-
公开(公告)号：US11544504B1
公开(公告)日：2023-01-03
申请号：US17022883
申请日：2020-09-16
发明人： Xing Fan , Hung Tuan Pham , Chenlei Guo , Xiaohu Liu , Shuting Tang
IPC分类号： G06K9/62 , G06F16/9032 , G06F40/35
摘要： Techniques for determining an intent of a subsequent user input in a dialog are described. The system processes historic interaction data that is structured based on natural language understanding (NLU) hypotheses, with each NLU hypothesis being associated with one or more past user inputs received by the system, one or more sample inputs, and one or more past system responses. Based on processing of the historic interaction data and dialog data of previous turns of the dialog, the system determines candidate intents for the subsequent turn of the dialog. The system also uses context data to determine the candidate intents.
-
公开(公告)号：US11437027B1
公开(公告)日：2022-09-06
申请号：US16703609
申请日：2019-12-04
发明人： Chenlei Guo , Xing Fan , Jin Hock Ong , Kai Wei
IPC分类号： G10L15/197 , G10L15/22 , G10L15/18 , G10L15/30
摘要： Techniques for handling errors during processing of natural language inputs are described. A system may process a natural language input to generate an ASR hypothesis or NLU hypothesis. The system may use more than one data searching technique (e.g., deep neural network searching, convolutional neural network searching, etc.) to generate an alternate ASR hypothesis or NLU hypothesis, depending on the type of hypothesis input for alternate hypothesis processing.
-
公开(公告)号：US20220246149A1
公开(公告)日：2022-08-04
申请号：US17682162
申请日：2022-02-28
发明人： Anjishnu Kumar , Xing Fan , Arpit Gupta , Ruhi Sarikaya
摘要： Techniques for determining a command or intent likely to be subsequently invoked by a user of a system are described. A user inputs a command (either via a spoken utterance or textual input) to a system. The system determines content responsive to the command. The system also determines a second command or corresponding intent likely to be invoked by the user subsequent to the previous command. Such determination may involve analyzing pairs of intents, with each pair being associated with a probability that one intent of the pair will be invoked by a user subsequent to a second intent of the pair. The system then outputs first content responsive to the first command and second content soliciting the user as to whether the system to execute the second command.
-
公开(公告)号：US11646035B1
公开(公告)日：2023-05-09
申请号：US17027903
申请日：2020-09-22
发明人： Xing Fan , Chenlei Guo
IPC分类号： G10L15/32 , G10L15/07 , G10L15/18 , G06F16/9032
CPC分类号： G10L15/32 , G06F16/90332 , G10L15/075 , G10L15/1815
摘要： Techniques for determining an intent for a user input in a dialog are described. The system processes historic interaction data that is structured based skills and intents, with each skill-intent pair being associated with one or more past user inputs received by the system, one or more sample inputs, and one or more alternative representations of the user inputs. Based on processing of the historic interaction data and dialog data of previous turns of the dialog, the system determines potential intents for the user input of the current turn of the dialog. The potential intents may correspond to a presently active skill or another skill, enabling the user to interact with another skill during the dialog.
-
公开(公告)号：US20200058300A1
公开(公告)日：2020-02-20
申请号：US16550639
申请日：2019-08-26
发明人： Anjishnu Kumar , Xing Fan , Arpit Gupta , Ruhi Sarikaya
摘要： Techniques for determining a command or intent likely to be subsequently invoked by a user of a system are described. A user inputs a command (either via a spoken utterance or textual input) to a system. The system determines content responsive to the command. The system also determines a second command or corresponding intent likely to be invoked by the user subsequent to the previous command. Such determination may involve analyzing pairs of intents, with each pair being associated with a probability that one intent of the pair will be invoked by a user subsequent to a second intent of the pair. The system then outputs first content responsive to the first command and second content soliciting the user as to whether the system to execute the second command.
