公开(公告)号：US20150038114A1

公开(公告)日：2015-02-05

申请号：US13958520

申请日：2013-08-02

Applicant: Yahoo! Inc.

Inventor： Daryl Low ,  Marco Wirasinghe ,  Gautam Godse

IPC: H04W12/06

CPC classification number: H04W12/06 ,  H04L63/107

Abstract: A request is received to access a user account. A geolocation of a mobile device registered with the user account is obtained directly from the mobile device. Authentication credentials for the user account are verified for correctness. A mobile device geolocation verification request is transmitted to a cellular data provider. The cellular data provider is equipped to independently determine a true geolocation region of the mobile device for comparison with the geolocation of the mobile device as obtained directly from the mobile device. A verification response to the mobile device geolocation verification request is received from the cellular data provider. The verification response indicates whether or not the geolocation of the mobile device as obtained directly from the mobile device corresponds to the true geolocation region of the mobile device. A response to the access request based on the verification response is transmitted.

Abstract translation: 接收到访问用户帐户的请求。 直接从移动设备获得注册到用户帐户的移动设备的地理定位。 验证用户帐户的身份验证凭据是否正确。 将移动设备地理位置验证请求发送到蜂窝数据提供商。 蜂窝数据提供者被配备为独立地确定移动设备的真实地理位置区域，以便与从移动设备直接获得的移动设备的地理位置进行比较。 从蜂窝数据提供者接收到对移动设备地理位置验证请求的验证响应。 验证响应指示直接从移动设备获得的移动设备的地理位置是否对应于移动设备的真实地理位置区域。 发送对基于验证响应的访问请求的响应。

公开(公告)号：US20150032535A1

公开(公告)日：2015-01-29

申请号：US13951078

申请日：2013-07-25

Applicant: YAHOO! INC.

Inventor： Jia Li ,  David Shamma

IPC: G06Q50/00 ,  G06Q30/02

CPC classification number: G06Q50/01 ,  G06Q30/0255

Abstract: Disclosed is a system and method for automatically detecting social relationships from consumer image collections. The disclosed systems and methods provide the ability to infer relationships between people thereby creating dynamic social networks from the occurrences of people appearing in digital images. Occurrences of people in pictures can be detected based on known or to be known facial recognition technology. These inferences enable relationship determinations regarding whether the people are family members, friends, acquaintances or merely strangers who happen to be in the same place at the same time. The disclosed detection of such relationships enables the building of intelligent image management systems. Furthermore, based on the detected social relationships, advertisements can be served not solely to a single person, but to multiple people within the scope of the social relationship

Abstract translation: 公开了一种用于从消费者图像集合自动检测社会关系的系统和方法。 所公开的系统和方法提供了推断人之间的关系的能力，从而创建出现在数字图像中出现的人的动态社交网络。 可以基于已知或已知的面部识别技术来检测图片中的人的出现。 这些推论能够确定人们是否是家庭成员，朋友，熟人，或者只是同时处于同一地点的陌生人。 披露的这种关系的检测使得能够构建智能图像管理系统。 此外，根据检测到的社会关系，广告不仅可以服务于一个人，而且可以在社会关系范围内的多个人

公开(公告)号：US08943401B2

公开(公告)日：2015-01-27

申请号：US11540849

申请日：2006-09-29

Applicant: Ronald Martinez ,  Balaji Ravindran ,  Chris Kalaboukis

Inventor： Ronald Martinez ,  Balaji Ravindran ,  Chris Kalaboukis

IPC: G06F17/00 ,  G06Q30/02 ,  G06F17/30

CPC classification number: G06F17/3089 ,  G06Q30/02 ,  G06Q30/0273

Abstract: Particular embodiments of the present invention are related to a digital media benefit attachment mechanism for generating or attaching revenue rights and other benefits to one or more entities associated with socially distributed media.

Abstract translation: 本发明的特定实施例涉及一种用于生成或附加收入权利和其他益处的数字媒体利益附加机制，所述实体与一个或多个与社会分布式媒体相关联的实体相关联。

公开(公告)号：US08935194B2

公开(公告)日：2015-01-13

申请号：US13767695

申请日：2013-02-14

Applicant: Yahoo! Inc.

