An Intelligent Agent-Based System for Automated Seat Assignment in Entertainment Venues
Source abstract
Abstract
Small and medium enterprises (SMEs) in the entertainment sector face significant challenges managing seat assignments through manual processes that are error-prone and time-consuming. This paper presents an intelligent agent-based system that automates seat assignment, while providing natural language support for operational staff. The system integrates a large language model (Gemini 2.5 Flash) for conversational interaction with a constraint-based optimization algorithm that considers capacity, accessibility, revenue, and business priorities. A fuzzy matching engine combining spaCywith the fuzzy string matching library FuzzyWuzzy consolidates duplicate reservations from multiple channels. The cloud-based architecture leverages AWS managed serverless services (ECS Fargate for container orchestration and Lambda for event-driven pipelines) with PostgreSQL for data management. Technology Readiness Level 4 (TRL4) validation demonstrated 94% precision in duplicate detection, successful assignment of 87% of reservations with 82% average capacity utilization, and effective natural language query handling. The system reduces manual processing time by 65%, while improving assignment quality through systematic enforcement of constraints. This work demonstrates the feasibility of AI-powered operations management for resource-constrained SMEs, offering a practical reference architecture combining conversational AI with algorithmic optimization.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Manufacturing and Logistics Optimization · Multi-Agent Systems and Negotiation · Maritime Ports and Logistics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
SPV Scala, 35100 San Bartolomé de Tirajana, Spain
Fundación Canaria Living Lab, 35017 Las Palmas de Gran Canaria, Spain
Biological Neurocomputational Group (BN), Department of Computer Science, Universidad Autónoma de Madrid, 28049 Madrid, Spain
Inteligent Data Analysis Laboratory (IDAL), Department of Electronic Engineering, Universitat de València, 46022 Valencia, Spain
Department of Economics and Business Management, Institute of Tourism and Sustainable Development (TIDES), Universidad de Las Palmas de Gran Canaria, 35017 Las Palmas de Gran Canaria, Spain
Funding
Spain Living Lab · Canarian Agency for Research, Innovation and the Information Society · Department of Universities, Science, Innovation and Culture of the Government of the Canary Islands · European Union
References (44)
Show source-provided references
1. Talluri, K.T., and van Ryzin, G.J. (2004). The Theory and Practice of Revenue Management, Springer. International Series in Operations Research & Management Science.10.1007/b139000 ↗
2. Stevenson, W.J. (2021). Operations Management, McGraw-Hill Education. [14th ed.].
3. Implementing restaurant revenue management: A five-step approach10.1177/001088049904000315 ↗
4. Şeker, Ş.E. (2024). Large language models in work and business. Front. Artif. Intell., 7.10.3389/frai.2024.1516832 ↗
5. Managing restaurant tables using constraints10.1016/j.knosys.2006.11.002 ↗
6. The role of ChatGPT on customer service in the hospitality industry: An exploratory study of hospitality workers’ experiences and perceptions10.20867/thm.29.4.9 ↗
7. Vicente-Martínez, P., Soria-Olivas, E., Esteve-Mompó, I., Sánchez-Montañés, M., García Escrivà, M.Á., and William-Secin, E. (2026). Design and Evaluation of an AI-Based Conversational Agent for Travel Agencies: Enhancing Training, Assistance, and Operational Efficiency. AI, 7.10.3390/ai7040123 ↗
8. Kukanja, M., and Planinc, T. (2025). Adoption of artificial intelligence in micro and small hospitality enterprises: The role of organisational characteristics and managers’ attitudes toward AI in relation to operating revenues. Tour. Hosp., 6.10.3390/tourhosp6050268 ↗
9. Honnibal, M., Montani, I., Van Landeghem, S., and Boyd, A. (2020). spaCy: Industrial-Strength Natural Language Processing in Python. Zenodo.
10. Cohen, A. (2024, October 01). FuzzyWuzzy: Fuzzy String Matching in Python. Available online: https://github.com/seatgeek/thefuzz.
