Method and system for conveying an example in a natural language understanding application
    71.
    发明申请
    Method and system for conveying an example in a natural language understanding application 有权
    用于传达自然语言理解应用中的示例的方法和系统

    公开(公告)号:US20070143099A1

    公开(公告)日:2007-06-21

    申请号:US11300799

    申请日:2005-12-15

    Abstract: A method (300) and system (100) is provided to add the creation of examples at a developer level in the generation of Natural Language Understanding (NLU) models, tying the examples into a NLU sentence database (130), automatically validating (310) a correct outcome of using the examples, and automatically resolving (316) problems the user has using the examples. The method (300) can convey examples of what a caller can say to a Natural Language Understanding (NLU) application. The method includes entering at least one example associated with an existing routing destination, and ensuring an NLU model correctly interprets the example unambiguously for correctly routing a call to the routing destination. The method can include presenting the example sentence in a help message (126) within an NLU dialogue as an example of what a caller can say for connecting the caller to a desired routing destination. The method can also include presented a failure dialogue for displaying at least one example that failed to be properly interpreted to ensure that ambiguous or incorrect examples are not presented in a help message.

    Abstract translation: 提供了一种方法(300)和系统(100),用于在生成自然语言理解(NLU)模型时在开发者级别添加示例的创建,将示例绑定到NLU句子数据库(130)中,自动验证(310 )使用示例的正确结果,并自动解析(316)用户使用示例的问题。 方法(300)可以传达呼叫者可以对自然语言理解(NLU)应用程序说什么的示例。 该方法包括输入与现有路由目的地相关联的至少一个示例,并且确保NLU模型明确地解释该示例以正确路由呼叫到路由目的地。 该方法可以包括将NLU对话内的帮助消息(126)中的示例呈现为呼叫者可以将呼叫者连接到期望的路由目的地的示例。 该方法还可以包括呈现失败对话,用于显示未被正确解释的至少一个示例,以确保在帮助消息中不呈现模糊或不正确的示例。

    Automatic generation of a callflow statistics application for speech systems
    72.
    发明申请
    Automatic generation of a callflow statistics application for speech systems 失效
    自动生成语音系统的呼叫流统计应用程序

    公开(公告)号:US20070133777A1

    公开(公告)日:2007-06-14

    申请号:US11297537

    申请日:2005-12-08

    CPC classification number: G10L2015/228 H04M3/4936 H04M2203/355

    Abstract: A method, system and computer program for automatically generating call flow statistics in a voice application. Embodiments of the present invention address deficiencies of the art in respect to call flow statistics generation systems and provide a novel and non-obvious method, system and computer program product for automatically generating a call flow statistics-generating application and presenting updated statistics on a call flow representation. Various statistics collection points are identified on the visual representation. Upon running of the voice application, call flow statistics are gathered and presented for each statistics collection point. Call identifiers corresponding to each call path can be selected and call paths corresponding to the selected call identifier may be highlighted and their call statistics displayed.

    Abstract translation: 一种用于在语音应用中自动生成呼叫流统计的方法,系统和计算机程序。 本发明的实施例解决了与呼叫流统计生成系统有关的本领域的缺陷,并且提供了一种新颖且非显而易见的方法,系统和计算机程序产品,用于自动生成呼叫流统计生成应用并呈现呼叫上的更新统计信息 流程表示。 在视觉表示上确定了各种统计数据收集点。 在运行语音应用程序时,将收集并显示每个统计信息收集点的呼叫流统计信息。 可以选择对应于每个呼叫路径的呼叫标识符,并且可以突出显示与所选呼叫标识符相对应的呼叫路径,并显示其呼叫统计信息。

    Driver system for MOSFET based, high voltage electronic relays for AC power switching and inductive loads
    73.
    发明申请
    Driver system for MOSFET based, high voltage electronic relays for AC power switching and inductive loads 有权
    驱动器系统,用于基于MOSFET的高压电子继电器,用于交流电源开关和电感负载

    公开(公告)号:US20070133144A1

    公开(公告)日:2007-06-14

    申请号:US11702535

    申请日:2007-02-06

    Applicant: James Lewis

    Inventor: James Lewis

    Abstract: A method and apparatus provides for high-speed switching of high-voltage and high power MOSFET-based solid state relays. A driver for a MOSFET based, high voltage, high current electronic relay includes a current supply for actuating the switching circuit and a transformer arrangement coupled to the current supply for receiving the supply of current from the current supply. The transformer arrangement is adapted for coupling with the switching circuit for selectively applying a predetermined voltage to the switching circuit which establishes the switching circuit in switch conducting or switch isolation.

