公开(公告)号：US08463565B1

公开(公告)日：2013-06-11

申请号：US13336796

申请日：2011-12-23

申请人： Ralph Osterhout ,  Michael J. Keating ,  Antony Van der Mude

发明人： Ralph Osterhout ,  Michael J. Keating ,  Antony Van der Mude

IPC分类号： G01R31/36

CPC分类号： F21L4/005 ,  H01M10/443 ,  H02J7/0047

摘要： A flashlight includes a light powered by a battery, and a circuit having: a memory for storing a battery life information and voltage output information versus time for the battery to power the light, a controller operating a count down timer to accumulate an amount of time that the battery powers the light, a voltage measure circuit for monitoring the voltage output by the battery while the battery powers the light and supply the voltage output to the controller. The controller determines: a first remaining battery life by comparing the accumulated time to the battery life, a second remaining battery life by comparing the voltage output to the voltage output information, and the lesser of the first and second remaining battery lives. The flashlight includes a display for receiving a command from the controller to display the lesser of the first remaining battery life and the second remaining battery life.

摘要翻译： 手电筒包括由电池供电的光，以及电路，具有：存储器，用于存储电池寿命信息和电压输出信息对电池供电的时间，控制器操作倒计时定时器以累积一定时间量 电池为光源供电，一个电压测量电路，用于在电池供电并向控制器提供电压输出时监视电池输出的电压。 所述控制器通过将所述累积时间与所述电池寿命进行比较来确定第一剩余电池寿命，通过将所述电压输出与所述电压输出信息进行比较来计算第二剩余电池寿命，以及所述第一和第二剩余电池寿命中的较小者。 手电筒包括用于从控制器接收命令以显示第一剩余电池寿命和第二剩余电池寿命中的较小者的显示器。

公开(公告)号：US08104915B1

公开(公告)日：2012-01-31

申请号：US12467828

申请日：2009-05-18

申请人： Ralph Osterhout ,  Michael J Keating ,  Antony Van der Mude

发明人： Ralph Osterhout ,  Michael J Keating ,  Antony Van der Mude

IPC分类号： F21L4/04

CPC分类号： F21L4/005 ,  H01M10/443 ,  H02J7/0047

摘要： A flashlight includes a light powered by a battery, and a circuit having: a memory for storing a battery life information and voltage output information versus time for the battery to power the light, a controller operating a count down timer to accumulate an amount of time that the battery powers the light, a voltage measure circuit for monitoring the voltage output by the battery while the battery powers the light and supply the voltage output to the controller. The controller determines: a first remaining battery life by comparing the accumulated time to the battery life, a second remaining battery life by comparing the voltage output to the voltage output information, and the lesser of the first and second remaining battery lives. The flashlight includes a display for receiving a command from the controller to display the lesser of the first remaining battery life and the second remaining battery life.

摘要翻译： 手电筒包括由电池供电的光，以及电路，具有：存储器，用于存储电池寿命信息和电压输出信息对电池供电的时间，控制器操作倒计时定时器以累积一定时间量 电池为光源供电，一个电压测量电路，用于在电池供电并向控制器提供电压输出时监视电池输出的电压。 所述控制器通过将所述累积时间与所述电池寿命进行比较来确定第一剩余电池寿命，通过将所述电压输出与所述电压输出信息进行比较来计算第二剩余电池寿命，以及所述第一和第二剩余电池寿命中的较小者。 手电筒包括用于从控制器接收命令以显示第一剩余电池寿命和第二剩余电池寿命中的较小者的显示器。

公开(公告)号：US07620550B1

公开(公告)日：2009-11-17

申请号：US11866685

申请日：2007-10-03

申请人： Narendra K. Gupta ,  Mazin G. Rahim ,  Gokhan Tur ,  Antony Van der Mude

发明人： Narendra K. Gupta ,  Mazin G. Rahim ,  Gokhan Tur ,  Antony Van der Mude

IPC分类号： G10L15/18

CPC分类号： G10L15/193 ,  G10L15/063 ,  G10L15/183

摘要： A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received. After all the training data is received, at least once, the method comprises building a third NLU model using all the labeling data, wherein the third NLU model is used in generating the spoken dialog service.

