公开(公告)号：US10374929B2

公开(公告)日：2019-08-06

申请号：US15390982

申请日：2016-12-27

申请人： Facebook, Inc.

发明人： Alexey Maykov ,  Ryan Edward Huettl ,  Anirudhan Vijayakanthan ,  Nipun Mathur

IPC分类号： G06F15/173 ,  H04L12/26 ,  H04L29/08

摘要： An online system determines a frequency with which its users delete information stored in a browser on client devices associated with each user. When a user accesses the online system, the online system determines a user identifier associated with the user and determines if one or more conditions are satisfied based on information received from a browser used to access the online system. If a condition is satisfied, the online system communicates an instruction to the browser to communicate information associated with a third party and the user identifier to the third party. Information previously stored in the browser and associated with the user identifier is compared to information associated with the user identifier received from the browser. Deletion of information stored in the browser is determined when stored information associated with the user identifier differs from received information associated with the user identifier.

公开(公告)号：US09565090B1

公开(公告)日：2017-02-07

申请号：US14086123

申请日：2013-11-21

申请人： Facebook, Inc.

发明人： Alexey Maykov ,  Ryan Edward Huettl ,  Anirudhan Vijayakanthan ,  Nipun Mathur

IPC分类号： G06F15/173 ,  H04L12/26

CPC分类号： H04L43/10 ,  H04L43/14 ,  H04L67/02 ,  H04L67/142 ,  H04L67/146 ,  H04L67/20

摘要： An online system determines a frequency with which its users delete information stored in a browser on client devices associated with each user. When a user accesses the online system, the online system determines a user identifier associated with the user and determines if one or more conditions are satisfied based on information received from a browser used to access the online system. If a condition is satisfied, the online system communicates an instruction to the browser to communicate information associated with a third party and the user identifier to the third party. Information previously stored in the browser and associated with the user identifier is compared to information associated with the user identifier received from the browser. Deletion of information stored in the browser is determined when stored information associated with the user identifier differs from received information associated with the user identifier.

摘要翻译： 在线系统确定其用户删除存储在与每个用户相关联的客户端设备上的浏览器中的信息的频率。 当用户访问在线系统时，在线系统确定与用户相关联的用户标识符，并且基于从用于访问在线系统的浏览器接收到的信息来确定是否满足一个或多个条件。 如果条件满足，则在线系统向浏览器传达指令以将与第三方相关联的信息和用户标识符传送给第三方。 将先前存储在浏览器中并与用户标识符相关联的信息与与从浏览器接收到的用户标识符相关联的信息进行比较。 当与用户标识符相关联的存储信息与与用户标识符相关联的接收信息不同时，确定存储在浏览器中的信息的删除。

公开(公告)号：US20140258191A1

公开(公告)日：2014-09-11

申请号：US14286803

申请日：2014-05-23

申请人： Facebook, Inc.

发明人： Max Gubin ,  Wayne Kao ,  David Vickrey ,  Alexey Maykov

IPC分类号： G06N99/00 ,  G06F17/30

CPC分类号： G06N99/005 ,  G06F17/30867 ,  G06Q10/06393 ,  G06Q50/01

摘要： Machine learning models are used for ranking news feed stories presented to users of a social networking system. The social networking system divides its users into different sets, for example, based on demographic characteristics of the users and generates one model for each set of users. The models are periodically retrained. The news feed ranking model may rank news feeds for a user based on information describing other users connected to the user in the social networking system. Information describing other users connected to the user includes interactions of the other users with objects associated with news feed stories. These interactions include commenting on a news feed story, liking a news feed story, or retrieving information, for example, images, videos associated with a news feed story.

摘要翻译： 机器学习模型用于对社交网络系统的用户提供新闻馈送故事。 社交网络系统将用户分为不同的集合，例如基于用户的人口特征，并为每组用户生成一个模型。 这些模型定期进行再培训。 新闻排序模型可以基于描述在社交网络系统中连接到用户的其他用户的信息来为用户排序新闻馈送。 描述连接到用户的其他用户的信息包括其他用户与与新闻馈送故事相关联的对象的交互。 这些互动包括评论新闻Feed故事，喜欢新闻Feed故事或检索信息，例如图像，与新闻Feed故事相关的视频。

公开(公告)号：US20170111255A1

公开(公告)日：2017-04-20

申请号：US15390982

申请日：2016-12-27

申请人： Facebook, Inc.

发明人： Alexey Maykov ,  Ryan Edward Huettl ,  Anirudhan Vijayakanthan ,  Nipun Mathur

IPC分类号： H04L12/26 ,  H04L29/08

CPC分类号： H04L43/10 ,  H04L43/14 ,  H04L67/02 ,  H04L67/142 ,  H04L67/146 ,  H04L67/20

摘要： An online system determines a frequency with which its users delete information stored in a browser on client devices associated with each user. When a user accesses the online system, the online system determines a user identifier associated with the user and determines if one or more conditions are satisfied based on information received from a browser used to access the online system. If a condition is satisfied, the online system communicates an instruction to the browser to communicate information associated with a third party and the user identifier to the third party. Information previously stored in the browser and associated with the user identifier is compared to information associated with the user identifier received from the browser. Deletion of information stored in the browser is determined when stored information associated with the user identifier differs from received information associated with the user identifier.

公开(公告)号：US09286575B2

公开(公告)日：2016-03-15

申请号：US14286803

申请日：2014-05-23

申请人： Facebook, Inc.

发明人： Max Gubin ,  Wayne Kao ,  David Vickrey ,  Alexey Maykov

IPC分类号： G06N99/00 ,  G06Q10/06 ,  G06Q50/00 ,  G06F17/30

CPC分类号： G06N99/005 ,  G06F17/30867 ,  G06Q10/06393 ,  G06Q50/01

摘要： Machine learning models are used for ranking news feed stories presented to users of a social networking system. The social networking system divides its users into different sets, for example, based on demographic characteristics of the users and generates one model for each set of users. The models are periodically retrained. The news feed ranking model may rank news feeds for a user based on information describing other users connected to the user in the social networking system. Information describing other users connected to the user includes interactions of the other users with objects associated with news feed stories. These interactions include commenting on a news feed story, liking a news feed story, or retrieving information, for example, images, videos associated with a news feed story.

摘要翻译： 机器学习模型用于对社交网络系统的用户提供新闻馈送故事。 社交网络系统将用户分为不同的集合，例如基于用户的人口特征，并为每组用户生成一个模型。 这些模型定期进行再培训。 新闻排序模型可以基于描述在社交网络系统中连接到用户的其他用户的信息来为用户排序新闻馈送。 描述连接到用户的其他用户的信息包括其他用户与与新闻馈送故事相关联的对象的交互。 这些互动包括评论新闻Feed故事，喜欢新闻Feed故事或检索信息，例如图像，与新闻Feed故事相关的视频。