Web-sensitive Url Found

Web is a huge distributed information space,and has become one of the most important ways by which information are shared and spread in the world. Web,which is still growing at an exponential rate,provides us massive and valuable information resources. But with its rapid growth,obtaining what users need is getting more difficult because of its characteristic of opening,heterogeneity and distribution. Although there are many popular search engines people can use,we need some faster and more intelligent methods to direct and navigate our exploring in Internet by semantic comprehension. So we developed the Web-based Intelligent Interesting-Information Discovering System(WHIDS),which is the method to address that problem.To implement WIIIDS,the research of Web-based Interesting-Website Discovering System(WIWDS),which is a part of the WIIIDS approved by the college,was put forward. This dissertation discusses the growth,characteristic and existing troubles of Web first,then researches several key technologies such as Web Robot,Web-page analysis and classification,Hyperlink analysis and classification,Website structure analysis,and text classification,etc.Web-based Interesting-Website Discovering System consists of many functional modules such as data collecting,pages and hyperlinks construing,Website structure building,subject obtaining,as well as Interesting-Website recognizing by their topics and structures. In this dissertation I showed all the algorithms,processes and data structure in each module. Moreover,according to the problems met in my research,the idea of VSM-based Interesting-Website recognition was brought forward,and many unique and novel algorithms related to the implementation of each module were brought forward also .