11. An online optimization-based procedure for the assignment of airplane seats10.1007/s11750-020-00579-6 ↗
12. Integer programming methods for large-scale practical classroom assignment problems10.1016/j.cor.2014.07.012 ↗
13. Gendreau, M., and Potvin, J.Y. (2019). Handbook of Metaheuristics, Springer. [3rd ed.]. International Series in Operations Research & Management Science.10.1007/978-3-319-91086-4 ↗
14. A taxonomy and research overview of perishable-asset revenue management: Yield management, overbooking, and pricing10.1287/opre.40.5.831 ↗
15. Metaheuristics in combinatorial optimization: Overview and conceptual comparison10.1145/937503.937505 ↗
16. Deep reinforcement learning for inventory control: A roadmap10.1016/j.ejor.2021.07.016 ↗
17. Industry 4.0: Smart scheduling10.1080/00207543.2018.1504248 ↗
18. Attention is all you need
19. Language models are few-shot learners
20. Neural approaches to conversational AI10.1561/1500000074 ↗
21. Meyer von Wolff, R., Hobert, S., and Schumann, M. (2019, January 8–11). How May I Help You?—State of the Art and Open Research Questions for Chatbots at the Digital Workplace. Proceedings of the 52nd Hawaii International Conference on System Sciences (HICSS 2019), Maui, HI, USA.10.24251/HICSS.2019.013 ↗
22. Survey of hallucination in natural language generation10.1145/3571730 ↗
23. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2023, January 1–5). ReAct: Synergizing Reasoning and Acting in Language Models. Proceedings of the 11th International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda.
24. Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., and Lin, Y. (2024). A Survey on Large Language Model Based Autonomous Agents. Front. Comput. Sci., 18.10.1007/s11704-024-40231-1 ↗
25. Christen, P. (2012). Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection, Springer. Data-Centric Systems and Applications.10.1007/978-3-642-31164-2 ↗
26. Batini, C., and Scannapieco, M. (2016). Data and Information Quality: Dimensions, Principles and Techniques, Springer. Data-Centric Systems and Applications.10.1007/978-3-319-24106-7 ↗
27. A theory for record linkage10.1080/01621459.1969.10501049 ↗
28. Mudgal, S., Li, H., Rekatsinas, T., Doan, A., Park, Y., Krishnan, G., Deep, R., Arcaute, E., and Raghavendra, V. (2018). Deep learning for entity matching: A design space exploration. Proceedings of the ACM SIGMOD 2018, ACM.10.1145/3183713.3196926 ↗
29. Binary codes capable of correcting deletions, insertions and reversals
30. Cohen, W.W., Ravikumar, P., and Fienberg, S.E. (2003). A comparison of string distance metrics for name-matching tasks. Proceedings of the IJCAI-2003 Workshop on Information Integration on the Web (IIWeb-2003), ACM.
31. Bilenko, M., Kamath, B., and Mooney, R.J. (2006). Adaptive blocking: Learning to scale up record linkage. Proceedings of the IEEE ICDM 2006, IEEE.10.1109/ICDM.2006.13 ↗
32. Marcus, G. (2020). The next decade in AI: Four steps towards robust artificial intelligence. arXiv.
33. National Aeronautics and Space Administration (2016). NASA Systems Engineering Handbook, Rev. 2, SP-2016-6105.
34. Bass, L., Clements, P., and Kazman, R. (2021). Software Architecture in Practice, Addison-Wesley Professional. [4th ed.].
35. Gemini Team, Google (2025). Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities. arXiv.
36. Bohnet, B., Tran, V.Q., Verga, P., Aharoni, R., Andor, D., Soares, L.B., Ciaramita, M., Eisenstein, J., Ganchev, K., and Herzig, J. (2022). Attributed question answering: Evaluation and modeling for attributed large language models. arXiv.
37. White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., and Schmidt, D.C. (2023). A prompt pattern catalog to enhance prompt engineering with ChatGPT. arXiv.
38. Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation
39. Iterated local search: Framework and applications10.1007/978-3-319-91086-4_5 ↗
40. Christen, P. (2006, January 18–22). A Comparison of Personal Name Matching: Techniques and Practical Issues. Proceedings of the IEEE ICDM 2006 Workshops, Hong Kong, China.
41. Peeking Inside the Black-Box: A Survey on Explainable AI10.1109/ACCESS.2018.2870052 ↗
42. Williams, J.D., Asadi, K., and Zweig, G. (August, January 30). Hybrid Code Networks: Practical and Efficient End-to-End Dialog Control with Supervised and Reinforcement Learning. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017), Vancouver, BC, Canada.10.18653/v1/P17-1062 ↗
43. Amershi, S., Weld, D., and Vorvoreanu, M. (2019, January 4–9). Guidelines for Human-AI Interaction. Proceedings of the CHI 2019, Glasgow, UK.10.1145/3290605.3300233 ↗
44. Vicente-Martínez, P., Soria-Olivas, E., Sebastiá-García, S., Vizcaíno-Ramírez, C., Chust-Ros, A., García-Escrivà, M.Á., and William-Secin, E. (2026). Integrating Conversational AI Agents with Digital Twins: A Systems Engineering Approach to Complex Infrastructure Management and Predictive Decision-Making. Electronics, 15.10.3390/electronics15091869 ↗