Please use this identifier to cite or link to this item:
http://elartu.tntu.edu.ua/handle/lib/48076| Title: | Optimization of Mass Service Systems using Ai algorithms |
| Authors: | Juliet Otojareri, Slyusarenko |
| Affiliation: | Тернопільський національний технічний університет імені Івана Пулюя, факультет комп’ютерно-інформаційних систем і програмної інженерії, кафедра комп’ютерних наук, м. Тернопіль, Україна |
| Bibliographic description (Ukraine): | Slyusarenko D. O. Optimization of Mass Service Systems using Ai algorithms : work towards a master's degree : spec. 124 - system analysis / supervisor O. S. Holotenko. Ternopil : Ternopil Ivan Puluj National Technical University, 2025. 51 p. |
| Issue Date: | 30-一月-2025 |
| Submitted date: | 16-一月-2025 |
| Date of entry: | 30-一月-2025 |
| Publisher: | Тернопільський національний технічний університет імені Івана Пулюя |
| Country (code): | UA |
| Place of the edition/event: | ТНТУ ім. І.Пулюя, ФІС, м. Тернопіль, Україна |
| Code and name of the specialty: | 51 |
| Supervisor: | Голотенко, Олександр Сергійович Holotenko, Olexandr S. |
| UDC: | 004.04 |
| Keywords: | system analysis virtual assistant mass service system artificial assistant telegram bot |
| Abstract: | The developed solution expands the capabilities of existing QMS through the use of VA and the development of AI, in particular GPT-3.5, to ensure more effective and informative communication with users. Thus, an effective tool has been developed to automate and improve service processes, which provides: improved interaction with by users, the use of AI to improve responses, efficient data storage and analysis, the possibility of automation thanks to GAS. In the future, it is planned to expand the language model, improve the user interface, add an automatic speech recognition module to support many languages and additional query analysis capabilities, develop algorithms that learn from user responses to provide personalized answers and improve the interaction experience, research and optimize data processing algorithms for faster and more efficient system operation with a large flow of requests. These scientific developments can improve the efficiency, accuracy and user experience of the MSS using VA. |
| Content: | INTRODUCTION 6 1. ANALYSIS OF THE SUBJECT AREA 8 1.1. Historical Context for the Evolution of Mass Service Systems and AI's Role in Transformation 8 1.2. Significance in healthcare, transportation, and customer service. 10 1.3. Why optimization of mass service systems using ai algorithms is important 11 1.4. Use of artificial intelligence in mass service systems 12 2. METHODOLOGY OF MACHINE LEARNING AND DATA PROCESSING ALGORITHMS 14 2.1. General Approach to AI-Based Optimization 14 2.2 Data Collection for Optimization 14 2.3 Design Considerations for the AI System 15 2.4. Ethical and Safety Considerations in AI-Optimized Systems 25 3. DEVELOPMENT OF PROGRAM STRUCTURE AND ALGORITHMS 29 3.1. Analysis of modern scientific achievements reading 29 3.2. Development of an optimization method QMO operations using AI-based VA. 30 4 SAFETY OF LIFE, BASIC LABOR PROTECTION 40 4.1. Effects of electromagnetic radiation on the human body 40 4.2 Types of hazards 43 4.3 Road Transport Safety 46 4.4 Conclusions 46 CONCLUSIONS 48 REFERNCES 49 |
| URI: | http://elartu.tntu.edu.ua/handle/lib/48076 |
| Copyright owner: | © Juliet Otojareri Slyusarenko, 2025 |
