公开(公告)号：EP2749038B1

公开(公告)日：2018-11-28

申请号：EP12741049.6

申请日：2012-06-22

申请人： Inview Technology Limited

发明人： AUSTIN, Kenneth

IPC分类号： H04N21/442 ,  H04N21/466 ,  G06F17/30

CPC分类号： H04N21/4666 ,  G06F17/30029 ,  H04N21/44222 ,  H04N21/4661 ,  H04N21/4668

摘要： A method for facilitating the generation of recommendations of audiovisual content for a first user. The method comprises receiving data from a plurality of second users, the received data indicating audiovisual content of interest to the second users. The method further comprises processing the received data to automatically identify a plurality of relationships between interests of one or more of the second users in respective items of audiovisual content in the audiovisual content represented by the received data and generate a recommendation engine. The recommendation engine is adapted to take as input indications of audiovisual content of interest to the first user and to generate recommendations of further audiovisual content of interest to the first user based upon a subset of the plurality of relationships.

公开(公告)号：EP3366043A1

公开(公告)日：2018-08-29

申请号：EP16787973.3

申请日：2016-10-13

申请人： Microsoft Technology Licensing, LLC

发明人： YAO, Ting ,  MEI, Tao ,  RUI, Yong

IPC分类号： H04N21/8549 ,  H04N21/4545 ,  H04N21/466

CPC分类号： G06K9/00718 ,  G06K9/00751 ,  G11B27/031 ,  G11B27/3081 ,  H04N21/45457 ,  H04N21/4666 ,  H04N21/8549

摘要： Video highlight detection using pairwise deep ranking neural network training is described. In some examples, highlights in a video are discovered, then used for generating summarization of videos, such as first-person videos. A pairwise deep ranking model is employed to learn the relationship between previously identified highlight and non-highlight video segments. This relationship is encapsulated in a neural network. An example two stream process generates highlight scores for each segment of a user's video. The obtained highlight scores are used to summarize highlights of the user's video.

公开(公告)号：EP2024862A4

公开(公告)日：2011-08-10

申请号：EP07761775

申请日：2007-05-02

申请人： INVIDI TECHNOLOGIES CORP

发明人： COX EARL ,  SHEEHAN PATRICK M ,  PETERSON II ALDEN LLOYD

IPC分类号： G06Q30/00 ,  G06F15/18

CPC分类号： H04N21/4666 ,  G06Q30/02 ,  H04H60/45 ,  H04H2201/70 ,  H04N21/25883 ,  H04N21/25891 ,  H04N21/2668 ,  H04N21/44218 ,  H04N21/44222 ,  H04N21/4667 ,  H04N21/6338 ,  H04N21/812

公开(公告)号：EP2024862A2

公开(公告)日：2009-02-18

申请号：EP07761775.1

申请日：2007-05-02

申请人： Invidi Technologies Corporation

发明人： COX, Earl ,  SHEEHAN, Patrick M. ,  PETERSON, II, Alden Lloyd

IPC分类号： G06F15/18

CPC分类号： H04N21/4666 ,  G06Q30/02 ,  H04H60/45 ,  H04H2201/70 ,  H04N21/25883 ,  H04N21/25891 ,  H04N21/2668 ,  H04N21/44218 ,  H04N21/44222 ,  H04N21/4667 ,  H04N21/6338 ,  H04N21/812

摘要： A targeted advertising system uses a machine learning tool to select an asset for a current user of a user equipment device, for example, to select an ad for delivery to a current user of a digital set top box in a cable network. The machine learning tool first operates in a learning mode to receive user inputs and develop evidence that can characterize multiple users of the user equipment device audience. In a working mode, the machine learning tool processes current user inputs to match a current user to one of the identified users of that user equipment device audience (Fig 8, Bl 1202). Fuzzy logic may be used to improve development of the user characterizations, as well as matching of the current user to those developed characterizations. In this manner, targeting of assets can be implemented not only based on characteristics of a household but based on a current user within that household (Fig 8, Bl 1214).

公开(公告)号：EP4374390A1

公开(公告)日：2024-05-29

申请号：EP22743859.5

申请日：2022-07-06

申请人： Sony Group Corporation ,  Sony Europe B.V.

