DOCUMENT STORAGE DEVICE, SIMILAR DOCUMENT RETRIEVAL DEVICE AND PROGRAM

PROBLEM TO BE SOLVED: To present a site desired by a user by a simple method. SOLUTION: The document storage device is configured to, in storing a document, calculate the word feature value of an appearing word in a read document, and to calculate the feature value of a designated tag appearing in the document, and to calculate the feature vector of the document by using the word feature value and the feature value of the tag, and to store the document, the word feature value and the feature value of the tag into a document DB. Then, the document storage device is configured to, in retrieving a similar document, calculate the word feature value in the number of appearance of each word appearing in the read user designation document, and to, when the tag is designated, calculate the feature value of the tag appearing in the user designation document, to compare the calculated word feature value with the tag feature value, and to calculate the feature vector of the user designation document, and to calculate the similarity of the user designation document and each document included in the document DB by using the calculated feature vector and the feature vector of the document DB. COPYRIGHT: (C)2009,JPO&INPIT