公开(公告)号：US09696874B2

公开(公告)日：2017-07-04

申请号：US14144745

申请日：2013-12-31

Applicant: Google Inc.

Inventor： Matthew Kulick ,  Aparna Chennapragada ,  Albert Segars ,  Hartmut Neven ,  Arcot J. Preetham

IPC: G06F3/0482 ,  G06F17/30

CPC classification number: G06F3/0482 ,  G06F17/30265 ,  G06F17/30867 ,  G06F17/3087

Abstract: Methods and apparatus related to determining a triggering event of a user, selecting media relevant to the triggering event, and providing the selected media to the user. Some implementations are directed to methods and apparatus for determining a past event of the user that is indicative of past interaction of the user with one or more past entities and the triggering event may be determined to be associated with the past event. The media selected to provide to the user may contain media that includes the one or more past entities associated with the past event and the media may be provided to the user in response to the triggering event.

公开(公告)号：US20170269802A1

公开(公告)日：2017-09-21

申请号：US15610359

申请日：2017-05-31

Applicant: Google Inc.

Inventor： Matthew Kulick ,  Aparna Chennapragada ,  Albert Segars ,  Hartmut Neven ,  Arcot J. Preetham

IPC: G06F3/0482 ,  G06F17/30

CPC classification number: G06F3/0482 ,  G06F16/58 ,  G06F16/9535 ,  G06F16/9537

Abstract: Methods and apparatus related to determining a triggering event of a user, selecting media relevant to the triggering event, and providing the selected media to the user. Some implementations are directed to methods and apparatus for determining a past event of the user that is indicative of past interaction of the user with one or more past entities and the triggering event may be determined to be associated with the past event. The media selected to provide to the user may contain media that includes the one or more past entities associated with the past event and the media may be provided to the user in response to the triggering event.

公开(公告)号：US08943099B1

公开(公告)日：2015-01-27

申请号：US13774448

申请日：2013-02-22

Applicant: Google Inc.

Inventor： Prateek Sarkar ,  Arcot J. Preetham ,  Hyung-Jin Kim ,  Gabriel Wolosin

IPC: G06F17/30

CPC classification number: G06F17/30864

Abstract: Methods, and systems, including computer programs encoded on computer-readable mediums, including a method for determining codomain relationship measures between domains pairs. The method includes accessing domain data specifying first and second domains; for each first domain: determining a total number of image links on web pages on the first domain, each image link being a link to an image on a second domain; identifying second domains hosting images to which image links on web pages on the first domain link; for each second domain: determining a number of image links from web pages on the first domain linking to images on the second domain; determining a codomain relationship measure for the first and second domain based on the number of image links from web pages on the first domain linking to images on the second domain and the total number of image links on web pages on the first domain.

Abstract translation: 方法和系统，包括在计算机可读介质上编码的计算机程序，包括用于确定域对之间的代码域关系度量的方法。 该方法包括访问指定第一和第二域的域数据; 对于每个第一域：确定第一域上的网页上的图像链接的总数，每个图像链接是到第二域上的图像的链接; 识别托管图像的第二域，所述图像在所述第一域链接上的网页上链接到所述图像; 对于每个第二域：确定与链接到第二域上的图像的第一域上的网页的图像链接的数量; 基于第一域上的网页上链接到第二域上的图像的图像链接的数量和第一域上的网页上的图像链接的总数，确定第一和第二域的代码关系度量。

公开(公告)号：US11275483B2

公开(公告)日：2022-03-15

申请号：US15610359

申请日：2017-05-31

Applicant: Google Inc.

Inventor： Matthew Kulick ,  Aparna Chennapragada ,  Albert Segars ,  Hartmut Neven ,  Arcot J. Preetham

IPC: G06F3/0482 ,  G06F16/58 ,  G06F16/9535 ,  G06F16/9537

Abstract: Methods and apparatus related to determining a triggering event of a user, selecting media relevant to the triggering event, and providing the selected media to the user. Some implementations are directed to methods and apparatus for determining a past event of the user that is indicative of past interaction of the user with one or more past entities and the triggering event may be determined to be associated with the past event. The media selected to provide to the user may contain media that includes the one or more past entities associated with the past event and the media may be provided to the user in response to the triggering event.

