搜索引擎的信息过滤技术

The Filtering Technology of Search Engine

随着网络信息数量的迅猛增长 ,“信息过载”、“信息超载”现象引起了人们的重视。信息过滤技术就是为了克服上述现象 ,减少用户在获得信息过程中的负担 ,向用户提供数量适宜、质量优良的信息。本文在略述了信息过滤技术的产生背景后 ,介绍了两种比较常用的信息过滤模型——布尔逻辑模型和向量空间模型。SIFT是一个著名的信息服务系统 ,它的核心就是信息过滤技术。因此 ,文章还详细地介绍了 SIFT的工作原理和其中所使用到的信息过滤技术 ,并且对 SIFT的性能、特点进行了分析 。

HT5”SS]With the rapid development of the network, the exploding volume of digital information make it very difficult to use for users. Then, the researches focus on the information filtering technology which can reduce the users' burden in the course of obtaining the network information. Firstly, The paper introduce two filtering model ——Boolean model and Vector Space model. After this, the paper give a detailed introduce to the famous information passive service system ——SIFT including its working principle and filtering kernel. Finally, the paper analysis SIFT's function and character and point out some defects in the filtering system. [HT5”H]