公开(公告)号：US09246990B2

公开(公告)日：2016-01-26

申请号：US14181183

申请日：2014-02-14

Applicant: Google Inc.

Inventor： Roman Kirillov ,  Hassan Mansoor

IPC: G06F15/173 ,  H04L29/08

CPC classification number: H04L67/10 ,  H04L67/20 ,  H04L67/26 ,  H04L67/2823 ,  H04L67/2838

Abstract: Systems and methods for predicting a conversion rate of a content publisher-third-party content provider pair are disclosed. A processor identifies, from log data, a plurality of publisher-provider pairs. Each publisher-provider pair corresponds to a content provider associated with at least one creative receiving at least one conversion when served on information resources of the publisher. The processor determines, for each publisher-provider pair, a conversion rate. The processor determines, for each publisher-provider pair, feature data of the publisher and feature data of the content provider. The processor can transform the determined feature data of the publishers and content providers and the conversion rates of the plurality of publisher-provider pairs into a conversion rate prediction model useful for predicting a conversion rate of a given publisher-provider pair different from the identified plurality of publisher-provider pairs.

Abstract translation: 公开了用于预测内容发行商 - 第三方内容提供商对的转换率的系统和方法。 处理器从日志数据识别多个发布者 - 提供者对。 每个发布者 - 提供商对对应于与在发布者的信息资源上服务时至少接收至少一个转换的至少一个广告素材相关联的内容提供商。 处理器为每个发行商 - 提供商对确定转化率。 处理器为每个发行商 - 提供商对确定发布者的特征数据和内容提供商的特征数据。 处理器可以将所确定的发布者和内容提供商的特征数据以及多个发行者 - 提供商对的转换率转换成用于预测与所识别的多个不同的给定发行商 - 提供商对的转换率的转换率预测模型 的发布商 - 供应商对。

公开(公告)号：US09536011B1

公开(公告)日：2017-01-03

申请号：US14461633

申请日：2014-08-18

Applicant: Google Inc.

Inventor： Roman Kirillov

IPC: G06F17/00 ,  G06F17/30 ,  G06Q30/02 ,  G06F17/21

CPC classification number: G06F17/3089 ,  G06F17/21 ,  G06Q30/0277

Abstract: Methods and systems for identifying availability of a content unit are described. Processors receive a request to reserve inventory of a content unit for a contiguous set of time units within a date range. The processors generate a request string including a first plurality of characters corresponding to a position in the request string and having a character value. The processors generate an inventory string including a second plurality of characters corresponding to a position in the inventory string and having a character value. The processors determine a substring of the inventory string that includes an equal number of characters as the request string and each character of the substring has a character value that is equal to or greater than a character value of a corresponding character of the request string. The processors display dates corresponding to the substring.

Abstract translation: 描述用于识别内容单元的可用性的方法和系统。 处理器接收一个请求，以在日期范围内为连续的一组时间单位预留内容单元的库存。 处理器生成包括与请求字符串中的位置对应的第一多个字符并且具有字符值的请求字符串。 处理器生成包括对应于库存字符串中的位置并具有字符值的第二多个字符的库存字符串。 处理器确定库存字符串的子字符串，其包括与请求字符串相等数量的字符，并且子字符串的每个字符的字符值等于或大于请求字符串的对应字符的字符值。 处理器显示对应于子串的日期。

公开(公告)号：US20160371231A1

公开(公告)日：2016-12-22

申请号：US15255600

申请日：2016-09-02

Applicant: Google Inc.

Inventor： Roman Kirillov ,  Andrew Tyler ,  Daniel Banfield ,  Hassan Mansoor ,  Daniel Matthew Goodridge ,  Louis Aidan Collard

IPC: G06F17/21 ,  G06F17/24 ,  G06T3/40

CPC classification number: G06F17/212 ,  G06F17/00 ,  G06F17/2247 ,  G06F17/24 ,  G06F17/30 ,  G06F17/30893 ,  G06Q10/00 ,  G06Q30/0275 ,  G06Q30/0277 ,  G06T3/403 ,  G06T2210/12 ,  G06T2210/22 ,  H04L47/806 ,  H04L67/02 ,  H04L67/20

