面向企业信息集成的数据一致性修复方法  

Data consistency repair method for enterprise information integration

作　　者：刘波[1] 刘欢[1] 

机构地区：[1]暨南大学信息科学技术学院计算机科学系,广东广州510632

出　　处：《计算机集成制造系统》2013年第10期2664-2669,共6页Computer Integrated Manufacturing Systems

基　　金：广东省自然科学基金资助项目(S2012010008831);广东省科技攻关资助项目(2010B010600026)~~

摘　　要：为了有效、自动地修复在企业多个信息源的数据库操作中产生的错误或不一致数据,基于数据库的函数依赖和包含依赖,提出新的修复算法。算法针对违背函数依赖的数据,计算相关属性的统计度量,根据元组的可信度选择需要修改的元组;针对违背包含依赖的数据,匹配不同数据集之间的部分属性值,确定如何修改或插入新元组。算法对数据库不实施删除操作,保证了原数据库信息的完整性,具有客观、准确、高效等特性,能够应用于解决企业信息集成中出现的数据不一致问题。To repair error or inconsistent data produced in the operations of enterprise＇s multiple sources databases effectively and automatically, a new repairing algorithm based on functional dependencies and inclusion dependencies was presented. For violations on functional dependencies, the related attribute statistical measures were computed by this algorithm and the tuples to be modified by tuples＇ confidence were selected. Aiming at the violations on in- clusion dependencies, parts of attribute values between different datasets were matched and the method to update or insert new tuples was determined. Deletion operations were not adopted in the algorithms for no loss of information in original databases. The proposed algorithm had features such as objective, accurate and efficient, and could solve the inconsistent problems in enterprise information integration.

关 键 词：信息集成 一致性 修复 数据库 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]