公开(公告)号：WO2015196352A1

公开(公告)日：2015-12-30

申请号：PCT/CN2014/080595

申请日：2014-06-24

Applicant: THE NIELSEN COMPANY (US), LLC ,  LU, Qiujing

Inventor： LU, Qiujing

IPC: G06F17/30

CPC classification number: G06Q30/02 ,  G06Q10/087

Abstract: Methods and apparatus are disclosed to categorize items.Adisclosed example method involves converting a natural language product description associated with a transaction record that does not include indexable identifiers to create input data comprising product descriptors.The method also involves generating a first confidence level associated with a first candidate category based on ones of the product descriptors having a first weighted value associated with the first candidate category.The example method also includes generating a second confidence level associated with a second candidate category based on ones of the product descriptors having a second weighted value associated with the second candidate category,and assigning the product to one of thefirst or second candidate categories based on a difference between the first and second confidence levels.

Abstract translation: 公开了分类项目的方法和装置。所公开的示例方法涉及转换与不包括可索引标识符的交易记录相关联的自然语言产品描述，以创建包括产品描述符的输入数据。该方法还涉及生成与 基于具有与第一候选类别相关联的第一加权值的产品描述符中的第一候选类别的第一候选类别。示例性方法还包括基于具有第二加权值的产品描述符之一生成与第二候选类别相关联的第二置信水平 与第二候选类别相关联，以及基于第一和第二置信水平之间的差异将产品分配给第一或第二候选类别之一。

公开(公告)号：WO2015123201A1

公开(公告)日：2015-08-20

申请号：PCT/US2015/015219

申请日：2015-02-10

Applicant: THE NIELSEN COMPANY (US), LLC

Inventor： WOOD, Ben ,  COUGHLIN, John Charles ,  POPPIE, Molly ,  KRAMER, Marie ,  FUHRER, Brian ,  BORAWSKI, Albert T. ,  MILAVSKY, Joseph G. ,  DONATO, Paul ,  SHANKAR, Balachander ,  KURZYNSKI, David J.

IPC: G06Q30/02 ,  G06Q10/10

CPC classification number: H04N21/2668 ,  H04N21/23424 ,  H04N21/2407 ,  H04N21/251 ,  H04N21/252 ,  H04N21/25883 ,  H04N21/44222 ,  H04N21/4663 ,  H04N21/4667 ,  H04N21/812

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to calculate video-on-demand viewing probability. Example methods disclosed herein include identifying a first set of households associated with a target set of categories that presented a first media having a first telecast delay, calculating first total tuning minutes and first total exposure minutes for the first set of households, identifying a second set of households that presented the first media having the first telecast delay and having a portion of the target set of categories, the second set of households having second total tuning minutes and second total exposure minutes for each category in the second set of households, calculating a household tuning proportion based on the first and second total tuning minutes, and calculating a household exposure proportion based on the first and second total exposure minutes, and calculating the panelist viewing probability associated with the first telecast delay based on a ratio of the household exposure proportion and the household tuning proportion.

Abstract translation: 公开了方法，装置，系统和制品以计算视频点播观看概率。 本文公开的示例方法包括识别与呈现具有第一电视广播延迟的第一媒体的目标类别组相关联的第一组户，计算第一组家庭的第一总调谐分钟和第一总曝光分钟，识别第二组 提供第一媒体的家庭具有第一个电视广播延迟并且具有目标集合的一部分，第二组家庭具有第二组家庭的每个类别的第二总调谐分钟和第二总曝光分钟，计算一个 基于第一和第二总调谐分钟的家庭调整比例，以及基于第一和第二总曝光分钟计算家庭曝光比例，并且基于家庭曝光比例的比率来计算与第一电视广播延迟相关联的小组成员观看概率 和家庭调整比例。

