Answering to conceptual queries

A new system is proposed that produces useful answers to conceptual queries. A conceptual query is a linguistic query expressing a user's desire for information when he is not familiar with the database. First, the authors propose a method to construct a "macro database", which is a set of fuzzy clusters of the data in the database, and is regarded as the knowledge for the distribution of the data. Then, the authors propose a new method to generate useful answers to conceptual queries using the macro database. Finally, the authors apply them to an actual database and show the effectiveness. >