公开(公告)号：US07925507B2

公开(公告)日：2011-04-12

申请号：US11483840

申请日：2006-07-07

申请人： Fuliang Weng ,  Tobias Scheideck ,  Zhe Feng ,  Badri Raghunathan

发明人： Fuliang Weng ,  Tobias Scheideck ,  Zhe Feng ,  Badri Raghunathan

IPC分类号： G10L15/18

CPC分类号： G06F17/278 ,  G06F17/30654 ,  G10L15/22

摘要： Embodiments of a name recognition process for use in dialog systems are described. In one embodiment, the name recognition process assigns weighting values to names used in a dialog based on the usage of these names. This process takes advantage of the general tendency of people to speak names, either full or partial, only after they have heard or read these names. Name input is taken in several different forms, including a static background database that contains all possible names, a background database that contains commonly used names (such as common trademarks or references), a database that contains names from a user model, and a dynamic database that constantly takes the names just mentioned. The names are then appended with proper weighting values. A high weight is given to names that have been mentioned recently, a lower weight is given to common names, and a lowest weight is given to names for the ones that have never been used or mentioned.

摘要翻译： 描述在对话系统中使用的名称识别过程的实施例。 在一个实施例中，名称识别过程基于这些名称的使用，将加权值分配给对话中使用的名称。 这个过程只有在听到或读过这些名字之后才能利用人们的全部或部分名字的一般倾向。 名称输入采用几种不同的形式，包括包含所有可能名称的静态后台数据库，包含常用名称（如公共商标或引用）的后台数据库，包含用户模型名称的数据库和动态 数据库不断提供刚才提到的名称。 然后，这些名称将附加适当的权重值。 给予最近提到的名称较高的重量，较低的重量被赋予通用名称，而对于从未被使用或提及的那些的名称来说，最小的重量是给予的。

公开(公告)号：US20080010058A1

公开(公告)日：2008-01-10

申请号：US11483840

申请日：2006-07-07

申请人： Fuliang Weng ,  Tobias Scheideck ,  Zhe Feng ,  Badri Raghunathan

发明人： Fuliang Weng ,  Tobias Scheideck ,  Zhe Feng ,  Badri Raghunathan

IPC分类号： G06F17/27

CPC分类号： G06F17/278 ,  G06F17/30654 ,  G10L15/22

摘要： Embodiments of a name recognition process for use in dialog systems are described. In one embodiment, the name recognition process assigns weighting values to names used in a dialog based on the usage of these names. This process takes advantage of the general tendency of people to speak names, either full or partial, only after they have heard or read these names. Name input is taken in several different forms, including a static background database that contains all possible names, a background database that contains commonly used names (such as common trademarks or references), a database that contains names from a user model, and a dynamic database that constantly takes the names just mentioned. The names are then appended with proper weighting values. A high weight is given to names that have been mentioned recently, a lower weight is given to common names, and a lowest weight is given to names for the ones that have never been used or mentioned.

摘要翻译： 描述在对话系统中使用的名称识别过程的实施例。 在一个实施例中，名称识别过程基于这些名称的使用，将加权值分配给对话中使用的名称。 这个过程只有在听到或读过这些名字之后才能利用人们的全部或部分名字的一般倾向。 名称输入采用几种不同的形式，包括包含所有可能名称的静态后台数据库，包含常用名称（如公共商标或引用）的后台数据库，包含用户模型名称的数据库和动态 数据库不断提供刚才提到的名称。 然后，这些名称将附加适当的权重值。 给予最近提到的名称较高的重量，较低的重量被赋予通用名称，而对于从未被使用或提及的那些的名称来说，最小的重量是给予的。

公开(公告)号：US08510032B2

公开(公告)日：2013-08-13

申请号：US13567242

申请日：2012-08-06

申请人： Zhongnan Shen ,  Fuliang Weng ,  Zhe Feng

发明人： Zhongnan Shen ,  Fuliang Weng ,  Zhe Feng

IPC分类号： G01C21/00

CPC分类号： G10L15/1815 ,  G10L2015/228

摘要： A method for speech recognition includes providing a source of geographical information within a vehicle. The geographical information pertains to a current location of the vehicle, a planned travel route of the vehicle, a map displayed within the vehicle, and/or a gesture marked by a user on a map. Words spoken within the vehicle are recognized by use of a speech recognition module. The recognizing is dependent upon the geographical information.

摘要翻译： 用于语音识别的方法包括在车辆内提供地理信息源。 地理信息涉及车辆的当前位置，车辆的计划行驶路线，车辆内显示的地图和/或用户在地图上标记的手势。 通过使用语音识别模块识别车内所说的话。 识别取决于地理信息。

公开(公告)号：US20130173268A1

公开(公告)日：2013-07-04

申请号：US13340213

申请日：2011-12-29

申请人： Fuliang Weng ,  Taufiq Hasan ,  Zhe Feng

发明人： Fuliang Weng ,  Taufiq Hasan ,  Zhe Feng

IPC分类号： G10L15/00

CPC分类号： G10L17/22 ,  G06F19/3418 ,  G10L17/10 ,  G10L17/24

摘要： A method for verifying that a person is registered to use a telemedical device includes identifying an unprompted trigger phrase in words spoken by a person and received by the telemedical device. The telemedical device prompts the person to state a name of a registered user and optionally prompts the person to state health tips for the person. The telemedical device verifies that the person is the registered user using utterance data generated from the unprompted trigger phrase, name of the registered user, and health tips.