公开(公告)号：WO2015102795A1

公开(公告)日：2015-07-09

申请号：PCT/US2014/068168

申请日：2014-12-02

Applicant: THE NIELSEN COMPANY (US), LLC

Inventor： TOUPET, Antonia ,  YI, Peng Fei ,  SRIVASTAVA, Seema Varma

IPC: G06F17/00 ,  G06F17/30

CPC classification number: G06Q30/0242 ,  G06Q50/01

Abstract: An example involves determining a missing-audience factor based on first impressions corresponding to first client devices that do not have database proprietor (DP) identifiers for use by a DP to identify subscribers registered with the DP, and based on second impressions corresponding to second client devices that do have the DP identifiers used by the DP to identify subscribers registered with the DP. The first impressions represent accesses to media via the first client devices. The second impressions represent access to the media via the second client devices. The example involves determining a coverage-corrected unique audience (CCUA) size based on the missing-audience factor and a UA size of DP subscribers exposed to the media. The UA size is determined based on impressions logged by the DP. The CCUA size corresponds to impressions logged by the DP and not logged by the DP.

Abstract translation: 一个示例涉及基于与没有数据库所有者（DP）标识符的第一客户端设备相对应的第一印象来确定缺少受众因素，以供DP使用以识别向DP注册的订户，并且基于对应于第二客户端的第二印象 确实具有由DP使用的DP标识符来识别在DP上注册的用户的设备。 第一印象表示通过第一个客户端设备访问媒体。 第二次展示代表通过第二个客户端设备访问媒体。 该示例涉及基于丢失的受众因素和暴露于媒体的DP订户的UA大小来确定覆盖率校正的唯一受众（CCUA）大小。 UA大小根据DP记录的印象确定。 CCUA大小对应于DP记录的展示次数，而DP不记录。

公开(公告)号：WO2015031262A1

公开(公告)日：2015-03-05

申请号：PCT/US2014/052537

申请日：2014-08-25

Applicant: THE NIELSEN COMPANY (US), LLC

Inventor： SHEPPARD, Michael Richard ,  REID, Matthew B. ,  TERRAZAS, Alex ,  LIPA, Peter Otto Robert ,  SCHILLER, Brian George

IPC: H04N21/258 ,  H04N21/25 ,  H04N21/45

CPC classification number: H04L51/32

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to estimate demographics of users employing social media. An example method disclosed herein includes (1) identifying a social media message regarding an asset, the social media message associated with a user identifier associated with the user, (2) determining demographics associated with a group of people exposed to the asset, (3) associating the user identifier with the asset, and (4) repeating (1) to (3). The example method also includes (5) combining demographics associated with two or more different groups of people with which the user identifier is associated to estimate a demographic profile for the user.

Abstract translation: 公开了方法，装置，系统和制品以估计使用社交媒体的用户的人口统计。 本文公开的示例性方法包括（1）识别关于资产的社交媒体消息，与与用户相关联的用户标识符相关联的社交媒体消息，（2）确定与暴露于资产的一组人相关联的人口统计学（3 ）将用户标识符与资产相关联，以及（4）重复（1）至（3）。 该示例方法还包括（5）将与用户标识符相关联的两个或多个不同的人群相关联的人口统计学结合以估计用户的人口统计简档。

公开(公告)号：WO2014164138A1

公开(公告)日：2014-10-09

申请号：PCT/US2014/020794

申请日：2014-03-05

Applicant: THE NIELSEN COMPANY (US), LLC

Inventor： SRINIVASAN, Venugopal ,  TOPCHY, Alexander

IPC: G10L19/018 ,  G10L19/008

CPC classification number: G10L19/018 ,  G10L19/008

Abstract: Example methods, apparatus, systems and articles of manufacture to implement down-mixing compensation for audio watermarking are disclosed. Example methods disclosed herein to compensate for audio channel down-mixing when embedding watermarks in a multichannel audio signal include obtaining a watermark to be embedded in respective ones of a plurality of audio channels of the multichannel audio signal. Such example methods also include embedding the watermark in a first one of the plurality of audio channels based on a compensation factor that is to reduce perceptibility of the watermark when the first one of the plurality of audio channels is down-mixed with a second one of the plurality of audio channels after the watermark has been applied to the first and second ones of the plurality of audio channels.

