基于TF-IDF的新型广播电视节目协同推荐流程

伴随着互联网技术的快速发展和应用拓展，三网（因特网、电信网、广播电视网）融合为传统广播电视媒介带来了发展机遇。但随着数据规模的增长，现有推荐算法对多“目录”广播电视用户精准推荐的效果并未达到预期要求，具有较为明显的不足。本文针对用户之间的相似关系和产品之间的相似度，分别用皮尔逊相关系数、基于TF-IDF的余弦相似度与协同推荐构建了2种可以对新型广播电视用户精准推荐的算法流程，并能够得到产品的准确分类与精准投放。

New Radio and Television Program Collaborative Recommendation Process Based on TF-IDF

With the rapid development of Internet technology and application expansion, triple play (Internet, telecommunication network, broadcast TV network) has brought development opportunities for traditional broadcast TV media. However, with the increase of data size, the existing recommendation algorithm does not meet the expected requirements for the accurate recommendation of many “category” broadcast TV users, and has obvious deficiencies. In this paper, based on the similarity between users and the similarity between products, Pearson correlation coefficient, TF-IDF-based cosine similarity and collaborative recommendation are used to construct two algorithm flows that can be accurately recommended for new broadcast TV users, and can get accurate classification and accurate delivery of products.