An Ontology-based Text Information Extraction Technology And Realized

Along with the development of society, the resources on the network are more and more abundant, it brings conveniences and inconveniences to people. Because it is difficult for people to find useful information in lots of information in a very short period time. In computer science, in order to overcome this problem many people study hard. In this case, extraction technology is generated. Today, information extraction technology has become the research focus.In this paper, firstly we described the information extraction technology, its background and history. Then, we studied the basic knowledge of the ontology. On this basis, we presented a new method of ontology-based information extraction and combined the ontology and information extraction technology. It was that using ontology rule generated module, and then generated extraction rule to extract the effective text to meet people. Therefore, using information extraction rule to extract information was the ontology-based information extraction.In this article, we designed and implemented an ontology-based university teachers resume information extraction system. We designed the overall framework of ontology-based information extraction system and detailed the design and implementation of the main modules in the system. It included the construction of ontology, the process of ontology analysis, the pretreatment of web page, the implementation of information extraction, etc. After pretreatment, we stored the no rules web pages into the database, constructed university teachers resume ontology with Protégé3.3, parsed ontology, stored the concept, properties and other relevant information into the database. At last, we used information extraction system to get results. At the end of the article, we compared and analyzed the experiment results from ontology-based information extraction system.