公开(公告)号：US20170013297A1

公开(公告)日：2017-01-12

申请号：US15276605

申请日：2016-09-26

Applicant: Google Inc.

Inventor： Li Wei ,  Kun Zhang ,  Yu He ,  Xinmei Cai

IPC: H04N21/2668 ,  G06N5/04 ,  H04N21/482 ,  G06F17/30 ,  H04N21/262 ,  H04N21/442

CPC classification number: H04N21/2668 ,  G06F16/735 ,  G06N5/00 ,  G06N5/04 ,  H04N21/26258 ,  H04N21/44222 ,  H04N21/4826

Abstract: A system and method provides video recommendations for a target video in a video sharing environment. The system selects one or more videos that are on one or more video playlists together with the target video. The video co-occurrence data of the target video associates the target video and another video on one or more same video playlists and frequency of the target video and another video on the video playlists is computed. Based on the video co-occurrence data of the target video, one or more co-occurrence videos are selected and ranked based on the video co-occurrence data of the target video. The system selects one or more videos from the co-occurrence videos as video recommendations for the target video.

Abstract translation: 系统和方法在视频共享环境中为目标视频提供视频推荐。 该系统与目标视频一起选择一个或多个视频播放列表上的一个或多个视频。 目标视频的视频同现数据在一个或多个相同的视频播放列表上将目标视频和另一视频相关联，并且计算目标视频的频率和视频播放列表上的另一视频。 基于目标视频的视频同现数据，基于目标视频的视频同现数据来选择和排列一个或多个同现视频。 该系统从共同视频中选择一个或多个视频作为目标视频的视频推荐。

公开(公告)号：US09514405B2

公开(公告)日：2016-12-06

申请号：US14860462

申请日：2015-09-21

Applicant: Google Inc.

Inventor： Kai Chen ,  Xiaodan Song ,  Gregory S. Corrado ,  Kun Zhang ,  Jeffrey A. Dean ,  Bahman Rabii

IPC: G06F15/18 ,  G06E1/00 ,  G06E3/00 ,  G06G7/00 ,  G06N3/08 ,  G06F17/30 ,  G06N3/04 ,  G06Q30/02

CPC classification number: G06N3/084 ,  G06F17/30707 ,  G06F17/30864 ,  G06N3/04 ,  G06N3/0427 ,  G06N3/08 ,  G06Q30/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource; processing each of the features using a respective embedding function to generate one or more numeric values; processing the numeric values to generate an alternative representation of the features of the resource, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values; and processing the alternative representation of the input to generate a respective relevance score for each concept term in a pre-determined set of concept terms, wherein each of the respective relevance scores measures a predicted relevance of the corresponding concept term to the resource.

公开(公告)号：US20160012331A1

公开(公告)日：2016-01-14

申请号：US14860462

申请日：2015-09-21

Applicant: Google Inc.

Inventor： Kai Chen ,  Xiaodan Song ,  Gregory S. Corrado ,  Kun Zhang ,  Jeffrey A. Dean ,  Bahman Rabii

IPC: G06N3/08 ,  G06F17/30 ,  G06N3/04

CPC classification number: G06N3/084 ,  G06F17/30707 ,  G06F17/30864 ,  G06N3/04 ,  G06N3/0427 ,  G06N3/08 ,  G06Q30/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource; processing each of the features using a respective embedding function to generate one or more numeric values; processing the numeric values to generate an alternative representation of the features of the resource, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values; and processing the alternative representation of the input to generate a respective relevance score for each concept term in a pre-determined set of concept terms, wherein each of the respective relevance scores measures a predicted relevance of the corresponding concept term to the resource.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于使用深层网络评分概念术语。 所述方法之一包括接收包括资源的多个特征的输入，其中每个特征是所述资源的相应属性的值; 使用相应的嵌入功能处理每个特征以生成一个或多个数值; 处理所述数值以产生所述资源的特征的替代表示，其中处理所述浮点值包括将一个或多个非线性变换应用于所述浮点值; 以及处理所述输入的替代表示，以在预定概念术语集中为每个概念项产生相应的相关性得分，其中各个相关性分数中的每一个测量相应概念项与资源的预测相关性。

公开(公告)号：US20190034589A1

公开(公告)日：2019-01-31

申请号：US15690703

申请日：2017-08-30

Applicant: Google Inc.