发明人： ROMAN, Andres Jose ,  DI FRANCESCO, Renaud

IPC分类号： G16H50/00 ,  G06F16/435 ,  H04N21/25

CPC分类号： G16H50/00 ,  H04N21/251 ,  H04N21/42201 ,  H04N21/485 ,  H04N21/4666 ,  H04N21/4668 ,  G06F16/436

公开(公告)号：EP3295669A1

公开(公告)日：2018-03-21

申请号：EP16724787

申请日：2016-05-09

申请人： NETFLIX INC

发明人： AARON ANNE ,  KIM DAE ,  LIN YU CHIEH ,  RONCA DAVID ,  SCHULER ANDY ,  TSAO KUYEN ,  WU CHI HAO

IPC分类号： H04N19/154 ,  G06T9/00 ,  H04N21/466

CPC分类号： G06T7/0002 ,  G06T7/20 ,  G06T9/002 ,  G06T2207/10016 ,  G06T2207/20084 ,  G06T2207/30168 ,  H04N19/154 ,  H04N21/466 ,  H04N21/4666

摘要： In one embodiment of the present invention, a quality trainer and quality calculator collaborate to establish a consistent perceptual quality metric via machine learning. In a training phase, the quality trainer leverages machine intelligence techniques to create a perceptual quality model that combines objective metrics to optimally track a subjective metric assigned during viewings of training videos. Subsequently, the quality calculator applies the perceptual quality model to values for the objective metrics for a target video, thereby generating a perceptual quality score for the target video. In this fashion, the perceptual quality model judiciously fuses the objective metrics for the target video based on the visual feedback processed during the training phase. Since the contribution of each objective metric to the perceptual quality score is determined based on empirical data, the perceptual quality score is a more accurate assessment of observed video quality than conventional objective metrics.

公开(公告)号：EP3038351A1

公开(公告)日：2016-06-29

申请号：EP16154355.8

申请日：1999-07-16

申请人： Rovi Guides, Inc.

发明人： Boyer, Franklin E. ,  Demers, Timothy B.

IPC分类号： H04N5/445 ,  H04N7/088 ,  H04N21/25 ,  H04N21/431 ,  H04N21/442 ,  H04N21/45 ,  H04N21/454 ,  H04N21/466 ,  H04N21/482

CPC分类号： H04N21/251 ,  H04N5/44543 ,  H04N21/4312 ,  H04N21/4314 ,  H04N21/44222 ,  H04N21/4532 ,  H04N21/454 ,  H04N21/466 ,  H04N21/4666 ,  H04N21/4667 ,  H04N21/4668 ,  H04N21/482 ,  H04N21/4826

摘要： A system having an adaptive browse feature and an adaptive flip feature is provided. The adaptive browse and flip features may be selected to receive program viewing suggestions. The system may provide a suggestion by displaying an adaptive browse region or adaptative flip region including a program suggestion. The system identifies programs to suggest based on a user's viewing activity. The system uses different algorithms that are user-selectable and user-adjustable to identify program suggestions. The system may query a program guide database to build a list of programs having attributes similar to the attributes of the current program or the last viewed program. The system may use an adaptive learning algorithm such as a neural network. The neural network maybe trained by the program guide by monitoring user-viewing activity. Each algorithm may be personalized for multiple users.

公开(公告)号：EP1295471A2

公开(公告)日：2003-03-26

申请号：EP01945560.9

申请日：2001-06-01

申请人： Tri-Vision Electronics Inc.

发明人： SIDDIQUI, Najmul, H.

IPC分类号： H04N5/445 ,  H04N7/16 ,  H04N7/173 ,  G06F3/033

CPC分类号： H04N21/466 ,  H04N7/163 ,  H04N7/17318 ,  H04N21/4532 ,  H04N21/454 ,  H04N21/4622 ,  H04N21/4666 ,  H04N21/4668 ,  H04N21/4756 ,  H04N21/4782 ,  H04N21/4826

摘要： A method for interacting with a user when establishing preferences for a media player that enables a user to quickly set his or her preferences by interacting with a graphical display. The media ratings system is converted to a numerical or ordered range so that the ratings are placed in a progressive order from least objectionable to most objectionable. One possible implementation is to associate a numerical value with each rating and then order the ratings in accordance with the numerical sequence. Once the ratings are ordered, the ratings are displayed to the user in a graphical fashion so that the user can select a position on the graph that represents the user's preferences without necessarily requiring the user to understand the underlying implications of the media ratings system.

