-
公开(公告)号：US10740419B2
公开(公告)日：2020-08-11
申请号：US15387571
申请日：2016-12-21
Applicant: Facebook, Inc.
Inventor： Bhalchandra Suresh Agashe , Gil Shklarski , Christopher Alexander Stein , Nickolay Vladimirov Tchervenski
IPC: G06F16/9535 , G06N5/02 , G06N20/00 , G06F16/35 , G06F16/2457 , G06Q50/00
Abstract: Some embodiments include tracking events and classifying assets within a computer system. A time series of occurrences of an event type associated with at least one asset is generated. A first signal value and a second signal value is determined based on the time series. The at least one asset can be classified based on comparison of the first signal value and the second signal value. The time series can be based on at least one time window including time intervals. Counters to determine a number of occurrences of an event type can be associated with the time intervals. Each of the counters can be incremented upon occurrence of the event type associated with the at least one asset during an associated time interval.
-
2.发明授权公开(公告)号：US09031883B2
公开(公告)日：2015-05-12
申请号：US13631523
申请日：2012-09-28
Applicant: Facebook, Inc.
Inventor： Bhalchandra Suresh Agashe , Gil Shklarski , Christopher Alexander Stein , Nickolay Vladimirov Tchervenski
CPC classification number: G06F17/30867 , G06F17/3053 , G06F17/30705 , G06N5/02 , G06N99/005 , G06Q50/01
Abstract: To allow for tracking events and classifying assets within a social networking system. A time series of occurrences of an event type associated with at least one asset is generated. A first signal value and a second signal value is determined based on the time series. The at least one asset is classified based on comparison of the first signal value and the second signal value. In an embodiment, the time series is based on at least one time window including time intervals. In an embodiment, counters to determine a number of occurrences of an event type are associated with the time intervals. In an embodiment, each of the counters are incremented upon occurrence of the event type associated with the at least one asset during an associated time interval.
Abstract translation: 允许在社交网络系统中跟踪事件和分类资产。 生成与至少一个资产相关联的事件类型的时间序列。 基于时间序列确定第一信号值和第二信号值。 基于第一信号值和第二信号值的比较来对至少一个资产进行分类。 在一个实施例中，时间序列基于包括时间间隔的至少一个时间窗。 在一个实施例中，用于确定事件类型的发生次数的计数器与时间间隔相关联。 在一个实施例中，每个计数器在相关联的时间间隔内与所述至少一个资产相关联的事件类型发生时递增。
-
3.发明申请Differentiating Between Good and Bad Content in a User-Provided Content System 审中-公开在用户提供的内容系统中区分好的和坏的内容公开(公告)号：US20140331283A1
公开(公告)日：2014-11-06
申请号：US14332042
申请日：2014-07-15
Applicant: Facebook, Inc.
Inventor： Christopher Alexander Stein , Lev Timourovich Popov , Evan Stratford
CPC classification number: H04L63/08 , G06F15/16 , G06F21/552 , G06F21/566 , H04L51/12 , H04L51/32 , H04L63/0245
Abstract: A system differentiates good content from bad content in a user-provided content system. Messages are analyzed for features that characterize messages. A feature may occur in one or more messages. A feature that has more than a threshold number of occurrences in messages in a time interval is identified for further analysis. Enhanced authentication is requested from senders of the messages with occurrences of the identified feature. Based on the rate at which senders of the messages pass authentication, the content associated with the message is determined to be good content or bad content. Subsequent messages are blocked or successfully delivered based on whether features occurring in the messages are indicative of good content or bad content.
Abstract translation: 系统将用户提供的内容系统中的良好内容与不良内容区分开来。 分析消息表征消息的功能。 一个或多个消息可能发生一个特征。 识别出在时间间隔内具有超过阈值数量的消息的特征以用于进一步分析。 来自发送者的发送者请求增强的身份验证，并发现已识别的功能。 基于消息的发送方通过认证的速率，与消息相关联的内容被确定为良好的内容或不良内容。 基于消息中发生的功能是否表示良好的内容或不良内容，后续消息被阻止或成功传送。
-
4.发明授权公开(公告)号：US09558279B2
公开(公告)日：2017-01-31
申请号：US14668030
申请日：2015-03-25
Applicant: Facebook, Inc.
Inventor： Bhalchandra Suresh Agashe , Gil Shklarski , Christopher Alexander Stein , Nickolay Vladimirov Tchervenski
CPC classification number: G06F17/30867 , G06F17/3053 , G06F17/30705 , G06N5/02 , G06N99/005 , G06Q50/01
Abstract: Some embodiments include tracking events and classifying assets within a computer system. A time series of occurrences of an event type associated with at least one asset is generated. A first signal value and a second signal value is determined based on the time series. The at least one asset can be classified based on comparison of the first signal value and the second signal value. The time series can be based on at least one time window including time intervals. Counters to determine a number of occurrences of an event type can be associated with the time intervals. Each of the counters can be incremented upon occurrence of the event type associated with the at least one asset during an associated time interval.
