基于Lucene的BM25模型的评分机制的研究  

Research on Scoring Mechanism of BM25 Model Based on Lucene

作　　者：范晨熙[1] 黄理灿[1] 李雪利[1] 

机构地区：[1]浙江理工大学信息学院,浙江杭州310018

出　　处：《工业控制计算机》2013年第3期78-79,共2页Industrial Control Computer

摘　　要：Okapi BM25是一种相关性排序函数,适用于搜索引擎根据与给定搜索查询的相关性对匹配文档进行排序。通过BM25模型与开源搜索框架Lucene的有机结合,实现了BM25模型在Lucene中的检索评分。经实验表明,BM25模型在Lucene中有较好的表现,为进一步根据实际需求利用BM25模型和Lucene进行全文检索做出了有益的探索。Okapi BM25 is a relevance ran＇king function,applied to the search engine according to the given search query relevance ranking documents to match.In this paper,through the BM25 model in the open source search framework of Lucene organically,realizing the BM25 model in Lucene score.The experiments show that,the BM25 model in Lucene have better performance,in order to further according to the actuat requirement by using BM25 model and Lucene made beneficial exploration.

关 键 词：BM25 LUCENE 全文检索 评分机制 搜索引擎 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]