퍼지관계식을 이용한 검색방법

초록

The directory searching method is generally used with the index searching method as a way of web searching engine. Index searching used to be evaluated at a high recall rate, however, it misleads user to a pitfall in that users have to do a hard work to select what they want from too many searching results. Skillful surfers tend to prefer the index searching method for web searching, while on the other, those who are not accustomed to web searching generally use the directory searching method. By that reason, the directory searching method is definitely needed at web searching. However, in the case that target documents for searching are obscurely categorized or users have no exact knowledge about the appropriate categories of target documents, occasionally the searching would fail to come up with satisfied results. That is, the directory searching method has a high accuracy and low recall rate. To enhance the recall rate of directory searching, this paper proposed a new way in which a category hierarchy is dynamically constructed using a fuzzy implication relation between categories computed by the fuzzy membership degree of keywords for categories. The merit of this method is exploited to enhance the recall rate of directory searching by considering the fuzzy implied relation between categories as a flexible category hierarchy expansion on the basis of similarity.