Research on One-stop Intelligent Tourism Planning Based on User Interests -- A Case Study of Beijing

With the improvement of peoples living standards in the new era, tourism consumption has gradually become a hotspot of popular entertainment. Beijing faces the challenges of high tourist carrying capacity at attractions and uneven distribution of tourism resources. There is a growing need for personalised travel path planning. This study aims to develop a one-stop personalised intelligent recommendation model for tourist attractions in the Beijing area to enhance tourists travel experience. By integrating data from mainstream travel websites such as Ctrip, Tongcheng, and Qunar, the paper uses natural language processing (NLP) technology to conduct analyses of online reviews to derive user sentiment and personalisation indicators. The entropy weight method is used to comprehensively consider the users personalised travel preferences, combined with the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method to scientifically rank the attractions and select the candidate set. Finally, the path planning algorithm with distance factor is implemented based on a greedy algorithm to optimise the travel path according to the users interest and achieve the recommendation of personalised travel routes. The model proposed in this study shows high accuracy and user satisfaction in empirical tests, which strengthens the user information processing support and personalisation needs in the era of big data, and contributes new solutions to the field of travel path recommendation.