Study on Application of Document Representation Model Based on Query and Content Information in Website Search Engine

We have proposed a document representation model based on query and content, this model uses users’ query behavior and content information of documents for representing document. The pragmatic information from users’ implicit feedback and the semantic and syntactic information from documents are integrated to dynamically regulate the term-weight of index database. In this paper, our document representation model is applied to website search engine and the key parameters of this model are determined by experiments. The results show that this model can consequently improve precision ratio in information retrieval.