-
公开(公告)号：US11379489B2
公开(公告)日：2022-07-05
申请号：US16572000
申请日：2019-09-16
IPC分类号： G06F16/2457 , G06N20/00 , G06Q10/10 , G06F16/9535 , H04L12/28
摘要： Representative embodiments disclose mechanisms to automatically rank and select extensions triggered in a digital assistant. A sample set of extensions are executed against a set of curated queries in order to extract a set of features and/or statistics. The system trains a machine learning model based on the features and/or statistics to rank and select extensions based on their response to a query. New extension incorporated into the system are executed against a second set of curated queries to obtain a set of extracted features and/or statistics which are saved for use at runtime. At runtime, a query phrase received by the system triggers one or more tasks from extensions. Extracted features for the triggered extensions are combined with stored features/statistics and at least a subset of the results presented to the trained ranking and selection model. The model ranks and selects appropriate tasks which are presented to the user.
-
公开(公告)号：US20170235465A1
公开(公告)日：2017-08-17
申请号：US15043317
申请日：2016-02-12
发明人： Marius Alexandru Marin , Paul Anthony Crook , Nikhil Holenarsipur Ramesh , Vipul Agarwal , Omar Zia Khan , Alexandre Rochette , Jean-Philippe Robichaud , Ruhi Sarikaya
IPC分类号： G06F3/0484 , G06F9/44 , G06F3/16 , G06F17/28 , G06F3/0482 , G06F3/0488
CPC分类号： G06F3/04847 , G06F3/0482 , G06F3/04883 , G06F3/167 , G06F8/34 , G06F9/451 , G06F17/28
摘要： Aspects herein provide third party application authors with a user interface authoring platform that automates and simplifies a task definition process while also providing the ability to leverage pre-existing language understanding models and canonicalization and resolution modules that are provided by the operating system on which the CU system resides or as provided by other third parties. In particular, the present disclosure provides a method and system for authoring a task using a user interface authoring platform.
-
公开(公告)号：US10437841B2
公开(公告)日：2019-10-08
申请号：US15289765
申请日：2016-10-10
IPC分类号： G06F16/2457 , G06N20/00 , G06Q10/10 , G06F16/9535 , H04L12/28
摘要： Representative embodiments disclose mechanisms to automatically rank and select extensions triggered in a digital assistant. A sample set of extensions are executed against a set of curated queries in order to extract a set of features and/or statistics. The system trains a machine learning model based on the features and/or statistics to rank and select extensions based on their response to a query. New extension incorporated into the system are executed against a second set of curated queries to obtain a set of extracted features and/or statistics which are saved for use at runtime. At runtime, a query phrase received by the system triggers one or more tasks from extensions. Extracted features for the triggered extensions are combined with stored features/statistics and at least a subset of the results presented to the trained ranking and selection model. The model ranks and selects appropriate tasks which are presented to the user.
-
公开(公告)号：US20170017519A1
公开(公告)日：2017-01-19
申请号：US14797444
申请日：2015-07-13
CPC分类号： G06F9/4881 , G06F9/4843 , G06F9/5083 , H04L51/02 , H04L51/32
摘要： Non-limiting examples of the present disclosure describe decoupling task state tracking that is managed by a shared task completion platform from execution of tasks by a task resource owner. Task registration data is received at a shared task state platform for a task that is executable by a task owner resource. Task registration data comprises parameters to be collected for execution of the task and ancillary information, such as the name of the task and whether to confirm the values of the parameters after collection. During interaction with a user, the shared task completion platform receives an input and determines the task is associated with the received input. During the interaction, parameters of the received task registration data are utilized to collect data for execution of the task. The collected data is transmitted to the task owner resource for execution of the task.
摘要翻译： 本公开的非限制性示例描述了由共享任务完成平台管理的解耦任务状态跟踪，由任务资源所有者执行任务。 任务注册数据在共享任务状态平台上被接收，用于可由任务所有者资源执行的任务。 任务注册数据包括要执行的任务的参数和辅助信息，例如任务的名称以及是否在收集后确认参数的值。 在与用户交互期间，共享任务完成平台接收输入并确定该任务与所接收的输入相关联。 在交互期间，利用接收到的任务登记数据的参数来收集执行任务的数据。 收集的数据被传送到任务所有者资源以执行任务。
-
公开(公告)号：US20160188565A1
公开(公告)日：2016-06-30
申请号：US14586395
申请日：2014-12-30
IPC分类号： G06F17/27
CPC分类号： G06F17/278 , G06F17/279 , G06F17/30646 , G06F17/30654 , G06F17/30657 , G06F17/30663 , G06F17/30666 , G06F17/30684 , G06F17/30693 , G10L15/22
摘要： Methods and systems are provided for discriminating ambiguous expressions to enhance user experience. For example, a natural language expression may be received by a speech recognition component. The natural language expression may include at least one of words, terms, and phrases of text. A dialog hypothesis set from the natural language expression may be created by using contextual information. In some cases, the dialog hypothesis set has at least two dialog hypotheses. A plurality of dialog responses may be generated for the dialog hypothesis set. The dialog hypothesis set may be ranked based on an analysis of the plurality of the dialog responses. An action may be performed based on ranking the dialog hypothesis set.
