公开(公告)号：US20150046528A1

公开(公告)日：2015-02-12

申请号：US13962821

申请日：2013-08-08

Applicant: Facebook, Inc.

Inventor： Brian Piepgrass ,  Deeptanshu Verma ,  Tony Hsien-yu Liu ,  Ashish Yadav ,  Julia Lee

IPC: G06F15/173

CPC classification number: G06F15/17306 ,  G06Q30/0269 ,  G06Q50/01

Abstract: A method for making entity recommendations to users of a social networking system (SNS) by maximizing a predicted benefit to the SNS through objective value models. The method includes generating a plurality of candidate entities eligible for recommendation, and determining a weight for each candidate entity based upon an output score generated by an objective value model. The objective value model utilizes objectively measurable input values describing the candidate entities and generates larger output scores for those candidate entities that would create larger predicted increases in an objectively measurable amount of benefit for the SNS created by a potential connection being created between the user and the respective candidate entity. One or more entities are selected based upon the determined weights, and an entity recommendation user interface is presented to the user that includes one or more recommendation modules identifying the selected one or more entities.

Abstract translation: 通过目标价值模型最大化对SNS的预期效益，为社交网络系统（SNS）的用户提供实体建议的方法。 该方法包括生成符合推荐标准的多个候选实体，并且基于由目标值模型生成的输出得分确定每个候选实体的权重。 目标价值模型利用描述候选实体的客观可衡量的输入值，并为那些候选实体产生更大的输出分数，这些候选实体将产生由在用户和用户之间创建的潜在连接所创建的SNS产生的可客观可衡量的有益效益的较大预测增长 各候选实体。 基于所确定的权重来选择一个或多个实体，并且向用户呈现包括标识所选择的一个或多个实体的一个或多个推荐模块的实体推荐用户界面。

公开(公告)号：US10587705B2

公开(公告)日：2020-03-10

申请号：US13659695

申请日：2012-10-24

Applicant: Facebook, Inc.

Inventor： Alexander Paul Schultz ,  Brian Piepgrass ,  Ching-Chih Weng ,  Daniel Ferrante ,  Deeptanshu Verma ,  Peter Martinazzi ,  Thomas Alison ,  Ziqing Mao

IPC: H04L29/08 ,  G06Q30/02 ,  G06Q50/00 ,  G06Q10/10

Abstract: Techniques introduced here include a system and method for determining whether to provide a user of a social networking system with candidate users (i.e., potential contacts) with whom the user does not already have any connections with. In some embodiments, the system generates a set of candidate users based on a value (e.g., to the social networking system) associated with each potential connection formed between the user and the set of candidate users. In one or more embodiments, the system ranks the candidate users based on their connection-value to the social networking system and provides the ranked candidate users as suggested new connections to the user.

公开(公告)号：US09146894B2

公开(公告)日：2015-09-29

申请号：US13962821

申请日：2013-08-08

Applicant: Facebook, Inc.

Inventor： Brian Piepgrass ,  Deeptanshu Verma ,  Tony Hsien-yu Liu ,  Ashish Yadav ,  Julia Lee

IPC: G06F15/16 ,  G06F15/173

CPC classification number: G06F15/17306 ,  G06Q30/0269 ,  G06Q50/01

Abstract: A method for making entity recommendations to users of a social networking system (SNS) by maximizing a predicted benefit to the SNS through objective value models. The method includes generating a plurality of candidate entities eligible for recommendation, and determining a weight for each candidate entity based upon an output score generated by an objective value model. The objective value model utilizes objectively measurable input values describing the candidate entities and generates larger output scores for those candidate entities that would create larger predicted increases in an objectively measurable amount of benefit for the SNS created by a potential connection being created between the user and the respective candidate entity. One or more entities are selected based upon the determined weights, and an entity recommendation user interface is presented to the user that includes one or more recommendation modules identifying the selected one or more entities.

Abstract translation: 通过目标价值模型最大化对SNS的预期效益，为社交网络系统（SNS）的用户提供实体建议的方法。 该方法包括生成符合推荐标准的多个候选实体，并且基于由目标值模型生成的输出得分确定每个候选实体的权重。 目标价值模型利用描述候选实体的客观可衡量的输入值，并为那些候选实体产生更大的输出分数，这些候选实体将产生由在用户和用户之间创建的潜在连接所创建的SNS产生的可客观可衡量的有益效益的较大预测增长 各候选实体。 基于所确定的权重来选择一个或多个实体，并且向用户呈现包括标识所选择的一个或多个实体的一个或多个推荐模块的实体推荐用户界面。

公开(公告)号：US20150127418A1

公开(公告)日：2015-05-07

申请号：US14070349

申请日：2013-11-01

Applicant: Facebook, Inc.

