Optimization method for mass service system with the use of a virtual assistant based on artificial intelligence
DOI:
https://doi.org/10.18372/2073-4751.75.18013Keywords:
Mass Service System, GAS, Virtual Assistant, Artificial Assistant, Telegram BotAbstract
In article, we present the development of an optimization method for mass service systems using a virtual assistant based on artificial intelligence as an effective tool for automating and enhancing user service processes. The proposed solution enhances user interaction, utilizes artificial intelligence to improve responses, efficiently stores and analyzes data, and enables automation through a GAS. Future plans include expanding the language model, improving the user interface, adding automatic language recognition to support multiple languages, and introducing additional query analysis capabilities. We aim to develop algorithms that learn from user responses to provide personalized answers and enhance the user interaction experience. Furthermore, we investigate and optimize data processing algorithms to ensure the system's efficient operation in high query volume scenarios. These research developments have the potential to enhance the efficiency, accuracy, and user experience of mass service systems utilizing a virtual assistant.
References
Kleinrock, L. Queueing Systems, Volume I – Theory. Wiley, 1976. 417 p.
Gelenbe E., Mitrani I. Analysis and Synthesis of Computer Systems. New York : Academic Press, 1980. 239 p.
Ananthanarayanan, G., et al. CloudScale: Elastic Resource Allocation for Cloud Computing Environments. ACM, 2010.
Zhang H., Hou J.C. Queue Length Estimation and Call Admission Control in Differentiated Services Networks. IEEE/ACM Transactions on Networking. 2005. Vol. 13. Iss. 2. P. 400–413.
Li W., Li Y. Learning Automata-based QoS-aware Web Service Selection. IEEE Transactions on Services Computing. 2009. Vol. 2. Iss. 1. P. 48–61.
Shead S. Why everyone is talking about the A.I. text generator released by an Elon Musk-backed lab. URL: https://ramaonhealthcare.com/why-everyone-is-talking-about-the-a-i-text-generator-released-by-an-elon-musk-backed-lab/.
Bussler F. Will GPT-3 Kill Coding? Towards Data Science. URL: https://towardsdatascience. com/will-gpt-3-kill-coding-630e4518c04d.
Brown T.B. et al. Language Models are Few-Shot Learners. URL: https://arxiv.org/abs/2005.14165
Sagar R. OpenAI Releases GPT-3, The Largest Model So Far. URL: https://analyticsindiamag.com/open-ai-gpt-3-language-model/.
Chalmers D. GPT-3 and General Intelligence. У Weinberg, Justin. Daily Nous. Philosophers On GPT-3 (updated with replies by GPT-3). URL: https://dailynous.com/2020/07/30/philosophers-gpt-3/.
Гнатюк В.О., Бондаренко І.О., Каплун І.С. Використання систем обміну миттєвими повідомленнями для автоматизації надання консультативних послуг. Реєстрація, зберігання і обробка даних. 2021. Т. 23. № 4. С. 58–67.
Гнатюк В.О., Батрак О.Г., Яроцький С.В. Автоматизована система реєстрації місцезнаходження працівника. Проблеми інформатизації та управління. 2023. В. 74. № 2. С. 14–20.
Downloads
Published
How to Cite
Issue
Section
License
The scientific journal adheres to the principles of Open Access and provides free, immediate, and permanent access to all published materials without financial, technical, or legal barriers for readers.
All articles are published in Open Access under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.
Copyright
Authors who publish their works in the journal:
-
retain the copyright to their publications;
-
grant the journal the right of first publication of the article;
-
agree to the distribution of their materials under the CC BY 4.0 license;
-
have the right to reuse, archive, and distribute their works (including in institutional and subject repositories), provided that proper reference is made to the original publication in the journal.