公开(公告)号：US20200090652A1

公开(公告)日：2020-03-19

申请号：US16576020

申请日：2019-09-19

申请人： SAMSUNG ELECTRONICS CO., LTD.

发明人： Inchul HWANG ,  Dohee Kang ,  Seungyoun Kim ,  Dongchul Ma ,  Minkyu Park ,  Daegeun Yi ,  Dohun Cha

IPC分类号： G10L15/22 ,  G10L15/18 ,  G10L13/02 ,  G10L13/08 ,  G10L15/26 ,  G06F3/16

摘要： Provided are an artificial intelligence (AI) system that utilizes a machine learning algorithm such as deep learning, etc., and an application of the AI system. A method performed by a device for providing a voice assistant service through a voice assistant program includes: receiving, from an external device, a character specialized model for the voice assistant program; receiving a user voice input including a request for a response of the voice assistant program and a word indicating a character; determining the character specialized model according to the word indicating the character; generating a response message to the request for the response of the voice assistant program, using the character specialized model; and outputting the generated response message.

公开(公告)号：US11848012B2

公开(公告)日：2023-12-19

申请号：US16576020

申请日：2019-09-19

申请人： SAMSUNG ELECTRONICS CO., LTD.

发明人： Inchul Hwang ,  Dohee Kang ,  Seungyoun Kim ,  Dongchul Ma ,  Minkyu Park ,  Daegeun Yi ,  Dohun Cha

IPC分类号： G10L15/22 ,  G06F3/16 ,  G10L13/02 ,  G10L13/08 ,  G10L15/18 ,  G10L15/26

CPC分类号： G10L15/22 ,  G06F3/167 ,  G10L13/02 ,  G10L13/08 ,  G10L15/1815 ,  G10L15/26

摘要： Provided are an artificial intelligence (AI) system that utilizes a machine learning algorithm such as deep learning, etc., and an application of the AI system. A method performed by a device for providing a voice assistant service through a voice assistant program includes: receiving, from an external device, a character specialized model for the voice assistant program; receiving a user voice input including a request for a response of the voice assistant program and a word indicating a character; determining the character specialized model according to the word indicating the character; generating a response message to the request for the response of the voice assistant program, using the character specialized model; and outputting the generated response message.