公开(公告)号：US20150319506A1

公开(公告)日：2015-11-05

申请号：US14698347

申请日：2015-04-28

Applicant: Netflix, Inc.

Inventor： APURVAKUMAR DILIPKUMAR KANSARA ,  TUSSANEE GARCIA-SHELTON ,  SHIHCHI HUANG ,  CHRISTINE SUEJANE Wu

IPC: H04N21/81 ,  H04N21/435 ,  H04N21/439 ,  H04N21/44

CPC classification number: H04N21/23418 ,  G06F16/5854 ,  G06F16/784 ,  G11B27/10 ,  G11B27/11 ,  G11B27/28 ,  H04N21/233 ,  H04N21/4122 ,  H04N21/4126 ,  H04N21/4307 ,  H04N21/435 ,  H04N21/4394 ,  H04N21/44008 ,  H04N21/8133 ,  H04N21/8547

Abstract: In one approach, a controller computer performs a pre-processing phase involves applying automatic facial recognition, audio recognition, and/or object recognition to frames or static images of a media item to identify actors, music, locations, vehicles, and props or other items that are depicted in the program. The recognized data is used as the basis of queries to one or more data sources to obtain descriptive metadata about people, items, and places that have been recognized in the program. The resulting metadata is stored in a database in association with time point values indicating when the recognized things appeared in the particular program. Thereafter, when an end user plays the same program using a first-screen device, the stored metadata is downloaded to a second-screen device of the end user. When playback reaches the same time point values on the first-screen device, one or more windows, panels or other displays are formed on the second-screen device to display the metadata associated with those time point values.

Abstract translation: 在一种方法中，控制器计算机执行预处理阶段，包括对媒体项目的帧或静态图像应用自动面部识别，音频识别和/或对象识别，以识别演员，音乐，位置，车辆和道具或其他 在程序中描绘的项目。 识别的数据被用作对一个或多个数据源的查询的基础，以获得关于在程序中被识别的人，项目和地点的描述性元数据。 所产生的元数据与时间点值相关联地存储在数据库中，指示在特定程序中出现识别的事件的时间点。 此后，当最终用户使用第一屏幕设备播放相同的节目时，所存储的元数据被下载到最终用户的第二屏幕设备。 当播放在第一屏幕设备上达到相同的时间点值时，在第二屏幕设备上形成一个或多个窗口，面板或其他显示器，以显示与这些时间点值相关联的元数据。