-
公开(公告)号:US20180374481A1
公开(公告)日:2018-12-27
申请号:US15992906
申请日:2018-05-30
Applicant: Samsung Electronics Co., Ltd.
Inventor: Ho Jun JAYGARL , Jin Woong KIM , Jae Gun NO , Jae Young YANG
CPC classification number: G10L15/22 , G06F3/04842 , G10L15/142 , G10L15/16 , G10L15/18 , G10L15/1815 , G10L15/265 , G10L15/30 , G10L2015/223
Abstract: An electronic device is provided. The electronic device includes a housing, a speaker, a microphone, a display, a communication circuit, at least one processor operatively connected to the speaker, the microphone, the display, and the communication circuit, and a memory operatively connected to the at least one processor, and storing instructions to cause the at least one processor to receive a first user utterance, including a request to perform a task by using an application program, through the microphone, transmit first data associated with the first user utterance to an external server, receive second data including a text generated by an automatic speech recognition (ASR) module, from the external server, identify the application program based on the second data, receive a first response including information of a sequence of states of the electronic device from the external server to perform at least part of the task, and perform the at least part of the task by controlling the electronic device to enter the sequence of the states by using the application program.
-
公开(公告)号:US20190304455A1
公开(公告)日:2019-10-03
申请号:US16360347
申请日:2019-03-21
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Ho Jun JAYGARL , Jae Gun NO , Min Sung KIM , Jin Woong KIM , Jae Young YANG , Kwang Bin LEE , Jae Yung YEO , Da Som LEE
Abstract: A system includes a first electronic device configured to receive a first user input through the touchscreen display and/or the microphone, to receive a sequence of touch and/or voice-based user inputs through the touchscreen display and/or the microphone, to store the sequence of the touch and/or voice-based user inputs in the at least one memory, to receive a second user input including at least one invoke word associated with the sequence through the touchscreen display and/or the microphone, and to store the at least one invoke word in the at least one memory such that the sequence and the at least one invoke word are mapped to each other.
-