Abstract translation: 一些实施例包括在计算机系统内跟踪事件和分类资产。 生成与至少一个资产相关联的事件类型的时间序列。 基于时间序列确定第一信号值和第二信号值。 可以基于第一信号值和第二信号值的比较来分类至少一个资产。 时间序列可以基于包括时间间隔在内的至少一个时间窗口。 确定事件类型发生次数的计数器可以与时间间隔相关联。 在相关联的时间间隔期间，当发生与至少一个资产相关联的事件类型时，每个计数器可以递增。
-
公开(公告)号：US20150199444A1
公开(公告)日：2015-07-16
申请号：US14668030
申请日：2015-03-25
Applicant: Facebook, Inc.
Inventor： Bhalchandra Suresh Agashe , Gil Shklarski , Christopher Alexander Stein , Nickolay Vladimirov Tchervenski
CPC classification number: G06F17/30867 , G06F17/3053 , G06F17/30705 , G06N5/02 , G06N99/005 , G06Q50/01
Abstract: Some embodiments include tracking events and classifying assets within a computer system. A time series of occurrences of an event type associated with at least one asset is generated. A first signal value and a second signal value is determined based on the time series. The at least one asset can be classified based on comparison of the first signal value and the second signal value. The time series can be based on at least one time window including time intervals. Counters to determine a number of occurrences of an event type can be associated with the time intervals. Each of the counters can be incremented upon occurrence of the event type associated with the at least one asset during an associated time interval.
Abstract translation: 一些实施例包括在计算机系统内跟踪事件和分类资产。 生成与至少一个资产相关联的事件类型的时间序列。 基于时间序列确定第一信号值和第二信号值。 可以基于第一信号值和第二信号值的比较来分类至少一个资产。 时间序列可以基于包括时间间隔在内的至少一个时间窗口。 确定事件类型发生次数的计数器可以与时间间隔相关联。 在相关联的时间间隔期间，当发生与至少一个资产相关联的事件类型时，每个计数器可以递增。
-
Patent Agency Ranking
6.发明申请UPDATING SYSTEM BEHAVIOR DYNAMICALLY USING FEATURE EXPRESSIONS AND FEATURE LOOPS 审中-公开使用特征表达和特征动态动态更新系统行为公开(公告)号：US20140289795A1
公开(公告)日：2014-09-25
申请号：US14296435
申请日：2014-06-04
Applicant: Facebook, Inc.
Inventor： Christopher Alexander Stein , Karan Mangla , Zhimin Chen , Erdong Chen
IPC: H04L29/06
Abstract: Behavior of an online system is modified dynamically using feature expressions and feature loops. A feature expression can be expressed as a combination of other features or feature expressions, thereby allowing specification of complex features. The sets of feature expressions and policies of an online system can be modified while the online system is running. Feature loops aggregate values of a feature expression across a plurality of actions, for example, number of occurrences of an event over a time interval. The online system evaluates a set of feature expressions in response to actions performed by users. Feature expressions are used to specify policies that determine how the online system reacts to certain types of user actions. The ability to dynamically modify the feature expressions and policies of the online system allows the online system to adapt to attacks by malicious users in a timely manner.
Abstract translation: 使用特征表达式和特征循环动态修改在线系统的行为。 特征表达式可以表示为其他特征或特征表达式的组合，从而允许指定复杂特征。 在线系统运行时，可以修改在线系统的功能表达式和策略。 特征循环跨多个动作聚合特征表达式的值，例如在时间间隔内事件的发生次数。 在线系统评估一组特征表达式以响应用户执行的动作。 功能表达式用于指定用于确定在线系统如何对某些类型的用户操作做出反应的策略。 动态修改在线系统的功能表达式和策略的能力使得在线系统能够及时适应恶意用户的攻击。
-
公开(公告)号：US20170098006A1
公开(公告)日：2017-04-06
申请号：US15387571
申请日：2016-12-21
Applicant: Facebook, Inc.
Inventor： Bhalchandra Suresh Agashe , Gil Shklarski , Christopher Alexander Stein , Nickolay Vladimirov Tchervenski
CPC classification number: G06F16/9535 , G06F16/24578 , G06F16/35 , G06N5/02 , G06N20/00 , G06Q50/01
Abstract: Some embodiments include tracking events and classifying assets within a computer system. A time series of occurrences of an event type associated with at least one asset is generated. A first signal value and a second signal value is determined based on the time series. The at least one asset can be classified based on comparison of the first signal value and the second signal value. The time series can be based on at least one time window including time intervals. Counters to determine a number of occurrences of an event type can be associated with the time intervals. Each of the counters can be incremented upon occurrence of the event type associated with the at least one asset during an associated time interval.
