-
公开(公告)号:US11615484B2
公开(公告)日:2023-03-28
申请号:US16998423
申请日:2020-08-20
Applicant: Meta Platforms, Inc.
Inventor: Armen Aghajanyan , Sonal Gupta , Brian Moran , Theodore Frank Levin , Crystal Annette Naomi Su Hua Nakatsu , Daniel Difranco , Jonathan David Christensen , Kirk LaBuda , Anuj Kumar
IPC: G06F40/30 , G06F9/54 , G06F40/205 , G06F40/242 , G06N3/04 , G06N3/08 , G06F16/9536 , G10L15/18 , G10L15/22 , G10L15/30 , G10L15/32 , G06F40/253 , G06N20/00 , G06F3/01 , G06Q50/00 , G06F16/9032 , G06F9/48 , G10L15/08 , H04N7/14 , H04L67/306 , G06V20/20 , G06V20/30 , H04L51/52 , H04L51/212 , H04L67/75 , G06F9/451 , G06F16/332 , G06F40/35 , G10L15/06 , G10L15/16 , G06F18/2321 , G06N3/045 , G06N3/047 , G06V10/764 , G06V10/82 , G06V10/20 , G06F3/16 , G06V20/40 , G06V40/16
Abstract: In one embodiment, a method includes receiving a user input comprising a natural-language utterance by an assistant xbot from a client system associated with a user, determining a semantic representation of the user input based on a structural ontology defining a labeling syntax for parsing the natural-language utterance to semantic units comprising actions, objects, and attributes, wherein the semantic representation embeds at least one object within at least one action and declares at least one attribute of the embedded object to be acted upon, sending a request based on the semantic representation to an agent for executing a task corresponding to the user input, receiving results of the executed task mapped to a structure determined by the structural ontology from the agent, and sending from the assistant xbot to the client system instructions for presenting a response based on the results of the executed task.
-
公开(公告)号:US11586823B2
公开(公告)日:2023-02-21
申请号:US16998423
申请日:2020-08-20
Applicant: Meta Platforms, Inc.
Inventor: Armen Aghajanyan , Sonal Gupta , Brian Moran , Theodore Frank Levin , Crystal Annette Naomi Su Hua Nakatsu , Daniel Difranco , Jonathan David Christensen , Kirk LaBuda , Anuj Kumar
IPC: G06F40/30 , G06F9/54 , G06F40/205 , G06F40/242 , G06N3/04 , G06N3/08 , G06F16/9536 , G10L15/18 , G10L15/22 , G10L15/30 , G10L15/32 , G06F40/253 , G06N20/00 , G06F3/01 , G06Q50/00 , G06F16/9032 , G06F9/48 , G10L15/08 , H04N7/14 , H04L67/306 , G06V10/20 , G06V20/20 , G06V20/30 , G06V20/40 , G06V40/16 , H04L51/52 , H04L51/212 , H04L67/75 , G06F9/451 , G06F16/332 , G06F40/35 , G06K9/62 , G10L15/06 , G10L15/16 , G06F3/16
Abstract: In one embodiment, a method includes receiving a user input comprising a natural-language utterance by an assistant xbot from a client system associated with a user, determining a semantic representation of the user input based on a structural ontology defining a labeling syntax for parsing the natural-language utterance to semantic units comprising actions, objects, and attributes, wherein the semantic representation embeds at least one object within at least one action and declares at least one attribute of the embedded object to be acted upon, sending a request based on the semantic representation to an agent for executing a task corresponding to the user input, receiving results of the executed task mapped to a structure determined by the structural ontology from the agent, and sending from the assistant xbot to the client system instructions for presenting a response based on the results of the executed task.
-
公开(公告)号:US11688022B2
公开(公告)日:2023-06-27
申请号:US16998423
申请日:2020-08-20
Applicant: Meta Platforms, Inc.
