-
公开(公告)号：US20240153505A1
公开(公告)日：2024-05-09
申请号：US18490029
申请日：2023-10-19
发明人： Anjishnu Kumar , Xing Fan , Arpit Gupta , Ruhi Sarikaya
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：US11527237B1
公开(公告)日：2022-12-13
申请号：US17024959
申请日：2020-09-18
发明人： Ruhi Sarikaya , Hung Tuan Pham , Savas Parastatidis , Dean Curtis , Pushpendre Rastogi , Nitin Ashok Jain , John Arland Nave , Abhinav Sethy , Arpit Gupta , Mayank Kumar , Nakul Dahiwade , Arshdeep Singh , Nikhil Reddy Kortha , Rohit Prasad
IPC分类号： G10L13/00 , G10L15/16 , G06F16/9032 , G10L13/08
摘要： Techniques for recommending a skill experience to a user after a user-system dialog session has ended are described. Upon a dialog session ending, the system uses a first machine learning model to determine potential intents to recommend to a user. The system then uses a second machine learning model to determine a particular skill and intent to recommend. The system then prompts the user to accept the recommended skill and intent. If the user accepts, the system calls the recommended skill to execute. As part of calling the skill, the system sends to the skill at least one entity provided in a natural language user input of the ended dialog session. This enables the skill to skip welcome prompts, and initiate processing to output a response based on the intent and the at least one entity of the ended dialog session.
-
公开(公告)号：US10755177B1
公开(公告)日：2020-08-25
申请号：US14985704
申请日：2015-12-31
摘要： A voice user interface (VUI) system use collaborative filtering to expand its own knowledge base. The system is designed to improve the accuracy and performance of the Natural Language Understanding (NLU) processing that underlies VUIs. The system leverages the knowledge of system users to crowdsource new information.
-
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：US20240347050A1
公开(公告)日：2024-10-17
申请号：US18663237
申请日：2024-05-14
发明人： Ruhi Sarikaya , Hung Tuan Pham , Savas Parastatidis , Dean Curtis , Pushpendre Rastogi , Nitin Ashok Jain , John Arland Nave , Abhinav Sethy , Arpit Gupta , Mayank Kumar , Nakul Dahiwade , Arshdeep Singh , Nikhil Reddy Kortha , Rohit Prasad
IPC分类号： G10L15/16 , G06F16/9032 , G10L13/08
CPC分类号： G10L15/16 , G06F16/90332 , G10L13/08
摘要： Techniques for recommending a skill experience to a user after a user-system dialog session has ended are described. Upon a dialog session ending, the system uses a first machine learning model to determine potential intents to recommend to a user. The system then uses a second machine learning model to determine a particular skill and intent to recommend. The system then prompts the user to accept the recommended skill and intent. If the user accepts, the system calls the recommended skill to execute. As part of calling the skill, the system sends to the skill at least one entity provided in a natural language user input of the ended dialog session. This enables the skill to skip welcome prompts, and initiate processing to output a response based on the intent and the at least one entity of the ended dialog session.
-
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：US11990122B2
公开(公告)日：2024-05-21
申请号：US18076987
申请日：2022-12-07
发明人： Ruhi Sarikaya , Hung Tuan Pham , Savas Parastatidis , Dean Curtis , Pushpendre Rastogi , Nitin Ashok Jain , John Arland Nave , Abhinav Sethy , Arpit Gupta , Mayank Kumar , Nakul Dahiwade , Arshdeep Singh , Nikhil Reddy Kortha , Rohit Prasad
IPC分类号： G10L15/26 , G06F16/9032 , G10L13/08 , G10L15/16
CPC分类号： G10L15/16 , G06F16/90332 , G10L13/08
摘要： Techniques for recommending a skill experience to a user after a user-system dialog session has ended are described. Upon a dialog session ending, the system uses a first machine learning model to determine potential intents to recommend to a user. The system then uses a second machine learning model to determine a particular skill and intent to recommend. The system then prompts the user to accept the recommended skill and intent. If the user accepts, the system calls the recommended skill to execute. As part of calling the skill, the system sends to the skill at least one entity provided in a natural language user input of the ended dialog session. This enables the skill to skip welcome prompts, and initiate processing to output a response based on the intent and the at least one entity of the ended dialog session.
-
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：US20230215425A1
公开(公告)日：2023-07-06
申请号：US18076987
申请日：2022-12-07
发明人： Ruhi Sarikaya , Hung Tuan Pham , Savas Parastatidis , Dean Curtis , Pushpendre Rastogi , Nitin Ashok Jain , John Arland Nave , Abhinav Sethy , Arpit Gupta , Mayank Kumar , Nakul Dahiwade , Arshdeep Singh , Nikhil Reddy Kortha , Rohit Prasad
IPC分类号： G10L15/16 , G06F16/9032 , G10L13/08
CPC分类号： G10L15/16 , G06F16/90332 , G10L13/08
摘要： Techniques for recommending a skill experience to a user after a user-system dialog session has ended are described. Upon a dialog session ending, the system uses a first machine learning model to determine potential intents to recommend to a user. The system then uses a second machine learning model to determine a particular skill and intent to recommend. The system then prompts the user to accept the recommended skill and intent. If the user accepts, the system calls the recommended skill to execute. As part of calling the skill, the system sends to the skill at least one entity provided in a natural language user input of the ended dialog session. This enables the skill to skip welcome prompts, and initiate processing to output a response based on the intent and the at least one entity of the ended dialog session.
-
-
-
-
-
-
-
-
-
搜索结果
11 条记录 (耗时 0.016 秒)
