公开(公告)号：US10192583B2

公开(公告)日：2019-01-29

申请号：US14811465

申请日：2015-07-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Meng Chee ,  Paul Dixon ,  Florian Dusch ,  Hyung Keun Kim ,  Luyza Viana Pereira ,  Bartley H. Calder ,  Scott Barrow ,  Sudhir Kumar Misra ,  Gabriel Nicolae

IPC: G11B27/031 ,  G11B27/06 ,  G11B27/11 ,  G11B27/34 ,  H04N5/265 ,  H04N5/77 ,  H04N21/239 ,  H04N21/25 ,  H04N21/258 ,  H04N21/2668 ,  H04N5/783 ,  H04N9/82 ,  H04N21/2743 ,  H04N21/414 ,  H04N21/4788 ,  H04N21/854 ,  H04N21/422 ,  H04N21/472 ,  H04N21/4722

Abstract: Video editing using contextual data may include collecting metadata from a sensor concurrently with recording a video, wherein the metadata is synchronized in time with the video, detecting attributes within the metadata and attributes from the video, and correlating the attributes with a plurality of editors. An editor may be selected from the plurality of editors according to the correlating and a video editing workflow may be automatically initiated. Content discovery using clusters may include receiving a user request for video content from a device, determining a behavioral cluster for the user according to demographic data for the user, determining a video of interest associated with the behavioral cluster, and providing a video of interest to the device using the processor.

公开(公告)号：US10073673B2

公开(公告)日：2018-09-11

申请号：US14330888

申请日：2014-07-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： George Brancovici ,  Gabriel Nicolae ,  Hiep Luong ,  Sindhu Vijaya-Raghavan ,  Yonghoon Lee

IPC: G06F17/21 ,  G06F3/16 ,  G06F17/27 ,  G10L15/18

CPC classification number: G06F3/167 ,  G06F17/2735 ,  G06F17/278 ,  G06F17/2785 ,  G10L15/1815

Abstract: A system includes a storage device configured to store a plurality of named entities collected from a plurality of sources, tokenized, and associated with a label. The system includes a tagging apparatus configured to receive textual communications, identify each of the textual communications, tokenize the textual communications, match the textual tokens with the named entities tokens stored in the storage device in order to assign the textual tokens to the labels associated with the named entity tokens, tag the textual communications based on the matching between the textual tokens and the named entity tokens in order to identify the intended meaning of each of the textual communications, and identify the intended meaning of the textual communications based on applying the tags to the textual communications. A method capable of disambiguating named entities using a common sense reasoning approach is also disclosed.

公开(公告)号：US20160104508A1

公开(公告)日：2016-04-14

申请号：US14811465

申请日：2015-07-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Meng Chee ,  Paul Dixon ,  Florian Dusch ,  Hyung Keun Kim ,  Luyza Viana Pereira ,  Bartley H. Calder ,  Scott Barrow ,  Sudhir Kumar Misra ,  Gabriel Nicolae

IPC: G11B27/031 ,  G11B27/34 ,  G11B27/11 ,  H04N21/2668 ,  H04N5/77 ,  H04N21/239 ,  H04N21/258 ,  H04N21/25 ,  G11B27/06 ,  H04N5/265

CPC classification number: G11B27/031 ,  G11B27/06 ,  G11B27/11 ,  G11B27/34 ,  H04N5/265 ,  H04N5/77 ,  H04N5/783 ,  H04N9/8205 ,  H04N21/2393 ,  H04N21/252 ,  H04N21/25883 ,  H04N21/25891 ,  H04N21/2668 ,  H04N21/2743 ,  H04N21/41407 ,  H04N21/42201 ,  H04N21/42202 ,  H04N21/47205 ,  H04N21/4722 ,  H04N21/4788 ,  H04N21/854

Abstract: Video editing using contextual data may include collecting metadata from a sensor concurrently with recording a video, wherein the metadata is synchronized in time with the video, detecting attributes within the metadata and attributes from the video, and correlating the attributes with a plurality of editors. An editor may be selected from the plurality of editors according to the correlating and a video editing workflow may be automatically initiated. Content discovery using clusters may include receiving a user request for video content from a device, determining a behavioral cluster for the user according to demographic data for the user, determining a video of interest associated with the behavioral cluster, and providing a video of interest to the device using the processor.

Abstract translation: 使用上下文数据的视频编辑可以包括从记录媒体同时收集来自传感器的元数据，其中元数据与视频同步，元数据中的属性和来自视频的属性，以及将属性与多个编辑器相关联。 可以根据相关性从多个编辑器中选择编辑器，并且可以自动启动视频编辑工作流程。 使用群集的内容发现可以包括从设备接收视频内容的用户请求，根据用户的人口统计数据确定用户的行为群集，确定与行为群集相关联的感兴趣的视频，以及提供感兴趣的视频 该设备使用处理器。