公开(公告)号：US08682677B2

公开(公告)日：2014-03-25

申请号：US13873661

申请日：2013-04-30

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Jason William ,  Suhrid Balakrishnan ,  Lihong Li

IPC: G10L21/00 ,  G10L11/00

CPC classification number: G10L15/063 ,  G06F3/167 ,  H04M3/4936 ,  H04M2203/355

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for automatically generating a dialog manager for use in a spoken dialog system. A system practicing the method receives a set of user interactions having features, identifies an initial policy, evaluates all of the features in a linear evaluation step of the algorithm to identify a set of most important features, performs a cubic policy improvement step on the identified set of most important features, repeats the previous two steps one or more times, and generates a dialog manager for use in a spoken dialog system based on the resulting policy and/or set of most important features. Evaluating all of the features can include estimating a weight for each feature which indicates how much each feature contributes to at least one of the identified policies. The system can ignore features not in the set of most important features.

Abstract translation: 这里公开了用于自动生成用于在口头对话系统中使用的对话管理器的系统，方法和计算机可读存储介质。 实施该方法的系统接收具有特征的一组用户交互，识别初始策略，评估算法的线性评估步骤中的所有特征以识别一组最重要的特征，对所识别的一个或多个特征进行立体策略改进步骤 一组最重要的特征，重复前一个步骤一次或多次，并且基于所得到的策略和/或一组最重要的特征生成用于在口头对话系统中的对话管理器。 评估所有特征可以包括估计每个特征的权重，其指示每个特征对至少一个所识别的策略贡献多少。 系统可以忽略不属于最重要功能集的功能。

公开(公告)号：US20130238333A1

公开(公告)日：2013-09-12

申请号：US13873661

申请日：2013-04-30

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： Jason William ,  Suhrid Balakrishnan ,  Lihong Li

IPC: G10L15/06

CPC classification number: G10L15/063 ,  G06F3/167 ,  H04M3/4936 ,  H04M2203/355

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for automatically generating a dialog manager for use in a spoken dialog system. A system practicing the method receives a set of user interactions having features, identifies an initial policy, evaluates all of the features in a linear evaluation step of the algorithm to identify a set of most important features, performs a cubic policy improvement step on the identified set of most important features, repeats the previous two steps one or more times, and generates a dialog manager for use in a spoken dialog system based on the resulting policy and/or set of most important features. Evaluating all of the features can include estimating a weight for each feature which indicates how much each feature contributes to at least one of the identified policies. The system can ignore features not in the set of most important features.

Abstract translation: 这里公开了用于自动生成用于在口头对话系统中使用的对话管理器的系统，方法和计算机可读存储介质。 实施该方法的系统接收具有特征的一组用户交互，识别初始策略，评估算法的线性评估步骤中的所有特征以识别一组最重要的特征，对所识别的一个或多个特征进行立体策略改进步骤 一组最重要的特征，重复前一个步骤一次或多次，并且基于所得到的策略和/或一组最重要的特征生成用于在口头对话系统中的对话管理器。 评估所有特征可以包括估计每个特征的权重，其指示每个特征对至少一个所识别的策略贡献多少。 系统可以忽略不属于最重要功能集的功能。