摘要
本体匹配是解决语义异构,实现本体共享与重用的一种方法。但本体规模越来越大,为降低匹配空间,提出一种基于模块化思想的本体匹配框架。首先,使用预处理算法将待匹配本体转换成概念图;然后,改进了ROCK聚类算法,并使用该算法将概念图划分成若干高内聚低耦合的概念块;最后,根据Tversky模型,从概念的父、子、兄弟以及内涵4个方面计算块的匹配度,并标记块的重要概念,进行n∶m匹配。实验结果表明,提出的本体匹配框架能够均衡本体分块大小,提高匹配效率。
Ontology matching is a way to solve semantic heterogeneity and to realize the sharing and reuse of ontology.But the size of ontology is increasing, in order to reduce match space, a modularization based ontology matching framework is proposed. Firstly, ontology is transformed into a concept map using preprocessed algorithm. Secondly, the ROCK clustering algorithm is improved, and the concept map is divided into several high cohesion and low coupling concept blocks using this algorithm. Lastly, according to the Tversky model, block match degree is calculated by the father concept, son concept, brother concept and intension. And important concepts of block are signed, n∶m matching is performed. It is observed that the proposed ontology matching framework can balance the block size, improve match efficiency.
引文
[1]Evans D.The internet of things:how the next evolution of the internet is changing everything[J].CISCO White Paper,2011,1:1-11.
[2]薛醒思.基于进化算法的本体匹配问题研究[D].西安:西安电子科技大学,2014.
[3]Ontology alignment evaluation initiative[EB/OL].[2016-05-17].http://oaei.ontologymatching.org/2016.
[4]Noy N F,Chugh A,Liu W,et al.A framework for ontology evolution in collaborative environments[C]//International Semantic Web Conference.Berlin/Heidelberg:Springer,2006:544-558.
[5]Isaac A,Wang S,Van der Meij L,et al.Evaluating thesaurus alignments for semantic interoperability in the library domain[J].IEEE Intelligent Systems,2009,24(2):76-86.
[6]Talukdar P P,Ives Z G,Pereira F.Automatically incorporating new sources in keyword search-based data integration[C]//Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data,2010:387-398.
[7]Dessloch S,Hernández M A,Wisnesky R,et al.Orchid:integrating schema mapping and ETL[C]//2008 IEEE 24th International Conference on Data Engineering,2008:1307-1316.
[8]Euzenat J,Shvaiko P.Ontology matching[M].Heidelberg:Springer,2007.
[9]Grau B,Parsia B,Sirin E.Combining OWL ontologies usingε-connections[J].Web Semantics:Science,Services and Agents on the World Wide Web,2006,4(1):40-59.
[10]Grau B,Parsia B,Sirin E,et al.Modularizing OWL ontologies[C]//Proceedings of 4th International Semantic Web Conference(ISWC-2005),2005.
[11]Grau B,Parsia B,Sirin E,et al.Automatic partitioning of OWL ontologies usingε-connections[C]//Proceedings of International Workshop on Description Logics,2005.
[12]Hu W,Zhao Y,Qu Y.Partition-based block matching of large class hierarchies[C]//Asian Semantic Web Conference.Berlin/Heidelberg:Springer,2006:72-83.
[13]Hu W,Qu Y.Block matching for ontologies[C]//International Semantic Web Conference.Berlin/Heidelberg:Springer,2006:300-313.
[14]杨峰.本体映射关键技术研究[D].长春:吉林大学,2011.
[15]仲茜,李涓子,唐杰,等.基于数据场的大规模本体映射[J].计算机学报,2010(6):955-965.
[16]Guha S,Rastogi R,Shim K.ROCK:a robust clustering algorithm for categorical attributes[C]//15th International Conference on Data Engineering,1999:512-521.
[17]Miller G A.Word Net:a lexical database for English[J].Communications of the ACM,1995,38(11):39-41.
[18]Wang Y.On concept algebra:a denotational mathematical structure for knowledge and software modeling[J].International Journal of Cognitive Informatics and Natural Intelligence(IJCINI),2008,2(2):1-19.
[19]Saruladha K,Ranjini S.COGOM:cognitive theory based ontology matching system[J].Procedia Computer Science,2016,85:301-308.
[20]Rodríguez M A,Egenhofer M J.Determining semantic similarity among entity classes from different ontologies[J].IEEE Transactions on Knowledge and Data Engineering,2003,15(2):442-456.
[21]Tversky A.Features of similarity[J].Psychological Review,1977,84(4).
[22]Ontology alignment evaluation initiative[EB/OL].http://oaei.ontologymatching.org/2016/anatomy/index.html.