Natural Language SQL Query Processing using Fuzzy Matching and Elimination Technique

Abstract

In Structured Query Language (SQL), complex queries are difficult to write or understand by a user, because every user is not familiar with SQL. A common user can able to retrieve the information from the query databases using natural language is considered as an important research area. To improve the communication between databases application and naive user, an enhanced application with intelligent interface are needed. A fuzzy system with matching and elimination technique is designed in this research study, where SQL queries are formed from the input given by the user through several steps like noise removal, lexicon normalization and query formation. Then, the system uses the Latent Dirichlet Allocation (LDA) to extract the keywords from the input query. Finally, matching and elimination techniques are used to find the data, which is related to the input query given by end-user. When compared with the existing SQL techniques, the proposed fuzzy method achieved 91% and 90.5% accuracy, 95% and 93% precision, and 0.10 and 0.12 error rate for both 28 and 50 queries.