Abstract: Systems and methods for providing an actionable object within a third-party content slot of an information resource of a content publisher. A processor receives an indication of interest in providing, for display, a creative within at least one third-party content slot of an information resource of a content publisher. The information resource includes third-party content slots available to be reserved to serve creatives. The processor identifies, on the information resource, at least one third-party content slot available to be reserved to serve one or more creatives. The processor inserts an actionable object within the identified third-party content slot, the actionable object configured to generate a request to provide an interface for reserving the identified third-party content slot to display the creative responsive to an action being taken on the actionable object. The processor renders the information resource including the inserted actionable object within the identified third-party content slot.

公开(公告)号：US20150237115A1

公开(公告)日：2015-08-20

申请号：US14181183

申请日：2014-02-14

Applicant: Google Inc.

Inventor： Roman Kirillov ,  Hassan Mansoor

IPC: H04L29/08

CPC classification number: H04L67/10 ,  H04L67/20 ,  H04L67/26 ,  H04L67/2823 ,  H04L67/2838

Abstract: Systems and methods for predicting a conversion rate of a content publisher-third-party content provider pair are disclosed. A processor identifies, from log data, a plurality of publisher-provider pairs. Each publisher-provider pair corresponds to a content provider associated with at least one creative receiving at least one conversion when served on information resources of the publisher. The processor determines, for each publisher-provider pair, a conversion rate. The processor determines, for each publisher-provider pair, feature data of the publisher and feature data of the content provider. The processor can transform the determined feature data of the publishers and content providers and the conversion rates of the plurality of publisher-provider pairs into a conversion rate prediction model useful for predicting a conversion rate of a given publisher-provider pair different from the identified plurality of publisher-provider pairs.

Abstract translation: 公开了用于预测内容发行商 - 第三方内容提供商对的转换率的系统和方法。 处理器从日志数据识别多个发布者 - 提供者对。 每个发布者 - 提供商对对应于与在发布者的信息资源上服务时至少接收至少一个转换的至少一个广告素材相关联的内容提供商。 处理器为每个发行商 - 提供商对确定转化率。 处理器为每个发行商 - 提供商对确定发布者的特征数据和内容提供商的特征数据。 处理器可以将所确定的发布者和内容提供商的特征数据以及多个发行者 - 提供商对的转换率转换成用于预测与所识别的多个不同的给定发行商 - 提供商对的转换率的转换率预测模型 的发布商 - 供应商对。

公开(公告)号：US09111231B2

公开(公告)日：2015-08-18

申请号：US13631635

申请日：2012-09-28

Applicant: GOOGLE INC.

Inventor： Roman Kirillov

IPC: G06N99/00 ,  G06Q30/02 ,  H04N21/258 ,  H04N21/426 ,  H04N21/436 ,  H04N21/61

CPC classification number: G06N99/005 ,  G06Q30/0201 ,  G06Q30/0255 ,  H04N21/25883 ,  H04N21/42684 ,  H04N21/43615 ,  H04N21/6125

Abstract: A method for associating a web session with a particular member of a group of users includes: receiving a plurality of training web sessions, each training web session including one or more web events generated by a respective known user having one or more demographic attributes; training one or more binary classifiers using the training web sessions and the demographic attributes of the users; receiving a plurality of target web sessions, each target web session including one or more web events that are generated by a respective unknown member of a group of users, wherein each user has one or more demographic attributes; and applying one or more of the binary classifiers to the target web sessions such that a respective target web session is uniquely associated with a member based on, at least in part, the demographic attributes of the member.

Abstract translation: 用于将网络会话与一组用户的特定成员相关联的方法包括：接收多个训练网络会话，每个训练网络会话包括由具有一个或多个人口统计属性的相应已知用户生成的一个或多个网络事件; 使用训练网络会话和用户的人口统计属性来训练一个或多个二进制分类器; 接收多个目标网络会话，每个目标网络会话包括由一组用户的相应未知成员生成的一个或多个web事件，其中每个用户具有一个或多个人口统计属性; 以及将一个或多个二进制分类器应用于目标网络会话，使得相应的目标网络会话至少部分地基于该成员的人口统计属性与成员唯一地相关联。

公开(公告)号：US10067916B2

公开(公告)日：2018-09-04

申请号：US15255591

申请日：2016-09-02

Applicant: Google Inc.

