User behavior analysis based on user interest by web log mining

With the rapid development of science and technology and the growing popularity of computer networks, the scale of network users is gradually expanding, and the behavior of network users is becoming more and more complicated. A large number of studies show that the user's actual interest is closely related to the browsing behavior on the web page. Through the user browsing behavior analysis can obtain the user interest information, and then build the user interest model, so that the search results closer to the user's expectations. This paper mainly introduces the method of web log mining, which can discover the mode of web pages by digging web log records. By analyzing and exploring the rules of web log records, we can identify the potential customers of the website and improve the quality of information services to users. In the stage of user behavior analysis, this paper explores the differences in user browsing behavior in different types of access events, and calculates the user's interest based on the M5 model tree to analyze the analytic events.