Inventor： Anirban Dasgupta ,  Liang Zhang ,  Maxim Gurevich ,  Achint Oommen Thomas ,  Belle Tseng

IPC: G06N5/02 ,  G06N7/00 ,  G06N99/00

CPC classification number: G06N99/005 ,  G06N7/005

Abstract: Embodiments are directed towards clustering cookies for identifying unique mobile devices for associating activities over a network with a given mobile device. The cookies are clustered based on a Bayes Factor similarity model that is trained from cookie features of known mobile devices. The clusters may be used to determine the number of unique mobile devices that access a website. The clusters may also be used to provide targeted content to each unique mobile device.

Abstract translation: 实施例针对用于识别用于将网络上的活动与给定移动设备相关联的唯一移动设备的聚类cookie。 基于由已知移动设备的cookie特征训练的贝叶斯因子相似性模型，cookie是聚类的。 群集可用于确定访问网站的唯一移动设备的数量。 集群也可以用于向每个唯一移动设备提供有针对性的内容。

公开(公告)号：US08935177B2

公开(公告)日：2015-01-13

申请号：US12976482

申请日：2010-12-22

Applicant: Shane Wiley ,  Amir Cory

Inventor： Shane Wiley ,  Amir Cory

IPC: G06Q30/00 ,  G06Q30/02

CPC classification number: G06Q30/0246

Abstract: Anonymous measurement of online advertising using offline sales is disclosed. The measurement uses anonymized online ad exposure data and anonymized offline sales, or conversion data, to measure effectiveness of online advertisement. The anonymized exposure and conversion data are matched using tokens from each data set; each token corresponds to a user and is generated from personally identifiable information of the user that is anonymized to preserve the user's privacy. The anonymized exposure and conversion data is aggregated using the tokens to map records in the data sets for a given user. Users' ad exposure and sales history is used, anonymously, to gauge ad effectiveness of a corresponding ad campaign. The effectiveness measure, or measures, can further be used to configure another ad campaign.

Abstract translation: 披露了使用离线销售进行在线广告的匿名测量。 该测量使用匿名在线广告曝光数据和匿名离线销售或转换数据来衡量在线广告的有效性。 使用来自每个数据集的令牌来匹配匿名曝光和转换数据; 每个令牌对应于用户，并且是由匿名的用户的个人身份信息生成的，以保护用户的隐私。 匿名曝光和转换数据使用令牌进行聚合，以映射给定用户的数据集中的记录。 匿名使用用户的广告曝光和销售历史来衡量相应广告系列的广告效果。 有效措施或措施可进一步用于配置其他广告活动。

公开(公告)号：US08934545B2

公开(公告)日：2015-01-13

申请号：US12706658

申请日：2010-02-16

Applicant: Sergiy Bilobrov

Inventor： Sergiy Bilobrov

IPC: H04N11/02 ,  G06T1/00

CPC classification number: G06K9/00067 ,  G06K9/00624 ,  G06K9/46 ,  G06K9/4604 ,  G06K2009/4666 ,  G06T1/00 ,  G06T1/0021 ,  G06T7/20

Abstract: A video fingerprinting algorithm extracts characteristic features from regions of interest in a media object, such as a video signal. The regions of interest contain the perceptually important parts of the video signal. A fingerprint may be extracted from a target media object, and the fingerprint the target media content may then be matched against multiple regions of interest of known reference fingerprints. This matching may allow identification of complex scenes, inserts, and different versions of the same content presented in different formats of the media object.

Abstract translation: 视频指纹算法从诸如视频信号的媒体对象中的感兴趣区域中提取特征特征。 感兴趣的区域包含视频信号的感知重要部分。 可以从目标媒体对象提取指纹，并且可以将目标媒体内容的指纹与已知参考指纹的多个感兴趣区域匹配。 该匹配可以允许识别以不同格式的媒体对象呈现的相同内容的复杂场景，插入和不同版本。

公开(公告)号：US08924799B2

公开(公告)日：2014-12-30

申请号：US13447301

申请日：2012-04-16

Applicant: Debashis Banerjee ,  Anand Balachandran

Inventor： Debashis Banerjee ,  Anand Balachandran

IPC: G06F11/00 ,  G06F11/07

CPC classification number: G06F11/0769 ,  G06F11/0748 ,  G06F11/0775 ,  G06F11/0781 ,  G06F11/0784

Abstract: A computer-implemented method of providing a predefined content to a user includes generating an error message at a user device, the error message based on unavailability of the predefined content to the user at a first instance of time. The method also includes receiving one or more error messages by a server, the one or more error messages being received from one or more user devices. Further, the method includes creating a list of one or more parameters by the server. Furthermore, the method includes providing the predefined content to the user at a second instance of time based on a predefined threshold of the one or more parameters in the list.