Inventor: Armen Aghajanyan , Sonal Gupta , Brian Moran , Theodore Frank Levin , Crystal Annette Naomi Su Hua Nakatsu , Daniel Difranco , Jonathan David Christensen , Kirk LaBuda , Anuj Kumar
IPC: G06F40/30 , G06F9/54 , G06F40/205 , G06F40/242 , G06N3/04 , G06N3/08 , G06F16/9536 , G10L15/18 , G10L15/22 , G10L15/30 , G10L15/32 , G06F40/253 , G06N20/00 , G06F3/01 , G06Q50/00 , G06F16/9032 , G06F9/48 , G10L15/08 , H04N7/14 , H04L67/306 , G06F9/451 , G06F16/332 , G06F40/35 , G06F40/56 , G06V20/20 , G06V10/82 , G06V40/16 , G06V20/30 , G06V10/20 , G06V10/764 , G06V20/00 , G06V40/20 , H04L51/222 , H04L51/224 , H04L51/52 , H04L51/212 , H04L67/75 , G06N3/047 , G06N3/045 , G06F18/2321 , G06Q10/109 , G10L15/06 , G10L15/16 , H04L51/18 , G06V20/40 , G06F3/16
CPC classification number: G06Q50/01 , G06F3/011 , G06F3/013 , G06F9/453 , G06F9/485 , G06F9/4881 , G06F9/547 , G06F16/3329 , G06F16/90332 , G06F16/9536 , G06F18/2321 , G06F40/205 , G06F40/242 , G06F40/253 , G06F40/30 , G06F40/35 , G06F40/56 , G06N3/045 , G06N3/047 , G06N3/08 , G06N20/00 , G06Q10/109 , G06V10/255 , G06V10/764 , G06V10/82 , G06V20/00 , G06V20/20 , G06V20/30 , G06V40/16 , G06V40/25 , G10L15/063 , G10L15/08 , G10L15/16 , G10L15/1815 , G10L15/1822 , G10L15/22 , G10L15/30 , G10L15/32 , H04L51/18 , H04L51/212 , H04L51/222 , H04L51/224 , H04L51/52 , H04L67/306 , H04L67/75 , H04N7/147 , G06F3/017 , G06F3/167 , G06V20/41 , G06V40/174 , G06V2201/10 , G10L2015/088 , G10L2015/223 , G10L2015/227
Abstract: In one embodiment, a method includes receiving a user input comprising a natural-language utterance by an assistant xbot from a client system associated with a user, determining a semantic representation of the user input based on a structural ontology defining a labeling syntax for parsing the natural-language utterance to semantic units comprising actions, objects, and attributes, wherein the semantic representation embeds at least one object within at least one action and declares at least one attribute of the embedded object to be acted upon, sending a request based on the semantic representation to an agent for executing a task corresponding to the user input, receiving results of the executed task mapped to a structure determined by the structural ontology from the agent, and sending from the assistant xbot to the client system instructions for presenting a response based on the results of the executed task.
-
公开(公告)号:US11651449B2
公开(公告)日:2023-05-16
申请号:US16998423
申请日:2020-08-20
Applicant: Meta Platforms, Inc.
Inventor: Armen Aghajanyan , Sonal Gupta , Brian Moran , Theodore Frank Levin , Crystal Annette Naomi Su Hua Nakatsu , Daniel Difranco , Jonathan David Christensen , Kirk LaBuda , Anuj Kumar
IPC: G06F40/30 , G06F9/54 , G06F40/205 , G06F40/242 , G06N3/04 , G06N3/08 , G06F16/9536 , G10L15/18 , G10L15/22 , G10L15/30 , G10L15/32 , G06F40/253 , G06N20/00 , G06F3/01 , G06Q50/00 , G06F16/9032 , G06F9/48 , G10L15/08 , H04N7/14 , H04L67/306 , G06V20/20 , G06V20/30 , H04L51/52 , H04L51/212 , H04L67/75 , G06F9/451 , G06F16/332 , G06F40/35 , G10L15/06 , G10L15/16 , G06F18/2321 , G06N3/045 , G06N3/047 , G06V10/764 , G06V10/82 , G06V10/20 , G06F40/56 , H04L51/18 , G06F3/16 , G06V20/40 , G06V40/16
CPC classification number: G06Q50/01 , G06F3/011 , G06F3/013 , G06F9/453 , G06F9/485 , G06F9/4881 , G06F9/547 , G06F16/3329 , G06F16/90332 , G06F16/9536 , G06F18/2321 , G06F40/205 , G06F40/242 , G06F40/253 , G06F40/30 , G06F40/35 , G06F40/56 , G06N3/045 , G06N3/047 , G06N3/08 , G06N20/00 , G06V10/255 , G06V10/764 , G06V10/82 , G06V20/20 , G06V20/30 , G10L15/063 , G10L15/08 , G10L15/16 , G10L15/1815 , G10L15/1822 , G10L15/22 , G10L15/30 , G10L15/32 , H04L51/18 , H04L51/212 , H04L51/52 , H04L67/306 , H04L67/75 , H04N7/147 , G06F3/017 , G06F3/167 , G06V20/41 , G06V40/174 , G06V2201/10 , G10L2015/088 , G10L2015/223 , G10L2015/227
Abstract: In one embodiment, a method includes receiving a user input comprising a natural-language utterance by an assistant xbot from a client system associated with a user, determining a semantic representation of the user input based on a structural ontology defining a labeling syntax for parsing the natural-language utterance to semantic units comprising actions, objects, and attributes, wherein the semantic representation embeds at least one object within at least one action and declares at least one attribute of the embedded object to be acted upon, sending a request based on the semantic representation to an agent for executing a task corresponding to the user input, receiving results of the executed task mapped to a structure determined by the structural ontology from the agent, and sending from the assistant xbot to the client system instructions for presenting a response based on the results of the executed task.
-
公开(公告)号:US20220415320A1
公开(公告)日:2022-12-29
申请号:US17745671
申请日:2022-05-16
Applicant: Meta Platforms, Inc.
Inventor: Pujie Zheng , Lin Sun , Ram Kumar Hariharan , Haidong Wang , Joshua Saylor McMullen , Mengxi Li , Long You Cai , Keith Diedrick , Crystal Annette Nakatsu Sung , Xi Chen , Stanislav Peshterliev , Debojeet Chatterjee , Sonal Gupta , Vikas Seshagiri Rao Bhardwaj , Yashar Mehdad , Anuj Kumar , Ashish Garg , Justin Denney , Hakan Inan , Iaroslav Markov , Surya Teja Appini , Bing Liu , Shusen Liu , Zhiqi Wang , Alexander Kolmykov-Zotov
Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.
-
-
-
-