Abstract: In view of the existing information retrieval systems which are difficult to process document retrieval problem according to query demand, this paper proposed one retrieval model based on relative feedback, analyzed the decomposi- lion of the query words, derived the correlation feedback mechanism and normalization process, and further expounded the document extraction method. Through relative feedback and query expansion, this model can overcome the problem that traditional methods can not calculate the similarity between document and query word, and can effectively deal with document retrieval. The simulation results proved the validity and feasibility of the model.

Key words: Information retrieval,Relative feedback,Query spfitting,I3oolean retrieval,Query expansion