Establishing an intelligent and smart tourism model using data mining in the context of big data

Abstract

AbstractNowadays, with the rapid development of information technology (IT), the tourism industry has begun to apply it in the tourism sector for the establishment of a smart tourism model. Smart tourism is formed based on the expansion of traditional tourism, focusing on personalized user experiences through TIYA, which is a social networking application. Its core is IT, such as cloud computing, the Internet of Things (IoT), artificial intelligence (AI), and big data technology. Smart tourism is a complete tourism service system that improves the convenience of tourists. Keeping in mind the vital role of smart tourism in developing the economy of a country, this study establishes a smart tourism management model based on data mining in the context of big data, with the purpose of strengthening the accuracy of smart tourism management and improving customer satisfaction with tourism. Before constructing the intelligent tourism management model, this study first describes the data mining technology in detail, introduces the Naive Bayes (NB) algorithm and the improved algorithm based on Apriori, analyzes the characteristics of tourism data, and establishes an intelligent tourism management model on this basis. In the proposed model, the government sector, the tourism industries, the community residents, tourists, and other forces are brought into full play, and a complete intelligent tourism management model is established. Using the proposed model, all the stakeholders can improve their own value and meet their tourism needs. Taking Beijing as an example for the experimental work, the improved algorithm based on Apriori is used to mine the tourist interest points. After evaluating the proposed model, it is concluded that the most interest points are obtained when the bandwidth parameter is set to 0.02. After the clustering operation, the first, second, and third tourist attractions in Beijing are obtained, and the results are consistent with the tourist interest. At the same time, the time index of three different mining algorithms (improved MapReduce algorithm (MA), the MapReduce algorithm (MRA), and the k-order MapReduce parallel algorithm (MRKA) based on the improved Apriori algorithm) under different minimum supports is compared. The results show that the MA algorithm can mine the required information in the shortest time.