一种改进的多策略模式匹配与结合方式研究  

Research on Improved Method of Multi-strategies Schema Matching and Combination

作　　者：潘峰[1] 孙鹏[1] 张电[1] 

机构地区：[1]72671部队

出　　处：《计算机与数字工程》2011年第11期101-105,共5页Computer & Digital Engineering

摘　　要：针对目前大多数模式匹配方法在应用于不同的匹配任务时,多策略结合时没有充分利用模式间的语义信息的问题,提出了一种改进的多策略匹配方法。该方法对部分关键匹配策略进行了改进,并通过对多策略的评价,考虑是否利用模糊综合评判法最优地结合各种策略。实验表明,该方法在保证通用性和稳定性的同时,提高了匹配结果的查全率和查准率。在现实的Web异构数据源场景中应用该方法,得到的查准率和查全率都很高,证明了该方法的正确性和有效性。Schema matching and entity resolution have been two topics widely studied in the field of database research.With the rising demand in the web data integration,both in schema and instance level,the study of the two tasks is becoming more practical importance.Most current study efforts at resolving one of the two matching tasks.In this paper,based on the new ideas of schema matching benefit from entity resolution,we propose a method that simultaneously attacks these two tasks and achieves a kind of improvement between them.By applying our method to a realistic web heterogeneous data source scenario,show that precision and recall are both quite high,and this method＇s correctness and validity.

关 键 词：WEB信息集成 模式匹配 多策略 模糊综合评判 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]