公开(公告)号：US20180121964A1

公开(公告)日：2018-05-03

申请号：US15340852

申请日：2016-11-01

Applicant: Facebook, Inc.

Inventor： Zhurun Zhang ,  Hao Zhang ,  Junbiao Tang ,  James Theodore Kleban ,  Avi Samuel Gavlovski ,  Hao Song ,  David Benjamin Lue ,  Anand Sumatilal Bhalgat

IPC: G06Q30/02 ,  G06Q50/00 ,  G06N99/00

CPC classification number: G06Q30/0269 ,  G06N20/00 ,  G06Q30/0277 ,  G06Q50/01

Abstract: An online system receives multiple candidate components for including in content items to be presented to online system users. Upon identifying an opportunity to present content to a subject user of the online system, the online system dynamically generates an optimal content item for presentation to the subject user that includes one or more candidate components. Candidate components included in the optimal content item are selected by predicting an affinity of the subject user for each candidate component. The affinity of the subject user for a candidate component may be predicted using a machine-learned model that is trained using historical performance information about content items including the candidate component that were presented to viewing users of the online system having at least a threshold measure of similarity to the subject user. Components of content items used to train the model may be selected using a heuristic (e.g., Thompson sampling).

公开(公告)号：US20190172089A1

公开(公告)日：2019-06-06

申请号：US15829841

申请日：2017-12-01

Applicant: Facebook, Inc.

Inventor： Junbiao Tang ,  Alexander Pivovarov ,  Anand Sumatilal Bhalgat ,  Janis Libeks ,  Hao Zhang ,  Yevgeniya Solyanik

IPC: G06Q30/02

Abstract: An online system determines an estimated conversion rate for sponsored content items placed on content publishers and on the online system. The estimated conversion rate can be determined by a machine learning model trained using data describing content campaigns, content publishers, and online system users. This data is collected by the online system from content publishers and/or content campaigns that report conversion rates to the online system. By determining a ratio of estimated conversion rates with third party content on the content publisher against those on the online system, the online system can determine a publisher quality score for that content publisher. The online system uses the publisher quality score to normalize third party value contributions toward placing sponsored content on content publishers and the online system. Thus, disparities in the intrinsic value across publishers are diminished as third party value contributions are normalized based on the publisher conversion rates.

公开(公告)号：US20160275554A1

公开(公告)日：2016-09-22

申请号：US14662222

申请日：2015-03-18

Applicant: Facebook, Inc.

Inventor： Feng Yan ,  Shyamsundar Rajaram ,  Hao Zhang ,  Lu Zheng ,  Tianshi Gao ,  David Michael Viner

IPC: G06Q30/02

CPC classification number: G06Q30/0255 ,  G06Q30/0277

Abstract: An online system tracks stores information identifying content provided by third party systems and accessed by online system users as well as interactions with advertisements performed by online system users. When the online system identifies an opportunity to present an advertisement to a viewing user, the online system identifies content from third party systems accessed by the viewing user and content from third party systems accessed by additional online system users who interacted with advertisements. A score is computed for various advertisements based at least in part on correlations between content from third party systems accessed by the viewing user and content from third party systems accessed by additional online system users who interacted with advertisements. The online system selects candidate advertisements to evaluate for presentation to the viewing user based on the scores.

Abstract translation: 在线系统跟踪识别由第三方系统提供并由在线系统用户访问的内容以及与在线系统用户执行的广告的交互的商店信息。 当在线系统识别向观看用户呈现广告的机会时，在线系统识别由观看用户访问的第三方系统的内容和来自与广告交互的其他在线系统用户访问的第三方系统的内容。 至少部分地基于由观看用户访问的来自第三方系统的内容与来自与由广告进行了互动的其他在线系统用户访问的第三方系统的内容的内容之间的相关性来计算各种广告的得分。 在线系统基于分数来选择候选广告来评估呈现给观看者。

公开(公告)号：US11157955B2

公开(公告)日：2021-10-26

申请号：US14662222

申请日：2015-03-18

Applicant: Facebook, Inc.

Inventor： Feng Yan ,  Shyamsundar Rajaram ,  Hao Zhang ,  Lu Zheng ,  Tianshi Gao ,  David Michael Viner

IPC: G06Q30/00 ,  G06Q30/02 ,  G05B19/418

Abstract: An online system tracks stores information identifying content provided by third party systems and accessed by online system users as well as interactions with advertisements performed by online system users. When the online system identifies an opportunity to present an advertisement to a viewing user, the online system identifies content from third party systems accessed by the viewing user and content from third party systems accessed by additional online system users who interacted with advertisements. A score is computed for various advertisements based at least in part on correlations between content from third party systems accessed by the viewing user and content from third party systems accessed by additional online system users who interacted with advertisements. The online system selects candidate advertisements to evaluate for presentation to the viewing user based on the scores.

公开(公告)号：US20140222802A1

公开(公告)日：2014-08-07

申请号：US13759838

申请日：2013-02-05

Applicant: Facebook, Inc.

Inventor： Rong Yan ,  Eytan Bakshy ,  Hao Zhang ,  Huajing Li

IPC: G06F17/30

CPC classification number: G06F16/248 ,  G06Q30/0241 ,  G06Q50/01

Abstract: A viewing user is provided with sponsored stories describes actions of a user connected to the viewing user associated with an object promoted by an advertiser or actions otherwise promoted by the advertiser. Based on a performance metric, the social networking system selects the user or action to be described by the sponsored story. For example, the social networking system ranks candidate sponsored stories describing different actions or users and selects a candidate sponsored story to increase the likelihood of a viewing user interacting with the selected candidate sponsored story.

Abstract translation: 查看用户被提供有赞助的故事，描述了连接到与广告主提出的对象相关联的观看用户的用户的动作或由广告主另外宣传的动作。 基于性能指标，社交网络系统选择由赞助故事描述的用户或动作。 例如，社交网络系统将候选赞助的故事描述为描述不同的动作或用户，并选择候选赞助的故事，以增加观看用户与所选择的候选赞助故事交互的可能性。