Adaptive bot-consultant for e-commerce systems based on the neural network architecture “TRANSFORMER

Authors

DOI:

https://doi.org/10.31649/1681-7893-2026-51-1-117-129

Keywords:

consultant bot, e-commerce, artificial intelligence, neural network, Transformer, LLM, RAG, natural language processing, NLP

Abstract

The article conducts a comprehensive study of the problem of automating customer communication in modern e-commerce systems. It is determined that existing scenario-based approaches to building chatbots have exhausted their potential given the growing demands for personalization and speed of service. A new information technology for creating an intelligent consultant bot is proposed, based on a hybrid combination of Large Language Models (LLM) of the Transformer architecture and RAG (Retrieval-Augmented Generation) methodology. This approach enables natural response generation using up-to-date product data stored in a relational database. The shortcomings of existing commercial solutions are analyzed in detail, and the advantages of the developed system are formulated

Author Biographies

O.K. Kolesnytskiy, Vinnytsia National Technical University

Кандидат технічних наук, професор кафедри комп’ютерних наук

S.O. Mirosnichenko, Vinnytsia National Technical University

Студент групи 2КН-25М, факультет інтелектуальних інформаційних технологій та автоматизації

References

Online Shopping Experiences Are Changing Due to Chatbots & LLM [Електронний ресурс]. – Режим доступу: https://www.okoone.com/spark/technology-innovation/online-shopping-experiences-are-

Shevchuk V. O. Electronic commerce: theory and practice: textbook / V. O. Shevchuk. – Kyiv: Publishing house “Professional”, 2022. – 400 p.

Vaswani A. Attention is All You Need / A. Vaswani et al. // Advances in Neural Information Processing Systems. – 2017. – Vol. 30. – URL: https://arxiv.org/abs/1706.03762.

Lewis P. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks / P. Lewis et al. // Advances in Neural Information Processing Systems. – 2020. – Vol. 33. – P. 9459–9474. – URL: https://arxiv.org/abs/2005.11401.

Ponomarenko L. A. Databases: design and administration: a manual / L. A. Ponomarenko. – Kharkiv: V. N. Karazin KhNU, 2018. – 256 p.

Gartner Reveals Three Technologies That Will Transform Customer Service and Support by 2028 [Електронний ресурс]. – Режим доступу: https://www.gartner.com/en/newsroom/press-releases/2023-08-30-gartner-reveals-three-technologies-that-will-transform-customer-service-and-support-by-2028.

Manning C. D. Introduction to Information Retrieval / C. D. Manning, P. Raghavan, H. Schütze. – Cambridge : Cambridge University Press, 2008. – 482 p.

Google AI for Developers. Gemini API Documentation [Access mode]. – Режим доступу: https://ai.google.dev/gemini-api/docs.

PostgreSQL Documentation. JSON Types [Access mode:]. – Режим доступу: https://www.postgresql.org/docs/current/datatype-json.html.

Kolesnitsky O. K. Analytical review of hardware implementations of spiking neural networks / O. K. Kolesnitsky // Mathematical Machines and Systems. – 2015. – No. 1. – P. 3–19. [Electronic resource]. – Access mode: http://www.immsp.kiev.ua/publications/articles/2015/2015_1/01_2015_Kolesnytskyy.pdf.

Downloads

Abstract views: 0

Published

2026-06-17

How to Cite

[1]
O. Kolesnytskiy and S. Mirosnichenko, “Adaptive bot-consultant for e-commerce systems based on the neural network architecture “TRANSFORMER”, Опт-ел. інф-енерг. техн., vol. 51, no. 1, pp. 117–129, Jun. 2026.

Issue

Section

Systems Of Technical Vision And Artificial Intelligence, Image Processing And Pattern Recognition

Metrics

Downloads

Download data is not yet available.

Most read articles by the same author(s)