-
公开(公告)号：US20160171385A1
公开(公告)日：2016-06-16
申请号：US14567901
申请日：2014-12-11
Applicant: Facebook, Inc.
Inventor： Jonathan J. Gross , Yihua Liao , Joshua Luke Krivoshein , Monika Leigh Bickert , Eugene Zarakhovsky
CPC classification number: G06N7/005 , G06N99/005 , G06Q30/0282 , G06Q50/01 , H04L67/22 , H04L67/306
Abstract: An online system extracts features from an application linked to the online system. The application is used by users of the online system and posts content to the online system. A trained model is applied to the extracted features to generate a quality score for the application. The trained model is trained using features extracted from a set of training applications and quality scores manually assigned to the training applications, wherein the manually assigned quality scores indicate whether each training application satisfies a set of criteria and the generated quality score represents a probability of the application satisfying the set of criteria. Based on the quality score, content provided by the application is ranked for presentation to a user of the online system in relation to other content of the online system. The online system presents the content provided by the application to the user according to the ranking
Abstract translation: 在线系统从链接到在线系统的应用程序中提取功能。 该应用程序由在线系统的用户使用，并将内容发布到在线系统。 将经过训练的模型应用于提取的特征以产生应用的质量得分。 使用从一组训练应用提取的特征和手动分配给训练应用的质量得分来训练训练的模型，其中手动分配的质量分数指示每个训练应用是否满足一组标准，并且所生成的质量得分表示 应用程序满足一套标准。 基于质量得分，应用程序所提供的内容被排列为与在线系统的其他内容相关联地呈现给在线系统的用户。 在线系统根据排名将用户提供的内容呈现给用户
-
公开(公告)号：US10083401B2
公开(公告)日：2018-09-25
申请号：US15406521
申请日：2017-01-13
Applicant: Facebook, Inc.
Inventor： Jonathan J. Gross , Yihua Liao , Joshua Luke Krivoshein , Monika Leigh Bickert , Eugene Zarakhovsky
CPC classification number: G06N7/005 , G06N20/00 , G06Q30/0282 , G06Q50/01 , H04L67/22 , H04L67/306
Abstract: An online system extracts features from an application linked to the online system. The application is used by users of the online system and posts content to the online system. A trained model is applied to the extracted features to generate a quality score for the application. The trained model is trained using features extracted from a set of training applications and quality scores manually assigned to the training applications, wherein the manually assigned quality scores indicate whether each training application satisfies a set of criteria and the generated quality score represents a probability of the application satisfying the set of criteria. Based on the quality score, content provided by the application is ranked for presentation to a user of the online system in relation to other content of the online system. The online system presents the content provided by the application to the user according to the ranking.
-
公开(公告)号：US10003590B2
公开(公告)日：2018-06-19
申请号：US14728841
申请日：2015-06-02
Applicant: Facebook, Inc.
Inventor： Jason Duane Clark , Eugene Zarakhovsky
CPC classification number: H04L63/0807 , G06Q50/01 , H04L63/0815 , H04L63/10 , H04L63/107 , H04L63/108 , H04L67/10 , H04W4/21
Abstract: An electronic device with a display detects an input in a user interface for a second application not associated with a server system. In response to detecting the first input, the device sends a first request from the second application to a first application associated with the server system. In response to the first request, the device sends a first command from the first application to the server system on behalf of the second application. The first command is a command for performance of a first operation at the server system. The first operation corresponds to the input detected by the device. The device receives a voucher, or an indication that a voucher has been created, at the second application pre-authorizing performance of a predefined second operation at the server system upon receipt, by the server system, of a second command from the second application.
-
公开(公告)号：US20150339705A1
公开(公告)日：2015-11-26
申请号：US14285289
申请日：2014-05-22
Applicant: Facebook, Inc.
Inventor： Vijaye Ganesh Raji , Jason Duane Clark , Eugene Zarakhovsky , Jonathan J. Gross , Brent Dorman
CPC classification number: G06Q30/0248 , G06F21/552 , G06F21/60 , G06Q30/02
Abstract: Embodiments are disclosed for identifying a suspect application based on multiple operating factors from use of multiple applications. The embodiments can generate a representative distribution of a selected factor based on collected information corresponding to multiple operating factors from use of multiple applications. The embodiments can compare a representative distribution of a target factor with the representative distribution of the selected factor and identify a suspect application when these distributions are different.