Abstract translation: 向用户提供预定义内容的计算机实现的方法包括在用户设备处生成错误消息，所述错误消息基于在第一时间对用户的预定义内容的不可用性。 该方法还包括由服务器接收一个或多个错误消息，从一个或多个用户设备接收一个或多个错误消息。 此外，该方法包括由服务器创建一个或多个参数的列表。 此外，该方法包括基于列表中的一个或多个参数的预定阈值，在第二时间点向用户提供预定内容。

公开(公告)号：US08923621B2

公开(公告)日：2014-12-30

申请号：US13434738

申请日：2012-03-29

Applicant: Malcolm Slaney ,  Bee-Chung Chen ,  Deepak K. Agarwal

Inventor： Malcolm Slaney ,  Bee-Chung Chen ,  Deepak K. Agarwal

IPC: G06K9/46

CPC classification number: G06K9/6263 ,  G06F17/3005 ,  G06F17/30247 ,  G06K9/00677 ,  G06K9/6277

Abstract: Software for initialized explore-exploit creates a plurality of probability distributions. Each of these probability distributions is generated by inputting a quantitative description of one or more features associated with an image into a regression model that outputs a probability distribution for a measure of engagingness for the image. Each of the images is conceptually related to the other images. The software uses the plurality of probability distributions to initialize a multi-armed bandit model that outputs a serving scheme for each of the images. Then the software serves a plurality of the images on a web page displaying search results, based at least in part on the serving scheme.

Abstract translation: 用于初始化的探险攻击的软件创建多个概率分布。 通过将与图像相关联的一个或多个特征的定量描述输入到输出图像的接合度的概率分布的回归模型中来生成这些概率分布中的每一个。 每个图像在概念上与其他图像相关。 软件使用多个概率分布来初始化针对每个图像输出服务方案的多武装强盗模型。 然后，至少部分地基于服务方案，软件在显示搜索结果的网页上提供多个图像。

公开(公告)号：US08918389B2

公开(公告)日：2014-12-23

申请号：US13182439

申请日：2011-07-13

Applicant: Omer Emre Velipasaoglu

Inventor： Omer Emre Velipasaoglu

IPC: G06F17/30

CPC classification number: G06F17/3097

Abstract: Search-engine software displays a group of search results in a graphical user interface (GUI) for a search engine. The search-engine software captures positive feedback and negative feedback as to the search results from a user. Then the search-engine software determines a collective aboutness signature for the search results associated with the positive feedback and a collective aboutness signature for search results associated with the negative feedback. The search-engine software obtains a score of similarity to each of the collective aboutness signatures for a representation of each query suggestion in a group of query suggestions. Then the search-engine software separates the scored query suggestions into two or more groups, based on the similarity scores, and displays query suggestions from the groups in the GUI.

Abstract translation: 搜索引擎软件在搜索引擎的图形用户界面（GUI）中显示一组搜索结果。 搜索引擎软件捕获来自用户的搜索结果的正反馈和负反馈。 然后，搜索引擎软件确定与正反馈相关联的搜索结果的集体关于性签名，以及与负反馈相关联的搜索结果的集体约性签名。 搜索引擎软件获得与每个集体约性签名相似度的得分，用于在一组查询建议中的每个查询建议的表示。 然后，搜索引擎软件基于相似性分数将得分查询建议分成两个或更多个组，并从GUI中显示组中的查询建议。

公开(公告)号：US08914382B2

公开(公告)日：2014-12-16

申请号：US13251666

申请日：2011-10-03

Applicant: Prasannakumar Jobigenahally Malleshaiah

Inventor： Prasannakumar Jobigenahally Malleshaiah

IPC: G06F17/30 ,  G06Q30/02 ,  G06Q50/00

CPC classification number: G06Q30/02 ,  G06Q30/0255 ,  G06Q30/0269 ,  G06Q50/01

Abstract: The present disclosure includes methods and systems for dynamically rendering a social page of the user based on the visiting user's interests. When a visiting user visits another user's social page, the visiting user will be presented with information from the user's social page related to interests for which the visiting user has exhibited an interest.

Abstract translation: 本公开包括用于基于访问用户的兴趣动态地呈现用户的社交页面的方法和系统。 当访问用户访问另一个用户的社交页面时，访问用户将被显示来自该用户的社交页面的相关信息，该用户的社交页面与该访问用户已经表现出兴趣的兴趣相关。