公开(公告)号：US20090306995A1

公开(公告)日：2009-12-10

申请号：US12133123

申请日：2008-06-04

申请人： Fuliang Weng ,  Hua Ai

发明人： Fuliang Weng ,  Hua Ai

IPC分类号： G06Q10/00 ,  G10L15/26 ,  G10L15/00

CPC分类号： G10L15/01 ,  G06Q10/103

摘要： Embodiments of an automated dialog system testing method and component are described. This automated testing method and system supplements real human-based testing with simulated user input and incorporates a set of evaluation measures that focus on three basic aspects of task-oriented dialog systems, namely, understanding ability, efficiency, and the appropriateness of system actions. These measures are first applied on a corpus generated between a dialog system and a group of human users to demonstrate the validity of these measures with the human users' satisfaction levels. Results generally show that these measures are significantly correlated with these satisfaction levels. A regression model is then built to predict the user satisfaction scores using these evaluation measures. The regression model is applied on a simulated dialog corpus trained from the above real user corpus, and show that the user satisfaction score estimated from the simulated dialogs do not significantly differ from the real users' satisfaction scores. These evaluation measures can then be used to assess the system performance based on the estimated user satisfaction.

摘要翻译： 描述了自动对话系统测试方法和组件的实施例。 这种自动测试方法和系统通过模拟用户输入来补充真正的基于人力的测试，并结合了一套关注面向任务的对话系统的三个基本方面的评估措施，即理解能力，效率和系统操作的适用性。 这些措施首先应用于对话系统和一组人类用户之间产生的语料库，以显示这些措施与人类用户满意度的有效性。 结果一般表明，这些措施与这些满意度水平显着相关。 然后建立回归模型，以使用这些评估措施来预测用户满意度评分。 回归模型应用于从上述真实用户语料库训练的模拟对话语料库，并显示从模拟对话框估计的用户满意度评分与实际用户满意度得分无显着差异。 这些评估措施可以用于根据估计的用户满意度来评估系统性能。

公开(公告)号：US07424363B2

公开(公告)日：2008-09-09

申请号：US10923590

申请日：2004-08-20

申请人： Hua Cheng ,  Lawrence Cavedon ,  Robert Dale ,  Fuliang Weng ,  Yao Meng ,  Stanley Peters

发明人： Hua Cheng ,  Lawrence Cavedon ,  Robert Dale ,  Fuliang Weng ,  Yao Meng ,  Stanley Peters

IPC分类号： G01C21/30

CPC分类号： G08G1/096872 ,  G01C21/3641 ,  G08G1/096822 ,  G08G1/096838

摘要： A method and system are described to adapt instructions for performing a task by a user, which includes receiving generalized instructions for the task, selecting a content of the generalized instructions based on user-specific knowledge regarding the task, constructing utterances using the selected content, and conveying the utterances to the user.

摘要翻译： 描述了一种方法和系统，以适应用户执行任务的指令，其包括接收用于该任务的通用指令，基于与该任务相关的用户特定知识来选择一般化指令的内容，使用所选择的内容构建话语， 并将话语传达给用户。

公开(公告)号：US20220180886A1

公开(公告)日：2022-06-09

申请号：US17544900

申请日：2021-12-07

申请人： Fuliang Weng

发明人： Fuliang Weng

IPC分类号： G10L21/0208

摘要： This invention provides a new and improved voice communication system with high quality noise cancellation method and devices to overcome the limitations and difficulties encountered in conventional technologies. This invention discloses a noise cancellation apparatus that includes a vibration sensor and a microphone for receiving and transmitting voice signals as incoming speeches. The vibration sensor is applied to receive vibration signals corresponding to the voice signals for applying the vibration signals as reference signals for removing noise signals generated from environmental noises by converting vibration signals to intermediate PDL representation together with the speaker characteristics, mapping them into full band high quality clean acoustic representation, and synthesizing clear personal speech with characteristics identical to the original microphone speech without noises.