-
公开(公告)号：US10395655B1
公开(公告)日：2019-08-27
申请号：US15703268
申请日：2017-09-13
发明人： Anjishnu Kumar , Xing Fan , Arpit Gupta , Ruhi Sarikaya
IPC分类号： G10L21/00 , G10L15/22 , G10L13/00 , G10L15/14 , G10L17/00 , G10L15/18 , G06N5/02 , G06F17/27
摘要： Techniques for determining a command or intent likely to be subsequently invoked by a user of a system are described. A user inputs a command (either via a spoken utterance or textual input) to a system. The system determines content responsive to the command. The system also determines a second command or corresponding intent likely to be invoked by the user subsequent to the previous command. Such determination may involve analyzing pairs of intents, with each pair being associated with a probability that one intent of the pair will be invoked by a user subsequent to a second intent of the pair. The system then outputs first content responsive to the first command and second content soliciting the user as to whether the system to execute the second command.
-
公开(公告)号：US11823678B2
公开(公告)日：2023-11-21
申请号：US17682162
申请日：2022-02-28
发明人： Anjishnu Kumar , Xing Fan , Arpit Gupta , Ruhi Sarikaya
IPC分类号： G10L15/22 , G10L13/00 , G10L15/14 , G10L15/18 , G06N5/022 , G06F40/30 , G10L17/00 , G06F40/295
CPC分类号： G10L15/22 , G06F40/30 , G06N5/022 , G10L13/00 , G10L15/14 , G10L15/1815 , G10L17/00 , G06F40/295 , G10L2015/223
摘要： Techniques for determining a command or intent likely to be subsequently invoked by a user of a system are described. A user inputs a command (either via a spoken utterance or textual input) to a system. The system determines content responsive to the command. The system also determines a second command or corresponding intent likely to be invoked by the user subsequent to the previous command. Such determination may involve analyzing pairs of intents, with each pair being associated with a probability that one intent of the pair will be invoked by a user subsequent to a second intent of the pair. The system then outputs first content responsive to the first command and second content soliciting the user as to whether the system to execute the second command.
-
公开(公告)号：US20230047811A1
公开(公告)日：2023-02-16
申请号：US17856090
申请日：2022-07-01
发明人： Chenlei Guo , Xing Fan , Chengyuan Ma , Shuting Tang , Kai Wei
摘要： A system is provided for a self-learning policy engine that can be used by various spoken language understanding (SLU) processing components. The system also provides for sharing contextual information from processing performed by an upstream SLU component to a downstream SLU component to facilitate decision making by the downstream SLU component. The system also provides for a SLU component to select from a variety of actions to take. A SLU component may implement an instance of the self-learning policy that is specifically configured for the particular SLU component.
-
公开(公告)号：US11270698B2
公开(公告)日：2022-03-08
申请号：US16550639
申请日：2019-08-26
发明人： Anjishnu Kumar , Xing Fan , Arpit Gupta , Ruhi Sarikaya
IPC分类号： G10L15/22 , G10L13/00 , G10L15/14 , G10L15/18 , G06N5/02 , G06F40/30 , G10L17/00 , G06F40/295
摘要： Techniques for determining a command or intent likely to be subsequently invoked by a user of a system are described. A user inputs a command (either via a spoken utterance or textual input) to a system. The system determines content responsive to the command. The system also determines a second command or corresponding intent likely to be invoked by the user subsequent to the previous command. Such determination may involve analyzing pairs of intents, with each pair being associated with a probability that one intent of the pair will be invoked by a user subsequent to a second intent of the pair. The system then outputs first content responsive to the first command and second content soliciting the user as to whether the system to execute the second command.
-
公开(公告)号：US11211058B1
公开(公告)日：2021-12-28
申请号：US16577394
申请日：2019-09-20
发明人： Aaron Eakin , Angela Sun , Ankur Gandhe , Ariya Rastrow , Chenlei Guo , Xing Fan
IPC分类号： G10L15/197 , G10L15/30 , G10L15/22
摘要： Described herein is a system for prompting a user for clarification when an automatic speech recognition (ASR) system encounters ambiguity with respect to the user's input. The feedback provided by the user is used to retrain machine-learning models and/or to generate new machine-learning models. Based on the type of ambiguity, the system may determine to retrain one or more ASR models that are widely used by the system or to generate/update one or more user-specific models that are used to process inputs from one or more particular users.
-
-
-
-
-
-
-
-
-
搜索结果
16 条记录 (耗时 0.054 秒)
