公开(公告)号：US20110246184A1

公开(公告)日：2011-10-06

申请号：US13164347

申请日：2011-06-20

Applicant: Mazin Gilbert ,  Christopher Volinsky

Inventor： Mazin Gilbert ,  Christopher Volinsky

IPC: G06F17/27

CPC classification number: G10L15/193 ,  G10L15/065 ,  G10L2015/228

Abstract: Disclosed are systems, methods and computer-readable media for using a local communication network to generate a speech model. The method includes retrieving for an individual a list of numbers in a calling history, identifying a local neighborhood associated with each number in the calling history, truncating the local neighborhood associated with each number based on the at least one parameter, retrieving a local communication network associated with each number in the calling history and each phone number in the local neighborhood, and creating a language model for the individual based on the retrieved local communication network. The generated language model may be used for improved automatic speech recognition for audible searches as well as other modules in a spoken dialog system.

Abstract translation: 公开了用于使用本地通信网络生成语音模型的系统，方法和计算机可读介质。 该方法包括检索个人在呼叫历史中的号码列表，识别与呼叫历史中的每个号码相关联的本地邻域，基于该至少一个参数截断与每个号码相关联的本地邻域，检索本地通信网络 与呼叫历史中的每个号码和本地邻域中的每个电话号码相关联，以及基于所检索的本地通信网络为个人创建语言模型。 生成的语言模型可以用于改善声音搜索的自动语音识别以及口语对话系统中的其他模块。

公开(公告)号：US08170866B2

公开(公告)日：2012-05-01

申请号：US13164347

申请日：2011-06-20

Applicant: Mazin Gilbert ,  Christopher Volinsky

Inventor： Mazin Gilbert ,  Christopher Volinsky

IPC: G10L17/20

CPC classification number: G10L15/193 ,  G10L15/065 ,  G10L2015/228

Abstract: Disclosed are systems, methods and computer-readable media for using a local communication network to generate a speech model. The method includes retrieving for an individual a list of numbers in a calling history, identifying a local neighborhood associated with each number in the calling history, truncating the local neighborhood associated with each number based on the at least one parameter, retrieving a local communication network associated with each number in the calling history and each phone number in the local neighborhood, and creating a language model for the individual based on the retrieved local communication network. The generated language model may be used for improved automatic speech recognition for audible searches as well as other modules in a spoken dialog system.

Abstract translation: 公开了用于使用本地通信网络生成语音模型的系统，方法和计算机可读介质。 该方法包括检索个人在呼叫历史中的号码列表，识别与呼叫历史中的每个号码相关联的本地邻域，基于该至少一个参数截断与每个号码相关联的本地邻域，检索本地通信网络 与呼叫历史中的每个号码和本地邻域中的每个电话号码相关联，以及基于所检索的本地通信网络为个人创建语言模型。 生成的语言模型可以用于改善声音搜索的自动语音识别以及口语对话系统中的其他模块。

公开(公告)号：US07966171B2

公开(公告)日：2011-06-21

申请号：US11931830

申请日：2007-10-31

Applicant: Mazin Gilbert ,  Christopher Volinsky

Inventor： Mazin Gilbert ,  Christopher Volinsky

IPC: G06F17/20

CPC classification number: G10L15/193 ,  G10L15/065 ,  G10L2015/228

Abstract: Disclosed are systems, methods and computer-readable media for using a local communication network to generate a speech model. The method includes retrieving for an individual a list of numbers in a calling history, identifying a local neighborhood associated with each number in the calling history, truncating the local neighborhood associated with each number based on the at least one parameter, retrieving a local communication network associated with each number in the calling history and each phone number in the local neighborhood, and creating a language model for the individual based on the retrieved local communication network. The generated language model may be used for improved automatic speech recognition for audible searches as well as other modules in a spoken dialog system.

Abstract translation: 公开了用于使用本地通信网络生成语音模型的系统，方法和计算机可读介质。 该方法包括检索个人在呼叫历史中的号码列表，识别与呼叫历史中的每个号码相关联的本地邻域，基于该至少一个参数截断与每个号码相关联的本地邻域，检索本地通信网络 与呼叫历史中的每个号码和本地邻域中的每个电话号码相关联，以及基于所检索的本地通信网络为个人创建语言模型。 生成的语言模型可以用于改善声音搜索的自动语音识别以及口语对话系统中的其他模块。

公开(公告)号：US20090112600A1

公开(公告)日：2009-04-30

申请号：US11931830

申请日：2007-10-31

Applicant: Mazin Gilbert ,  Christopher Volinsky

Inventor： Mazin Gilbert ,  Christopher Volinsky

IPC: G10L11/00

CPC classification number: G10L15/193 ,  G10L15/065 ,  G10L2015/228

Abstract: Disclosed are systems, methods and computer-readable media for using a local communication network to generate a speech model. The method includes retrieving for an individual a list of numbers in a calling history, identifying a local neighborhood associated with each number in the calling history, truncating the local neighborhood associated with each number based on the at least one parameter, retrieving a local communication network associated with each number in the calling history and each phone number in the local neighborhood, and creating a language model for the individual based on the retrieved local communication network. The generated language model may be used for improved automatic speech recognition for audible searches as well as other modules in a spoken dialog system.

