摘要
以延安大学图书馆读者数据为例,首先通过图书管理系统提取延安大学2012年至2019年读者基础数据,其次对数据进行了清洗、转换、集成。主要采用K-means和Apriori算法对集成后的读者数据进行分析,借助当下较流行的数据分析软件MATLAB和IBM SPSS Modeler实现读者数据的聚类,进而进行数据挖掘,分析各个类别学生的借阅特点及其关联性。最后以延安大学本次搬迁过程中未搬迁四个学院读者数据为例,为本次学校图书馆搬迁中保留院系兴趣书预留情况合理调配提供有力数据支撑,提高纸质图书的利用率。
Taking the library reader data of Yan′an University as an example,the article first extracts the basic reader data of Yan′an University from 2012 to 2019 through the book management system,and then carries on the cleaning,transformation and integration of the data.Using K-means and Apriori algorithm to analyze the integrated reader data,With the more popular data analysis software MATLAB and IBM SPSS Modeler to realize the clustering of reader data,and then carry on the data mining to analyze the borrowing characteristics of the students in each category and its relevance.Finally,the reader data of four colleges which are not relocated during the relocation process of Yan′an University is extracted as examples,which provides a strong data support for the reasonable allocation of the reservation of interest books in the school library,and improves the utilization rate of paper books.
作者
王小娟
WANG Xiao-juan(Library,Yan′an University,Yan′an 716000,China)
出处
《延安大学学报（自然科学版）》
2020年第1期43-47,共5页
Journal of Yan'an University：Natural Science Edition
基金
延安大学2019年科研计划项目(YDY2019-35)。
关键词
读者服务
数据挖掘
聚类算法
关联规则
reader service
data mining
clustering algorithm
association rules
