基于二元中文分词的高效检索算法研究

An Effective Retrieval Research Based on 2-gram Chinese Word Segmentation

针对传统的like通配符检索存在的问题,提出基于二元中文分词的高效率检索算法的思路、流程,给出核心算法代码;在消除重复词语、查全率、查准率、多字词检索等方面,与传统检索进行比较,各方面评测结果都优于传统检索;基于二元中文分词的高效率检索算法,简单、高效、容易实现,以期在信息系统的检索模块中得以利用,提高信息检索效率,减小信息搜索成本。

For the problem of ＇like＇ in traditional information retrieval, this paper gives ideas, processes, and the core algorithm code which based on the 2-gram Chinese word segmentation. It compares the new solution with the traditional information retrieval on the eliminating same words, precision ratio, recall ratio, and multi-words search, and finds it works more effective. The effective way which based on the 2-gram Chinese word segmentation is simple, effective, and can be implemented easily in the search module of many information systems. It can improve the efficiency of information retrieval, and reduce the cost of information search.