An Intelligent System for Relational Databases

Todays present computing world, most new-generation database applications demand intelligent interface to enhance efficient interactions between database and the users. The most accessible interfaces for databases must be intelligent and able to understand natural language expressions. In this paper mapping of natural language queries to SQL is suggested. We propose a general architecture for an intelligent database system and also a real implementation of such a system which can be connected to any database. One of the main characteristics of this interface is domain-independence, which means that this interface can be used with any database. Another characteristic of this system is ease of configuration. The intelligent system employs semantic matching technique to convert natural language query to SQL using dictionary and set of production rules. The dictionary consists of semantics sets for tables and columns. The shaped query is executed and the results are presented to the user. This interface was first tested using Supplier-Parts database and secondly with Northwind database of SQL server 7.0.