聚类挖掘在高校图书馆管理系统中的应用  

The Application of Clustering mining in University Library Management System

作　　者：韩存鸽[1] 

机构地区：[1]武夷学院数学与计算机系,福建武夷山354300

出　　处：《重庆理工大学学报（自然科学）》2012年第11期83-87,共5页Journal of Chongqing University of Technology：Natural Science

基　　金：武夷学院科研资金资助项目(xl201014)

摘　　要：介绍了聚类挖掘的基本理论。对武夷学院图书馆提供的流通数据进行了聚类分析,主要采集读者借阅册数和图书流通量2类数据,在Clementine中使用K-means模型从读者的借阅册数角度进行分类,将读者划分成"活跃读者""消极读者"及"一般读者"3类。根据图书流通量进行分类,将图书分成"热门书""冷门书"及"一般书"3类。根据聚类挖掘的结果,为不同类的读者提供不同的服务,针对不同类的图书采取相应的措施。This paper made clear the basic theory of clustering mining.Wuyi institute library provided circulation data processing： the main collection book borrowing amount of data and book circulation data these two kinds.K-means model was used in Clementine to classify the readers from the perspective of lending copies.Readers could be divided into ＂active readers＂,＂negative readers＂ and ＂general readers＂ three kinds.According to the book circulation classification,the books were divided into ＂hot books＂,＂unpopular books＂ and ＂general books＂ three categories.According to the results of cluster mining,different services could be provided for different kinds of readers,and corresponding measures could be taken to different books.

关 键 词：聚类挖掘 CLEMENTINE K-means模型 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]