公开(公告)号：US20130339787A1

公开(公告)日：2013-12-19

申请号：US13562913

申请日：2012-07-31

申请人： Vasanth Bala ,  Niyu Ge ,  Ea-Ee Jan ,  Darrell C. Reimer ,  Lakshminarayanan Renganarayana ,  Xiaolan Zhang

发明人： Vasanth Bala ,  Niyu Ge ,  Ea-Ee Jan ,  Darrell C. Reimer ,  Lakshminarayanan Renganarayana ,  Xiaolan Zhang

IPC分类号： G06F11/14

CPC分类号： G06F11/1433 ,  G06F2201/83

摘要： Aspects of the present invention provide a tool for analyzing and remediating an update-related failure. In an embodiment, a failure state of a computer system that has been arrived at as a result of an update is captured. A semantic diff that includes the difference between the failure state and at least one of an original state or a completion state is then computed. This semantic diff is transformed into a feature vector format. Then the transformed semantic diff is analyzed to determine a remediation for the update. Failure and/or resolution signatures can be constructed using the semantic diff and contextual data, and these signatures can be used in comparison and analysis of failures and resolutions.

公开(公告)号：US07206387B2

公开(公告)日：2007-04-17

申请号：US10645051

申请日：2003-08-21

申请人： Ea-Ee Jan ,  Benoit Maison ,  Andrzei Sakrajda

发明人： Ea-Ee Jan ,  Benoit Maison ,  Andrzei Sakrajda

IPC分类号： H04M1/64

CPC分类号： H04M3/50 ,  H04L67/1002 ,  H04L2012/6443 ,  H04L2012/6481 ,  H04M2201/39 ,  H04M2201/40 ,  H04M2201/41

摘要： A voice processing system is provided in which sets of engines running on a plurality of servers are configured differently from one another. The sets of engines may be configured to achieve different trade-offs between performance of a task and resources required to perform the task. In the voice processing system, a task routing server is provided that assigns different sets of sub-tasks to different sets of task engines. The number of engines used to perform a task and the number of engines in each set are adjusted. By adjusting the parameters settings for the set of engines based on the type of application, the particular requirements of the application, or the nature and importance of the subtasks, for example, advantages such as improvement of resource utilization and the hardware and software costs reduction may be obtained.

摘要翻译： 提供语音处理系统，其中在多个服务器上运行的引擎组彼此不同地配置。 发动机组可以被配置为在执行任务和执行任务所需的资源之间实现不同的权衡。 在语音处理系统中，提供了将不同的子任务集分配给不同的任务引擎组的任务路由服务器。 调整用于执行任务的引擎数量和每组中的引擎数量。 通过基于应用程序的类型，应用程序的特定要求或子任务的性质和重要性调整引擎集的参数设置，例如资源利用率的提高以及降低硬件和软件成本的优点 可以获得。

公开(公告)号：US09043651B2

公开(公告)日：2015-05-26

申请号：US13565139

申请日：2012-08-02

申请人： Vasanth Bala ,  Niyu Ge ,  Ea-Ee Jan ,  Darrell C. Reimer ,  Lakshminarayanan Renganarayana ,  Xiaolan Zhang

发明人： Vasanth Bala ,  Niyu Ge ,  Ea-Ee Jan ,  Darrell C. Reimer ,  Lakshminarayanan Renganarayana ,  Xiaolan Zhang

IPC分类号： G06F11/00 ,  G06F11/14

CPC分类号： G06F11/1433 ,  G06F2201/83

摘要： Aspects of the present invention provide a tool for analyzing and remediating an update-related failure. In an embodiment, a failure state of a computer system that has been arrived at as a result of an update is captured. A semantic diff that includes the difference between the failure state and at least one of an original state or a completion state is then computed. This semantic diff is transformed into a feature vector format. Then the transformed semantic diff is analyzed to determine a remediation for the update. Failure and/or resolution signatures can be constructed using the semantic diff and contextual data, and these signatures can be used in comparison and analysis of failures and resolutions.

摘要翻译： 本发明的方面提供了用于分析和修复与更新相关的故障的工具。 在一个实施例中，捕获由于更新而到达的计算机系统的故障状态。 然后计算包括故障状态与原始状态或完成状态中的至少一个之间的差异的语义差异。 这种语义差异被转换成特征向量格式。 然后分析转换的语义差异以确定更新的修复。 可以使用语义差异和上下文数据构建故障和/或解析签名，并且可以将这些签名用于比较和分析故障和分辨率。

公开(公告)号：US07558734B1

公开(公告)日：2009-07-07

申请号：US12271912

申请日：2008-11-16

申请人： Osamuyimen T. Stewart ,  David M. Lubensky ,  Ea-Ee Jan ,  Xiang Li

发明人： Osamuyimen T. Stewart ,  David M. Lubensky ,  Ea-Ee Jan ,  Xiang Li

IPC分类号： G10L21/00

CPC分类号： G06F17/30861 ,  G06F17/2785 ,  G06F17/30684 ,  G10L15/26 ,  H04M3/4938

摘要： In one example, this invention presents a method of providing the same self-service content that is available on the web interface to users contacting by telephone, knowing that the web and telephone are fundamentally different user interfaces. In one embodiment, this patent seeks to protect the general idea of how to playback web data in real-time to the user over the speech interface. For this purpose, a method is presented comprising of the general steps through which the web data is initially sent to an automatic transformation module. Then, that transformation module refines or re-structures the web data to make it suitable for the speech interface. The algorithm in the module is predicated on the user interface principles of cognitive complexity and limitations on short term memory based on which FAQ types are classified into one of the following four classes: simple, medium, complex, and complex-complex.

