Research On Personalized Tourist Attractions Recommendation

With the wide popularity of the mobile Internet and the increasing demand of tourists for the quality of tourism services,the online travel,the mobile travel and other services have gradually risen.The personalized recommendation of online tourist attraction has gradually become a hot topic in the field of personalized recommendation technology.In the face of large,complex of tourism data,the demand for personalized service for tourists is becoming more and more intense,so the efficient and accurate personalized tourist attraction recommender system has an important value.This paper leverages social network and Bayesian network and fully mines the matched-degree between users and attractions to provide personalized recommendation.In this paper,the main research work is as follows:(1)A personalized tourist attractions recommendation algorithm based on social network is proposed.In order to improve the accuracy of tourist attractions recommended to solve the problem of cold start for new users,the algorithm will be added to the social network factor to the tourist attractions recommended,and fully mines the social network relationship among users.The algorithm process is as follows: Firstly,the coupled two-way clustering algorithm is used to cluster the users.Then,the DBSCAN algorithm is applied to cluster the tourist attractions.Finally,the two stable sets of users and tourist attractions are applied to the personalized recommendation algorithm to predict the user the next tourist attraction for users.The proposed algorithm is compared with some traditional algorithms in the dataset.The experimental results show that the proposed method in this paper has higher recommendation accuracy.(2)In order to quantify the recommendation of tourist attractions,this paper proposes a personalized tourist attraction recommendation algorithm based on Bayesian network learning.To solve the problem of new users and new attractions,the algorithm makes full use of the user's demographic information,users-attractions rating information and the properties of attractions.Specifically,the algorithm firstly uses the traditional collaborative filtering algorithm to handle the similarity between user attribute similarity and user behavior,and uses a content-based algorithm to deal with the relationship between tourist attractions.Then,the probability of the user accessing each site to a tourist attraction is calculated by Bayesian probability model.Finally,the algorithm is validated with the traditional algorithm on the Crip dataset.The results show that the proposed algorithm has better performance in dealing with new users and new tourist attractions.