摘要： 针对服务提供者收割的大量元数据组织问题，提出一种基于以高频项目组合为基础之阶层式文件群聚法(FIHC)的元数据收割协议服务提供者框架，通过FIHC模块对元数据进行聚类并生成一棵簇树。实验结果表明，该框架能够合理组织元数据，提高了检索速度，便于用户按类浏览。

关键词: 以高频项目组合为基础之阶层式文件群聚法, 元数据收割协议, 服务提供者, 元数据

Abstract:

Aiming at the organizational problem of metadata harvested by the service provider, this paper proposes Open Archives Initiative Protocol for Metadata Harvesting(OAI-PMH) service provider framework based on Frequent Itemset-based Hierarchical Clustering(FIHC). It utilizes FIHC module to cluster the metadata and generate a cluster tree. Experimental result shows that this framework can reasonably organize metadata, improve metadata search speed and be convenient for user to browse metadata by category.

Key words: Frequent Itemset-based Hierarchical Clustering(FIHC), Open Archives Initiative Protocol for Metadata Harvesting(OAI-PMH), service provider, metadata

中图分类号: 

• TP393