Research progress in similarity join query of big data
In order to deeply understand and fully grasp the research progress of similarity join query technology of big data and to promote its wide application in image clustering,entity resolution,similar document detection,similar trajectory retrieval,a comprehensive survey was conducted on similarity join query technology of big data.Firstly,the basic concepts of similarity join query were introduced;then intensive study on the big data similarity join research works for different data types,such as set,vector,spatial data,probabilistic data,string and graph was elaborated,their advantages and disadvantages were analyzed and summarized.Finally,some challenging research problems and future research priorities in big data similarity join query were pointed out.
big datasimilarity join queryMapReduce frameworkK-Nearest Neighbors (KNN)
NETL
NSTL
万方数据
维普
