影视节目扁平化标签获取技术研究

针对影视节目标签手动采集费时费力，以及传统树状标签体系信息冗余且不全面等问题，提出一种标签自动获取技术。通过数据爬取技术采集与节目相关的互联网原始数据，然后通过文本分析、同义匹配、数据库匹配等技术进行数据分析与挖掘，最终实现对扁平化节目标签的获取。实验结果表明，在选取8～10个标签时，该算法准确率为84.3%~ 92.4%，召回率为53.4%~ 63.1%，说明该算法获取的标签能够很好地对影视节目进行描述。

Research on the Acquisition Technology of Film and Television Program Flat Tags

This paper proposes an automatic tag acquisition technology for the which is time-consuming and labor-intensive manual collection of film and television program tags and the information redundancy and incompleteness of the traditional tree tag system. Our research collects the original Internet data related to the program through data crawling technology， and then analyzes and mines the data through text analysis， synonym matching， database matching and other technologies. Finally we achieve the acquisition of flat program tags. The experimental results show that the accuracy of this algorithm is 84.3%~92.4% when 8-10 labels are selected， and the recall rate is 53.4%~63.1%. This proves that the label obtained by the algorithm in this paper can describe a program well.