    Abstract translation: 一种方法和装置提供高速和高功率基于MOSFET的固态继电器的高速切换。 用于基于MOSFET的高电压大电流电子继电器的驱动器包括用于致动开关电路的电流源和耦合到电流源的变压器装置,用于接收来自电流源的电流供应。 变压器布置适于与开关电路耦合,用于选择性地向开关电路施加预定电压,该开关电路在开关导通或开关隔离中建立开关电路。

    Real-time processor
    74.
    发明申请
    Real-time processor 审中-公开
    实时处理器

    公开(公告)号:US20060288194A1

    公开(公告)日:2006-12-21

    申请号:US11240535

    申请日:2005-10-03

    CPC classification number: G06F15/7832 G06F9/30076 G06F9/3836 G06F9/3869

    Abstract: A real-time processor for a data processing system includes a continuous clock counter, an instruction parser parsing instructions based upon whether they a clock command or no timing specific instruction, a clock comparator only operating upon instructions including a clock command and an execution mechanism for executing a series of instructions in a timely manner based upon absolute timing of the clock counter such that events may be scheduled from the beginning of a sequence.

    Abstract translation: 用于数据处理系统的实时处理器包括连续时钟计数器,指令解析器,基于它们是时钟指令还是无定时特定指令来解析指令,时钟比较器仅对包括时钟指令的指令和执行机制进行操作 基于时钟计数器的绝对定时,及时地执行一系列指令,从而可以从序列开始调度事件。

    Automating input when testing voice-enabled applications
    75.
    发明申请
    Automating input when testing voice-enabled applications 有权
    测试支持语音的应用程序时自动输入

    公开(公告)号:US20060235699A1

    公开(公告)日:2006-10-19

    申请号:US11108289

    申请日:2005-04-18

    CPC classification number: G10L15/22

    Abstract: A method for automating an input process during a testing of a voice-enabled application so that a tester is not required to manually respond to each prompt of the voice-enabled application. The method including the step of identifying a session input store that includes input data associated with voice-enabled application prompts and the step of executing the voice-enabled application. The voice-enabled application can prompt for user input that is to be used when performing a speech processing task. Input data from the session input store can be automatically extracted responsive to the prompting and used in place of manually entered input. The speech processing service can perform the speech processing task based upon the extracted data.

    Abstract translation: 一种在启用语音的应用程序的测试期间自动化输入过程的方法,使得测试者不需要手动响应语音使能应用的每个提示。 该方法包括识别包括与支持语音的应用程序提示相关联的输入数据的会话输入存储的步骤以及执行支持语音的应用程序的步骤。 支持语音的应用程序可以提示在执行语音处理任务时要使用的用户输入。 来自会话输入存储器的输入数据可以根据提示自动提取,并用于代替手动输入的输入。 语音处理服务可以基于所提取的数据执行语音处理任务。

    Method and system of dynamically adjusting a speech output rate to match a speech input rate
    80.
    发明申请
    Method and system of dynamically adjusting a speech output rate to match a speech input rate 有权
    动态调整语音输出速率以匹配语音输入速率的方法和系统

    公开(公告)号:US20050228672A1

    公开(公告)日:2005-10-13

    申请号:US10815309

    申请日:2004-04-01

    CPC classification number: G10L21/04

    Abstract: A method (10) and system of adjusting a speech output rate to match a speech input rate can include the steps of receiving (12) speech input, computing (14) a speech input rate, and dynamically adjusting (18 or 26) a speech output rate to match the speech input rate. If the type of speech output is TTS, then a rate of TTS can be adjusted (18). If the type of speech output is recorded and alternate text is available, then steps (22 and 24) of counting alternate text available from a recorded output and determining an audio file length is used to compute a default output rate to adjust a recorded output rate. If the type is recorded and alternate text is unavailable, then steps (21 and 24) of obtaining an output word count from a transcription of a recorded speech output and determining an audio file length is used.

    Abstract translation: 一种方法(10)和调整语音输出速率以匹配语音输入速率的系统可以包括以下步骤:接收(12)语音输入,计算(14)语音输入速率,以及动态地调整(18或26)语音 输出速率匹配语音输入速率。 如果语音输出的类型是TTS,则可以调整TTS的速率(18)。 如果语音输出的类型被记录并且替代文本可用,则使用计数从记录输出可用的替代文本并确定音频文件长度的步骤(22和24)来计算默认输出速率以调整记录的输出速率 。 如果记录类型并且替代文本不可用,则使用从记录的语音输出的转录获得输出字数并确定音频文件长度的步骤(21和24)。

Patent Agency Ranking