公开(公告)号：US09201923B2

公开(公告)日：2015-12-01

申请号：US11243599

申请日：2005-10-04

申请人： Fuliang Weng ,  Heather Pon-Barry

发明人： Fuliang Weng ,  Heather Pon-Barry

IPC分类号： G06F17/30

CPC分类号： G06F17/30401 ,  G06F17/3064 ,  G06F17/30646 ,  G06F17/30654 ,  G06F17/30672 ,  G06F17/30976 ,  G06F17/30979 ,  G10L2015/221

摘要： Embodiments of a configurable content optimizer for use in dialog systems are described. In one embodiment, the content optimizer is a configurable component that acts as an intermediary between a dialog management module and a knowledge management module of a dialog system during the query process. The content optimizer module makes extensive use of the system ontology and organizes items returned by the knowledge base and makes adjustments to the query so that a reasonable number of responses are returned. Each query is broken down into a number of constraints, the constraints are characterized by type, and adjustments are made by strategies that include relaxing or tightening constraints in the query. Generic strategies for the potential adjustments are represented in a configurable manner so that the content optimizing module can be easily applied to new domains.

摘要翻译： 描述在对话系统中使用的可配置内容优化器的实施例。 在一个实施例中，内容优化器是在查询过程期间充当对话系统的对话管理模块和知识管理模块之间的中介的可配置组件。 内容优化器模块广泛使用系统本体并组织知识库返回的项目，并对查询进行调整，以便返回合理数量的响应。 每个查询被分解成许多约束，约束由类型表征，并且通过包括在查询中放松或紧缩约束的策略进行调整。 潜在调整的通用策略以可配置的方式表示，使内容优化模块可以轻松应用于新域。

公开(公告)号：US07774373B2

公开(公告)日：2010-08-10

申请号：US12072707

申请日：2008-02-26

申请人： Qi Yu ,  Yao Meng ,  Fuliang Weng

发明人： Qi Yu ,  Yao Meng ,  Fuliang Weng

IPC分类号： G06F17/30

CPC分类号： G06F9/5055 ,  G06F2209/5015

摘要： In a system and method for fulfilling a service query for a user, a processor may parse the query into a set of operations, identify a set of service providers that each provides functionality for performing at least one respective operation of the set of operations, and, for each of the set of operations, select a respective one of the set of service providers to perform the operation, and interface with the service provider selected for the operation to cause the service provider to perform the operation.

摘要翻译： 在用于满足用户的服务查询的系统和方法中，处理器可以将查询解析为一组操作，识别每组提供用于执行该组操作的至少一个相应操作的功能的一组服务提供者，以及 对于所述一组操作中的每一个，选择所述一组服务提供者中的相应一个以执行操作，并且与为操作选择的服务提供商进行接口以使服务提供商执行该操作。

公开(公告)号：US06629066B1

公开(公告)日：2003-09-30

申请号：US09390457

申请日：1999-09-07

申请人： Eric G. Jackson ,  Michael H. Cohen ,  Fuliang Weng

发明人： Eric G. Jackson ,  Michael H. Cohen ,  Fuliang Weng

IPC分类号： G06F1728

CPC分类号： G06F17/2785 ,  G06F17/279

摘要： A computerized method for building and running natural language understanding systems, wherein a natural language understanding system takes a sentence as input and returns some representation of the possible meanings of the sentence as output (the “interpretation”) using a run-time interpreter th assigns interpretations to sentences and a compiler that produces (in a computer memory) an internal specification needed for the run-time interpreter from a user specification of the semantics of the application. The compiler builds a natural language system, while the run-time interpreter runs the system.

摘要翻译： 一种用于构建和运行自然语言理解系统的计算机化方法，其中自然语言理解系统将句子作为输入，并且使用运行时解释器将所述句子的可能含义的一些表示作为输出（“解释”）返回 对句子的解释以及从应用程序的语义的用户规范生成（在计算机存储器中）运行时解释器所需的内部规范的编译器。 编译器构建自然语言系统，而运行时解释器则运行系统。

公开(公告)号：US08817087B2

公开(公告)日：2014-08-26

申请号：US12916862

申请日：2010-11-01

申请人： Fuliang Weng ,  You-Chi Cheng ,  Liu Ren

发明人： Fuliang Weng ,  You-Chi Cheng ,  Liu Ren

IPC分类号： H04N9/47 ,  G06K9/00 ,  G06F3/042 ,  H04N5/232

CPC分类号： G06K9/00 ,  G01C21/3664 ,  G06F3/017 ,  G06F3/0425 ,  G06F2203/04108 ,  G06K9/00355 ,  G06T2207/30196 ,  G06T2207/30241 ,  H04N5/23264

摘要： A method of receiving input from a user includes sensing a first trajectory of a center of mass of a hand of the user during a gesture made by the hand. A second trajectory of a finger tip of the hand of the user during the gesture made by the hand is also sensed. An alphanumeric character represented by the gesture made by the hand is determined dependent upon both the first trajectory and the second trajectory.