Abstract translation: 公开了用于实现音频水印的下混补偿的示例性方法，装置，系统和制品。 当将水印嵌入多声道音频信号中时，本文公开的用于补偿音频通道下混的示例方法包括获得嵌入在多声道音频信号的多个音频通道的相应的一个中的水印。 这种示例性方法还包括：基于当多个音频通道中的第一个音频通道与第一个音频通道中的第二个被混合时降低水印的可感知性的补偿因子，将该水印嵌入多个音频通道的第一个中 水印之后的多个音频通道已被应用于多个音频通道中的第一和第二音频通道。

公开(公告)号：WO2014123819A1

公开(公告)日：2014-08-14

申请号：PCT/US2014/014474

申请日：2014-02-03

Applicant: THE NIELSEN COMPANY (US), LLC ,  RAU, Nicholas Naveen ,  O'HEARN, Ryan ,  STURM, Thomas ,  BENNETT, Jeremy

Inventor： RAU, Nicholas Naveen ,  O'HEARN, Ryan ,  STURM, Thomas ,  BENNETT, Jeremy

IPC: G06F17/00 ,  G06Q30/02

CPC classification number: G06Q30/0277

Abstract: Methods and apparatus for efficient execution of modules are disclosed. An example method includes generating, by a first module, a first module identifier, the first module having been instantiated by an advertisement on a webpage, loading, by the first module, a component, communicating the module identifier to the component, determining that a second module having a second module identifier has been loaded, and, in response to determining that the second module has been loaded, communicating, by the first module, the second module identifier to the component to instruct the component to communicate with the second module.

Abstract translation: 公开了用于有效执行模块的方法和装置。 一个示例性方法包括由第一模块生成第一模块标识符，第一模块已被网页上的广告实例化，由第一模块加载组件，将模块标识符传送到组件，确定一个 已经加载了具有第二模块标识符的第二模块，并且响应于确定第二模块已被加载，由第一模块将第二模块标识符通信给组件以指示组件与第二模块通信。

公开(公告)号：WO2014052028A1

公开(公告)日：2014-04-03

申请号：PCT/US2013/059497

申请日：2013-09-12

Applicant: THE NIELSEN COMPANY (US), LLC ,  SRINIVASAN, Venugopal ,  TOPCHY, Alexander

Inventor： SRINIVASAN, Venugopal ,  TOPCHY, Alexander

IPC: H04N21/435 ,  H04N21/45

CPC classification number: G10L25/54 ,  G10L19/018 ,  H04H20/31 ,  H04H60/37 ,  H04H60/372 ,  H04H60/39 ,  H04H60/58 ,  H04H2201/37 ,  H04H2201/50

Abstract: Methods and apparatus are disclosed for identifying media and, more particularly, to methods and apparatus for decoding identifiers after broadcast. An example method includes a portion of an identifying code from a media signal, determine a partition of the look-up table based on the portion of the identifying code wherein the partition of the look-up table includes reference signatures associated with the portion of the identifying code, and identify the media signal by comparing a signature extracted from the media signal to reference signatures in the partition of the look-up table.

Abstract translation: 公开了用于识别媒体的方法和装置，更具体地，涉及用于在广播之后解码标识符的方法和装置。 示例性方法包括来自媒体信号的识别码的一部分，基于识别码的部分确定查找表的分区，其中查找表的分区包括与该部分相关联的参考签名 识别代码，并通过将从媒体信号提取的签名与查找表的分区中的参考签名进行比较来识别媒体信号。

公开(公告)号：WO2013122907A1

公开(公告)日：2013-08-22

申请号：PCT/US2013/025687

申请日：2013-02-12

Applicant: THE NIELSEN COMPANY (US), LLC ,  DUTERQUE, Gilles ,  SRIVASTAVA, Seema, Varma ,  ION, Cristina

Inventor： DUTERQUE, Gilles ,  SRIVASTAVA, Seema, Varma ,  ION, Cristina

IPC: G06F17/00 ,  G06Q50/30

CPC classification number: H04L67/146 ,  G06Q30/0201 ,  H04L43/04 ,  H04L67/22

Abstract: Methods and apparatus are disclosed to identify session users with cookie information. An example method includes identifying activity associated with a first cookie having a first type, in response to identifying the first, parsing the first cookie to identify a first panelist, when the first cookie includes an identifier associated with a first panelist, associating current usage activity of the computing device with the first panelist, and when the first cookie includes an identifier unassociated with the first panelist, associating current usage activity of the computing device with a guest.

