类Gnutella网络文本检索研究

Research on Text Retrieval in Gnutella-like Networks

提出类Gnutella网络文本检索的方法,借助文本聚类技术构建无结构P2P语义覆盖网,每个节点维护一定数量的短程连接和长程连接邻居节点,使P2P网络具有小世界特性。邻居节点的更新在查询和应答的交互中进行,节点能动态快速地了解网络的拓扑情况。实验结果表明,小世界P2P网络具有较大的聚类系数、较小的特征路径长度和较高的文本检索查全率。

A text retrieval method is proposed in Gnutella-like networks, which resorts to text clustering to construct a semantic overlay in the unstructured Peer-to-Peer（P2P） network. Each node maintains several long-link neighbors and short-link neighbors to build a small world P2P networks. Neighbors update is processed during the query and response. This makes it rapidly to find out the networks topology. Experimental results show that small world P2P network yields higher recall and takes on the characteristics of small world with greater clustering coefficient and lower average path length.