摘要翻译： 提供方法和系统用于区分不明确的表达以增强用户体验。 例如，语音识别组件可以接收自然语言表达。 自然语言表达可以包括文本的单词，术语和短语中的至少一个。 可以通过使用上下文信息来创建从自然语言表达式设置的对话假设。 在某些情况下，对话假设集至少有两个对话假设。 可以为对话假设组生成多个对话响应。 对话假设集合可以基于对多个对话响应的分析进行排名。 可以基于对话假设集合的排序来执行动作。
-
公开(公告)号：US10338959B2
公开(公告)日：2019-07-02
申请号：US14797444
申请日：2015-07-13
发明人： Omar Zia Khan , Paul Anthony Crook , Marius Alexandru Marin , Ruhi Sarikaya , Jean-Philippe Robichaud
摘要： Non-limiting examples of the present disclosure describe decoupling task state tracking that is managed by a shared task completion platform from execution of tasks by a task resource owner. Task registration data is received at a shared task state platform for a task that is executable by a task owner resource. Task registration data comprises parameters to be collected for execution of the task and ancillary information, such as the name of the task and whether to confirm the values of the parameters after collection. During interaction with a user, the shared task completion platform receives an input and determines the task is associated with the received input. During the interaction, parameters of the received task registration data are utilized to collect data for execution of the task. The collected data is transmitted to the task owner resource for execution of the task.
-
公开(公告)号：US20180089167A1
公开(公告)日：2018-03-29
申请号：US15830767
申请日：2017-12-04
CPC分类号： G06F17/278 , G06F16/3325 , G06F16/3329 , G06F16/3331 , G06F16/3334 , G06F16/3335 , G06F16/3344 , G06F16/3349 , G06F17/279 , G10L15/22
摘要： Methods and systems are provided for discriminating ambiguous expressions to enhance user experience. For example, a natural language expression may be received by a speech recognition component. The natural language expression may include at least one of words, terms, and phrases of text. A dialog hypothesis set from the natural language expression may be created by using contextual information. In some cases, the dialog hypothesis set has at least two dialog hypotheses. A plurality of dialog responses may be generated for the dialog hypothesis set. The dialog hypothesis set may be ranked based on an analysis of the plurality of the dialog responses. An action may be performed based on ranking the dialog hypothesis set.
-
公开(公告)号：US11386268B2
公开(公告)日：2022-07-12
申请号：US15830767
申请日：2017-12-04
IPC分类号： G06F40/30 , G10L15/22 , G06F40/295 , G06F16/332 , G06F16/33 , G06F40/35 , G10L15/18 , G10L15/183
摘要： Methods and systems are provided for discriminating ambiguous expressions to enhance user experience. For example, a natural language expression may be received by a speech recognition component. The natural language expression may include at least one of words, terms, and phrases of text. A dialog hypothesis set from the natural language expression may be created by using contextual information. In some cases, the dialog hypothesis set has at least two dialog hypotheses. A plurality of dialog responses may be generated for the dialog hypothesis set. The dialog hypothesis set may be ranked based on an analysis of the plurality of the dialog responses. An action may be performed based on ranking the dialog hypothesis set.
-
公开(公告)号：US20200225839A1
公开(公告)日：2020-07-16
申请号：US16831441
申请日：2020-03-26
发明人： Marius Alexandru Marin , Paul Anthony Crook , Nikhil Holenarsipur Ramesh , Vipul Agarwal , Omar Zia Khan , Alexandre Rochette , Jean-Philippe Robichaud , Ruhi Sarikaya
IPC分类号： G06F3/0484 , G06F8/34 , G06F40/40 , G06F9/451 , G06F3/0482 , G06F3/0488 , G06F3/16
摘要： Aspects herein provide third party application authors with a user interface authoring platform that automates and simplifies a task definition process while also providing the ability to leverage pre-existing language understanding models and canonicalization and resolution modules that are provided by the operating system on which the CU system resides or as provided by other third parties. In particular, the present disclosure provides a method and system for authoring a task using a user interface authoring platform.
-
公开(公告)号：US10162813B2
公开(公告)日：2018-12-25
申请号：US14086897
申请日：2013-11-21
摘要： In language evaluation systems, user expressions are often evaluated by speech recognizers and language parsers, and among several possible translations, a highest-probability translation is selected and added to a dialog sequence. However, such systems may exhibit inadequacies by discarding alternative translations that may initially exhibit a lower probability, but that may have a higher probability when evaluated in the full context of the dialog, including subsequent expressions. Presented herein are techniques for communicating with a user by formulating a dialog hypothesis set identifying hypothesis probabilities for a set of dialog hypotheses, using generative and/or discriminative models, and repeatedly re-ranks the dialog hypotheses based on subsequent expressions. Additionally, knowledge sources may inform a model-based with a pre-knowledge fetch that facilitates pruning of the hypothesis search space at an early stage, thereby enhancing the accuracy of language parsing while also reducing the latency of the expression evaluation and economizing computing resources.
-
-
-
-
-
-
-
-
-
搜索结果
16 条记录 (耗时 0.022 秒)
