Paper Title
K-Nearest Neighbours Approximate Keyword Search For Spatial Database

Keyword search over a large amount of data is an important operation in a wide range of domains. Nearest neighbor objects with required for location-based search from spatial database has been well studied for years due to its importance to commercial search engines. Specially, the top-k spatial keyword query takes a user location and user-supplied keywords as arguments and returns objects that is nearest k objects from user current location and textually relevant to the user required keyword. In these systems, inconsistencies and errors can exist in the user’s typed queries. This paper proposes new index structure that combines K-d tree and inverted file to answer such query efficiently and we also discuss how to answer the queries that contain the user typing error in keyword. Keywords- KNN Approximate Keyword Search, Experimental Results.