Automatic Knowledge Acquire System Oriented to Web Pages

The disordered way of the Web information organization has seriously hindered the knowledge sharing and interoperability, this paper presents a knowledge-oriented Web page automatic acquisition system (AKAS2WP). This system includes four core modules, and they are accessing of web pages, text extraction, the management and organizations of the concept and the attribute extraction of the concept. Accessing of Internet web pages is to download Web pages form certain site, saves and uses for web analytics, and text extraction filter module format Html document control symbols, to get a plain text file. Meanwhile, the management and organizations of the concept and the attribute extraction of the concept, respectively, obtains terminology of given certain domain, and get the terms' description of the structure of property and structure of domain ontology. This system can be directly applied to the relevant field of automatic knowledge acquisition, so as to enhance the efficiency and accuracy of knowledge acquisition.