-
8.发明授权Differentiating between good and bad content in a user-provided content system 有权区分用户提供的内容系统中的好与坏内容公开(公告)号：US09356920B2
公开(公告)日：2016-05-31
申请号：US14332042
申请日：2014-07-15
Applicant: Facebook, Inc.
Inventor： Christopher Alexander Stein , Lev Timourovich Popov , Evan Stratford
IPC: G06F11/00 , G06F12/14 , G06F12/16 , G08B23/00 , H04L29/06 , H04L12/58 , G06F15/16 , G06F21/55 , G06F21/56
CPC classification number: H04L63/08 , G06F15/16 , G06F21/552 , G06F21/566 , H04L51/12 , H04L51/32 , H04L63/0245
Abstract: A system differentiates good content from bad content in a user-provided content system. Messages are analyzed for features that characterize messages. A feature may occur in one or more messages. A feature that has more than a threshold number of occurrences in messages in a time interval is identified for further analysis. Enhanced authentication is requested from senders of the messages with occurrences of the identified feature. Based on the rate at which senders of the messages pass authentication, the content associated with the message is determined to be good content or bad content. Subsequent messages are blocked or successfully delivered based on whether features occurring in the messages are indicative of good content or bad content.
Abstract translation: 系统将用户提供的内容系统中的良好内容与不良内容区分开来。 分析消息表征消息的功能。 一个或多个消息可能发生一个特征。 识别出在时间间隔内具有超过阈值数量的消息的特征以用于进一步分析。 来自发送者的发送者请求增强的身份验证，并发现已识别的功能。 基于消息的发送方通过认证的速率，与消息相关联的内容被确定为良好的内容或不良内容。 基于消息中发生的功能是否表示良好的内容或不良内容，后续消息被阻止或成功传送。
-
9.发明授权Updating system behavior dynamically using feature expressions and feature loops 有权使用特征表达式和特征循环动态更新系统行为公开(公告)号：US09130997B2
公开(公告)日：2015-09-08
申请号：US14296435
申请日：2014-06-04
Applicant: Facebook, Inc.
Inventor： Christopher Alexander Stein , Karan Mangla , Zhimin Chen , Erdong Chen
Abstract: Behavior of an online system is modified dynamically using feature expressions and feature loops. A feature expression can be expressed as a combination of other features or feature expressions, thereby allowing specification of complex features. The sets of feature expressions and policies of an online system can be modified while the online system is running. Feature loops aggregate values of a feature expression across a plurality of actions, for example, number of occurrences of an event over a time interval. The online system evaluates a set of feature expressions in response to actions performed by users. Feature expressions are used to specify policies that determine how the online system reacts to certain types of user actions. The ability to dynamically modify the feature expressions and policies of the online system allows the online system to adapt to attacks by malicious users in a timely manner.
Abstract translation: 使用特征表达式和特征循环动态修改在线系统的行为。 特征表达式可以表示为其他特征或特征表达式的组合，从而允许指定复杂特征。 在线系统运行时，可以修改在线系统的功能表达式和策略集。 特征循环跨多个动作聚合特征表达式的值，例如在时间间隔内事件的发生次数。 在线系统评估一组特征表达式以响应用户执行的动作。 功能表达式用于指定用于确定在线系统如何对某些类型的用户操作做出反应的策略。 动态修改在线系统的功能表达式和策略的能力使得在线系统能够及时适应恶意用户的攻击。
-
公开(公告)号：US20140095412A1
公开(公告)日：2014-04-03
申请号：US13631523
申请日：2012-09-28
Applicant: Facebook, Inc.
Inventor： Bhalchandra Suresh Agashe , Gil Shklarski , Christopher Alexander Stein , Nickolay Vladimirov Tchervenski
CPC classification number: G06F17/30867 , G06F17/3053 , G06F17/30705 , G06N5/02 , G06N99/005 , G06Q50/01
Abstract: To allow for tracking events and classifying assets within a social networking system. A time series of occurrences of an event type associated with at least one asset is generated. A first signal value and a second signal value is determined based on the time series. The at least one asset is classified based on comparison of the first signal value and the second signal value. In an embodiment, the time series is based on at least one time window including time intervals. In an embodiment, counters to determine a number of occurrences of an event type are associated with the time intervals. In an embodiment, each of the counters are incremented upon occurrence of the event type associated with the at least one asset during an associated time interval.
Abstract translation: 允许在社交网络系统中跟踪事件和分类资产。 生成与至少一个资产相关联的事件类型的时间序列。 基于时间序列确定第一信号值和第二信号值。 基于第一信号值和第二信号值的比较来对至少一个资产进行分类。 在一个实施例中，时间序列基于包括时间间隔的至少一个时间窗。 在一个实施例中，用于确定事件类型的发生次数的计数器与时间间隔相关联。 在一个实施例中，每个计数器在相关联的时间间隔内与所述至少一个资产相关联的事件类型发生时递增。
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.015 seconds)
