公开(公告)号：US09767489B1

公开(公告)日：2017-09-19

申请号：US14032169

申请日：2013-09-19

Applicant: Google Inc.

Inventor： Yifang Liu ,  Konstantinos Katsiapis ,  Christopher Kenneth Harris

IPC: G06Q30/02 ,  H04L29/08 ,  G06F17/30

CPC classification number: G06Q30/0277 ,  G06F17/30867 ,  G06Q30/0241 ,  G06Q30/0249 ,  G06Q30/0253 ,  H04L67/22 ,  H04L67/32

Abstract: When a content item is initially served to a client device, the content item may result in an impression effect. As time elapses, the initial impression may fade. Such a decay of the impression effect may be predicted through the use of a predictive model. In some implementations, one or more impression effect parameters may be accessed and used with the predictive model to determine a decay factor or predicted value that incorporates the impression effect decay for a content item. A value, such as a score, may be determined based on the decay factor or the predicted value and a bid associated with a content item. A content item may be selected based on the determined value and data to effect presentation of the content item may be provided.

公开(公告)号：US10417286B1

公开(公告)日：2019-09-17

申请号：US15704980

申请日：2017-09-14

Applicant: Google Inc.

Inventor： Yefei Peng ,  Christopher Kenneth Harris

IPC: G06F16/95

Abstract: Systems and methods of the present disclosure are directed generally to facilitating content selection by identifying low impact criteria. In some implementations, a data processing system accesses a data structure storing, in a memory element, a plurality of impression records. Each impression record can include one or more features and an indication of user interest corresponding to a content impression. The data processing system can identify a combination feature based on at least two of the features. The data processing system can execute a statistical model (e.g., logistic regression model) using the impression records and the combination feature. The data processing system can determine a weight for the combination feature. Responsive to the weight being less than a threshold, the data processing system can transmit an indication to disable the combination feature for selecting content associated with the plurality of impression records.

公开(公告)号：US09767196B1

公开(公告)日：2017-09-19

申请号：US14085153

申请日：2013-11-20

Applicant: Google Inc.

Inventor： Yefei Peng ,  Christopher Kenneth Harris

IPC: G06F7/00 ,  G06F17/30

CPC classification number: G06F17/30861 ,  G06F17/30867

Abstract: Systems and methods of the present disclosure are directed generally to facilitating content selection by identifying low impact criteria. In some implementations, a data processing system accesses a data structure storing, in a memory element, a plurality of impression records. Each impression record can include one or more features and an indication of user interest corresponding to a content impression. The data processing system can identify a combination feature based on at least two of the features. The data processing system can execute a statistical model (e.g., logistic regression model) using the impression records and the combination feature. The data processing system can determine a weight for the combination feature. Responsive to the weight being less than a threshold, the data processing system can transmit an indication to disable the combination feature for selecting content associated with the plurality of impression records.

公开(公告)号：US20180330387A1

公开(公告)日：2018-11-15

申请号：US13673906

申请日：2012-11-09

Applicant: GOOGLE INC.

Inventor： Christopher Kenneth Harris ,  Xiaofeng Guo ,  Ke Huang ,  Bahman Rabii ,  Alok Goel

IPC: G06Q30/02 ,  G06Q10/08 ,  G06Q30/06

CPC classification number: G06Q30/02 ,  G06Q10/08 ,  G06Q30/06

Abstract: Conducting a group buying advertising campaign. Receiving a specification for a group-buying offer. Creating a candidate ad campaign based on the received specification. The candidate ad campaign includes at least one campaign feature. The candidate ad is characterized by at least one generalized feature. Determining the expected effectiveness of the candidate ad campaign. For an expected effectiveness less than the aggregate effectiveness of a set of at least one previously run ad campaigns having a generalized feature in common with the candidate campaign, editing the candidate ad campaign to incorporate at least one feature of the set of at least one previously run ad campaigns. Running the edited ad campaign in an ad display network. Collecting effectiveness data for each run ad campaign.

公开(公告)号：US10726453B1

公开(公告)日：2020-07-28

申请号：US15704940

申请日：2017-09-14

Applicant: Google Inc.

Inventor： Yifang Liu ,  Konstantinos Katsiapis ,  Christopher Kenneth Harris

IPC: G06Q30/02 ,  H04L29/08 ,  G06F16/9535

Abstract: When a content item is initially served to a client device, the content item may result in an impression effect. As time elapses, the initial impression may fade. Such a decay of the impression effect may be predicted through the use of a predictive model. In some implementations, one or more impression effect parameters may be accessed and used with the predictive model to determine a decay factor or predicted value that incorporates the impression effect decay for a content item. A value, such as a score, may be determined based on the decay factor or the predicted value and a bid associated with a content item. A content item may be selected based on the determined value and data to effect presentation of the content item may be provided.

公开(公告)号：US20170055145A1

公开(公告)日：2017-02-23

申请号：US15236968

申请日：2016-08-15

Applicant: Google Inc.

Inventor： Kavita Kannan ,  Charlie Guo ,  Christopher Kenneth Harris ,  Xi Mao ,  Thomas Matthew James Hennigan ,  Sissie Ling-Ie Hsiao ,  Riccardo Govoni ,  Kotwani Sachin

IPC: H04W8/22 ,  H04L29/08 ,  H04W4/00 ,  G06Q30/08 ,  H04W4/02 ,  H04W8/26

CPC classification number: G06Q30/08 ,  H04L67/06 ,  H04L67/20 ,  H04L67/303 ,  H04W4/60

Abstract: Implementations described herein relate to filtering content items from a set of eligible content items based on a device filter. A mobile application may be incompatible with one or more devices based on an operating system, an operating system version, hardware configurations of the one or more client devices, etc. To remove incompatible content items, a device filter can be generated by comparing a set of required features for the corresponding mobile application with data from a data structure identifying several known mobile devices and associated sets of features. The set of required features for the mobile application may include a minimum operating system version, one or more eligible countries, and/or one or more features of a mobile device. The device filter can include a set of identifiers for the known mobile devices that are incompatible with the mobile application based on the comparison.

Abstract translation: 本文描述的实现涉及基于设备过滤器来从一组合格的内容项过滤内容项。 移动应用可以与基于操作系统，操作系统版本，一个或多个客户端设备的硬件配置等的一个或多个设备不兼容。为了移除不兼容的内容项目，可以通过比较设置 使用来自标识几个已知移动设备和相关联的特征集合的数据结构的数据的相应移动应用的所需特征。 移动应用的所需功能集合可以包括最小操作系统版本，一个或多个合格国家，和/或移动设备的一个或多个特征。 基于比较，设备过滤器可以包括与移动应用不兼容的已知移动设备的一组标识符。