摘要翻译： 公开了一种生成在口头对话系统中使用的自然语言模型的方法。 该方法包括对标签指南中定义的每个呼叫类型使用样本话语和创建许多手工制作规则。 使用手工制作的规则和样品说话来生成和测试第一个NLU模型。 使用示例语句作为新的训练数据并使用手工制作规则构建了第二个NLU模型。 使用第一批标签数据对第二个NLU模型进行性能测试。 通过将前一批标签数据添加到训练数据并使用新批签名数据作为测试数据来生成一系列NLU模型，训练数据不断增加，构建了一系列NLU模型。 如果不是全部接收到标签数据，则该方法包括重复建立一系列NLU模型的步骤，直到接收到所有标记数据为止。 在接收到所有训练数据之后，至少一次，该方法包括使用所有标签数据构建第三NLU模型，其中第三NLU模型用于生成口语对话服务。

公开(公告)号：US20100042404A1

公开(公告)日：2010-02-18

申请号：US12582062

申请日：2009-10-20

申请人： Narendra K. Gupta ,  Mazin G. Rahim ,  Gokhan Tur ,  Antony Van der Mude

发明人： Narendra K. Gupta ,  Mazin G. Rahim ,  Gokhan Tur ,  Antony Van der Mude

IPC分类号： G10L15/18 ,  G06F17/27

CPC分类号： G10L15/193 ,  G10L15/063 ,  G10L15/183

摘要： A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received. After all the training data is received, at least once, the method comprises building a third NLU model using all the labeling data, wherein the third NLU model is used in generating the spoken dialog service.

摘要翻译： 公开了一种生成在口头对话系统中使用的自然语言模型的方法。 该方法包括对标签指南中定义的每个呼叫类型使用样本话语和创建许多手工制作规则。 使用手工制作的规则和样品说话来生成和测试第一个NLU模型。 使用示例语句作为新的训练数据并使用手工制作规则构建了第二个NLU模型。 使用第一批标签数据对第二个NLU模型进行性能测试。 通过将前一批标签数据添加到训练数据并使用新批签名数据作为测试数据来生成一系列NLU模型，训练数据不断增加，构建了一系列NLU模型。 如果不是全部接收到标签数据，则该方法包括重复建立一系列NLU模型的步骤，直到接收到所有标记数据为止。 在接收到所有训练数据之后，至少一次，该方法包括使用所有标签数据构建第三NLU模型，其中第三NLU模型用于生成口语对话服务。

公开(公告)号：US07933766B2

公开(公告)日：2011-04-26

申请号：US12582062

申请日：2009-10-20

申请人： Narendra K. Gupta ,  Mazin G. Rahim ,  Gokhan Tur ,  Antony Van der Mude

发明人： Narendra K. Gupta ,  Mazin G. Rahim ,  Gokhan Tur ,  Antony Van der Mude

IPC分类号： G06F17/27

CPC分类号： G10L15/193 ,  G10L15/063 ,  G10L15/183

摘要： A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received. After all the training data is received, at least once, the method comprises building a third NLU model using all the labeling data, wherein the third NLU model is used in generating the spoken dialog service.

摘要翻译： 公开了一种生成在口头对话系统中使用的自然语言模型的方法。 该方法包括对标签指南中定义的每个呼叫类型使用样本话语和创建许多手工制作规则。 使用手工制作的规则和样品说话来生成和测试第一个NLU模型。 使用示例语句作为新的训练数据并使用手工制作规则构建了第二个NLU模型。 使用第一批标签数据对第二个NLU模型进行性能测试。 通过将前一批标签数据添加到训练数据并使用新批签名数据作为测试数据来生成一系列NLU模型，训练数据不断增加，构建了一系列NLU模型。 如果不是全部接收到标签数据，则该方法包括重复建立一系列NLU模型的步骤，直到接收到所有标记数据为止。 在接收到所有训练数据之后，至少一次，该方法包括使用所有标签数据构建第三NLU模型，其中第三NLU模型用于生成口语对话服务。

公开(公告)号：US07295981B1

公开(公告)日：2007-11-13

申请号：US10755014

申请日：2004-01-09

申请人： Narendra K. Gupta ,  Mazin G. Rahim ,  Gokhan Tur ,  Antony Van der Mude

发明人： Narendra K. Gupta ,  Mazin G. Rahim ,  Gokhan Tur ,  Antony Van der Mude

IPC分类号： G10L15/18

CPC分类号： G10L15/193 ,  G10L15/063 ,  G10L15/183

摘要： A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received. After all the training data is received, at least once, the method comprises building a third NLU model using all the labeling data, wherein the third NLU model is used in generating the spoken dialog service.

摘要翻译： 公开了一种生成在口头对话系统中使用的自然语言模型的方法。 该方法包括对标签指南中定义的每个呼叫类型使用样本话语和创建许多手工制作规则。 使用手工制作的规则和样品说话来生成和测试第一个NLU模型。 使用示例语句作为新的训练数据并使用手工制作规则构建了第二个NLU模型。 使用第一批标签数据对第二个NLU模型进行性能测试。 通过将前一批标签数据添加到训练数据并使用新批签名数据作为测试数据来生成一系列NLU模型，训练数据不断增加，构建了一系列NLU模型。 如果不是全部接收到标签数据，则该方法包括重复建立一系列NLU模型的步骤，直到接收到所有标记数据为止。 在接收到所有训练数据之后，至少一次，该方法包括使用所有标签数据构建第三NLU模型，其中第三NLU模型用于生成口语对话服务。