公开(公告)号：US20160092689A1

公开(公告)日：2016-03-31

申请号：US14964681

申请日：2015-12-10

Applicant: Google Inc.

Inventor： Matthew E. Kulick ,  Arcot J. Preetham ,  Manish M. Sambhu ,  Hyduke Noshadi

IPC: G06F21/62 ,  G06F17/30

CPC classification number: G06F21/62 ,  G06F17/30067 ,  G06F17/30321 ,  G06F17/30867 ,  G06F21/6218 ,  G06F21/6227 ,  G06F21/6245 ,  G06F2221/2113 ,  G06F2221/2141 ,  H04L63/10 ,  H04L63/101 ,  H04L63/104 ,  H04L63/105

Abstract: One or more computer devices may receive a document from private content that is accessible by a set of users, and may extract metadata from the document. The metadata may provide information relating to one or more aspects of the document. The one or more computer devices may determine, based on the metadata, whether a portion of the document includes information that is only to be accessible by a particular user from the set of users, and may append a restrict indicator to the metadata when the portion of the document includes information that is only to be accessible by the particular user. The restrict indicator may identify the particular user and the portion of the document. The one or more computer devices may store the metadata and the restrict indicator in a personal search index.

Abstract translation: 一个或多个计算机设备可以从可由一组用户访问的专用内容接收文档，并且可以从文档中提取元数据。 元数据可以提供与文档的一个或多个方面有关的信息。 一个或多个计算机设备可以基于元数据来确定文档的一部分是否包括仅从特定用户可从该组用户访问的信息，并且可以在元数据部分附加限制指示符到元数据 的文档包括仅由特定用户访问的信息。 限制指示符可以标识特定用户和文档的部分。 一个或多个计算机设备可将元数据和限制指示符存储在个人搜索索引中。

公开(公告)号：US09177046B2

公开(公告)日：2015-11-03

申请号：US14543312

申请日：2014-11-17

Applicant: Google Inc.

Inventor： Arcot J. Preetham ,  Thomas J. Duerig ,  Charles J. Rosenberg ,  Yangli Hector Yee ,  Samy Bengio

IPC: G06K9/62 ,  G06F17/30 ,  G06K9/66 ,  G06K9/52

CPC classification number: G06F17/30675 ,  G06F17/3028 ,  G06K9/52 ,  G06K9/6202 ,  G06K9/6256 ,  G06K9/6262 ,  G06K9/6296 ,  G06K9/66

Abstract: Methods, systems and apparatus for refining image relevance models. In general, one aspect of the subject matter described in this specification can be implemented in methods that include re-training an image relevance model by generating a first re-trained model based on content feature values of first images of a first portion of training images in a set of training images, receiving, from the first re-trained model, image relevance scores for second images of a second portion of the set of training images, removing, from the set of training images, some of the second images identified as outlier images for which the image relevance score received from the first re-trained model is below a threshold score, and generating a second re-trained model based on content feature values of the first images of the first portion and the second images of the second portion that remain following removal of the outlier images.

Abstract translation: 图像相关模型的方法，系统和装置。 通常，本说明书中描述的主题的一个方面可以以包括通过基于训练图像的第一部分的第一图像的内容特征值生成第一重新训练的模型来重新训练图像相关性模型的方法来实现 在一组训练图像中，从所述第一重新训练的模型中接收所述训练图像集合的第二部分的第二图像的图像相关性分数，从所述训练图像集合中去除被识别为 从第一重新训练的模型接收的图像相关性得分低于阈值分数的异常值图像，并且基于第一部分的第一图像和第二图像的第二图像的内容特征值生成第二重新训练的模型 删除离群图像后仍保留的部分。

公开(公告)号：US09069794B1

公开(公告)日：2015-06-30

申请号：US14052157

申请日：2013-10-11

Applicant: Google Inc.

Inventor： Farhana Bandukwala ,  Hartwig Adam ,  John Flynn ,  Krzysztof Sikora ,  Marco Andreetto ,  Arcot J. Preetham

IPC: G06F17/30 ,  G06K9/46

CPC classification number: G06F17/30256 ,  G06F17/30265 ,  G06K9/46

Abstract: Methods, systems, and apparatus are provided for determining location information for images. In one aspect, a method includes obtaining landmark location data from content depicted in an image and corresponding confidence scores. Also, the method includes obtaining caption location data from user input and corresponding confidence scores, and obtaining metadata location data from data provided by an image capturing device. Further, the method includes identifying location pairs from the landmark, caption, and metadata location data, and generating, for each location pair, a geographic consistency score. Additionally, the method includes selecting a location pair based on the geographic consistency scores, and selecting an image location for the image from the selected location pair. Moreover, the method includes determining an image location score based on a confidence score for one of the locations in the selected location pair, and associating the image location and image location score with the image.

