjev, D. Sc. (Eng.), Associate Professor, Department of Mathematical Modeling and Information Technologies, solovjevdenis@mail.ru, E. O. Korabelnikov, Student, serent2003@mail.ru, M. A. Egorov, Student, max.egorov12345@gmail.com, Derzhavin Tambov State University, Tambov, 392000, Russian Federation

Corresponding author: Alexey V. Samokhvalov, Cand. Sc. (Ped.), Head of the Department of Mathematical Modeling and Information Technologies, Derzhavin Tambov State University, Tambov, 392000, Russian Federation, E-mail: samohvalov@gmail.com

The article addresses the pressing challenge of personalizing educational programs in the field of IT specialist training. To tackle this issue, the authors propose a software module that integrates into the Moodle learning management system and interacts with an external FastAPI server and a pre-trained neural network model to automate the construction of individual educational trajectories based on an analysis of students' initial competencies. Requirements for the module are formulated, and its development is carried out using an event-driven architecture. The functional model, system architecture, and information and software components are described. The results of a comparative experimental evaluation of the module's effectiveness are presented, demonstrating its advantages over both the traditional method of manual educational trajectory determination and the approach based on automated assessment funds.

Keywords: distance learning, automated system, artificial intelligence, educational data analysis, learner distribution, Moodle, FastAPI, intelligent analysis, language testing

pp. 497—509

For citation:
Samokhvalov A. V., Solovjev D. S., Korabelnikov E. O., Egorov M. A. Towards the Development of a Module for Automated Construction of an Individual Educational Trajectory for IT Specialist Training using Artificial Intelligence Technologies, Programmnaya Ingeneria, 2026, vol. 17, no. 9, pp. 497—509. DOI: 10.17587/prin.17.497-509.

The research was carried out within the framework of implementation of the development program of Derzhavin Tambov State University "Priority-2030"

References:

1. Büchner A. Moodle 3 Administration. Third Edition, Birmingham, Packt Publishing, 2016, 492 p.
2. Vlasova I. V. The Analysis of the Possibilities of E-Learning System Moodle to Improve the Efficiency of the Learning Process in a Technical University, Vysshee Obrazovanie Segodnya, 2022, no. 9, pp. 38—40. DOI: 10.18137/RNU.HET.22.09.P. 038.
3. Chen L., Chen P., Lin Z. Artificial Intelligence in Education: A Review, IEEE Access, 2020, vol. 8, pp. 75264—75278. DOI: 10.1109/ACCESS.2020.2988510.
4. Baker R. S., Inventado P. S. Educational Data Mining and Learning Analytics, Learning Analytics, Springer, New York, NY. 2014, pp. 61—75. DOI: 10.1007/978-1-4614-3305-7_4.
5. Protasova Yu. V., Nemtinov V. A., Shipilova V. G. et al. Hybrid Educational Environment of the University’s Engineering Schools for the Implementation of Early Career Guidance for Schoolchildren, Programmnaya Ingeneria, 2024, vol. 15, no. 12, pp. 648—661. DOI: 10.17587/prin.15.648-661 (in Russian).
6. Ke Z., Ng V. Automated Essay Scoring: A Survey of the State of the Art, Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI-19), 2019, pp. 6300—6308. DOI: 10.24963/ijcai.2019/879.
7. Dolinina O. N., Kushnikov V. A. Methods and Technologies for Quality Assurance of Intelligent Decision-Making Systems, Programmnaya Ingeneria, 2021, vol. 12, no. 4, pp. 189—199. DOI: 10.17587/prin.12.189-199 (in Russian).
8. Romero C., Ventura S. Educational Data Mining and Learning Analytics: An Updated Survey, WIREs Data Mining and Knowledge Discovery, 2020, vol. 10, no. 3, article e1355. DOI: 10.1002/widm.1355.
9. Orlova E. V. Reinforcement Learning Methods and Algorithms for Modeling Individual Trajectories of Professional Development, Programmnaya Ingeneria, 2023, vol. 14, no. 12, pp. 603—615. DOI: 10.17587/prin.14.603-615 (in Russian).
10. Kiyan I. V. Automation and management principles tech­nological processes in education sphere, Energobezopasnost' i energosberezhenie, 2009, no. 4, pp. 43—47 (in Russian).
11. Karpenko S. N., Kuzenkova G. V., Shestakova N. V. et al. Creation of an Electronic Testing System Based on the Moodle LMS as an Element of the Assessment Fund, Sovremennye Informatsionnye Tekhnolo-gii i IT-Obrazovanie, 2016, vol. 12, no. 3-2, pp. 55—61 (in Russian).
12. Hohpe G., Woolf B. Enterprise Integration Patterns: Designing, Building, and Deploying Messaging Solutions, Addison-Wesley Profes­sional, 2004, 741 p.
13. Methodology of functional modeling IDEF0. Guiding document RD IDEF0-2000, Moscow, Gosstandart of Russia, 2000, 75 p. (in Russian).
14. Rybalchenko M. V. Architecture of information systems, Mos­cow, Yurait Publishing House, 2019, 91 p. (in Russian).
15. Nesterov S. A. Databases, Moscow, Yurait Publishing House, 2025, 258 p. (in Russian).
16. Wild I., Tak J. Moodle 3.x Developer's Guide, Birmingham, Packt Publishing, 2025, 368 p.
17. De Luca G. FastAPI Cookbook: Develop High-Performance APIs and Web Applications with Python, 1st ed, Birmingham, Packt Publishing, 2024, 359 p.
18. Wyte D. Pydantic in Action: Data Integrity and Schema Design for Intelligent Systems, Independently published, 2025, 339 p.