Mining User Traversal Sequential Patterns Based On User Traversal Interest From Web Log

In recent years, with the wide applications of Internet and the rapid development of network technology, It has a lot of data, message, and also because of this reason, it becomes more and more difficult for users to find useful information in time. And it has become more and more difficult to organize the layout of web sites for administrators.As to solve the problem above, we can apply the data mining techniques to inter net, and that forms a new research area—Web Mining which includes Web Content Mining, Web Structure Mining and Web Usage Mining. Web Usage mining is one of the most important application research directions aiming at finding out user access pa tterns of web sites and identifying the user interest in browsing. It plays a significant role in optimizing the website structure and providing customized service.This paper mainly researches the mining of access sequence patterns based on User Traversal Interest. The traditional algorithms only take frequent access paths as traversal interest paths, which is not an accurate approach. Regarding this issue, the concept of User Traversal Interest has been proposed in this essay, which comprehensively involves more factors such as the times of navigation, browsing time, information amount and bandwidth. And this User Traversal Interest is also used to improve the algorithm of WAP-mine. The algorithm is validated by a concrete instance in the end. Experiments have shown that this algorithm is feasible, effective and also more precise than the currently popular algorithm of WAP-mine, with respect to measuring User Traversal Interests.