-
公开(公告)号:US20160062621A1
公开(公告)日:2016-03-03
申请号:US14473372
申请日:2014-08-29
Applicant: Erin Delacroix , Christina Lynn Lopus , James Lee Baker , Benjamin Arai , Kaushik Rangadurai , Deepak Neralla , Ishita Shah , Sanketh Suresh Katta
Inventor: Erin Delacroix , Christina Lynn Lopus , James Lee Baker , Benjamin Arai , Kaushik Rangadurai , Deepak Neralla , Ishita Shah , Sanketh Suresh Katta
IPC: G06F3/0484 , G06Q10/10 , G06Q30/06
CPC classification number: G06Q10/10 , G06Q30/0641
Abstract: Techniques for providing information describing how users are funneling through various products and features of a website are described. According to various embodiments, a user specification of a first set of one or more entities is received. A user interface element is then displayed, the user interface element indicating an amount of total online user sessions that include user interactions with at least one of the entities in the first set during a specific time interval. Thereafter, a user specification of a second set of one or more entities is received. A second user interface element is then displayed, the second user interface element indicating a subset of the total online user sessions that include user interactions with at least one of the entities in the second set subsequent to the user interactions with at least one of the entities in the first set.
Abstract translation: 描述了用于提供描述用户如何通过网站的各种产品和特征进行渠道的信息的技术。 根据各种实施例,接收一个或多个实体的第一组的用户指定。 然后显示用户界面元素,所述用户界面元素指示在特定时间间隔期间包括与第一集合中的至少一个实体的用户交互的总在线用户会话的量。 此后,接收一个或多个实体的第二组的用户指定。 然后显示第二用户界面元素,第二用户界面元素指示在用户与至少一个实体的交互之后,包括与第二集合中的至少一个实体的用户交互的总在线用户会话的子集 在第一集。
-
公开(公告)号:US20150381552A1
公开(公告)日:2015-12-31
申请号:US14320397
申请日:2014-06-30
Applicant: Ravi Kiran Holur Vijay , Benjamin Arai , Mark Hull , Utku Irmak , Pramod Khincha , Samir M. Shah , Ji Yan , Lawrence Yuan
Inventor: Ravi Kiran Holur Vijay , Benjamin Arai , Mark Hull , Utku Irmak , Pramod Khincha , Samir M. Shah , Ji Yan , Lawrence Yuan
IPC: H04L12/58
CPC classification number: H04L51/32 , G06F17/30041 , G06F17/3053 , G06F17/30699 , G06F17/30828 , G06Q10/107 , G06Q50/01 , H04L41/147 , H04L43/08 , H04L51/14 , H04L51/20 , H04L51/26 , H04L63/102 , H04L67/306
Abstract: Techniques for optimizing a delivery time for the delivery of messages are described. According to various embodiments, a system determines, for each of a plurality of time intervals, a likelihood of a particular member of an online social network service performing a particular member user action on a particular message content item during the corresponding time interval. The plurality of time intervals are then ranked, based on the determined likelihoods corresponding to the plurality of time intervals. Thereafter, a particular time interval is identified from among the plurality of time intervals that is associated with a highest ranking. The particular time interval is then classified as an optimum personalized message delivery time for the particular member.
Abstract translation: 描述用于优化用于传递消息的传送时间的技术。 根据各种实施例,系统针对多个时间间隔中的每一个确定在相应时间间隔期间在线社交网络服务的特定成员在特定消息内容项目上执行特定成员用户动作的可能性。 然后,基于所确定的与多个时间间隔相对应的可能性来对多个时间间隔进行排序。 此后,从与最高排名相关联的多个时间间隔中识别特定的时间间隔。 然后将特定时间间隔分类为特定成员的最佳个性化消息传递时间。
-
公开(公告)号:US20150249716A1
公开(公告)日:2015-09-03
申请号:US14587567
申请日:2014-12-31
Applicant: Guangde Chen , Yael Garten , Sarah Tolman , Benjamin Arai
Inventor: Guangde Chen , Yael Garten , Sarah Tolman , Benjamin Arai
CPC classification number: H04L67/22
Abstract: Techniques for measuring user engagement with online products and content are described. According to various embodiments, user sequence flow information is generated for a given member, based on online session log data, the user sequence flow information indicating a chronological sequence of steps and associated activities, each of the activities being any one of a product page view activity and a user action activity. The generation of the user sequence flow information may comprise grouping one or more sequential page views of a product described in the online session log data for the member into a product page view activity in the user sequence flow information, and grouping one or more sequential user actions performed in conjunction with a product described in the online session log data for the member into a user action activity in the user sequence flow information.
