摘要
为提升用户获取所需资源的速度与精度,研究一种图书馆信息库资源自动检索方法。利用谱聚类算法聚类资源词特征,得到特征簇,确定资源标签和特征簇的相关性,再完成资源聚类;对聚类资源进行预处理;再提取预处理后资源的特征;建立多属性灰色关联度决策模型,将提取的特征转换成二元特征函数输入决策模型,输出最佳检索方案,完成资源自动检索。实验证明:该方法可有效检索图书馆资源,具备较高的资源检索效率,检索精度高,可有效提升资源检索效果。
In order to improve the speed and accuracy of users'access to required resources,this paper studies an automatic retrieval method of library information database resources.The spectral clustering algorithm is used to cluster the features of resource words,ob-tain the feature clusters,determine the correlation between resource tags and feature clusters,and then complete resource cluster-ing,preprocess clustering resources,then extract the characteristics of the preprocessed resources.The multi-attribute grey corre-lation decision-making model is established,the extracted features are transformed into binary feature functions,input the deci-sion-making model,output the best retrieval scheme,and complete the automatic retrieval of resources.Experiments show that this method can effectively retrieve library resources and has faster resource retrieval efficiency;High retrieval accuracy can ef-fectively improve the effect of resource retrieval.
作者
顾志芹
GU Zhi-qin(Huazhong University of Science and Technology Library,Wuhan 430074 China)
出处
《自动化技术与应用》
2023年第11期77-81,共5页
Techniques of Automation and Applications
关键词
图书馆信息库
自动化
资源检索
谱聚类
library information base
automation
resource retrieval
spectral clustering
