Mapping Restaurant and Supplier Product Nomenclatures Using LLM – Case Study for a Restaurant Holding
https://doi.org/10.15514/ISPRAS-2025-37(6)-43
Abstract
In the modern restaurant business, accurate mapping of product nomenclatures between restaurants and suppliers is a critical task. Effective inventory management and procurement optimization directly impact business profitability. With the increase in suppliers and product variety, traditional mapping methods become less efficient. This study proposes using large language models (LLM) to automate and improve the accuracy of product matching. Through a pilot project for a restaurant holding, we tested five product groups (shrimp, eel, parmesan cheese, cottage cheese, butter), achieving an average test accuracy of 83.8%. The solution architecture leverages prompt engineering, low-code platforms like Flowise, and Telegram integration for user-friendly processing. Key challenges, including semantic ambiguity and model hallucinations, were addressed via domain-specific dictionaries and validation. This approach reduces manual effort by approximately 90%, enabling scalable supply chain solutions applicable beyond restaurants to retail and e-commerce.
Keywords
Large Language Models,
Supply Chain Management,
Product Mapping,
Automation,
Inventory Optimization.
Supporting agencies: The work was carried out within the framework of the fundamental research program of the National Research University Higher School of Economics.
About the Authors
Seungmin JIN
Национальный исследовательский университет «Высшая школа экономики»,
Russian Federation
Russian Federation
Cand. Sci. (Tech.), has been working at HSE University since 2024 as an associate professor in the Department of Business Informatics at the HSE Graduate School of Business, as well as a senior researcher at the International Laboratory of Intelligent Systems and Structural Analysis at the HSE Faculty of Computer Science. Research interests: visual analytics, artificial intelligence, neural networks, machine learning and deep learning and their applications in recommender systems and other areas.
Petr Borisovich PANFILOV
Национальный исследовательский университет «Высшая школа экономики»,
Russian Federation
Russian Federation
Сand. Sci. (Tech.), professor in the Department of Business Informatics of the Graduate School of Business at HSE University since 2014. His research interests include computer science and engineering, data science, distributed computing and data processing and their applications.
Aleksander Sergeevich SULEYKIN
Национальный исследовательский университет «Высшая школа экономики»,
Russian Federation
Russian Federation
Сand. Sci. (Tech.), a researcher at the Research Laboratory of Process-Oriented Information Systems at the HSE Faculty of Computer Science. His research interests include computer science and engineering, data science, artificial intelligence, and generative AI-based solutions in industry and business.
References
1. Dhara S., Delgado Barba S. (2024). Large language models in supply chain management [Master's thesis]. POLITesi Repository (online), Available at: https://www.politesi.polimi.it/retrieve/9f1da09d-256f-428c-8bae-a94d529df3e6/2024_07_Dhara_Delgado.pdf, accessed 25.10.2025.
2. Li B., Mellou K., Zhang B., Pathuri J., Menache I. (2023). Large language models for supply chain optimization. arXiv preprint arXiv:2307.03875.
3. Kumar S., Mellou K., Pathuri J. (2023). Large language models for supply chain optimization. ArXiv Preprint. Available at: https://arxiv.org/abs/2307.03875, accessed 25.10.2025.
4. Bag S., Rahman M.S., Srivastava G., Shore A., Ram, P. (2023) Examining the role of virtue ethics and big data in enhancing viable, sustainable, and digital supply chain performance, Technological Forecasting and Social Change, Vol. 186, DOI: 10.1016/j.techfore.2022.122154.
5. HBR Editors. (2025). How generative AI improves supply chain management. Harvard Business Review (online). Available at: https://hbr.org/2025/01/how-generative-ai-improves-supply-chain-management, accessed 25.10.2025.
6. Aporia AI Insights. (2024). Risks of using LLMs in enterprise applications (online). Available at: https://www.aporia.com/learn/risks-of-using-llms-in-enterprise-applications/, accessed 25.10.2025.
7. McKinsey Global Institute. (2025). Beyond automation: How gen AI is reshaping supply chains, Available at: https://www.mckinsey.com/capabilities/operations/our-insights/beyond-automation-how-gen-ai-is-reshaping-supply-chains/, accessed 25.10.2025.
8. IMD. (2024). How will large language models impact supply chains? Available at: https://www.imd.org/ibyimd/supply-chain/large-language-model-impacts-on-supply-chain/, accessed 25.10.2025.
9. Kellton Tech Blog. (2024). Large language models (LLMs): Navigating challenges and uncovering benefits. Available at: https://www.kellton.com/kellton-tech-blog/large-language-models-challenges-benefits, accessed 25.10.2025.
10. Lokad TV. (2023). Large language models in supply chain [online video]. Available at: https://www.lokad.com/tv/2023/12/13/large-language-models-in-supply-chain/, accessed 25.10.2025.
11. Cobalt.io. (2024). LLM supply chain attack prevention strategies (online). Available at: https://www.cobalt.io/blog/llm-supply-chain-attack-prevention-strategies, accessed 25.10.2025.
12. OWASP Foundation. (2023). OWASP Top Ten for Large Language Model Applications (online). Available at: https://owasp.org/www-project-top-10-for-large-language-model-applications), accessed 25.10.2025.
13. Атаки на цепочки поставок: как уязвимости распространяются через зависимости (online). Available at: https://www.securitylab.ru/blog/personal/xiaomite-journal/355832.php, accessed 27.10.2025.
14. Поисковый сервис DUC SmartSearch. Available at: https://duc-technologies.ru/smartsearch, accessed 27.10.2025.
15. Open Source AI Platform for Work (online). Available at: https://www.onyx.app/, accessed 27.10.2025.
16. Open source agentic systems development platform (online). Available at: https://flowiseai.com/, accessed 27.10.2025.
17. Cервис GigaChat (online). Available at: https://giga.chat/, accessed 27.10.2025.
Review
For citations:
JIN S., PANFILOV P.B., SULEYKIN A.S. Mapping Restaurant and Supplier Product Nomenclatures Using LLM – Case Study for a Restaurant Holding. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2025;37(6):163-176. (In Russ.) https://doi.org/10.15514/ISPRAS-2025-37(6)-43
Email this article 