Abstract translation: 描述了用于衡量与在线产品和内容的用户参与度的技术。 根据各种实施例,基于在线会话日志数据,给定成员生成用户序列流信息,所述用户序列流信息指示步骤的时间顺序和相关联的活动,每个活动是产品页面视图中的任何一个 活动和用户操作活动。 用户序列流信息的生成可以包括将用于成员的在线会话日志数据中描述的产品的一个或多个顺序页面视图分组为用户序列流信息中的产品页面查看活动,并且对一个或多个顺序用户进行分组 与在线会话中描述的用于成员的产品一起描述的用于在用户序列流信息中的用户动作活动中执行的动作。
-
公开(公告)号:US20110191342A1
公开(公告)日:2011-08-04
申请号:US12697306
申请日:2010-02-01
Applicant: Jason COHEN , Benjamin Arai , Craig Boucher , Nicholas Waggoner , Jose Marcos de Oliveira , Yun Lin
Inventor: Jason COHEN , Benjamin Arai , Craig Boucher , Nicholas Waggoner , Jose Marcos de Oliveira , Yun Lin
IPC: G06F17/30
CPC classification number: G06Q30/02
Abstract: A URL reputation system may have a reputation server and a client device with a cache of reputation information. A URL reputation query from the client to the server may return reputation data along with probabilistic set membership information for several variants of the requested URL. The client may use the probabilistic set membership information to determine if the reputation server has additional information for another related URL as well as whether the classifications are inheritable from one of the variants. If the probabilistic set membership determines that the reputation server may have additional information, a query may be made to the reputation server, otherwise the reputation may be inferred from the data stored in the cache.
Abstract translation: URL信誉系统可以具有信誉服务器和具有信誉信息缓存的客户端设备。 从客户端到服务器的URL信誉查询可以返回信誉数据以及所请求URL的几个变体的概率集合成员资格信息。 客户端可以使用概率集合成员关系信息来确定信誉服务器是否具有用于另一相关URL的附加信息,以及分类是否可从其中一个变体继承。 如果概率集合成员确定信誉服务器可能具有附加信息,则可以向信誉服务器进行查询,否则可以从存储在高速缓存中的数据推断信誉。
-
公开(公告)号:US20160062558A1
公开(公告)日:2016-03-03
申请号:US14473503
申请日:2014-08-29
Applicant: Erin Delacroix , Christina Lynn Lopus , James Lee Baker , Benjamin Arai , Kaushik Rangadurai , Deepak Neralla , Ishita Shah , Sanketh Suresh Katta
Inventor: Erin Delacroix , Christina Lynn Lopus , James Lee Baker , Benjamin Arai , Kaushik Rangadurai , Deepak Neralla , Ishita Shah , Sanketh Suresh Katta
IPC: G06F3/0482 , G06F17/30 , G06F17/22 , G06Q50/00
CPC classification number: G06F17/2247 , G06F16/2264 , G06F16/2291 , G06F16/283 , G06F16/285 , G06F16/957 , G06Q50/01
Abstract: Techniques for providing information describing how users are funneling through various products and features of a website are described. According to various embodiments, a user specification of a first set of one or more entities is received. A data structure storing a plurality of data structure entities is then accessed, each of the data structure entities corresponding to an online user session and describing one or more user interaction events included in the corresponding online user session. A set of the plurality of data structure entities are then retrieved from the data structure, the set of the plurality of data structure entities corresponding to online user sessions that include a user interaction event with at least one of the entities in the first set. Information regarding the retrieved set of the plurality of data structure entities is then provided to a user, via a user interface.
