摘要
随着数字化时代的到来,图书馆数字资源的管理和维护变得越来越重要,然而传统的评价方法往往无法准确地衡量图书馆数字资源的完整性。研究提出一种融合k-prototypes算法和信息熵加权的图书馆数字资源完整性自动化评价方法。该方法综合考虑了数据属性的类型差异、属性之间的关联性和重要性。经实验表明,研究算法聚类纯度超过0.9;图书馆目录数据集内部样本的离散程度最大,图书馆的数据覆盖率的平均分值为8.4,比数据准确性和数据更新性的平均分值分别高0.21和3.9,为图书馆数字资源的管理和维护提供了一种有效的工具和方法。
With the advent of the digital age,the management and maintenance of library digital resources are becoming more and more important.However,traditional evaluation methods are often unable to accurately measure the integrity of library digital resources.Therefore,an automated evaluation method for the integrity of library digital resources is proposed in this study,which integrates k-prototypes algorithm and information entropy weighting.The method comprehensively considers the type difference of data attributes,the relevance and importance among attributes.The experimental results show that the clustering purity of the proposed algorithm exceeds 0.9.The sample within the library catalog dataset has the largest degree of dispersion,and the average score of the library's data coverage is 8.4,which is 0.21 and 3.9 higher than the average score of data accuracy and data updating,respectively.To sum up,this study provides an effective tool and method for the management and maintenance of library digital resources.
作者
任阳红
REN Yang-hong(Yangling Vocational&Technical College,Yangling 712100,China)
出处
《自动化技术与应用》
2025年第6期67-71,116,共6页
Techniques of Automation and Applications
基金
陕西省重点研发计划项目(2024NC-YBXM-207)
杨凌职业技术学院2023年校内基金项目(SKYB-2364)
杨凌职业技术学院2024年校内教改项目(JG24092)。
关键词
信息熵加权
图书馆数字资源
自动化评价
聚类分析
information entropy weighting
library digital resources
automatic evaluation
cluster analysis