Inventor： Roman Kirillov ,  Andrew Tyler ,  Daniel Banfield ,  Hassan Mansoor ,  Daniel Matthew Goodridge ,  Louis Aidan Collard

IPC: G06F15/16 ,  G06F17/21 ,  H04L12/927 ,  G06F17/00 ,  G06F17/30 ,  G06Q10/00 ,  G06F17/22 ,  G06F17/24 ,  G06Q30/02 ,  G06T3/40 ,  H04L29/08

Abstract: Systems and methods for providing an actionable object within a third-party content slot of an information resource of a content publisher. A processor receives an indication of interest in providing, for display, a creative within at least one third-party content slot of an information resource of a content publisher. The information resource includes third-party content slots available to be reserved to serve creatives. The processor identifies, on the information resource, at least one third-party content slot available to be reserved to serve one or more creatives. The processor inserts an actionable object within the identified third-party content slot, the actionable object configured to generate a request to provide an interface for reserving the identified third-party content slot to display the creative responsive to an action being taken on the actionable object. The processor renders the information resource including the inserted actionable object within the identified third-party content slot.

公开(公告)号：US09461936B2

公开(公告)日：2016-10-04

申请号：US14181199

申请日：2014-02-14

Applicant: Google Inc.

Inventor： Roman Kirillov ,  Andrew Tyler ,  Daniel Banfield ,  Hassan Mansoor ,  Daniel Matthew Goodridge ,  Louis Aidan Collard

IPC: G06F15/173 ,  H04L12/927 ,  G06F17/00 ,  G06F17/30 ,  G06Q10/00

CPC classification number: G06F17/212 ,  G06F17/00 ,  G06F17/2247 ,  G06F17/24 ,  G06F17/30 ,  G06F17/30893 ,  G06Q10/00 ,  G06Q30/0275 ,  G06Q30/0277 ,  G06T3/403 ,  G06T2210/12 ,  G06T2210/22 ,  H04L47/806 ,  H04L67/02 ,  H04L67/20

Abstract: Systems and methods for providing an actionable object within a third-party content slot of an information resource of a content publisher. A processor receives an indication of interest in providing, for display, a creative within at least one third-party content slot of an information resource of a content publisher. The information resource includes third-party content slots available to be reserved to serve creatives. The processor identifies, on the information resource, at least one third-party content slot available to be reserved to serve one or more creatives. The processor inserts an actionable object within the identified third-party content slot, the actionable object configured to generate a request to provide an interface for reserving the identified third-party content slot to display the creative responsive to an action being taken on the actionable object. The processor renders the information resource including the inserted actionable object within the identified third-party content slot.

Abstract translation: 用于在内容发布者的信息资源的第三方内容时隙内提供可操作对象的系统和方法。 处理器在内容发布者的信息资源的至少一个第三方内容时隙内接收提供用于显示广告素材的感兴趣的指示。 信息资源包括可用于投放广告素材的第三方内容插槽。 处理器在信息资源上识别至少一个可被保留以供服务一个或多个广告素材的第三方内容时隙。 所述处理器在所识别的第三方内容时隙内插入可操作对象，所述可操作对象被配置为生成请求以提供用于保留所识别的第三方内容时隙的接口，以响应于对所述可动作对象采取的动作来显示所述广告素材 。 处理器将包括所插入的可操作对象的信息资源呈现在所识别的第三方内容时隙内。

公开(公告)号：US20140351234A1

公开(公告)日：2014-11-27

申请号：US14455776

申请日：2014-08-08

Applicant: Google Inc.