摘要翻译： 一种用于验证人被注册以使用远程医疗设备的方法包括以由人员说出并由远程医疗设备接收的话来标识不起动的触发短语。 远程医疗设备提示该人员陈述注册用户的姓名，并且可选地提示该人员向该人员陈述健康提示。 远程医疗设备使用从不起动的触发短语，注册用户的名称和健康提示生成的话语数据来验证该人是注册用户。

公开(公告)号：US08019594B2

公开(公告)日：2011-09-13

申请号：US11478990

申请日：2006-06-30

申请人： Fuliang Weng ,  Zhe Feng ,  Qi Zhang

发明人： Fuliang Weng ,  Zhe Feng ,  Qi Zhang

IPC分类号： G06F17/27

CPC分类号： G06F17/277 ,  G06K9/6228 ,  G10L15/02 ,  G10L15/063

摘要： Embodiments of a progressive feature selection method that selects features in multiple rounds are described. In one embodiment, the progressive feature selection method splits the feature space into tractable sub-spaces such that a feature selection algorithm can be performed on each sub-space. In a merge-split operation, the subset of features that the feature selection algorithm selects from the different sub-spaces are merged into subsequent sets of features. Instead of re-generating the mapping table for each subsequent set from scratch, a new mapping table from the previous round's tables is created by collecting those entries that correspond to the selected features. The feature selection method is then performed again on each of the subsequent feature sets and new features are selected from each of these feature sets. This feature selection-merge-split process is repeated on successively smaller numbers of feature sets until a single final set of features is selected.

摘要翻译： 描述了选择多个轮中的特征的渐进特征选择方法的实施例。 在一个实施例中，逐行特征选择方法将特征空间分解成易处理的子空间，使得可以对每个子空间执行特征选择算法。 在合并分割操作中，特征选择算法从不同子空间中选择的特征子集被合并到随后的特征集中。 不是从头重新生成每个后续集合的映射表，而是通过收集与所选特征相对应的条目来创建来自前一轮的表的新映射表。 然后在每个后续特征集上再次执行特征选择方法，并且从这些特征集中的每一个中选择新特征。 在连续较小数量的特征集上重复该特征选择合并分割处理，直到选择单个最终特征集。

公开(公告)号：US08019593B2

公开(公告)日：2011-09-13

申请号：US11478989

申请日：2006-06-30

申请人： Fuliang Weng ,  Zhe Feng ,  Qi Zhang

发明人： Fuliang Weng ,  Zhe Feng ,  Qi Zhang

IPC分类号： G06F17/27

CPC分类号： G10L15/18 ,  G06K9/6228 ,  G06K9/6232 ,  G10L15/02

摘要： Embodiments of a feature generation system and process for use in machine learning applications utilizing statistical modeling systems are described. In one embodiment, the feature generation process generates large feature spaces by combining features using logical, arithmetic and/or functional operations. A first set of features in an initial feature space are defined. Some or all of the first set of features are processed using one or more arithmetic, logic, user-defined combinatorial processes, or combinations thereof, to produce additional features. The additional features and at least some of the first set of features are combined to produce an expanded feature space. The expanded feature space is processed through a feature selection and optimization process to produce a model in a statistical modeling system.

摘要翻译： 描述了使用统计建模系统的特征生成系统和用于机器学习应用的过程的实施例。 在一个实施例中，特征生成过程通过使用逻辑，算术和/或功能操作组合特征来生成大的特征空间。 定义初始特征空间中的第一组特征。 使用一个或多个算术，逻辑，用户定义的组合过程或其组合来处理第一组特征中的一些或全部，以产生附加特征。 附加特征和第一组特征中的至少一些被组合以产生扩展的特征空间。 扩展的特征空间通过特征选择和优化过程进行处理，以在统计建模系统中产生模型。

公开(公告)号：US20100057463A1

公开(公告)日：2010-03-04

申请号：US12199520

申请日：2008-08-27

申请人： Fuliang Weng ,  Laura Stoia ,  Junling Hu ,  Zhe Feng ,  Junkuo Cao

发明人： Fuliang Weng ,  Laura Stoia ,  Junling Hu ,  Zhe Feng ,  Junkuo Cao

IPC分类号： G10L15/18

CPC分类号： G10L15/22 ,  G06F17/27 ,  G06F17/28

摘要： Embodiments of a dialog system that employs a corpus-based approach to generate responses based on a given number of semantic constraint-value pairs are described. The system makes full use of the data from the user input to produce dialog system responses in combination with a template generator. The system primarily utilizes constraint values in order to realize efficiencies based on the more frequent tasks performed in real dialog systems although rhetorical or discourse aspects of the dialog could also be included in a similar way, that is, labeling the data with such information and performing a training process. The benefits of this system include higher quality user-aligned responses, broader coverage, faster response time, and shorter development cycles.

