Usage Of Web Data Mining In Public Security Monitor

Internet is an important tool for us, it so deeply concern our life. There are more than 10 million web pages in the web and more than 80 billion were indexed by Google. The Internet content is so abundant, and may illegal information in it. For people' s health and the stability of the society, the department of public security must take some measure to care the Internet.Though the Web Information Retrieval System(WIRS) such as Google is perfect for retrieval some information, but use to manage the Internet is no enough, especial for the department of Public Security to control some important information, so that need to build a special program to do that.This article first introduce some theory of the WIRS, then enumerate some Algorithm frequently used in data mining , at last concentrates on the techniques of design and implementation a program Public Security Information Monitor System(PSIMS), which is implemented by using search engines techniques and Web robot downloads documents. At the same time, through Chinese language word segmentation and similarity compute, the system collects and retrieval web information. In this way, it improves efficiency and precision for Public Security Bureau, so that can control the illegal information in the Internet.