An approach to extending the functionality of artificial intelligence in the form of chatgpt using pinecone technology

Олена Ігорівна Феоктистова, Ярослав Михайлович Альошин

Abstract


The article addresses the problem of diversity of web interfaces, which affects the efficiency of business analysis, particularly in terms of time costs and the search for relevant information. The purpose of the study is to develop a theoretical and methodological framework for extending the functionality of artificial intelligence systems through the use of vector semantic database technology. The proposed approach is aimed at optimizing the processes of data search, structuring, and interpretation in business analysis, thereby increasing the productivity of business analysts and the quality of the results obtained.

The object of the research is business analysis processes using artificial intelligence systems, while the subject is the methodological and software support for their application based on vector semantic database technology. The core idea is to create a set of methods and software solutions that ensure effective human–machine interaction and reduce time costs in performing analytical operations.

In the course of the study, a critical review of the current state of the use of language models in business analytics was conducted, methods of human–machine interaction were improved, and an experimental prototype was developed to verify the effectiveness of the proposed solutions. The experimental results confirmed an increase in the efficiency of solving applied business analysis tasks using language models enhanced by semantic search and content matching technologies.

The obtained results can be applied in related fields of digital analytics, big data processing, e-commerce, and information flow management on the Internet. This increases the universality and practical value of the proposed approach, making it a promising direction for further development of intelligent analytical systems, their integration with semantic databases, and the enhancement of their adaptability to the dynamic web environment.

Keywords


AI; semantic search; artificial intelligence; business analysis; semantic vector databases; human–machine interaction; data optimization

References


Vizniuk I., Buhlai N., Kutsak L., Polishchuk A., Kylyvnyk V. Vykorystannia shtuchnoho intelektu v osviti. Modern Information Technologies and Innovation Methodologies of Education in Professional Training: Methodology Theory, Experience, Problems, 2021. № 59. S. 14–22.

Hrytsyshyn V., Habruseva N. Shtuchnyi intelekt sohodni i zavtra. Fundamentalni ta prykladni problemy suchasnykh tekhnolohii: tezy Mizhnarodnoi naukovo-tekhnichnoi konferentsii. Ternopil, 2020. S. 247– 248. URL: https://cutt. ly/EwDG4ks9 (data zvernennia: 07.10.2025)

Denesiak O., Palamarchuk Ye. Kompleksna systema proktorinhu v informatsiinykh tekhnolohiiakh analizu kontekstu v systemakh otsiniuvannia znan. Visnyk Vinnytskoho politekhnichnoho instytutu, 2021. № 6. S. 93–99.

Drozdova V. V., Rudnitska K. V., Roskvas I. A. Innovatsiini tekhnolohii vykladannia inozemnykh mov v umovakh zrostaiuchoho vplyvu tekhnolohii shtuchnoho intelektu na osvitni protsesy. Akademichni vizii, 2023. № 26. C. 1–16.

Dutchak A. «Redaktor telebachennia v merezhi Internet: terminy ta funktsii». Zbirnyk prats NDI presoznavstva, Lviv, 2017. Vyp. 7(25). S. 326-340.

Kozubai I. V. Kompleksnyi analiz vplyvu shtuchnoho intelektu na vykladannia ta vyvchennia inozemnykh mov. Aktualni pytannia humanitarnykh nauk, 2023. № 1 (63). S. 210–214.

Lieboshyna, N., Cherkashyna, Yu., Kharatian, E. Metodychni perspektyvy implementatsii ShI u navchanni anhliiskoi movy viiskovykh fakhivtsiv: implementatsiia tekhnolohii shtuchnoho intelektu u systemu pidhotovky viiskovykh spetsialistiv. Suchasni doslidzhennia z inozemnoi filolohii, 2024. № 2(26). S. 145–152.

Khoroshailo O. S., Kocherhina S. S. Vykorystannia shtuchnoho intelektu dlia pidvyshchennia yakosti vykladannia inozemnykh mov u vyshchomu zakladi osvity. Naukovyi chasopys Natsionalnoho pedahohichnoho universytetu imeni M. P. Draho-manova. Seriia 5. Pedahohichni nauky: realii ta perspektyvy, 2023. № 93. S. 123-127. URL: https://doi.org/10.31392/NPU-nc.series5.2023.93.25. (data zvernennia: 05.09.2025).

A. Kargin and T. Petrenko, “Feeling Artificial Intelligence for AI-Enabled Autonomous Systems,” in Proc. of 2022 IEEE Global Conf. on Artificial Intelligence and Internet of Things (GCAIoT) Alamein New City, Egypt, Dec.18, 2022, pp.88-93.

Beltagy I., Lo K., Cohan A. Longformer: The Long-Document Transformer // arXiv preprint, 2020. arXiv:2004.05150.

Bessen, J. E. «AI and Jobs: The Role of Demand». NBER Working Paper, №. 24235. National Bureau of Economic Research, 2019. pp. 14-15.

Davenport T. H., Kalakota, R. The potential for artificial intelligence in healthcare. Future Healthcare Journal, 6(2), 2019. pp. 94-98.

David Bunting. How to use GenAI for database query optimization and natural language analysis. URL: https://www.chaossearch.io/blog/genai-database-query-natural-language (accessed Nov. 20, 2024).

E. Guizzo, Types of Robots. Categories frequently used to classify robots. Robotsguide.com. URL: https://robotsguide.com/learn/types-of-robots (accessed Jun. 15, 2025).

Lewis P. S. et al. Retrieval-augmented generation for knowledge-intensive NLP tasks. arXiv preprint, 2020. arXiv:2005.11401.

Open X-Embodiment: Robotic Learning Datasets and RT-X Models Open X-Embodiment Collaboration, 2024. [Online]. URL: https://robotics-transformer-x.github.io/ (data zvernennia: 10.10.2025).

Sapaty P, Morozov A, Finkelstein R, et al.) A new concept of flexible organization for distributed robotized systems. Proceedings of the 12th International Symposium on Artificial Life and Robotics (AROB 12), Beppu, Oita, Japan, Jan, 2007. 25–27, 2007, 8 p

Topol, E. Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again / E. Topol. New York: Basic Books, Mar, 2019. pp.75–120.

Tserkovnyi V. O., Lytvynenko I. V. Analiz platform Arduino, Raspberry Pi ta ESP8266 v zadachakh monitorynhu perevezen bahazhu. Analysis of Arduino, Raspberry Pi and ESP8266 platforms in the tasks of baggage transportation monitoring. ⅩⅠ International scientific and practical conference of young researchers and students «Current issues in modern technologies» (Tern., 7-8 December 2022), 2022. pp. 59.

Variant Effect Prediction in the Age of Machine Learning — Y. Bromberg, R. Prabakaran, A. Kabir, A. Shehu. Cold Spring Harbor Perspectives in Biology. 2024. DOI:10.1101

Vykorystannia system biznes‑analityky v stratehichnomu upravlinni pidpryiemstvom (Honcharuk O., Landiak T., Melnyk L.) — «Review of Transport Economics and Management», №13(29), 2025. DOI: 10.15802/rtem2025/339100.




DOI: https://doi.org/10.32620/oikit.2026.107.08

Refbacks

  • There are currently no refbacks.