A system to transform natural language queries into SQL queries

In the present scenario, every user is not familiar with the use of Structured Query Language (SQL). So, user is not able to understand or write complex queries in SQL. An enhanced application with intelligent interface is needed to improve communication between the naïve user and the databases application. The database is an efficient structure for handling data. To understand the structure of the database, a user has to learn SQL. The non-expert users who are not familiar with the use of SQL, need a system by which the user can interact with the database in their natural language. The system must have the ability to understand the natural language and interact with the database accordingly. In this research, an improved system with three-tier architecture is developed. Pattern matching and semantic matching techniques are used to develop the system which transforms natural language into SQL queries. The SQL query is generated with the production rules and the predefined data dictionary. The predefined data dictionary contains semantics for attributes and relation among attributes. The input given by the user is transformed by the system into SQL query by passing through steps like tokenization, escape word removal, classification of elements and query formation. Finally, the output is in the form of a SQL query. The results are compared with the existing system. The results given by the proposed system are better than the existing system. The proposed system has better recall value, accuracy, and precision in comparison to existing systems.