摘要
因特网上信息检索的新问题需要新理论来解决,概率检索理论是其中选择之一。本文在基于英文的概率检索理论基础上,提出了改进的基于汉字的概率检索理论,在实现中又以直接排序代替了先计算后排序的思路,使得所开发软件达到实用程度。
In order to solve the new problem in information retrieval on Internet,the new theory is needed.The probabilistic retrieval theory is one option among them.On the basis of English probabilistic retrieval theory,this article puts forward an improved one based on Chinese character.In the implementation,the thought of computing first and ordering afterwards is replaced by direct ordering,so the developing software can be practically used.
出处
《情报学报》
CSSCI
北大核心
1999年第5期399-403,共5页
Journal of the China Society for Scientific and Technical Information
关键词
因特网
信息检索
汉字
概率检索
计算机网络
Internet,information retrieval,software,Chinese character,probabilistic retrieval.