摘要翻译： 描述了使用基于语料库的方法来基于给定数量的语义约束 - 值对来生成响应的对话系统的实施例。 系统充分利用用户输入的数据，与模板生成器结合产生对话系统响应。 该系统主要利用约束值来实现基于在真实对话系统中执行的更频繁任务的效率，尽管对话框的修辞或话语方面也可以以类似的方式包括在内，即用这样的信息标记数据并执行 一个培训过程。 该系统的优点包括更高质量的用户对应响应，更广泛的覆盖范围，更快的响应时间和更短的开发周期。

公开(公告)号：US20160313868A1

公开(公告)日：2016-10-27

申请号：US15104695

申请日：2014-12-11

申请人： Fuliang Weng ,  Kui Xu ,  Fel Liu ,  Lin Zhao ,  Zhe Feng ,  Zhongnan Shen ,  ROBERT BOSCH GMBH

发明人： Fuliang Weng ,  Kui Xu ,  Fel Liu ,  Lin Zhao ,  Zhe Feng ,  Zhongnan Shen

IPC分类号： G06F3/0481 ,  B60K35/00 ,  H04L29/06 ,  H04L29/08 ,  G10L15/22 ,  G06F3/01

CPC分类号： G06F3/0481 ,  B60K35/00 ,  B60K2350/1028 ,  B60K2350/1044 ,  B60K2350/1052 ,  B60K2350/2052 ,  B60K2350/901 ,  B60K2350/962 ,  G06F3/017 ,  G06F3/04883 ,  G06F9/451 ,  G06F2203/0381 ,  G06Q30/02 ,  G10L15/22 ,  H04L65/4069 ,  H04L67/12

摘要： An in-vehicle infotainment system, smart home information access and device control unit, or mobile system presents summarized information to a user based on a user preference model that is associated with the user. The system modifies the presentation of information to the user based on environmental context data about the vehicle and user context data about the activity of the user. During presentation of the information, the system modifies the content and presentation of the summarized information in response to multi-modal input requests from the user.

摘要翻译： 车载信息娱乐系统，智能家居信息访问和设备控制单元或移动系统基于与用户相关联的用户偏好模型向用户呈现总结信息。 系统基于关于车辆的环境上下文数据和关于用户的活动的用户上下文数据来向用户修改信息呈现。 在呈现信息期间，系统响应于来自用户的多模式输入请求来修改总结信息的内容和呈现。

公开(公告)号：US20120303267A1

公开(公告)日：2012-11-29

申请号：US13567242

申请日：2012-08-06

申请人： Zhongnan Shen ,  Fuliang Weng ,  Zhe Feng

发明人： Zhongnan Shen ,  Fuliang Weng ,  Zhe Feng

IPC分类号： G01C21/00 ,  G10L15/04

CPC分类号： G10L15/1815 ,  G10L2015/228

摘要： A method for speech recognition includes providing a source of geographical information within a vehicle. The geographical information pertains to a current location of the vehicle, a planned travel route of the vehicle, a map displayed within the vehicle, and/or a gesture marked by a user on a map. Words spoken within the vehicle are recognized by use of a speech recognition module. The recognizing is dependent upon the geographical information.

摘要翻译： 用于语音识别的方法包括在车辆内提供地理信息源。 地理信息涉及车辆的当前位置，车辆的计划行驶路线，车辆内显示的地图和/或用户在地图上标记的手势。 通过使用语音识别模块识别车内所说的话。 识别取决于地理信息。

公开(公告)号：US08001469B2

公开(公告)日：2011-08-16

申请号：US11936644

申请日：2007-11-07

申请人： Fuliang Weng ,  William Chang ,  Baoshi Yan ,  Zhe Feng

发明人： Fuliang Weng ,  William Chang ,  Baoshi Yan ,  Zhe Feng

IPC分类号： G06F3/00

CPC分类号： G06F8/30 ,  G06Q10/06

摘要： Systems and methods are described that automatically generate interactive systems configured for collecting dialog data of human-machine interactions in dialog systems. The systems and methods comprise receiving a task flow that describes operations of a dialog system. A formal description of the task flow is generated, and an interactive system comprising a graphical user interface (GUI) is automatically generated from the formal description. The GUI consists of templates for control of the dialog system and real-time collection and annotating of dialog data during a live dialog between only the dialog system and callers to the dialog system. The dialog data consists of data of the live dialog.

摘要翻译： 描述了系统和方法，其自动生成配置用于在对话系统中收集人机交互的对话数据的交互式系统。 系统和方法包括接收描述对话系统的操作的任务流。 生成任务流程的形式描述，并且从形式描述中自动生成包括图形用户界面（GUI）的交互式系统。 GUI包括用于控制对话系统的模板以及仅在对话系统和对话系统的呼叫者之间的实时对话期间对话数据的实时收集和注释。 对话数据由实时对话框的数据组成。