摘要翻译： 在一个示例中，本发明提供了一种方法，即知道网络和电话是根本上不同的用户界面的，通过电话向网络接口提供与用户联系的相同的自助服务内容。 在一个实施例中，该专利旨在保护如何通过语音界面实时地向用户播放web数据的一般思想。 为此，提出了一种方法，其包括最初将web数据发送到自动变换模块的一般步骤。 然后，该转换模块对网络数据进行优化或重构，使其适合于语音界面。 模块中的算法基于用户界面的认知复杂性原理和短期记忆的限制，基于哪些常见问题类型分为以下四个类别之一：简单，中等，复杂和复杂。

公开(公告)号：US5666466A

公开(公告)日：1997-09-09

申请号：US365598

申请日：1994-12-27

申请人： Qiguang Lin ,  James L. Flanagan ,  Ea-Ee Jan

发明人： Qiguang Lin ,  James L. Flanagan ,  Ea-Ee Jan

IPC分类号： G10L17/00 ,  G10L7/08

CPC分类号： G10L17/02 ,  G10L17/00 ,  G10L17/04 ,  G10L25/24

摘要： A method and apparatus are disclosed for robust, text-independent (and text-dependent) speaker recognition in which identification of a speaker is based on selected spectral information from the speaker's voice. Traditionally, speaker recognition systems (i) render a speech sample in the frequency domain to produce a spectrum, (ii) produce cepstrum coefficients from the spectrum, (iii) produce a codebook from the cepstrum coefficients, and (iv) use the codebook as the feature measure for comparing training speech samples with testing speech samples. The present invention, on the other hand, introduces the important and previously unknown step of truncating the spectrum prior to producing the cepstrum coefficients. Through the use of selected spectra as the feature measure for speaker recognition, the present invention has been shown to yield significant improvements in performance over prior art systems.

摘要翻译： 公开了用于稳健，文本无关（和文本相关）的扬声器识别的方法和装置，其中扬声器的识别基于来自扬声器的声音的所选频谱信息。 传统上，讲话者识别系统（i）在频域中呈现语音样本以产生频谱，（ii）从频谱产生倒谱系数，（iii）从倒谱系数产生码本，以及（iv）使用码本作为 将训练语音样本与测试语音样本进行比较的特征措施。 另一方面，本发明介绍了在产生倒谱系数之前截断频谱的重要且未知的步骤。 通过使用所选择的光谱作为说话者识别的特征量度，已经证明本发明在现有技术系统方面显着提高了性能。

公开(公告)号：US08370127B2

公开(公告)日：2013-02-05

申请号：US11454694

申请日：2006-06-16

申请人： Ea-Ee Jan ,  Xiang Li ,  David Lubensky ,  Osamuyimen Thompson Stewart

发明人： Ea-Ee Jan ,  Xiang Li ,  David Lubensky ,  Osamuyimen Thompson Stewart

IPC分类号： G06F17/27 ,  G10L15/00 ,  G10L11/00 ,  H04M1/64

CPC分类号： G10L15/1822 ,  G10L15/063 ,  G10L15/183

摘要： A method of processing limited natural language data to automatically develop an optimal feature set, bypassing the standard Wizard of OZ (WOZ) approach. Natural language understanding models process existing data from other domains, such as the Internet, for domain-specific adaptation through the use of an optimal feature set. When the optimal feature set is passed on to any engine, the optimal feature set produces robust models that can be used for natural language call routing.

摘要翻译： 一种处理有限自然语言数据以自动开发最佳特征集的方法，绕过标准的OZ向导（WOZ）方法。 自然语言理解模型通过使用最佳特征集处理来自其他领域（例如因特网）的现有数据，用于特定领域的适应。 当最优特征集传递给任何引擎时，最优特征集可以产生可用于自然语言呼叫路由的鲁棒模型。

公开(公告)号：US08200492B2

公开(公告)日：2012-06-12

申请号：US12061566

申请日：2008-04-02

申请人： Ea-Ee Jan ,  Benoit Emmanuel Maison

发明人： Ea-Ee Jan ,  Benoit Emmanuel Maison

IPC分类号： G10L21/00

CPC分类号： G06F8/656

摘要： A method of updating an application in a processing system, the processing system including a plurality of computing resource units wherein at least two of the resource units are initially allocated to a first application, and wherein the processing system has insufficient resources to simultaneously run both of the first application and a second application at full capacity, the method including de-allocating fewer than all of the resource units allocated to the first application, then allocating at least one resource unit to the second application, and then de-allocating at least one resource unit from the first application.

