| With the rapid development of economy and the improving of people’s living standards, tourism has also become one necessary part of life. Tourism gradually becomes one of emerging industries with the fastest growing and the best prospects, too. In recent years, with the development of information technology, tourism model is also changing. Tourists are updating the way and content of tourism demand. They pay more attention to the quality of tourism services and personalized experience. So demand for personalized tourism service recommendation system came into being. We hope it can combine features of tourism and information technology. It can make people convenient, improve the management of tourism providers and service quality. Finally it promotes the development of tourism.Personalized tourism service recommendation system stores a series of related methods, data and service by building the database. It integrates the related tourism resources. Then it gives a interested and complete personalized solutions for the different needs of different visitors. It offers food, housing, transportation, travel and other services for visitors. Finally, it helps visitors make the best tourism options.The paper studies personalized tourism service recommendation system based on multi-objective optimization. First we build the model of tourism service composition based on multi-objective optimization according to characteristics of tourism. The model includes three goals such as time, cost, quality of service. According to the model the paper proposes the method of tourism service combination based on multi-objective optimization. This method considers historical data and the current preference of tourists. According to time, cost and quality of service, it combines various travel elements of tourists including transportations, restaurants and hotels, in order to give tourists an optimal solution. The method can solve the problem of online processing tourism service combination. It fits the actual needs of tourism industries. Then the paper proposes a recommendation algorithm called Sing CF. The algorithm first estimates the unrated scores for singular ratings and transform them into dual ones. Then we perform a CF process to discover neighborhood users and make predictions for each target user. The purpose is to improve the recommendation accuracy. The algorithm can get more accurate recommendation results. Furthermore, the paper provides a algorithm called DSing CF for significant improvement in efficiency. It is a Map Reduce-based distributed Sing CF algorithm on Hadoop. The algorithm significantly improves the efficiency of the recommendation.According to the above method the paper designs and achieves a personalized tourism service recommendation system based on multi-objective optimization. The system can obtain the needs of tourists accurately through the visual interface. It provides catering, accommodation, shopping and sighting. Finally, it recommends optimal solution for visitors. |