Inventor： Kyle Maddison ,  Roman Kirillov

IPC: G06F17/30

CPC classification number: G06F17/30867 ,  G06F17/30781 ,  G06F17/3087 ,  G06F17/30967 ,  G06F17/30973 ,  H04N21/4524 ,  H04N21/4782 ,  H04N21/4828

Abstract: A method receives a search query from a user device during a time window and accesses a repository of streaming media related information to determine one or more streaming media programs available to the user device during the time window. The method identifies a first set of categories associated with the received search query and identifies a respective program-specific set of categories associated with each of the respective available streaming media programs. The method compares the first set of categories to each respective program-specific set of categories to infer that a first streaming media program is being displayed in proximity to the user device. The method modifies the search query based on adding search terms from the streaming media related information corresponding to the first streaming media program. The method identifies search results corresponding to the modified search query and returns the search results to the user device.

Abstract translation: 一种方法在时间窗口期间从用户设备接收搜索查询，并访问流媒体相关信息的存储库以确定在该时间窗口期间可用于该用户设备的一个或多个流媒体节目。 该方法识别与接收到的搜索查询相关联的第一组类别，并且识别与相应可用的流媒体节目中的每一个相关联的各自的节目特定的类别集合。 该方法将第一组类别与每个相应的特定于类别的集合进行比较，以推断第一流媒体节目正在用户设备附近被显示。 该方法基于从与第一流媒体程序相对应的流媒体相关信息添加搜索词来修改搜索查询。 该方法识别与修改的搜索查询相对应的搜索结果，并将搜索结果返回给用户设备。

公开(公告)号：US10210140B2

公开(公告)日：2019-02-19

申请号：US15255600

申请日：2016-09-02

Applicant: Google Inc.

Inventor： Roman Kirillov ,  Andrew Tyler ,  Daniel Banfield ,  Hassan Mansoor ,  Daniel Matthew Goodridge ,  Louis Aidan Collard

IPC: G06F15/16 ,  G06F17/21 ,  H04L12/927 ,  G06F17/00 ,  G06F17/30 ,  G06Q10/00 ,  G06F17/22 ,  G06F17/24 ,  G06Q30/02 ,  G06T3/40 ,  H04L29/08

Abstract: Systems and methods for providing an actionable object within a third-party content slot of an information resource of a content publisher. A processor receives an indication of interest in providing, for display, a creative within at least one third-party content slot of an information resource of a content publisher. The information resource includes third-party content slots available to be reserved to serve creatives. The processor identifies, on the information resource, at least one third-party content slot available to be reserved to serve one or more creatives. The processor inserts an actionable object within the identified third-party content slot, the actionable object configured to generate a request to provide an interface for reserving the identified third-party content slot to display the creative responsive to an action being taken on the actionable object. The processor renders the information resource including the inserted actionable object within the identified third-party content slot.

公开(公告)号：US20160165277A1

公开(公告)日：2016-06-09

申请号：US13843683

申请日：2013-03-15

Applicant: Google Inc.

Inventor： Roman Kirillov ,  Nicolas Remy ,  James Robert Koehler ,  Simon Michael Rowe ,  Xiaojing Wang ,  Diane Lambert

IPC: H04N21/24

CPC classification number: H04N21/251 ,  H04N21/25883 ,  H04N21/25891 ,  H04N21/44222

Abstract: A method, executed by a processor, for estimating media metrics from large population data includes formatting and storing panel data, the panel data comprising observed viewing data of a plurality of individual panelists and demographic data for the plurality of panelists, the panel being drawn from a large population; accessing the large population data, the large population data comprising household-level viewing data and household level demographics; training a model to estimate viewing audience size based on the observed panel data; estimating, using the trained model, audience size for each household in the large population data; estimating a viewing score for each individual viewer in a plurality of households in the large population data; and combining the estimates of audience size and viewing score to produce probabilities that each of the viewers in the household viewed a specific media event.

Abstract translation: 由处理器执行的用于从大量数据估计媒体度量的方法包括格式化和存储面板数据，面板数据包括多个单独小组成员的观察数据和多个小组成员的人口统计数据，面板从 人口众多 获取大量人口数据，大量人口数据包括家庭层面的观看数据和家庭层面的人口统计; 培训模型以根据观察到的面板数据估计观众人数; 在大量人口数据中，使用受过训练的模型估计每个家庭的受众人数; 估计大群体数据中多个家庭中每个单独观众的观看分数; 并且将观众大小和观看分数的估计结合起来，以产生每个家庭观众观看特定媒体事件的概率。