一种基于序列相似性的图书采访查重算法  

On the Algorithms of Sequence Alignment in Duplicate Checking of Book Acquisition

作　　者：马凯[1] 

机构地区：[1]钦州学院图书馆,广西钦州535000

出　　处：《钦州学院学报》2015年第5期41-44,共4页Journal of Qinzhou University

基　　金：2012年钦州学院校级科研项目:智能图书采访查重系统研究(2012XJKYQN-05)

摘　　要：传统图书采访查重方法存在容错性差、漏检等问题,将序列相似性S3M引入查重过程作为字符串相似的度量,能有效地对查重的书目数据进行模糊匹配,提高查重的查全率和查准率。This paper proposes algorithms of sequence alignment in duplicate checking of book acquisition, which introduces duplicate checking process of sequence alignment S^3M as a string similarity t according to the characteristics of the duplicate checking data. The practical results show that the algorithm can effectively make fuzzy matching to bibliographic data and increase the recall and precision ratio, which is of practical value.

关 键 词：图书采访查重 模糊匹配 序列相似性 S^3M相似度 

分 类 号：G250[文化科学—图书馆学]