摘要翻译： 从用户接收输入的方法包括在由手制作的手势期间感测用户的手的质心的第一轨迹。 还感测到在由手制作的手势期间用户的手指尖的第二轨迹。 由手动手势表示的字母数字字符取决于第一轨迹和第二轨迹。

公开(公告)号：US08140330B2

公开(公告)日：2012-03-20

申请号：US12139401

申请日：2008-06-13

申请人： Mert Cevik ,  Fuliang Weng

发明人： Mert Cevik ,  Fuliang Weng

IPC分类号： G10L15/00 ,  G10L15/04 ,  G10L15/10 ,  G10L15/12

CPC分类号： G10L15/22 ,  G10L15/12

摘要： Embodiments of a method and system for detecting repeated patterns in dialog systems are described. The system includes a dynamic time warping (DTW) based pattern comparison algorithm that is used to find the best matching parts between a correction utterance and an original utterance. Reference patterns are generated from the correction utterance by an unsupervised segmentation scheme. No significant information about the position of the repeated parts in the correction utterance is assumed, as each reference pattern is compared with the original utterance from the beginning of the utterance to the end. A pattern comparison process with DTW is executed without knowledge of fixed end-points. A recursive DTW computation is executed to find the best matching parts that are considered as the repeated parts as well as the end-points of the utterance.

摘要翻译： 描述用于检测对话系统中的重复模式的方法和系统的实施例。 该系统包括基于动态时间扭曲（DTW）的模式比较算法，用于在校正发声和原始话语之间找到最佳匹配部分。 通过无监督分割方案从校正发声产生参考模式。 假设在校正发声中重复部分的位置的重要信息，因为每个参考图案与从话语开始到结束的原始话语进行比较。 在不知道固定端点的情况下执行DTW的模式比较过程。 执行递归DTW计算，以找到被认为是重复部分以及话语终点的最佳匹配部分。

公开(公告)号：US20090313016A1

公开(公告)日：2009-12-17

申请号：US12139401

申请日：2008-06-13

申请人： Mert Cevik ,  Fuliang Weng

发明人： Mert Cevik ,  Fuliang Weng

IPC分类号： G10L15/00

CPC分类号： G10L15/22 ,  G10L15/12

摘要： Embodiments of a method and system for detecting repeated patterns in dialog systems are described. The system includes a dynamic time warping (DTW) based pattern comparison algorithm that is used to find the best matching parts between a correction utterance and an original utterance. Reference patterns are generated from the correction utterance by an unsupervised segmentation scheme. No significant information about the position of the repeated parts in the correction utterance is assumed, as each reference pattern is compared with the original utterance from the beginning of the utterance to the end. A pattern comparison process with DTW is executed without knowledge of fixed end-points. A recursive DTW computation is executed to find the best matching parts that are considered as the repeated parts as well as the end-points of the utterance.

摘要翻译： 描述用于检测对话系统中的重复模式的方法和系统的实施例。 该系统包括基于动态时间扭曲（DTW）的模式比较算法，用于在校正发声和原始话语之间找到最佳匹配部分。 通过无监督分割方案从校正发声产生参考模式。 假设在校正发声中重复部分的位置的重要信息，因为每个参考图案与从话语开始到结束的原始话语进行比较。 在不知道固定端点的情况下执行DTW的模式比较过程。 执行递归DTW计算，以找到被认为是重复部分以及话语终点的最佳匹配部分。

公开(公告)号：US20090216711A1

公开(公告)日：2009-08-27

申请号：US12072707

申请日：2008-02-26

申请人： Qi Yu ,  Yao Meng ,  Fuliang Weng

发明人： Qi Yu ,  Yao Meng ,  Fuliang Weng

IPC分类号： G06F17/30

CPC分类号： G06F9/5055 ,  G06F2209/5015

摘要： In a system and method for fulfilling a service query for a user, a processor may parse the query into a set of operations, identify a set of service providers that each provides functionality for performing at least one respective operation of the set of operations, and, for each of the set of operations, select a respective one of the set of service providers to perform the operation, and interface with the service provider selected for the operation to cause the service provider to perform the operation.

摘要翻译： 在用于满足用户的服务查询的系统和方法中，处理器可以将查询解析为一组操作，识别每组提供用于执行该组操作的至少一个相应操作的功能的一组服务提供者，以及 对于所述一组操作中的每一个，选择所述一组服务提供者中的相应一个以执行操作，并且与为操作选择的服务提供商进行接口以使服务提供商执行该操作。