公开(公告)号：US10789276B2

公开(公告)日：2020-09-29

申请号：US15379451

申请日：2016-12-14

Applicant: Google Inc.

Inventor： Xiaonan Zhang ,  Shankar Ponnekanti ,  Oren Eli Zamir ,  Ting Liu

IPC: G06F16/28 ,  H04L29/08 ,  G06F16/583 ,  G06F16/9535 ,  G06N5/02

Abstract: Systems and methods for predicting content performance with interest data include receiving a content selection request that includes a client identifier. One or more topical interest categories associated with the client identifier may be used as inputs to a prediction model to predict the likelihood of an online action occurring as a result of third-party content being selected. The predicted likelihood may be used to select third-party content.

公开(公告)号：US20170097982A1

公开(公告)日：2017-04-06

申请号：US15379451

申请日：2016-12-14

Applicant: Google Inc.

Inventor： Xiaonan Zhang ,  Shankar Ponnekanti ,  Oren Eli Zamir ,  Ting Liu

IPC: G06F17/30 ,  G06N5/02 ,  H04L29/08

Abstract: Systems and methods for predicting content performance with interest data include receiving a content selection request that includes a client identifier. One or more topical interest categories associated with the client identifier may be used as inputs to a prediction model to predict the likelihood of an online action occurring as a result of third-party content being selected. The predicted likelihood may be used to select third-party content.

公开(公告)号：US20140068011A1

公开(公告)日：2014-03-06

申请号：US13831110

申请日：2013-03-14

Applicant: GOOGLE INC.

Inventor： Xiaonan Zhang ,  Shankar Ponnekanti ,  Oren Eli Zamir ,  Ting Liu

IPC: H04L29/08

CPC classification number: G06F17/30598 ,  G06F17/30253 ,  G06F17/30256 ,  G06F17/30867 ,  G06N5/02 ,  H04L67/02 ,  H04L67/20 ,  H04L67/303

Abstract: Systems and methods for predicting content performance with interest data include receiving a content selection request that includes a client identifier. One or more topical interest categories associated with the client identifier may be used as inputs to a prediction model to predict the likelihood of an online action occurring as a result of third-party content being selected. The predicted likelihood may be used to select third-party content.

Abstract translation: 用兴趣数据预测内容表现的系统和方法包括接收包括客户标识符的内容选择请求。 可以将与客户端标识符相关联的一个或多个主题兴趣类别用作预测模型的输入，以预测作为选择的第三方内容的结果发生在线动作的可能性。 预测的可能性可用于选择第三方内容。

公开(公告)号：US09549017B2

公开(公告)日：2017-01-17

申请号：US13831110

申请日：2013-03-14

Applicant: Google Inc.

Inventor： Xiaonan Zhang ,  Shankar Ponnekanti ,  Oren Eli Zamir ,  Ting Liu

IPC: H04L29/08 ,  G06F17/30

CPC classification number: G06F17/30598 ,  G06F17/30253 ,  G06F17/30256 ,  G06F17/30867 ,  G06N5/02 ,  H04L67/02 ,  H04L67/20 ,  H04L67/303

Abstract: Systems and methods for predicting content performance with interest data include receiving a content selection request that includes a client identifier. One or more topical interest categories associated with the client identifier may be used as inputs to a prediction model to predict the likelihood of an online action occurring as a result of third-party content being selected. The predicted likelihood may be used to select third-party content.

Abstract translation: 用兴趣数据预测内容表现的系统和方法包括接收包括客户标识符的内容选择请求。 可以将与客户端标识符相关联的一个或多个主题兴趣类别用作预测模型的输入，以预测作为选择的第三方内容的结果发生在线动作的可能性。 预测的可能性可用于选择第三方内容。