A Hybrid Method to Evaluate Similarity of XML Document

Abstract

Abstract-XML is an important standard of information representation and data exchange over the Internet, document classification is an important way to get useful information from the mass of information solutions, a method of XML document classification is proposed based on fuzzy matching path in the paper. First, the information that has no influence on the classification is removed; Then a mixed method is used to compute XML document similarity, XML document is expressed as a collection of path, deleting the recurring and matching fuzzy path in order to improve efficiency, Hungarian algorithm to calculate the similarity between documents; Finally, 2 experiments are done and the results show that the method is effective.