摘要翻译： 一种在处理系统中更新应用的方法，所述处理系统包括多个计算资源单元，其中所述资源单元中的至少两个初始分配给第一应用，并且其中所述处理系统具有足够的资源以同时运行 所述第一应用和第二应用是全容量的，所述方法包括：分配少于分配给所述第一应用的所有资源单元，然后将至少一个资源单元分配给所述第二应用，然后去分配至少一个 资源单元从第一个应用程序。

公开(公告)号：US20080270135A1

公开(公告)日：2008-10-30

申请号：US11742149

申请日：2007-04-30

申请人： Vaibhava Goel ,  Ramesh Gopinath ,  Ea-Ee Jan ,  Karthik Visweswariah

发明人： Vaibhava Goel ,  Ramesh Gopinath ,  Ea-Ee Jan ,  Karthik Visweswariah

IPC分类号： G10L15/18

CPC分类号： G10L15/1822 ,  G10L15/193 ,  G10L15/197

摘要： A method (and system) of handling out-of-grammar utterances includes building a statistical language model for a dialog state using, generating sentences and semantic interpretations for the sentences using finite state grammar, building a statistical action classifier, receiving user input, carrying out recognition with the finite state grammar, carrying out recognition with the statistical language model, using the statistical action classifier to find semantic interpretations, comparing an output from the finite state grammar and an output from the statistical language model, deciding which output of the output from the finite state grammar and the output from the statistical language model to keep as a final recognition output, selecting the final recognition output, and outputting the final recognition result, wherein the statistical action classifier, the finite state grammar and the statistical language model are used in conjunction to carry out speech recognition and interpretation.

摘要翻译： 处理语法语法的方法（和系统）包括使用有限状态语法为对话状态建立统计语言模型，使用有限状态语法生成句子和语义解释，构建统计动作分类器，接收用户输入，携带 使用有限状态语法进行识别，使用统计语言模型进行识别，使用统计动作分类器来查找语义解释，比较有限状态语法的输出和来自统计语言模型的输出，决定输出的哪个输出 从有限状态语法和统计语言模型的输出，作为最终识别输出，选择最终识别输出，并输出最终识别结果，其中统计动作分类器，有限状态语法和统计语言模型是 结合使用来进行语音识别和解释 。

公开(公告)号：US20080226058A1

公开(公告)日：2008-09-18

申请号：US12132000

申请日：2008-06-03

申请人： Subrata K. Das ,  Ea-Ee Jan

发明人： Subrata K. Das ,  Ea-Ee Jan

IPC分类号： H04M3/00 ,  G10L15/00

CPC分类号： H04M3/527 ,  H04M2201/40

摘要： An automated agent system and method includes an action classifier which scores a representation of a portion of a user inquiry based on a knowledge bank. A comparing device compares a running score of the representation to a threshold to determine if enough information has been collected to respond early to the inquiry. An action mechanism provides an early response to the user prior to the user completing the inquiry if the threshold has been exceeded.

摘要翻译： 一种自动化代理系统和方法包括：动作分类器，其基于知识库来评分用户查询的一部分的表示。 比较装置将表示的运行分数与阈值进行比较，以确定是否已经收集了足够的信息以及早响应查询。 如果已经超过阈值，则在用户完成查询之前，动作机制提供对用户的早期响应。

公开(公告)号：US20080208583A1

公开(公告)日：2008-08-28

申请号：US12115622

申请日：2008-05-06

申请人： Ea-Ee JAN ,  Xiang Li ,  David Lubensky ,  Osamuyimen Thompson Stewart

发明人： Ea-Ee JAN ,  Xiang Li ,  David Lubensky ,  Osamuyimen Thompson Stewart

IPC分类号： G10L15/18

CPC分类号： G10L15/1822 ,  G10L15/063 ,  G10L15/183

摘要： A method of processing limited natural language data to automatically develop an optimal feature set, bypassing the standard Wizard of OZ (WOZ) approach is provided. The method provides for building natural language understanding models or for processing existing data from other domains, such as the Internet, for domain-specific adaptation through the use of an optimal feature set. Consequently, when the optimal feature set is passed on to any engine, the optimal feature set produces robust models that can be used for natural language call routing.

摘要翻译： 提供了一种处理有限自然语言数据以自动开发最佳特征集的方法，绕过标准的OZ向导（WOZ）方法。 该方法提供了构建自然语言理解模型，或者通过使用最优特征集来处理来自其他领域（例如因特网）的现有数据，用于域特定适应。 因此，当最优特征集合被传递给任何引擎时，最优特征集合产生可用于自然语言呼叫路由的鲁棒模型。