Abstract translation: 描述了用于提供描述用户如何通过网站的各种产品和特征进行渠道的信息的技术。 根据各种实施例,接收一个或多个实体的第一组的用户指定。 然后访问存储多个数据结构实体的数据结构,每个数据结构实体对应于在线用户会话并描述包括在相应的在线用户会话中的一个或多个用户交互事件。 然后从数据结构中检索多个数据结构实体的集合,所述多个数据结构实体的集合对应于在线用户会话,其包括与第一集合中的至少一个实体的用户交互事件。 然后,经由用户界面将关于所检索到的多个数据结构实体的信息提供给用户。
-
公开(公告)号:US20150350376A1
公开(公告)日:2015-12-03
申请号:US14292201
申请日:2014-05-30
Applicant: Ravi Kiran Holur Vijay , Benjamin Arai , Mark Hull , Utku Irmak , Pramod Khincha , Samir M. Shah , Ji Yan , Lawrence Yuan
Inventor: Ravi Kiran Holur Vijay , Benjamin Arai , Mark Hull , Utku Irmak , Pramod Khincha , Samir M. Shah , Ji Yan , Lawrence Yuan
Abstract: Techniques for optimizing a delivery time for the delivery of messages are described. According to various embodiments, members of an online social network service that are currently located in a particular geographic location (e.g., a particular time zone) are identified. Thereafter, messages (e.g., e-mails) are transmitted to the members at multiple local times (e.g., multiple times of the day). It is then determined that one or more of the messages that were transmitted at a particular local time have received a highest value for a response metric among the messages, the response metric indicating responses by the members to the messages. The particular local time is then classified as an optimum local message delivery time for the particular geographic location.
Abstract translation: 描述用于优化用于传递消息的传送时间的技术。 根据各种实施例,识别当前位于特定地理位置(例如,特定时区)的在线社交网络服务的成员。 此后,消息(例如,电子邮件)在多个本地时间(例如,一天中的多个时间)被发送到成员。 然后确定在特定本地时间发送的一个或多个消息已经在消息中接收到响应度量的最高值,响应度量指示成员对消息的响应。 然后将特定的本地时间分类为特定地理位置的最佳本地消息传递时间。
-
公开(公告)号:US08229930B2
公开(公告)日:2012-07-24
申请号:US12697306
申请日:2010-02-01
Applicant: Jason Cohen , Benjamin Arai , Craig Boucher , Nicholas Waggoner , Jose Marcos de Oliveira , Yun Lin
Inventor: Jason Cohen , Benjamin Arai , Craig Boucher , Nicholas Waggoner , Jose Marcos de Oliveira , Yun Lin
CPC classification number: G06Q30/02
Abstract: A URL reputation system may have a reputation server and a client device with a cache of reputation information. A URL reputation query from the client to the server may return reputation data along with probabilistic set membership information for several variants of the requested URL. The client may use the probabilistic set membership information to determine if the reputation server has additional information for another related URL as well as whether the classifications are inheritable from one of the variants. If the probabilistic set membership determines that the reputation server may have additional information, a query may be made to the reputation server, otherwise the reputation may be inferred from the data stored in the cache.
Abstract translation: URL信誉系统可以具有信誉服务器和具有信誉信息缓存的客户端设备。 从客户端到服务器的URL信誉查询可以返回信誉数据以及所请求URL的几个变体的概率集合成员资格信息。 客户端可以使用概率集合成员关系信息来确定信誉服务器是否具有用于另一相关URL的附加信息,以及分类是否可从其中一个变体继承。 如果概率集合成员确定信誉服务器可能具有附加信息,则可以向信誉服务器进行查询,否则可以从存储在高速缓存中的数据推断信誉。
-
-
-
-
-
-