DOCUMENT SIMILARITY DETERMINING METHOD, UNIT AND PROGRAM

摘要

PROBLEM TO BE SOLVED: To provide a technology to detect a degree of similarity between documents in which text and non-text information are intermingled.

SOLUTION: In a method which can be executed on a computer for detecting a degree of similarity between two documents which include a text object, a non-text object or a composite thereof, the method comprises a step to convert each document data into a digraph and to store the same; and a step to calculate a degree of similarity between the converted digraphs by an arithmetic processing of the computer taking into consideration of an importance of the object.

COPYRIGHT: (C)2012,JPO&INPIT