Abstract translation: 公开了用于基于来自多个应用的使用的多个操作因素识别可疑应用的实施例。 基于来自使用多个应用的多个操作因素的收集的信息，实施例可以生成所选因子的代表性分布。 实施例可以将目标因子的代表性分布与所选因子的代表性分布进行比较，并且当这些分布不同时识别可疑应用。
-
公开(公告)号：US11023923B2
公开(公告)日：2021-06-01
申请号：US14285289
申请日：2014-05-22
Applicant: Facebook, Inc.
Inventor： Vijaye Ganesh Raji , Jason Duane Clark , Eugene Zarakhovsky , Jonathan J. Gross , Brent Dorman
Abstract: Embodiments are disclosed for identifying a suspect application based on multiple operating factors from use of multiple applications. The embodiments can generate a representative distribution of a selected factor based on collected information corresponding to multiple operating factors from use of multiple applications. The embodiments can compare a representative distribution of a target factor with the representative distribution of the selected factor and identify a suspect application when these distributions are different.
-
Patent Agency Ranking
公开(公告)号：US20140324741A1
公开(公告)日：2014-10-30
申请号：US13872811
申请日：2013-04-29
Applicant: Facebook, Inc.
Inventor： Allan Stewart , Eugene Zarakhovsky , Christopher Palow , Chetan Gowda , Brent Dorman
CPC classification number: G06N99/005
Abstract: A method of operation of a URL spam detection system includes: identifying a feature dimension of a user action on a social networking system to detect anomalies; extracting URL chunks from a content associated with the user action; aggregating a non-content feature of the user action along the feature dimension into a URL distribution store to produce a feature distribution for each of the URL chunks; determining whether the feature distribution of a particular URL chunk within the URL chunks exceeds an expectation threshold for the feature dimension; and classifying the particular URL chunk as an illegitimate URL when the feature distribution exceeds the expectation threshold to restrict access to a particular URL chunk on a social networking system.
Abstract translation: URL垃圾邮件检测系统的操作方法包括：识别社交网络系统上的用户动作的特征维度以检测异常; 从与用户操作相关联的内容中提取URL块; 将沿着所述特征维度的所述用户动作的非内容特征聚合到URL分发存储器中，以为每个所述URL块生成特征分布; 确定所述URL块内的特定URL块的特征分布是否超过所述特征维度的期望阈值; 并且当特征分布超过期望阈值以限制对社交网络系统上的特定URL块的访问时，将特定URL块分类为非法URL。
-
公开(公告)号：US09571594B2
公开(公告)日：2017-02-14
申请号：US14567901
申请日：2014-12-11
Applicant: Facebook, Inc.
Inventor： Jonathan J Gross , Yihua Liao , Joshua Luke Krivoshein , Monika Leigh Bickert , Eugene Zarakhovsky
CPC classification number: G06N7/005 , G06N99/005 , G06Q30/0282 , G06Q50/01 , H04L67/22 , H04L67/306
Abstract: An online system extracts features from an application linked to the online system. The application is used by users of the online system and posts content to the online system. A trained model is applied to the extracted features to generate a quality score for the application. The trained model is trained using features extracted from a set of training applications and quality scores manually assigned to the training applications, wherein the manually assigned quality scores indicate whether each training application satisfies a set of criteria and the generated quality score represents a probability of the application satisfying the set of criteria. Based on the quality score, content provided by the application is ranked for presentation to a user of the online system in relation to other content of the online system. The online system presents the content provided by the application to the user according to the ranking.
Abstract translation: 在线系统从链接到在线系统的应用程序中提取功能。 该应用程序由在线系统的用户使用，并将内容发布到在线系统。 将经过训练的模型应用于提取的特征以产生应用的质量得分。 使用从一组训练应用提取的特征和手动分配给训练应用的质量得分来训练训练的模型，其中手动分配的质量分数指示每个训练应用是否满足一组标准，并且所生成的质量得分表示 应用程序满足一套标准。 基于质量得分，应用程序所提供的内容被排列为与在线系统的其他内容相关联地呈现给在线系统的用户。 在线系统根据排名将用户提供的内容呈现给用户。
-
公开(公告)号：US09378465B2
公开(公告)日：2016-06-28
申请号：US13872811
申请日：2013-04-29
Applicant: Facebook, Inc.
