Meta Search Engine Based On Neural Network

The last 20 years have witnessed the great success of the Internet and the World Wide Web, The capacity of information is increasing in the way of index, It is estimated that now there are at least 800 million pages on the Web, To help users mine the Web efficiently, Web search engines have been developed.Search Engine is becoming an independent tool now after developed from simple Robot Search Software, Single Search Engine to Specialized Search and Meta Search Engine, since it came into being to play up to people's requirements.In this paper, the search engine principles and its current development status were firstly discussed, The advantages and disadvantages of meta search engine relative to existing traditional search engines were also analyzed, Based on the preceding analysis, we have proposed the necessity of introducing meta search engine and the future research directions. In this paper I present a neural network based algorithm to classify the relevancy of search results on a me'ta search engine. The fast learning neural network technology enables the meta search engine to handle a query term in a reasonably short time and return the search results with high accuracy. Based on the algorithm, I develop a meta search engine and demonstrate how can a meta search engine submits query terms inputted by users to standard search engines and captures the useful information returned by standard search engines and how can a meta search engine arranges the result list appropriately. The neural network based algorithm which utilizes the pattern identification capability of the CC4 network to classify the relevancy of search results provides a new point of view of the rank algorithm of a meta search engine.