Inventor： Brian Piepgrass ,  Atol Fortin de Oliveira ,  Bin Jiang ,  Simon Goldman

IPC: G06Q30/02 ,  G06Q50/00

CPC classification number: G06Q30/0201 ,  G06Q30/0269 ,  G06Q50/01

Abstract: To enhance user engagement with a page posts maintained by a social networking system, a social networking system reviews posts associated with a page (e.g., a business or brand page) in a social networking system and measures a degree of user engagement with each post at one or more measures of exposure (e.g., time points or impressions). The social networking system then identifies posts for which the user engagement exceeds a threshold as high engagement or “hot” posts. An administrator associated with the page is notified of the identified high engagement post and can use this information for further promotion or boosting of the identified high engagement post.

Abstract translation: 为了增强与社交网络系统维护的页面帖子的用户参与度，社交网络系统评估与社交网络系统中的页面（例如，商业或品牌页面）相关联的帖子，并且测量与每个帖子的用户参与程度 一种或多种暴露措施（例如，时间点或印象）。 然后，社交网络系统会识别用户参与超过阈值的帖子，因为高参与度或“热门”职位。 与页面相关联的管理员通知所识别的高参与度帖子，并且可以使用该信息进一步推广或提升所识别的高参与度职位。

公开(公告)号：US20150095324A1

公开(公告)日：2015-04-02

申请号：US14562958

申请日：2014-12-08

Applicant: Facebook, Inc.

Inventor： Brian Piepgrass ,  Rohit Dhawan ,  Nicolas Andrij Bushak ,  Thomas Giovanni Carriero

IPC: G06F17/30 ,  H04L12/18

CPC classification number: G06F17/3053 ,  G06F17/30867 ,  H04L12/1813

Abstract: In one embodiment, a social-networking system accesses a social graph with a plurality of user nodes and a plurality of location nodes, receives a search query with location parameters, identifies a set of location nodes based on the search query, and determines a value for each location nodes in the set based on the edges connected to the location nodes in the social graph.

Abstract translation: 在一个实施例中，社交网络系统使用多个用户节点和多个位置节点访问社交图，接收具有位置参数的搜索查询，基于搜索查询来标识一组位置节点，并且确定值 基于连接到社交图中的位置节点的边缘，针对集合中的每个位置的节点。

公开(公告)号：US20140114774A1

公开(公告)日：2014-04-24

申请号：US13659695

申请日：2012-10-24

Applicant: Facebook, Inc.

Inventor： Alexander Paul Schultz ,  Brian Piepgrass ,  Ching-Chih Weng ,  Daniel Ferrante ,  Deeptanshu Verma ,  Peter Martinazzi ,  Thomas Alison ,  Ziqing Mao

IPC: H04L29/08 ,  G06Q50/00

Abstract: Techniques introduced here include a system and method for determining whether to provide a user of a social networking system with candidate users (i.e., potential contacts) with whom the user does not already have any connections with. In some embodiments, the system generates a set of candidate users based on a value (e.g., to the social networking system) associated with each potential connection formed between the user and the set of candidate users. In one or more embodiments, the system ranks the candidate users based on their connection-value to the social networking system and provides the ranked candidate users as suggested new connections to the user.

Abstract translation: 这里介绍的技术包括用于确定是否向社交网络系统的用户提供与用户尚未具有任何连接的候选用户（即，潜在联系人）的系统和方法。 在一些实施例中，系统基于与用户和一组候选用户之间形成的每个潜在连接相关联的值（例如，到社交网络系统）生成一组候选用户。 在一个或多个实施例中，系统基于其与社交网络系统的连接值对候选用户进行排名，并且将所排名的候选用户作为建议的新连接提供给用户。

公开(公告)号：US20150169787A1

公开(公告)日：2015-06-18

申请号：US14628180

申请日：2015-02-20

Applicant: Facebook, Inc.

Inventor： Brian Piepgrass ,  Siddharth Kar

IPC: G06F17/30

CPC classification number: G06F17/30958 ,  G06Q30/02 ,  G06Q50/01 ,  H04L51/32

Abstract: In one embodiment, a social graph associated with a social networking system may comprise user nodes, concept nodes, meta nodes, and edges between the nodes. A meta node may be connected by an edge to each of a set of concept nodes sharing attributes. A request associated with a first user may be received, wherein a user node for the first user is associated with a first one of the concept nodes. A meta node connected to the first concept node may be identified. Second concept nodes may be identified, wherein each of the second concept nodes is connected to the identified meta node. A value may be determined for each of the second concept nodes. Finally, information may be presented to the first user, wherein the information is related to at least one of the second concept nodes based on respective values for the second concept nodes.

Abstract translation: 在一个实施例中，与社交网络系统相关联的社交图可以包括用户节点，概念节点，元节点以及节点之间的边缘。 元节点可以通过边缘连接到共享属性的一组概念节点中的每一个。 可以接收与第一用户相关联的请求，其中用于第一用户的用户节点与概念节点中的第一个相关联。 可以识别连接到第一概念节点的元节点。 可以识别第二概念节点，其中每个第二概念节点连接到所识别的元节点。 可以为每个第二概念节点确定一个值。 最后，可以向第一用户呈现信息，其中基于第二概念节点的相应值，该信息与第二概念节点中的至少一个相关。