Semantic Web-based Information Processing Technology In Distance Education

With the developing of Internet, Distance education has been used in company and school education. Due to the rapic development of distance education, the number of distance education resources is becoming bigger. The resources come from many different web sites; they have various species and have many styles. In order to search the requisite information in this environment, a system that can exactly and quickly do it must be built.Information extraction is a system that can extract specific information from lots texts and can transform that information into structure data user can use that on various purposes. There are many technologies that can deal with unstructured texts. They are shallow NLP, ILP and so on. Information retrieval is a process in which what a user asks for are found from many texts and the results are returned to the user. For structure data(database data), the technology of retrieval is very complete. However, it is necessary to strength the accuracy of information retrieval in Web. Now the query language on XML is XML-QL.In this paper, a frame of information disposal in distance education was proposed. In this frame information extraction and information retrieval was connected to improve the accuracy and rate of information inquiry. The basement of this frame was Sematic Web. This paper the center of research is the technology of information extraction. This paper analyses the characteristics of the HTML pages in distance education, advances the two ways of information predisposal and their methods, explores the way to use ontology in information extraction. This paper researches the realizion of information retrival based on XML and XML query language. This paper proposes paces of information retrival and expressed the realizations of the paces.