AN EFFECTIVE NEAREST METHOD TO REDUCE THE INTER-OBJECT'S DISTANCE

A fascinating problem referred to as Nearest Key phrases search would be to query objects, known as keyword cover, which together cover some query key phrases and also have the minimum inter-objects distance. Recently, we take notice of the growing availability and need for keyword rating in object evaluation for that better making decisions. It's quite common the objects inside a spatial database (e.g., restaurants/hotels) are connected with keyword(s) to point their companies/services/features. This motivates us to research a normal form of Nearest Key phrases search known as Best Keyword Cover which views inter-objects distance along with the keyword rating of objects. The baseline formula is inspired through the techniques of Nearest Key phrases search which is dependent on exhaustively mixing objects from various query key phrases to create candidate keyword covers. The in-depth analysis and extensive experiments on real data sets have justified the brilliance in our keyword-NNE formula. When the amount of query key phrases increases, the performance from the baseline formula drops significantly because of massive candidate keyword covers produced. To fight this drawback, the work proposes an infinitely more scalable formula known as keyword nearest neighbor expansion (keyword-NNE). In comparison towards the baseline formula, keyword-NNE formula considerably reduces the amount of candidate keyword covers produced