公开(公告)号：US20130159348A1

公开(公告)日：2013-06-20

申请号：US13327949

申请日：2011-12-16

申请人： Bruce Monroe Mills ,  John Courtney Haws ,  John Clare Brocklebank ,  Thomas Robert Lehman

发明人： Bruce Monroe Mills ,  John Courtney Haws ,  John Clare Brocklebank ,  Thomas Robert Lehman

IPC分类号： G06F17/30

CPC分类号： G06F17/30731 ,  G06F17/30705

摘要： Systems and methods are provided for generating a set of classifiers. A location is determined for each instance of a topic term in a collection of documents. One or more topic term phrases are identified, and one or more sentiment terms within each topic term phrase. Candidate classifiers are identified by parsing words in the one or more topic term phrases, and a colocation matrix is generated. A seed row of the colocation associated with a particular attribute is identified, and distance metrics are determined by comparing each row of the colocation matrix to the seed row. A set of classifiers are generated for the particular attribute, where classifiers in the set of classifiers are selected using the distance metrics.

摘要翻译： 提供了用于生成一组分类器的系统和方法。 确定文档集合中每个主题项的实例的位置。 识别一个或多个主题术语短语，以及每个主题术语短语内的一个或多个情绪术语。 候选分类器通过解析一个或多个主题术语短语中的单词来识别，并且生成了一个位置矩阵。 识别与特定属性相关联的托盘的种子行，并且通过将托管矩阵的每一行与种子行进行比较来确定距离度量。 为特定属性生成一组分类器，其中使用距离度量来选择分类器集合中的分类器。

公开(公告)号：US09116985B2

公开(公告)日：2015-08-25

申请号：US13327949

申请日：2011-12-16

申请人： Bruce Monroe Mills ,  John Courtney Haws ,  John Clare Brocklebank ,  Thomas Robert Lehman

发明人： Bruce Monroe Mills ,  John Courtney Haws ,  John Clare Brocklebank ,  Thomas Robert Lehman

IPC分类号： G06F17/30

CPC分类号： G06F17/30731 ,  G06F17/30705

摘要： Systems and methods are provided for generating a set of classifiers. A location is determined for each instance of a topic term in a collection of documents. One or more topic term phrases are identified, and one or more sentiment terms within each topic term phrase. Candidate classifiers are identified by parsing words in the one or more topic term phrases, and a colocation matrix is generated. A seed row of the colocation associated with a particular attribute is identified, and distance metrics are determined by comparing each row of the colocation matrix to the seed row. A set of classifiers are generated for the particular attribute, where classifiers in the set of classifiers are selected using the distance metrics.

摘要翻译： 提供了用于生成一组分类器的系统和方法。 确定文档集合中每个主题项的实例的位置。 识别一个或多个主题术语短语，以及每个主题术语短语内的一个或多个情绪术语。 候选分类器通过解析一个或多个主题术语短语中的单词来识别，并且生成了一个位置矩阵。 识别与特定属性相关联的托盘的种子行，并且通过将托管矩阵的每一行与种子行进行比较来确定距离度量。 为特定属性生成一组分类器，其中使用距离度量来选择分类器集合中的分类器。

公开(公告)号：US20130129060A1

公开(公告)日：2013-05-23

申请号：US13302154

申请日：2011-11-22

申请人： Balaji Gopalakrishnan ,  William Elliot Inman ,  Thomas Robert Lehman ,  John Clare Brocklebank

发明人： Balaji Gopalakrishnan ,  William Elliot Inman ,  Thomas Robert Lehman ,  John Clare Brocklebank

IPC分类号： H04M11/00

CPC分类号： G06Q30/0244 ,  G06Q30/02 ,  H04L67/18

摘要： In accordance with the teachings described herein, systems and methods are provided for optimizing distribution of advertisement information. In one example, call tracking data may be generated from a plurality of telephone calls made to a business entity, where the call tracking data includes geographical information to identify locations from which the plurality of telephone calls originated. A call distribution may be determined from the call tracking data, where the call distribution groups the call tracking data based at least in part on distances between the business entity and the locations from which the plurality of telephone calls originated. A probability density function may be generated from the call distribution and used in the generation of the advertisement distribution plan.

摘要翻译： 根据本文所述的教导，提供用于优化广告信息分发的系统和方法。 在一个示例中，呼叫跟踪数据可以从对业务实体进行的多个电话呼叫生成，其中呼叫跟踪数据包括地理信息以识别发起多个电话呼叫的位置。 呼叫分配可以根据呼叫跟踪数据确定，其中呼叫分配至少部分地基于业务实体与发起多个电话呼叫的位置之间的距离来分组呼叫跟踪数据。 可以从呼叫分配生成概率密度函数，并用于生成广告分发计划。

公开(公告)号：US08619955B2

公开(公告)日：2013-12-31

申请号：US13302154

申请日：2011-11-22

申请人： Balaji Gopalakrishnan ,  William Elliot Inman ,  Thomas Robert Lehman ,  John Clare Brocklebank

发明人： Balaji Gopalakrishnan ,  William Elliot Inman ,  Thomas Robert Lehman ,  John Clare Brocklebank

IPC分类号： H04M15/00 ,  G06Q30/00

CPC分类号： G06Q30/0244 ,  G06Q30/02 ,  H04L67/18

摘要： In accordance with the teachings described herein, systems and methods are provided for optimizing distribution of advertisement information. In one example, call tracking data may be generated from a plurality of telephone calls made to a business entity, where the call tracking data includes geographical information to identify locations from which the plurality of telephone calls originated. A call distribution may be determined from the call tracking data, where the call distribution groups the call tracking data based at least in part on distances between the business entity and the locations from which the plurality of telephone calls originated. A probability density function may be generated from the call distribution and used in the generation of the advertisement distribution plan.

摘要翻译： 根据本文所述的教导，提供用于优化广告信息分发的系统和方法。 在一个示例中，呼叫跟踪数据可以从对业务实体进行的多个电话呼叫生成，其中呼叫跟踪数据包括地理信息以识别发起多个电话呼叫的位置。 呼叫分配可以根据呼叫跟踪数据确定，其中呼叫分配至少部分地基于业务实体与发起多个电话呼叫的位置之间的距离来分组呼叫跟踪数据。 可以从呼叫分配生成概率密度函数，并用于生成广告分发计划。