公开(公告)号：EP2290958B1

公开(公告)日：2016-03-23

申请号：EP10178617.6

申请日：1999-07-16

申请人： Rovi Guides, Inc.

发明人： Boyer, Franklin E. ,  Demers, Timothy B

IPC分类号： H04N21/431 ,  H04N21/442 ,  H04N21/45 ,  H04N21/454 ,  H04N21/466 ,  H04N21/482 ,  H04N21/25 ,  H04N5/445

CPC分类号： H04N21/251 ,  H04N5/44543 ,  H04N21/4312 ,  H04N21/4314 ,  H04N21/44222 ,  H04N21/4532 ,  H04N21/454 ,  H04N21/466 ,  H04N21/4666 ,  H04N21/4667 ,  H04N21/4668 ,  H04N21/482 ,  H04N21/4826

摘要： A system having an adaptive browse feature and an adaptive flip feature is provided. The adaptive browse and flip features may be selected to receive program viewing suggestions. The system may provide a suggestion by displaying an adaptive browse region or adaptative flip region including a program suggestion. The system identifies programs to suggest based on a user's viewing activity. The system uses different algorithms that are user-selectable and user-adjustable to identify program suggestions. The system may query a program guide database to build a list of programs having attributes similar to the attributes of the current program or the last viewed program. The system may use an adaptive learning algorithm such as a neural network. The neural network maybe trained by the program guide by monitoring user-viewing activity. Each algorithm may be personalized for multiple users.

公开(公告)号：EP2843859A1

公开(公告)日：2015-03-04

申请号：EP14182927.5

申请日：2014-08-29

申请人： Comcast Cable Communications, LLC

发明人： Orlowski, Robert Alan

IPC分类号： H04H60/31 ,  H04H60/33 ,  H04N21/24 ,  H04N21/442 ,  H04N21/466 ,  H04N21/25 ,  G06F11/34

CPC分类号： H04N21/2407 ,  G06Q30/02 ,  H04H60/31 ,  H04H60/32 ,  H04H60/33 ,  H04H60/40 ,  H04H60/43 ,  H04H60/45 ,  H04N21/252 ,  H04N21/44222 ,  H04N21/4666

摘要： A computer-implemented method of using video viewing activity data as input to an aggregation engine built on the Hadoop MapReduce framework which calculates second-by-second video viewing activity aggregated to the analyst's choice of (a) geographic area, (b) video server, (c) video content (channel call sign, video program, etc.), or (d) viewer demographic, or any combination of these fields, for each second of the day represented in the video viewing activity data. Also calculates overall viewing for use as a denominator in calculations. The source data may be extracted from a database defined according to the Cable Television Laboratories, Inc. Media Measurement Data Model defined in "Audience Data Measurement Specification" as "OpenCable™ Specifications, Audience Measurement, Audience Measurement Data Specification"document OC-SP-AMD-I01-130502 or any similar format. These metrics provide detailed data needed to calculate information on customer viewing behavior that can drive business decisions for service providers, advertisers, and content producers.

摘要翻译： 一种使用视频观看活动数据作为基于Hadoop MapReduce框架的聚合引擎的​​输入的计算机实现的方法，该框架计算聚合到（a）地理区域的分析师选择的逐秒视频观看活动，（b）视频服务器 ，（c）视频内容（频道呼叫标志，视频节目等），或（d）观众人口统计或这些字段的任何组合，用于视频观看活动数据中表示的一天中的每一天。 还可以计算出在计算中用作分母的整体视图。 源数据可以从根据“有线电视实验室有限公司”定义的数据库中提取。媒体测量数据模型在“受众数据测量规范”中定义为“OpenCable”¢规范，受众测量，受众测量数据规范“文档OC-SP -AMD-I01-130502或任何类似的格式。 这些指标提供了计算有关客户观看行为的信息所需的详细数据，可以为服务提供商，广告客户和内容制作者推动业务决策。