发明名称 Methods and systems for online recommendation
摘要 A method for recommending videos is presented. The method includes generating a cross-usage matrix based upon a data of video sessions for a plurality of videos, generating a temporal matrix based upon release dates of the plurality of videos, generating a cross-temporal matrix based upon the cross-usage matrix and the temporal matrix, computing a global video rank corresponding to each of the plurality of videos based upon the cross-temporal matrix, generating a similarity score corresponding to each pair of videos in the plurality of videos based upon meta-data of the plurality of videos, and generating a local video rank corresponding to each of the plurality of videos relative to another video in the plurality of videos based upon the generated cross-usage matrix, the computed global video rank and the generated similarity score.
申请公布号 US9071857(B2) 申请公布日期 2015.06.30
申请号 US201313744243 申请日期 2013.01.17
申请人 NBCUniversal Media, LLC 发明人 Xue Ya;Moitra Abha;Gustafson Steven Matt
分类号 H04N21/258;G06F17/30;H04N21/466;H04N21/482;H04N21/84 主分类号 H04N21/258
代理机构 Fletcher Yoder, P.C. 代理人 Fletcher Yoder, P.C.
主权项 1. A computer implemented method for recommending videos, comprising: generating, via a processing subsystem, a first attribute based on data of video sessions for a plurality of videos; generating, via the processing subsystem, a temporal attribute based on release dates of the plurality of videos; generating, via the processing subsystem, temporal video session data based on the first attribute and the temporal attribute; computing a global video rank corresponding to each of the plurality of videos based on a cross-temporal attribute derived from the temporal video session data; generating, via the processing subsystem, a similarity attribute corresponding to a pair of videos in the plurality of videos based on meta-data of the plurality of videos generating, via the processing subsystem, temporal video session data based on the first attribute and the temporal attribute; generating a local video rank based on the cross-temporal attribute, the global video rank, and the similarity attribute; and recommending, via the processing subsystem, a video to a user based on the local video rank corresponding to a video of the plurality of videos relative to another video in the plurality of videos and the similarity attribute.
地址 Wilmington DE US