Research On Kernel Techniques In Intelligent Search Engines And Its Implementation

As a main kind of method to retrieve information on Internet, search engine has been used in many fields. But the traditional search engine cannot meet people's demands on intelligent and personalized information service. We try to develop a system framework of intelligent search engine to solve these problems, at the same time some problems involved are expounded.First, the paper provides an overview of this intelligent search engine's searching sub-system, and with a meta-search module inside the searching sub-system can search on WWW, BBS and Newsgroup. And searching on BBS, which is not a common technique today, is a helpful experiment in this field. Because of the searching sub-system's better performance on search, it can meet users' demands on searching faster and wider.Second, this paper focuses on an approach of concept-based information retrieval system which is based on semantic linguistic network of concepts. Concept-based information retrieval is search for information objects based on their meaning rather than on the presence of the keywords in the object. So it is a new and promising way of improving search on the web.Finally, we propose a text summarization method which is based on weight of sentences and genetic algorithm, and it is also a corpus-based approach. The experimental results indicate that this method is good enough to summarize text of the web pages.