公开(公告)号：US20170186101A1

公开(公告)日：2017-06-29

申请号：US14981029

申请日：2015-12-28

Applicant: Facebook, Inc.

Inventor： Komal Kapoor ,  Jonathan Daniel Sorg ,  Bradley Ray Green ,  Jason Brewer ,  David Tomotsu Sasaki

IPC: G06Q50/00

Abstract: Systems, methods, and non-transitory computer-readable media can determine a plurality of candidate entities for recommendation to a user of a social networking system. A predicted activity objective value model configured to calculate activity stores for candidate entities is established. The activity score is indicative of the probability of future activity on the social networking system by a candidate entity. A first activity score is determined for each of the plurality of candidate entities based on the predicted activity object value model and a first set of feature values. A second activity score is determined for each of the plurality of candidate entities based on the predicted activity object value model and a second set of feature values that is different from the first set of feature values. A first entity is selected of the plurality of candidate entities based on the first and second activity scores.

公开(公告)号：US20160044121A1

公开(公告)日：2016-02-11

申请号：US14887008

申请日：2015-10-19

Applicant: Facebook, Inc.

Inventor： Joshua Williams ,  Daniel Jeng-Ping Hui ,  Mao Xue ,  Jason Brewer ,  Justin Moore ,  Keegan Jones

IPC: H04L29/08

CPC classification number: H04L67/22 ,  H04L67/306

Abstract: Particular embodiments detect events associated with information about activities that a user has engaged in. The activities may be associated with a location or location-agnostic. Based on the received information, the social-networking system sends the user a request for follow-up information after an appropriate time delay. The time delay may vary based on the user activity and the context of the event that triggered the request. After the follow-up information is received, such information is stored in the social-networking system and may be used to determine recommendations, sponsored stories, advertisements, etc. to send to friends of the user. The information may also be used for ranking or filtering recommendations.

公开(公告)号：US10733678B2

公开(公告)日：2020-08-04

申请号：US14981029

申请日：2015-12-28

Applicant: Facebook, Inc.

Inventor： Komal Kapoor ,  Jonathan Daniel Sorg ,  Bradley Ray Green ,  Jason Brewer ,  David Tomotsu Sasaki

IPC: G06Q10/00 ,  G06Q50/00

Abstract: Systems, methods, and non-transitory computer-readable media can determine a plurality of candidate entities for recommendation to a user of a social networking system. A predicted activity objective value model configured to calculate activity stores for candidate entities is established. The activity score is indicative of the probability of future activity on the social networking system by a candidate entity. A first activity score is determined for each of the plurality of candidate entities based on the predicted activity object value model and a first set of feature values. A second activity score is determined for each of the plurality of candidate entities based on the predicted activity object value model and a second set of feature values that is different from the first set of feature values. A first entity is selected of the plurality of candidate entities based on the first and second activity scores.

公开(公告)号：US09710756B2

公开(公告)日：2017-07-18

申请号：US14570825

申请日：2014-12-15

Applicant: Facebook, Inc.

Inventor： Jason Brewer ,  Bradley Ray Green

IPC: G06N3/08 ,  G06F17/30 ,  G06N7/00 ,  G06N99/00 ,  H04N21/25

CPC classification number: G06N7/005 ,  G06F17/30 ,  G06N3/08 ,  G06N99/005 ,  G06Q50/01 ,  H04N21/251

Abstract: Systems, methods, and non-transitory computer readable media configured to determine whether a candidate content item may be presented in response to an indication of approval by a user regarding a seed content item according to a first technique. It is determined whether the seed content item may be presented in response to an indication of approval by the user regarding the candidate content item according to a second technique. Features, including a reciprocity feature based on the determining whether a candidate item may be presented and the determining whether the seed content item may be presented, are processed to generate a probability that the user will interact with the candidate content item.

公开(公告)号：US20160162503A1

公开(公告)日：2016-06-09

申请号：US14565237

申请日：2014-12-09

Applicant: Facebook, Inc.

Inventor： Jinyi Yao ,  James Wah Hou Wong ,  Jason Brewer ,  Bradley Ray Green

IPC: G06F17/30 ,  G06Q50/00 ,  G06Q30/02

CPC classification number: G06Q50/01 ,  G06F16/9535 ,  G06Q30/0275

Abstract: Systems, methods, and non-transitory computer readable media configured to determine seed content items based on interests of a user. Candidate content items can be determined for potential presentation to the user based at least in part on the seed content items. Features associated with the candidate content items can be processed to generate probabilities that the user will perform interactions with the candidate content items. Values can be assigned to the candidate content items based on the probabilities that the user will perform interactions with the candidate content items and the importance of the interactions. The values can be provided as bid values to an auction system to determine constraints regarding presentation of the candidate content items. Presentation of the candidate content items can be optimized.

Abstract translation: 配置为基于用户的兴趣来确定种子内容项的系统，方法和非暂时计算机可读介质。 可以至少部分地基于种子内容项目来确定可能呈现给用户的候选内容项目。 可以处理与候选内容项相关联的特征以产生用户将执行与候选内容项目的交互的概率。 可以基于用户将执行与候选内容项目的交互以及交互的重要性的概率将值分配给候选内容项目。 这些值可以作为投标价值提供给拍卖系统，以确定关于候选内容项目的呈现的约束。 可以优化候选内容项目的呈现。