Inventor： Kai Chen ,  Patrik Sundberg ,  Alexander Mossin ,  Nissan Hajaj ,  Kurt Litsch ,  James Wexler ,  Yi Zhang ,  Kun Zhang ,  Jacob Marcus ,  Eyal Oren ,  Hector Yee ,  Jeffrey Dean ,  Michaela Hardt ,  Benjamin Irvine ,  James Wilson ,  Andrew Dai ,  Peter Liu ,  Xiaomi Sun ,  Quoc Le ,  Xiaobing Liu ,  Alvin Rajkomar ,  Gregory Corrado ,  Gerardo Flores ,  Yingwei Cui ,  Gavin Duggan

IPC: G06F19/00 ,  G06N3/08 ,  G06N3/04

Abstract: A system for predicting and summarizing medical events from electronic health records includes a computer memory storing aggregated electronic health records from a multitude of patients of diverse age, health conditions, and demographics including medications, laboratory values, diagnoses, vital signs, and medical notes. The aggregated electronic health records are converted into a single standardized data structure format and ordered arrangement per patient, e.g., into a chronological order. A computer (or computer system) executes one or more deep learning models trained on the aggregated health records to predict one or more future clinical events and summarize pertinent past medical events related to the predicted events on an input electronic health record of a patient having the standardized data structure format and ordered into a chronological order. An electronic device configured with a healthcare provider-facing interface displays the predicted one or more future clinical events and the pertinent past medical events of the patient.

公开(公告)号：US20170255698A1

公开(公告)日：2017-09-07

申请号：US15599868

申请日：2017-05-19

Applicant: Google Inc.

Inventor： Kun Zhang ,  Yu He ,  Cristos Jon Goodrow

IPC: G06F17/30

CPC classification number: G06F16/639 ,  G06F16/4387

Abstract: This disclosure relates to adaptive recommendations for user-generated mediasets. A mediaset component provides for users to generate mediasets. A user-generated mediaset can include a user-generated playlist or a user-generated media channel. A monitoring component monitors consumption of media, e.g., by a consumer. A relatedness component determines a set of the user-generated mediasets that are related to the media consumed by the consumer. A recommendation component recommends a subset of the user-generated mediasets based on a set of criteria. A rights management component determines a set of authorizations of the consumer for respective media content associated with the set of user-generated mediasets, and takes at least one action based on the set of authorizations, e.g., updating one of the mediasets based on the set of authorizations.

公开(公告)号：US20160381419A1

公开(公告)日：2016-12-29

申请号：US15263671

申请日：2016-09-13

Applicant: Google Inc.

Inventor： Kun Zhang ,  Yu He

IPC: H04N21/442 ,  H04N21/44 ,  H04N21/45 ,  H04N21/431 ,  H04N21/434

CPC classification number: H04N21/44222 ,  G06F3/01 ,  H04N21/252 ,  H04N21/25883 ,  H04N21/42201 ,  H04N21/42202 ,  H04N21/42203 ,  H04N21/4223 ,  H04N21/4312 ,  H04N21/4345 ,  H04N21/44 ,  H04N21/4532 ,  H04N21/6582 ,  H04N21/8456 ,  H04N21/8549

Abstract: Systems and methods for segmenting a video based on user engagement in respective segments of the video are presented. In one or more aspects, a system is provided that includes an engagement component configured to receive information regarding respective engagement of a plurality of users in connection with respective segments of a video. The system further includes an analysis component configured to analyze the information and calculate user engagement scores for the respective video segments, wherein the user engagement scores reflect level of the plurality of users' interest regarding the respective video segments, and an identification component configured to identify a subset of the video segments associated with relatively higher user engagement scores in comparison to other video segments.

Abstract translation: 呈现了基于视频的相应段中的用户参与来分割视频的系统和方法。 在一个或多个方面，提供了一种系统，其包括接合部件，所述接合部件被配置为接收关于与视频的相应部分相关联的多个用户的相关联的信息。 该系统还包括一个分析部件，被配置为分析各个视频段的信息并计算用户参与度分数，其中用户参与度分数反映了多个用户对各个视频段的兴趣的水平，以及被配置为识别 与其他视频片段相比，与相对较高的用户参与度分数相关联的视频片段的子集。

公开(公告)号：US20140279773A1

公开(公告)日：2014-09-18

申请号：US13802184

申请日：2013-03-13

Applicant: Google Inc.

Inventor： Kai Chen ,  Xiaodan Song ,  Gregory S. Corrado ,  Kun Zhang ,  Jeffrey A. Dean ,  Bahman Rabii

IPC: G06N3/08

CPC classification number: G06N3/084 ,  G06F17/30707 ,  G06F17/30864 ,  G06N3/04 ,  G06N3/0427 ,  G06N3/08 ,  G06Q30/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource; processing each of the features using a respective embedding function to generate one or more numeric values; processing the numeric values to generate an alternative representation of the features of the resource, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values; and processing the alternative representation of the input to generate a respective relevance score for each concept term in a pre-determined set of concept terms, wherein each of the respective relevance scores measures a predicted relevance of the corresponding concept term to the resource.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于使用深层网络评分概念术语。 所述方法之一包括接收包括资源的多个特征的输入，其中每个特征是所述资源的相应属性的值; 使用相应的嵌入功能处理每个特征以生成一个或多个数值; 处理所述数值以产生所述资源的特征的替代表示，其中处理所述浮点值包括将一个或多个非线性变换应用于所述浮点值; 以及处理所述输入的替代表示，以在预定概念术语集中为每个概念项产生相应的相关性得分，其中各个相关性分数中的每一个测量相应概念项与资源的预测相关性。