FURTHER DEVELOPMENT OF THE ONLINE PLATFORM FOR PREPARATION FOR THE ALL-RUSSIAN TEST ASSIGNMENT (VPR)

Tatyana V. Skvortsova; P. Piskursky; O. Avilova

doi:doi:10.58168/MIST2026_502-510

Home / Conferences / MODELING INFORMATION SYSTEMS AND TECHNOLOGIES – 2026 / MODELING INFORMATION SYSTEMS AND TECHNOLOGIES – 2026 : Proceedings of the International Scientific and Practical Conference dedicated to the 5th anniversary of the Faculty of Computer Science and Technology, Voronezh, Marth 30, 2026

FURTHER DEVELOPMENT OF THE ONLINE PLATFORM FOR PREPARATION FOR THE ALL-RUSSIAN TEST ASSIGNMENT (VPR)

Submit manuscript

To cite

FURTHER DEVELOPMENT OF THE ONLINE PLATFORM FOR PREPARATION FOR THE ALL-RUSSIAN TEST ASSIGNMENT (VPR)

Section: SECTION 1. SYSTEM ANALYSIS, MANAGEMENT, INFORMATION PROCESSING

Proceedings: MODELING INFORMATION SYSTEMS AND TECHNOLOGIES – 2026 : PROCEEDINGS OF THE INTERNATIONAL SCIENTIFIC AND PRACTICAL CONFERENCE DEDICATED TO THE 5TH ANNIVERSARY OF THE FACULTY OF COMPUTER SCIENCE AND TECHNOLOGY, VORONEZH, MARTH 30, 2026

UDC 004

Tatyana V. Skvortsova ¹

P. Piskursky ²

O. Avilova ³

Author and publication information

Authors:

1. Voronezh State University of Forestry and Technologies named after G.F. Morozov
Russian Federation

2. Voronezh State University of Forestry and Technologies named after G.F. Morozov
Russian Federation

3. Voronezh State University of Forestry and Technologies named after G.F. Morozov
Russian Federation

Type:

Сonference article

DOI:

https://doi.org/10.58168/MIST2026_502-510

Pages:

from 502 to 510

Published:

30.06.2026

Subject area:

UDC 004

Language:

Russian

Keywords:

AI, neural networks, machine learning, latent semantic analysis, WEB development

Abstract and keywords

Abstract:
The article analyzes how to improve and optimize the online platform to maintain its market demand. Modern semantic embeddings (AI models) aimed at solving the main disadvantages of TF-IDF and cosine similarity algorithms were studied. A promising opportunity aimed at using the transfer learning method of AI models to reduce computational costs, achieve optimal performance and increase the accuracy of word processing was also considered.

Keywords:
AI, neural networks, machine learning, latent semantic analysis, WEB development

References

1. Meropriyatiya po ocenke kachestva obrazovaniya – Portal. URL: https://fioco.ru/ru/osoko (data obrascheniya: 08.02.2026).

2. Embeddingi dlya nachinayuschih. URL: https://habr.com/ru/companies/otus/articles/787116/ (data obrascheniya (08.02.2026).

3. Kosinusnoe shodstvo – Metrika shodstva teksta – Izuchite mashinnoe obuchenie. URL: https://studymachinelearning.com/cosine-similarity-text-similarity-metric/ (data obrascheniya 08.02.2026).

4. Kosinusnoe shodstvo: preimuschestva dlya vstraivaniya teksta. URL: https://www.csharpcorner.com/article/cosine-similarity-benefits-for-text-embeddings/ (data obrascheniya 08.02.2026).

5. Kosinusnoe shodstvo – GeeksforGeeks. URL: https://www.geeksforgeeks.org/dbms/cosine-similarity/ (data obrascheniya 08.02.2026).

6. Transfernoe obuchenie: podrobnyy gayd dlya nachinayuschih. URL: https://habr.com/ru/companies/skillfactory/articles/835020/ (data obrascheniya 08.02.2026).

Submit manuscript

To cite

Citations:

Confirmation

Регистрация