公开(公告)号：US11151986B1

公开(公告)日：2021-10-19

申请号：US16138447

申请日：2018-09-21

Applicant: Amazon Technologies, Inc.

Inventor： Bigyan Rajbhandari ,  Praveen Kumar Bodigutla ,  Zhenxiang Zhou ,  Karen Catelyn Stabile ,  Chenlei Guo ,  Abhinav Sethy ,  Alireza Roshan Ghias ,  Pragaash Ponnusamy ,  Kevin Quinn

IPC: G10L15/00 ,  G10L15/18 ,  G10L15/30 ,  G10L15/22

Abstract: Techniques for decreasing (or eliminating) the possibility of a skill performing an action that is not responsive to a corresponding user input are described. A system may train one or more machine learning models with respect to user inputs, which resulted in incorrect actions being performed by skills, and corresponding user inputs, which resulted in the correct action being performed. The system may use the trained machine learning model(s) to rewrite user inputs that, if not rewritten, may result in incorrect actions being performed. The system may implement the trained machine learning model(s) with respect to ASR output text data to determine if the ASR output text data corresponds (or substantially corresponds) to previous ASR output text data that resulted in an incorrect action being performed. If the trained machine learning model(s) indicates the present ASR output text data corresponds (or substantially corresponds) to such previous ASR output text data, the system may rewrite the present ASR output text data to correspond to text data representing a rephrase of the user input that will (or is more likely to) result in a correct action being performed.

公开(公告)号：US11862149B2

公开(公告)日：2024-01-02

申请号：US17464755

申请日：2021-09-02

Applicant: Amazon Technologies, Inc.

Inventor： Bigyan Rajbhandari ,  Praveen Kumar Bodigutla ,  Zhenxiang Zhou ,  Karen Catelyn Stabile ,  Chenlei Guo ,  Abhinav Sethy ,  Alireza Roshan Ghias ,  Pragaash Ponnusamy ,  Kevin Quinn

IPC: G10L15/00 ,  G10L15/18 ,  G10L15/30 ,  G10L15/22

CPC classification number: G10L15/1815 ,  G10L15/22 ,  G10L15/30 ,  G10L2015/223

Abstract: Techniques for decreasing (or eliminating) the possibility of a skill performing an action that is not responsive to a corresponding user input are described. A system may train one or more machine learning models with respect to user inputs, which resulted in incorrect actions being performed by skills, and corresponding user inputs, which resulted in the correct action being performed. The system may use the trained machine learning model(s) to rewrite user inputs that, if not rewritten, may result in incorrect actions being performed. The system may implement the trained machine learning model(s) with respect to ASR output text data to determine if the ASR output text data corresponds (or substantially corresponds) to previous ASR output text data that resulted in an incorrect action being performed. If the trained machine learning model(s) indicates the present ASR output text data corresponds (or substantially corresponds) to such previous ASR output text data, the system may rewrite the present ASR output text data to correspond to text data representing a rephrase of the user input that will (or is more likely to) result in a correct action being performed.

公开(公告)号：US20220059086A1

公开(公告)日：2022-02-24

申请号：US17464755

申请日：2021-09-02

Applicant: Amazon Technologies, Inc.

Inventor： Bigyan Rajbhandari ,  Praveen Kumar Bodigutla ,  Zhenxiang Zhou ,  Karen Catelyn Stabile ,  Chenlei Guo ,  Abhinav Sethy ,  Alireza Roshan Ghias ,  Pragaash Ponnusamy ,  Kevin Quinn

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

Abstract: Techniques for decreasing (or eliminating) the possibility of a skill performing an action that is not responsive to a corresponding user input are described. A system may train one or more machine learning models with respect to user inputs, which resulted in incorrect actions being performed by skills, and corresponding user inputs, which resulted in the correct action being performed. The system may use the trained machine learning model(s) to rewrite user inputs that, if not rewritten, may result in incorrect actions being performed. The system may implement the trained machine learning model(s) with respect to ASR output text data to determine if the ASR output text data corresponds (or substantially corresponds) to previous ASR output text data that resulted in an incorrect action being performed. If the trained machine learning model(s) indicates the present ASR output text data corresponds (or substantially corresponds) to such previous ASR output text data, the system may rewrite the present ASR output text data to correspond to text data representing a rephrase of the user input that will (or is more likely to) result in a correct action being performed.