Study Of Web Usage Mining Based On Rough Set Theory

Web Servers are now evolving themselves from Server-Centered to C1ient-Centered Servers, so the trend of Internet web sites' development is Personalization Web Sites. Personalization Web Site should cater to every web user's interests and adapt itself frequently to trace the fluctuation of web user's interests．In more detail,When an old customer of a Personalization Web Site is visiting this site,he should have such a familiar feeling that it seems the whole web site is designed for him,while the new comer of a Personalization Web site would feel the convenience of finding what he is interested in. With the explosive growth of information sources available on the World Wide Web, it has become increasingly necessary for users to utilize automated tools in find the desired information resources. So the application of data mining techniques to World Wide Web (referred to as Web mining) has been the focus of several recent research projects and papers. With the explosive growth of information sources on the World Wide Web,it has become increasingly necessary for E-commerce companies,Who have transfer the Web into the primary tool for its development,to utilize data mining tools to find, extract and analyze user access patterns in their E-commerce websites, In this paper, We use the data mining technology on the Web Site to find user access patterns, and use user access patterns to improve Web Site's structure and content timely and satisfiy the users' need of personalization.The current domestic and international research of web usage mining is focus on the users browsing path when the users visit the web sites. But in this thesis, we proceed the consideration from another angle, we focus on the contents the users pay attention to when they are visiting the web sites. We subdivide each page into one or several concepts. The user often interest in some of concepts in all concepts. At first, we bring forward the web site's Concept Tree Model on the basis of web site's topology. secondly, we put forward a kind of method which can convert the transaction of browsing pages path into the transaction of browsing concepts path, and a way to calculate the concept view time according to the page view time approximately. Then, we use the Interest Recognition algorithm based on the Concept Tree model and the VPRS model of the Rough Set theory to find user concept model, in order to recommend the service for the personalization of the website, we convert the concept model into user interest concepttree. At last, we come up with a logic frame of a Personalization Web Site.