Video Semantic Information Architecture Based on Web Crawlers

In order to apply the web crawler´s technology to the construction of video semantic information, this paper propose the video information collection architecture based on Web crawler after has analyzed the basic principles, key technologies and problems of the current crawler technology. The system framework divided to two parts. The background part mainly manage Web crawler; Foreground part mainly view and artificial secondary correct the video semantic information which the crawler has collected. The results showed that: the video semantic information library based on the Web crawler is not only complete, and become more reasonable after adding the necessary human intervention.