Database discovery in intelligent search engine

The World Wide Web has become a vast information resource in recent years. Determining the relevancy of databases to a given query is basic to the working of a search engine. In this paper, we survey and analyze several approaches that have been proposed to tackle the database discovery problem and classify these approaches into three categories: Learning-based approaches, Qualitative approaches, Quantitative approaches. Especially describing a neural network based intelligent metasearch. The study and analysis in the paper are useful for selecting and designing the intelligent search engine.