Abstract translation: 披露方法和装置来识别具有cookie信息的会话用户。 示例性方法包括识别与具有第一类型的第一cookie相关联的活动，响应于识别第一cookie，解析第一cookie以识别第一小组成员，当第一cookie包括与第一小组成员关联的标识符时，将当前使用活动 的第一小组成员，并且当第一个cookie包含与第一小组成员不相关的标识符时，将计算设备的当前使用活动与客人相关联。

公开(公告)号：WO2013119654A1

公开(公告)日：2013-08-15

申请号：PCT/US2013/024919

申请日：2013-02-06

Applicant: THE NIELSEN COMPANY (US), LLC ,  RAMASWAMY, Arun ,  SOUNDARARAJAN, Padmanabhan ,  TOPCHY, Alexander Pavlovich ,  BESEHANIC, Jan

Inventor： RAMASWAMY, Arun ,  SOUNDARARAJAN, Padmanabhan ,  TOPCHY, Alexander Pavlovich ,  BESEHANIC, Jan

IPC: H04N21/45

CPC classification number: H04N21/44218 ,  H04H60/33 ,  H04H60/45 ,  H04H2201/90 ,  H04N21/24 ,  H04N21/42201 ,  H04N21/4223 ,  H04N21/44213 ,  H04N21/4532 ,  H04N21/4667

Abstract: Methods and apparatus to control a state of data collection devices are disclosed. An example method includes generating a level of engagement based on an analysis of an audience associated with a media exposure environment; and controlling a state of a data collection device based on the level of engagement.

Abstract translation: 公开了控制数据采集装置的状态的方法和装置。 示例性方法包括基于与媒体曝光环境相关联的观众的分析来生成参与级别; 以及基于所述接合程度来控制数据收集装置的状态。

公开(公告)号：WO2013028619A2

公开(公告)日：2013-02-28

申请号：PCT/US2012/051580

申请日：2012-08-20

Applicant: THE NIELSEN COMPANY (US), LLC ,  HICKS, Michael A.

Inventor： HICKS, Michael A.

IPC: G06Q30/06

CPC classification number: G06T7/001 ,  G06K9/4652 ,  G06K9/4661 ,  G06K9/6215 ,  G06K2009/4666 ,  G06Q10/0875 ,  G06T7/11 ,  G06T7/90 ,  G06T11/60 ,  G06T2207/20112 ,  G06T2207/30108

Abstract: Image overlaying and comparison for inventory display auditing is disclosed herein. An example method to perform inventory display auditing disclosed herein comprises overlaying a reference image over a current image displayed on a camera display, the reference image corresponding to an inventory display to be audited, comparing the reference image and the current image to determine whether the current image and the reference image correspond to a same scene and when the reference image and the current image are determined to correspond to the same scene, indicating a difference region in the current image displayed on the camera display, the difference region being a first region of the current image that differs from a corresponding first region of the reference image.

Abstract translation: 本文公开了库存显示审核的图像叠加和比较。 执行本文公开的库存显示审核的示例性方法包括：将参考图像覆盖在相机显示器上显示的当前图像上，对应于要审核的库存显示的参考图像，比较参考图像和当前图像，以确定当前图像 图像和参考图像对应于相同的场景，并且当确定参考图像和当前图像对应于相同场景时，指示在相机显示器上显示的当前图像中的差异区域，差异区域是 当前图像与参考图像的对应的第一区域不同。