公开(公告)号：US20240119932A1

公开(公告)日：2024-04-11

申请号：US18466568

申请日：2023-09-13

Applicant: Meta Platforms, Inc.

Inventor： Mokhtar Mohamed Khorshid ,  Brian Moran ,  James Benefits McCready ,  Ahmed Kamal Atwa Mohamed ,  Katherina Nguyen ,  Gary Warren Barbon ,  Ryan Bailey ,  Irina-Elena Veliche ,  Frank Torsten Bernd Seide

IPC: G10L15/22 ,  G10L15/18 ,  G10L15/26

CPC classification number: G10L15/22 ,  G10L15/18 ,  G10L15/26 ,  G10L2015/223 ,  G10L2015/225

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.

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：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：US20230135179A1

公开(公告)日：2023-05-04

申请号：US17938561

申请日：2022-10-06

Applicant: Meta Platforms, Inc.

Inventor： Sebastian Jonathan Mielke ,  Arthur David Szlam ,  Emily Dinan ,  Y-Lan Boureau ,  Mokhtar Mohamed Khorshid ,  Jeremy Dohmann ,  Brian Moran ,  Lintao Cui ,  Jonathan Richard Goetz ,  Ahmed Kamal Atwa Mohamed ,  Paul Anthony Crook ,  Andrea Madotto ,  Shrey Desai ,  Alexander Kolmykov-Zotov ,  Jason Pazis ,  Zhaojun Yang ,  Haichuan Yang ,  Yangyang Shi ,  Biqiao Zhang ,  Ivaylo Enchev ,  Xin Lei ,  Ming Sun

IPC: G10L15/22 ,  G10L15/06 ,  G10L15/18 ,  G10L15/30 ,  G10L15/16

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.

公开(公告)号：US20230419952A1

公开(公告)日：2023-12-28

申请号：US17747345

申请日：2022-05-18

Applicant: Meta Platforms, Inc.

Inventor： Shrey Desai ,  Theodore Frank Levin ,  Brian Moran ,  Daniel Difranco ,  Alexander Kolmykov-Zotov

IPC: G10L15/06 ,  G06F40/211 ,  G06F40/30 ,  G06F40/284 ,  G06F40/40 ,  G10L15/22 ,  G10L15/18 ,  G10L15/30

CPC classification number: G10L15/063 ,  G06F40/211 ,  G06F40/30 ,  G10L15/30 ,  G06F40/40 ,  G10L15/22 ,  G10L15/1815 ,  G06F40/284

Abstract: In one embodiment, a method includes receiving a request to train a natural-language understanding (NLU) model for a new domain, accessing a context-free grammar associated with the new domain, wherein the context-free grammar defines production rules with respect to ontology tokens associated with the new domain and utterance tokens for generating natural-language strings in the new domain, generating utterance-frame pairs based on traversing a hierarchical grammar tree associated with the context-free grammar based on the production rules, wherein each utterance-frame pair comprises an utterance and a corresponding frame, wherein each frame comprises ontology tokens associated with the new domain and utterance tokens corresponding to one or more of the ontology tokens of the frame, and training the NLU model based on the utterance-frame pairs.

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.