Abstract translation: 公开了用于使用本地通信网络生成语音模型的系统，方法和计算机可读介质。 该方法包括检索个人在呼叫历史中的号码列表，识别与呼叫历史中的每个号码相关联的本地邻域，基于该至少一个参数截断与每个号码相关联的本地邻域，检索本地通信网络 与呼叫历史中的每个号码和本地邻域中的每个电话号码相关联，以及基于所检索的本地通信网络为个人创建语言模型。 生成的语言模型可以用于改善声音搜索的自动语音识别以及口语对话系统中的其他模块。

公开(公告)号：US08463662B2

公开(公告)日：2013-06-11

申请号：US13526112

申请日：2012-06-18

Applicant: Yehuda Koren ,  Robert Bell ,  Christopher Volinsky

Inventor： Yehuda Koren ,  Robert Bell ,  Christopher Volinsky

IPC: G06Q10/00

CPC classification number: G06Q30/0201 ,  G06Q30/02 ,  G06Q30/0627 ,  G06Q30/0631

Abstract: Systems and techniques for generating item ratings for a user in order to allow for recommendations of selected items for that user. A set of known ratings of different items for a plurality of users is collected and maintained, and these known ratings are used to estimate rating factors influencing ratings, including user and item factors. Initial user and item factors are estimated and new user and item factors are successively added, with the original rating factors being progressively shrunk so as to reduce their magnitude and their contribution to the rating estimation as successive factors are added. When an appropriate number of user and item factors has been estimated, the rating factors are used to estimate ratings of items for a user, and the estimated ratings are employed to generate recommendations for that user.

Abstract translation: 用于为用户生成项目评级的系统和技术，以便允许针对该用户的所选项目的推荐。 收集和维护一组用于多个用户的不同项目的已知评级，并且使用这些已知评级来估计影响评级的评级因素，包括用户和项目因素。 初始用户和项目因素被估计，并且连续添加新的用户和项目因素，原始评级因子逐渐收缩，以便随着连续因素的增加而减小它们的大小和对评估估计的贡献。 当估计出适当数量的用户和项目因素时，使用评级因子来估计用户的项目的评级，并且使用估计的等级来为该用户生成推荐。

公开(公告)号：US08565122B2

公开(公告)日：2013-10-22

申请号：US12938340

申请日：2010-11-02

Applicant: Yehuda Koren ,  Stephen North ,  Christopher Volinsky

Inventor： Yehuda Koren ,  Stephen North ,  Christopher Volinsky

IPC: H04L29/12 ,  H04L12/24 ,  H04L12/56

CPC classification number: H04L41/12 ,  G06Q30/02 ,  H04L45/02

Abstract: A method and apparatus for measuring and extracting proximity in networks are disclosed. In one embodiment, the present method receives a network from a user for analysis and extraction of a smaller proximity sub-graph. The method computes a candidate sub-graph and determines at least one Cycle Free Escape Conductivity (CFEC) proximity of at least two nodes in accordance with the candidate sub-graph. The method then extracts and presents a proximity sub-graph that best captures the proximity.

Abstract translation: 公开了一种用于测量和提取网络中的接近度的方法和装置。 在一个实施例中，本方法从用户接收用于分析和提取较小邻近子图的网络。 该方法计算候选子图并且根据候选子图确定至少两个节点的至少一个循环自由逃脱电导率（CFEC）接近度。 该方法然后提取并呈现最佳捕获邻近度的邻近子图。

公开(公告)号：US20100100493A1

公开(公告)日：2010-04-22

申请号：US12252854

申请日：2008-10-16

Applicant: L. Russell Canfield ,  Christopher Volinsky

Inventor： L. Russell Canfield ,  Christopher Volinsky

IPC: G06Q99/00

CPC classification number: G06Q50/22 ,  G06Q10/06 ,  G06Q50/01 ,  G16H50/30

Abstract: A method and apparatus for providing social health tracking over one or more communication networks are disclosed. For example, the method receives a request from a customer for a communication service having a social health tracking feature, and gathers data on one or more interactions for the customer. The method updates a statistical model for the one or more interactions for the customer over a period of time, and determines a social health status for the customer from the statistical model.

