isrjournals
User Sign in    Editor Sign in

an ai-powered intelligent travel and tourism support system in india

Harish E A,Karthi S,Likith Kumar M,Thiyagarajan R

Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology

ISSN: 2321-3337          Impact Factor:1.521         Volume:6         Issue:3         Year: 31 March,2026         Pages:2057-2062

International Journal of Advanced Research in Computer Science Engineering and Information Technology

Abstract

Travel planning often faces challenges such as lack of personalization, inefficient routing, limited real-time information, and communication barriers, resulting in suboptimal travel experiences. The purpose of this study is to develop an intelligent travel assistant as a Flask based web application integrated with an SQLite3 database to manage users, itineraries, and local guide listings. The system provides optimized route calculation for bus and car travel and integrates real time weather updates through external APIs to ensure safe and timely travel decisions. It offers recommendations for hotels, food, and sightseeing locations based on user preferences and contextual information. To overcome the challenge of identifying reliable local guides, the platform includes a secure on demand marketplace where verified guides can list their services. A trip planning module generates optimized multi-day itineraries, virtual assistant using GPT 4o mini model and NLP powered chatbot with multilingual text-to-speech support enhances user interaction. Geolocation services and email notifications further improve usability and communication.

Kewords

Flask Web Application, NLP, Multilingual Chatbot, Email Notifications, LLM

Reference

[1]. C. Dong, J. Bao, J. Wang and J. Wang, "Modeling the Dynamic Choice of Travel Locations With the Spatial-Temporal Bounded Rationality," in IEEE Access, vol. 11, pp. 125291-125306, 2023, doi: 10.1109/ACCESS.2023.3331060. [2]. Y. Wang and P. Hu, "Deep Reinforcement Learning-Based Multi-Object Adaptive Route Planning for Traveling Recommender Systems," in IEEE Access, vol. 11, pp. 120258-120269, 10.1109/ACCESS.2023.3327273. [3]. J. Xu, Z. Bai and Q. Ma, "Tourist Attractions Recommendation by Using Enhanced Location Knowledge Graph," in IEEE Access, vol. 13, pp. 168463-168477, 2025, 10.1109/ACCESS.2025.3613788. [4]. J. Kyeong Kim, W. Cheul Kwon, I. Young Choi, H. Heo and H. S. Moon, "A Group Travel Recommender System Based on Group Approximate Constraint Satisfaction," in IEEE Access, vol. 12, pp. 96113-96125, 2024, doi: 10.1109/ACCESS.2024.3427122. [5]. L. Tang, X. Lin, J. Yu and C. Tang, "Integrating Travel Survey and Amap API Data Into Travel Mode Choice Analysis With Interpretable Machine Learning Models: A Case Study in China," in IEEE Access, vol. 13, pp. 27852-27867, 10.1109/ACCESS.2025.3540082. [6]. C. Ouaddi, L. Benaddi, A. Souha, and A. Jakimi, ‘‘Towards a metamodelfor proactive chatbots,’’ in Proc. ASU Int. Conf. Emerg. Technol.Sustainability Intell. Syst. (ICETSIS), Jan. 2024, pp. 1129–1133. [7]. C. Ouaddi, L. Benaddi, E. M. Bouziane, A. Jakimi, A. Chehri,and R. Saadane, ‘‘DSL-driven approaches and metamodels for chatbot development: A systematic literature review,’’ Exp. Syst., vol. 42, no. 2,p. 13787, Feb. 2025. [8]. C. Ouaddi, L. Benaddi, L. Naimi, E. M. Bouziane, and A. Jakimi,‘‘A graphical DSL for accelerating chatbot development,’’ in Proc. 7th Int.Conf. Adv. Commun. Technol. Netw. (CommNet), Dec. 2024, pp. 1–6. [9]. L. Benaddi, C. Ouaddi, A. Jakimi, and B. Ouchao, ‘‘A systematic review ofchatbots: Classification, development, and their impact on tourism,’’ IEEE Access, vol. 12, pp. 78799–78810, 2024. [10]. C. Di Sipio, J. Rocco, D. Ruscio, and P. T. Nguyen, ‘‘Lev4rec: A low-code environment to support the development Res.Square, 2022.. of recommender systems,’’