An Amended Keyword Cover Search Approaches

Abstract

In recent years, we notice the increasing availability and value of keyword rating in object evaluation for the simpler choice making. This motivates us to investigate a frequent variation of closest keyword phrases search called generic key word which considers inter-objects distance as well as the keyword ranking of objects. The baseline algorithm is motivated with the aid of the methods of closest key words search which is established on exhaustively combining objects from extraordinary query keywords to generate candidate keyword covers. When the number of query keywords increases, the performance of the baseline algorithm drops dramatically thus of massive candidate key phrase covers generated. To attack this situation, this work proposes a way more scalable algorithm called keyword nearest neighbor expansion (key phrase-NNE).In comparison with the baseline algorithm, keyword-NNEalgorithm vastly reduces the number of candidate keyword covers generated. The in-depth analysis and broad experiments on actual data units have justified the prevalence of our key phrase-NE algorithm.