一种两阶段的多媒体教育资源网页消重方法

A Two-stage Method on the Elimination of Duplicated Multimedia Webpages

随着开放教育资源运动开展与深入，在互联网络中形成开放的、超大规模的、世界范围内最先进的多媒体教育资源网页集群。然而使用搜索引擎检索的结果中存在大量的重复网页，导致资源获取难、利用率低的问题。文章在总结现有网页消重方法的基础上提出一种可行的两阶段的多媒体教育资源网页消重方法，实验证明，通过对网页文本信息及多媒体信息分开消重，能有效地提高消重的效果。

With the development of the open educational resources movement， there have been formed an open， ultra-large-scale， world-wide the most advanced multimedia educational web page cluster in the Internet .However there are a lot of duplicate pages after using the search engines ， which leading to the difficult access to resources and the low utilization rate.This article proposes a two-stage method on the elimination of duplicated multimedia webpages on the basis of summing up the existing way.The experimental results show that it can improve the results effectively .