-
1.
公开(公告)号:US20230177263A1
公开(公告)日:2023-06-08
申请号:US18160960
申请日:2023-01-27
Applicant: Amazon Technologies, Inc.
Inventor: Saab Mansour
IPC: G06F40/232 , G06Q50/00 , G06Q30/0601 , G06N20/00 , G06N5/04 , H04L51/212
CPC classification number: G06F40/232 , G06N5/04 , G06N20/00 , G06Q30/0623 , G06Q30/0633 , G06Q50/01 , H04L51/212
Abstract: A chat input identifier may receive various chat inputs based on voice or text inputs from a user. The chat input identifier may apply different filters to the chat inputs to identify one or more chat correction pairs (e.g., chat input with errors, corrected chat input) from among the plurality of chat inputs. The chat correction pairs are used to train an auto-correction model. The trained auto-correction model receives a given chat input that has one or more errors. The auto-correction model processes the given chat input to generate a corrected version of the given chat input (without the need to obtain a correction from the user). The corrected chat input is then provided to a dialog-driven application.
-
2.
公开(公告)号:US12079571B2
公开(公告)日:2024-09-03
申请号:US18160960
申请日:2023-01-27
Applicant: Amazon Technologies, Inc.
Inventor: Saab Mansour
IPC: G06F40/232 , G06N5/04 , G06N20/00 , G06Q30/0601 , G06Q50/00 , H04L51/212
CPC classification number: G06F40/232 , G06N5/04 , G06N20/00 , G06Q30/0623 , G06Q30/0633 , G06Q50/01 , H04L51/212
Abstract: A chat input identifier may receive various chat inputs based on voice or text inputs from a user. The chat input identifier may apply different filters to the chat inputs to identify one or more chat correction pairs (e.g., chat input with errors, corrected chat input) from among the plurality of chat inputs. The chat correction pairs are used to train an auto-correction model. The trained auto-correction model receives a given chat input that has one or more errors. The auto-correction model processes the given chat input to generate a corrected version of the given chat input (without the need to obtain a correction from the user). The corrected chat input is then provided to a dialog-driven application.
-
3.
公开(公告)号:US11568135B1
公开(公告)日:2023-01-31
申请号:US17030204
申请日:2020-09-23
Applicant: Amazon Technologies, Inc.
Inventor: Saab Mansour
IPC: G06F40/232 , G06Q50/00 , G06Q30/06 , G06N20/00 , G06N5/04 , H04L51/212
Abstract: A chat input identifier may receive various chat inputs based on voice or text inputs from a user. The chat input identifier may apply different filters to the chat inputs to identify one or more chat correction pairs (e.g., chat input with errors, corrected chat input) from among the plurality of chat inputs. The chat correction pairs are used to train an auto-correction model. The trained auto-correction model receives a given chat input that has one or more errors. The auto-correction model processes the given chat input to generate a corrected version of the given chat input (without the need to obtain a correction from the user). The corrected chat input is then provided to a dialog-driven application.
-
4.
公开(公告)号:US20240394473A1
公开(公告)日:2024-11-28
申请号:US18796187
申请日:2024-08-06
Applicant: Amazon Technologies, Inc.
Inventor: Saab Mansour
IPC: G06F40/232 , G06N5/04 , G06N20/00 , G06Q30/0601 , G06Q50/00 , H04L51/212
Abstract: A chat input identifier may receive various chat inputs based on voice or text inputs from a user. The chat input identifier may apply different filters to the chat inputs to identify one or more chat correction pairs (e.g., chat input with errors, corrected chat input) from among the plurality of chat inputs. The chat correction pairs are used to train an auto-correction model. The trained auto-correction model receives a given chat input that has one or more errors. The auto-correction model processes the given chat input to generate a corrected version of the given chat input (without the need to obtain a correction from the user). The corrected chat input is then provided to a dialog-driven application.
-
公开(公告)号:US12143343B1
公开(公告)日:2024-11-12
申请号:US17532958
申请日:2021-11-22
Applicant: Amazon Technologies, Inc.
Inventor: Swaminathan Sivasubramanian , Vasanth Philomin , Ganesh Kumar Gella , Santosh Kumar Ameti , Meghana Puvvadi , Manikya Pavan Kiran Pothukuchi , Harshal Pimpalkhute , Rama Krishna Sandeep Pokkunuri , Yahor Pushkin , Roger Scott Jenke , Yaser Al-Onaizan , Yi Zhang , Saab Mansour , Salvatore Romeo
Abstract: A system receives one or more transcripts of communications between entities. The system identifies a requested action in the communications based at least in part on a mapping between the requested action and an application programming interface. The system identifies one or more statements eliciting information, based on parameters to the application programming interface. The system generates a definition of an artificial agent based, at least in part, on the requested action and the one more statements eliciting information.
-
-
-
-