时间约束的实体解析中记录对排序研究  

Research on Record Pair Ranking for Entity Resolution with Time Constraint

作　　者：孙琛琛 申德荣 李玉坤[1,2] 肖迎元[1,2] 马建红 SUN Chen-Chen;SHEN De-Rong;LI Yu-Kun;XIAO Ying-Yuan;MA Jian-Hong(Key Laboratory of Computer Vision and System of Ministry of Education(Tianjin University of Technology),Tianjin 300384,China;Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology(Tianjin University of Technology),Tianjin 300384,China;School of Computer Science and Engineering,Northeastern University,Shenyang 110189,China;School of ArtificialIntelligence,Hebei University of Technology,Tianjin 300401,China)

机构地区：[1]计算机视觉与系统教育部重点实验室(天津理工大学),天津300384 [2]天津市智能计算及软件新技术重点实验室(天津理工大学),天津300384 [3]东北大学计算机科学与工程学院,辽宁沈阳110189 [4]河北工业大学人工智能与数据科学学院,天津300401

出　　处：《软件学报》2020年第3期695-709,共15页Journal of Software

基　　金：国家重点研发计划(2018YFB1003404);国家自然科学基金(61672142,61472070,61602103);天津市自然科学基金(17JCYBJC15200)。

摘　　要：实体解析是数据集成和数据清洗的重要组成部分,也是大数据分析与挖掘的必要预处理步骤.传统的批处理式实体解析的整体运行时间较长,无法满足当前(近似)实时的数据应用需求.因此,研究时间约束的实体解析,其核心问题是基于匹配可能性的记录对排序.通过对多路分块得到的块内信息与块间信息分别进行分析,提出两个基本的记录匹配可能性计算方法.在此基础上,提出一种基于二分图上相似性传播的记录匹配可能性计算方法.将记录对、块及其关联关系构建二分图;相似性沿着二分图不断地在记录对结点与块结点之间传播,直到收敛.收敛结果可以通过不动点计算得到.提出近似的收敛计算方法来降低计算代价,从而保证实体解析的实时召回率.最后,在两个数据集上进行实验评价,验证了所提出方法的有效性,并测试方法的各个方面.Entity resolution(ER)is an important aspect of data integration and data cleaning,and is also a necessary pre-process step of big data analytics and mining.Traditional batch based ER’s overall runtime is costly,and cannot satisfy current(nearly)real-time data applications’requirements.Therefore,time constraint entity resolution(TC-ER)is focused on,while core problem is record pair ranking according to match probability both information inner blocks and information across blocks are analyzed from multi-pass blocking respectively,and two basic recordsmatch probability methods are proposed.The basic methods are improved by proposing an advanced record match probability method based on similarity flowing over a biparitite graph.A bipartite graph is constructed according to record pairs,blocks,and relations between them.Similarities iteratively flow between pair nodes and block nodes over the bipartite graph until convergence.The convergence result is computed with fixpoint iterations.An approximate convergence computation mehod is proposed to reduce cost,and it improves real-time recall in TC-ER.Finally,the proposed methods are evaluated on two datasets,which shows their effectiveness and also tests different aspects of the proposed methods.

关 键 词：实体解析 记录对排序 时间约束 数据集成 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]