Information Retrieval Based on Heuristic Key Words Extraction and Clusterings for Documents

Accumulated data has become enormous according to development and spread of Information technology. Generally the data is saved and is organized on the database system with some kinds of keywords and its clustering. In the case of performing the decision for some problems, we often refer to past cases that are similar to the problem. In such a case, if solutions of past cases are kept in the database as documents, it is very useful to solve a problem. We propose a new information retrieval system based on-heuristic key words extracted from documents and a set of clusters for the documents.