Inventor： Allan Stewart , Eugene Zarakhovsky , Christopher Palow , Chetan Gowda , Brent Dorman
CPC classification number: G06N99/005
Abstract: A method of operation of a URL spam detection system includes: identifying a feature dimension of a user action on a social networking system to detect anomalies; extracting URL chunks from a content associated with the user action; aggregating a non-content feature of the user action along the feature dimension into a URL distribution store to produce a feature distribution for each of the URL chunks; determining whether the feature distribution of a particular URL chunk within the URL chunks exceeds an expectation threshold for the feature dimension; and classifying the particular URL chunk as an illegitimate URL when the feature distribution exceeds the expectation threshold to restrict access to a particular URL chunk on a social networking system.
Abstract translation: URL垃圾邮件检测系统的操作方法包括：识别社交网络系统上的用户动作的特征维度以检测异常; 从与用户操作相关联的内容中提取URL块; 将沿着所述特征维度的所述用户动作的非内容特征聚合到URL分发存储器中，以为每个所述URL块生成特征分布; 确定所述URL块内的特定URL块的特征分布是否超过所述特征维度的期望阈值; 并且当特征分布超过期望阈值以限制对社交网络系统上的特定URL块的访问时，将特定URL块分类为非法URL。
-
公开(公告)号：US20170147936A1
公开(公告)日：2017-05-25
申请号：US15406521
申请日：2017-01-13
Applicant: Facebook, Inc.
Inventor： Jonathan J. Gross , Yihua Liao , Joshua Luke Krivoshein , Monika Leigh Bickert , Eugene Zarakhovsky
CPC classification number: G06N7/005 , G06N99/005 , G06Q30/0282 , G06Q50/01 , H04L67/22 , H04L67/306
Abstract: An online system extracts features from an application linked to the online system. The application is used by users of the online system and posts content to the online system. A trained model is applied to the extracted features to generate a quality score for the application. The trained model is trained using features extracted from a set of training applications and quality scores manually assigned to the training applications, wherein the manually assigned quality scores indicate whether each training application satisfies a set of criteria and the generated quality score represents a probability of the application satisfying the set of criteria. Based on the quality score, content provided by the application is ranked for presentation to a user of the online system in relation to other content of the online system. The online system presents the content provided by the application to the user according to the ranking.
-
10.发明申请Methods and Systems for Linking Untrusted Applications to Server Systems 有权将不受信任的应用程序链接到服务器系统的方法和系统公开(公告)号：US20160359826A1
公开(公告)日：2016-12-08
申请号：US14728841
申请日：2015-06-02
Applicant: Facebook, Inc.
Inventor： Jason Duane Clark , Eugene Zarakhovsky
CPC classification number: H04L63/0807 , G06Q50/01 , H04L63/0815 , H04L63/10 , H04L63/107 , H04L63/108 , H04L67/10 , H04W4/21
Abstract: An electronic device with a display detects an input in a user interface for a second application not associated with a server system. In response to detecting the first input, the device sends a first request from the second application to a first application associated with the server system. In response to the first request, the device sends a first command from the first application to the server system on behalf of the second application, for performance of a first operation at the server system. The first operation corresponds to the input detected by the device. The device receives a voucher, or an indication that a voucher has been created, at the second application pre-authorizing performance of a predefined second operation at the server system upon receipt, by the server system, of a second command from the second application.
Abstract translation: 具有显示器的电子设备检测用户界面中对于与服务器系统无关的第二应用的输入。 响应于检测到第一输入，设备从第二应用发送第一请求到与服务器系统相关联的第一应用。 响应于第一请求，设备代表第二应用从第一应用向服务器系统发送第一命令，以在服务器系统上执行第一操作。 第一个操作对应于设备检测到的输入。 在服务器系统接收到来自第二应用程序的第二命令时，在第二应用程序处，服务器系统接收凭证或者已经创建凭单的指示，以在服务器系统预先授权执行预定义的第二操作。
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.013 seconds)
