Research On Multiple Entities Diversifying Association Search

Searching for associations between entities is needed in many domains like na-tional security and bioinformatics.In recent years,it has been facilitated by the emer-gence of graph-structured semantic data on the Web,which offers structured seman-tic associations more explicit than those hiding in unstructured text for computers to discover.The increasing volume of semantic data often produces excessively many semantic associations,and requires ranking techniques to identify the more important ones for users.Users often only want to understand a number of entities and their relationships by looking at some important,valuable associations that contain as much information as possible.Therefore,there is a need to search for multiple entities top-k association.The multiple entities top-k association search returns a list of k semantic associations with the largest scores for this query.In fact,some of the top-k results may be similar,they contain very similar semantics,providing users with redundant information.The multiple entities diversifying top-k association search not only considers the spores of semantic associations,but also the diversity of semantic associations.In order to do multiple entities diversifying top-k association search,three issues need to be addressed.First,how to measure the importance of semantic association,that is,how to sort semantic associations;second,how to measure the similarity be-tween two semantic associations;third,how to fast search for optimal diversifying top-k semantic association.This article explores these issues,and there are two main contributions:1.Designed a method for multiple entities association ranking.The ranking prin-ciples are size and entity homogeneity of semantic association,and implemented a mul-tiple entities top-k association search method.2.Implemented some multiple entities diversifying top-k association search meth-ods.Jointly considering structural and semantic similarity,a similarity measure method for semantic association was proposed.