| References (Ukraine): | 1. Kleinrock, L. Queuing Systems, Volume I - Theory. Wiley, 1976. 417 p. 2. Gelenbe E., Mitrani I. Analysis and Synthesis of Computer Systems. New York: Academic Press, 1980. 239 p. 3. Ananthanarayanan, G., et al. CloudScale: Elastic Resource Allocation for Cloud Computing Environments. ACM, 2010. 4. Zhang H., Hou JC Queue Length Estimation and Call Admission Control in Differentiated Services Networks. IEEE/ACM Transactions on Networking. 2005. Vol. 13. Iss. 2. P. 400–413. 5. 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. 6. Shead S. Why everyone is talking about the AI text generator released by an Elon Musk-backed lab. URL: https://ramaon-healthcare.com/why-everyone-is-talking-about-the-ai-text-generator-released-by-an-elon-musk-backed-lab/ 7. Bussler F. Will GPT-3 Kill Coding? Towards Data Science. URL: https://towardsdatascience. com/will-gpt-3-kill-cod- ing-630e4518c04d 8. Brown TB et al. Language Models are Few-Shot Learners. URL: https://arxiv.org/abs/2005.14165 9. Sagar R. OpenAI Releases GPT-3, The Largest Model So Far. URL: https://analyticsindiamag.com/open-ai-gpt-3-language-model/ 10. Chalmers D. GPT-3 and General Intelligence. In Weinberg, Justin. Daily Nous. Philosophers On GPT-3 (updated with replies by GPT-3). URL: https://dai- lynous.com/2020/07/30/philosophers-gpt-3/ 11. Hnatyuk V.O., Bondarenko I.O., Kaplun I.S. Using instant messaging systems to automate the provision of advisory services. Registration, storage and data processing. 2021. Vol. 23. No. 4. Pp. 58–67 12. Hnatyuk V.O., Batrak O.G., Yarotsky S.V. Automated system for registering the location of an employee. Problems of informatization and management. 2023. V. 74. No. 2. P. 14–20 13. Y. Leshchyshyn, L. Scherbak, O. Nazarevych, V. Gotovych, P. Tymkiv and G. Shymchuk, «Multicomponent Model of the Heart Rate Variability Change-point,» 2019 IEEE XVth International Conference on the Perspective Technologies and Methods in MEMS Design (MEMSTECH), Polyana, Ukraine, 2019, pp. 110-113, doi: 10.1109/MEMSTECH.2019.8817379 14. Lytvynenko, S. Lupenko, O. Nazarevych, G. Shymchuk and V. Hotovych, «Mathematical model of gas consumption process in the form of cyclic random process,» 2021 IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT), LVIV, Ukraine, 2021, pp. 232-235, doi: 10.1109/CSIT52700.2021.9648621 15. V. Kozlovskyi, Y. Balanyuk, H. Martyniuk, O. Nazarevych, L. Scherbak and G. Shymchuk, «Information Technology for Estimating City Gas Consumption During the Year,» 2022 International Conference on Smart Information Systems and Technologies (SIST), Nur-Sultan, Kazakhstan, 2022, pp. 1-4, doi: 10.1109/SIST54437.2022.9945786 16. I. Lytvynenko, S. Lupenko, N. Kunanets, O. Nazarevych, G. Shymchuk and V. Hotovych, "Simulation of gas consumption process based on the mathematical model in the form of cyclic random process considering the scale factors", 1st International Workshop on Information Technologies: Theoretical and Applied Problems ITTAP 2021, 16–18 November 2021 17. Approach to gas consumption process forecasting on the basis of a mathematical model in the form of a random cyclic process / Serhii Lupenko, Iaroslav Lytvynenko, Oleg Nazarevych, Grigorii Shymchuk, Volodymyr Hotovych // ICAAEIT 2021, 15-17 December 2021. – Tern. : TNTU, Zhytomyr «Publishing house „Book-Druk“» LLC, 2021. – P. 213–219. – (Mathematical modeling in power engineering and information technologies) 18. Конспект лекцій з дисципліни «Грід-системи та технології хмарних обчислень» для студентів освітніх рівнів «бакалавр», «магістр» / Укладачі : Шимчук Г.В., Маєвський О.В., Назаревич О.Б., Стадник М.А. – Тернопіль : Тернопільський національний технічний університет імені Івана Пулюя, 2016 – 340 с |
| Content type: | Master Thesis |
| �蝷箔����: | 124 — системний аналіз |
��辣銝剔�﹝獢�:
| 獢�獢� | ��膩 | 憭批�� | �撘� | |
|---|---|---|---|---|
| 1_SLIUSARENKO_MAG_KN.pdf | Дипломна робота | 2,09 MB | Adobe PDF | 璉�閫�/撘�� |
�DSpace銝剜�������★��������雿��.
Admin Tools