Abstract translation: 公开了一种用于在一个或多个通信网络上提供社会健康跟踪的方法和装置。 例如，该方法从具有社会健康跟踪特征的通信服务的客户接收请求，并收集关于客户的一个或多个交互的数据。 该方法在一段时间内更新客户的一个或多个交互的统计模型，并从统计模型确定客户的社会健康状况。

公开(公告)号：US20110044197A1

公开(公告)日：2011-02-24

申请号：US12938340

申请日：2010-11-02

Applicant: Yehuda Koren ,  Stephen North ,  Christopher Volinsky

Inventor： Yehuda Koren ,  Stephen North ,  Christopher Volinsky

IPC: H04L12/26

CPC classification number: H04L41/12 ,  G06Q30/02 ,  H04L45/02

Abstract: A method and apparatus for measuring and extracting proximity in networks are disclosed. In one embodiment, the present method receives a network from a user for analysis and extraction of a smaller proximity sub-graph. The method computes a candidate sub-graph and determines at least one Cycle Free Escape Conductivity (CFEC) proximity of at least two nodes in accordance with the candidate sub-graph. The method then extracts and presents a proximity sub-graph that best captures the proximity.

Abstract translation: 公开了一种用于测量和提取网络中的接近度的方法和装置。 在一个实施例中，本方法从用户接收用于分析和提取较小邻近子图的网络。 该方法计算候选子图并且根据候选子图确定至少两个节点的至少一个循环自由逃脱电导率（CFEC）接近度。 该方法然后提取并呈现最佳捕获邻近度的邻近子图。

公开(公告)号：US20120253884A1

公开(公告)日：2012-10-04

申请号：US13526112

申请日：2012-06-18

Applicant: Yehuda Koren ,  Robert Bell ,  Christopher Volinsky

Inventor： Yehuda Koren ,  Robert Bell ,  Christopher Volinsky

IPC: G06Q30/02

CPC classification number: G06Q30/0201 ,  G06Q30/02 ,  G06Q30/0627 ,  G06Q30/0631

Abstract: Systems and techniques for generating item ratings for a user in order to allow for recommendations of selected items for that user. A set of known ratings of different items for a plurality of users is collected and maintained, and these known ratings are used to estimate rating factors influencing ratings, including user and item factors. Initial user and item factors are estimated and new user and item factors are successively added, with the original rating factors being progressively shrunk so as to reduce their magnitude and their contribution to the rating estimation as successive factors are added. When an appropriate number of user and item factors has been estimated, the rating factors are used to estimate ratings of items for a user, and the estimated ratings are employed to generate recommendations for that user.

Abstract translation: 用于为用户生成项目评级的系统和技术，以便允许针对该用户的所选项目的推荐。 收集和维护一组用于多个用户的不同项目的已知评级，并且使用这些已知评级来估计影响评级的评级因素，包括用户和项目因素。 初始用户和项目因素被估计，并且连续添加新的用户和项目因素，原始评级因子逐渐收缩，以便随着连续因素的增加而减小它们的大小和对评估估计的贡献。 当估计出适当数量的用户和项目因素时，使用评级因子来估计用户的项目的评级，并且使用估计的等级来为该用户生成推荐。

公开(公告)号：US20090083126A1

公开(公告)日：2009-03-26

申请号：US12107309

申请日：2008-04-22

Applicant: Yehuda Koren ,  Robert Bell ,  Christopher Volinsky

Inventor： Yehuda Koren ,  Robert Bell ,  Christopher Volinsky

IPC: G06Q10/00

CPC classification number: G06Q30/0201 ,  G06Q30/02 ,  G06Q30/0627 ,  G06Q30/0631

Abstract: Systems and techniques for generating item ratings for a user in order to allow for recommendations of selected items for that user. A set of known ratings of different items for a plurality of users is collected and maintained, and these known ratings are used to estimate rating factors influencing ratings, including user and item factors. Initial user and item factors are estimated and new user and item factors are successively added, with the original rating factors being progressively shrunk so as to reduce their magnitude and their contribution to the rating estimation as successive factors are added. When an appropriate number of user and item factors has been estimated, the rating factors are used to estimate ratings of items for a user, and the estimated ratings are employed to generate recommendations for that user.

Abstract translation: 用于为用户生成项目评级的系统和技术，以便允许针对该用户的所选项目的推荐。 收集和维护一组用于多个用户的不同项目的已知评级，并且使用这些已知评级来估计影响评级的评级因素，包括用户和项目因素。 初始用户和项目因素被估计，并且连续添加新的用户和项目因素，原始评级因子逐渐收缩，以便随着连续因素的增加而减小它们的大小和对评估估计的贡献。 当估计出适当数量的用户和项目因素时，使用评级因子来估计用户的项目的评级，并且使用估计的等级来为该用户生成推荐。