Abstract translation: 提供了用于确定图像的位置信息的方法，系统和装置。 一方面，一种方法包括从图像中描绘的内容和相应的置信度得分获得界标位置数据。 此外，该方法包括从用户输入获得字幕位置数据和相应的置信度分数，以及从由图像捕获设备提供的数据获得元数据位置数据。 此外，该方法包括从地标，标题和元数据位置数据识别位置对，并且针对每个位置对，生成地理一致性分数。 另外，该方法包括基于地理一致性分数来选择位置对，以及从所选位置对中选择图像的图像位置。 此外，该方法包括基于所选位置对中的一个位置的置信度分数来确定图像位置分数，以及将图像位置和图像位置分数与图像相关联。

公开(公告)号：US20150161482A1

公开(公告)日：2015-06-11

申请号：US14543312

申请日：2014-11-17

Applicant: Google Inc.

Inventor： Arcot J. Preetham ,  Thomas J. Duerig ,  Charles J. Rosenberg ,  Yangli Hector Yee ,  Samy Bengio

IPC: G06K9/62 ,  G06F17/30

CPC classification number: G06F17/30675 ,  G06F17/3028 ,  G06K9/52 ,  G06K9/6202 ,  G06K9/6256 ,  G06K9/6262 ,  G06K9/6296 ,  G06K9/66

Abstract: Methods, systems and apparatus for refining image relevance models. In general, one aspect of the subject matter described in this specification can be implemented in methods that include re-training an image relevance model by generating a first re-trained model based on content feature values of first images of a first portion of training images in a set of training images, receiving, from the first re-trained model, image relevance scores for second images of a second portion of the set of training images, removing, from the set of training images, some of the second images identified as outlier images for which the image relevance score received from the first re-trained model is below a threshold score, and generating a second re-trained model based on content feature values of the first images of the first portion and the second images of the second portion that remain following removal of the outlier images.

Abstract translation: 图像相关模型的方法，系统和装置。 通常，本说明书中描述的主题的一个方面可以以包括通过基于训练图像的第一部分的第一图像的内容特征值生成第一重新训练的模型来重新训练图像相关性模型的方法来实现 在一组训练图像中，从所述第一重新训练的模型中接收所述训练图像集合的第二部分的第二图像的图像相关性分数，从所述训练图像集合中去除被识别为 从第一重新训练的模型接收的图像相关性得分低于阈值分数的异常值图像，并且基于第一部分的第一图像和第二图像的第二图像的内容特征值生成第二重新训练的模型 删除离群图像后仍保留的部分。

公开(公告)号：US20140344688A1

公开(公告)日：2014-11-20

申请号：US14144745

申请日：2013-12-31

Applicant: Google Inc.

Inventor： Matthew Kulick ,  Aparna Chennapragada ,  Albert Segars ,  Hartmut Neven ,  Arcot J. Preetham

IPC: G06F3/0482

CPC classification number: G06F3/0482 ,  G06F17/30265 ,  G06F17/30867 ,  G06F17/3087

Abstract: Methods and apparatus related to determining a triggering event of a user, selecting media relevant to the triggering event, and providing the selected media to the user. Some implementations are directed to methods and apparatus for determining a past event of the user that is indicative of past interaction of the user with one or more past entities and the triggering event may be determined to be associated with the past event. The media selected to provide to the user may contain media that includes the one or more past entities associated with the past event and the media may be provided to the user in response to the triggering event.

Abstract translation: 与确定用户的触发事件相关的方法和装置，选择与触发事件相关的媒体，以及向所述用户提供所选择的媒体。 一些实现涉及用于确定用户的过去事件的方法和装置，其指示用户与一个或多个过去实体的过去交互，并且触发事件可被确定为与过去事件相关联。 选择提供给用户的媒体可以包含包含与过去事件相关联的一个或多个过去实体的媒体，并且响应于触发事件可以向用户提供媒体。