Voice input processing method and electronic device supporting same

Patent metadata

Field	Value
Publication number	US-11961508-B2
Application number	US-202017097046-A
Country	US
Kind code	B2
Filing date	Nov 13, 2020
Priority date	Nov 15, 2019
Publication date	Apr 16, 2024
Grant date	Apr 16, 2024

Abstract

An electronic device and method are disclosed. The electronic device includes a microphone, a speaker and a processor. The processor implements the method, including: receiving a first voice input through the microphone, outputting a response related to a function through the speaker, based on the first voice input, when a second voice input is received through the microphone during output of the response, interrupting the output of the response and continue to receive the second voice input, and executing the function based on content of the received second voice input and content of the response output up to one of: a first time point when the second voice input was initially received, and a second time point when the output of the response was interrupted.

First claim

What is claimed is:

1. An electronic device, comprising:
a microphone;
a speaker; and
a processor,
wherein the processor is configured to:
receive a first voice input through the microphone;
output a response to the first voice input related to a function through the speaker, based on the first voice input, wherein the response includes a plurality of optional elements that are output in a consecutive sequence of turns;
when a second voice input is received through the microphone during output of the response so that two or more of the plurality of optional elements are output, interrupt the output of the response and continue to receive the second voice input;
based on the second voice input, select one of a first optional element currently being output upon the second voice input being received and a second optional element as a last optional element output before the first optional element among the two or more of the plurality of optional elements, and determine whether selection of one of the first optional element and the second optional element is successful;
when the selection of the one of the first optional element and the second optional element is successful, output a response for notifying one optional element to be executed among the two or more of the plurality of optional elements;
when the selection of the one of the first optional element and the second optional element is not successful, output an audio prompt comprising at least part of the first optional element and the second optional element for requesting to specify one optional element to be executed, receive a third voice input for specifying the one optional element; and
execute the function on an object associated with the one optional element.

2. The electronic device of claim 1 , wherein, when text data generated from the second voice input lacks text data related to the function, the processor is configured to maintain the outputting of the response through the speaker.

3. The electronic device of claim 1 ,
wherein the processor is configured to:
receive, through the microphone, a fourth voice input at a time point prior to a time point when the second voice input was initially received, while a first optional element among the plurality of optional elements is output at a designated turn in the consecutive sequence of turns;
interrupt the output of the response at the time point when the fourth voice input is received;
when text data generated from the fourth voice input indicates a previous turn rather than the designated turn, output the second optional element; and
when the text data generated from the fourth voice input indicates a next turn rather than the designated turn, output a third optional element corresponding to the next turn in the consecutive sequence of turns from among the plurality of optional elements.

4. The electronic device of claim 1 , wherein the response includes a request for information related to executing the function, and
wherein the processor is configured to:
when text data generated from the second voice input includes the requested information, configure the information using at least a part of the generated text data.

5. The electronic device of claim 1 , wherein the response includes a request to confirm execution of the function, and
wherein the processor is configured to execute the function when text data generated from the second voice input indicates confirmation of the execution.

6. The electronic device of claim 1 , wherein, when text data generated from the second voice input requests execution of a connected function associated with the function, the processor is configured to execute the connected function.

7. The electronic device of claim 1 , wherein the processor is configured to output, through the speaker, an audio prompt request confirmation of whether to continue outputting the response, when insufficient information for execution of the function is acquired.

8. A method in an electronic device, the method comprising:
receiving a first voice input through a microphone;
outputting a response to the first voice input related to a function through a speaker, based on the first voice input, wherein the response includes a plurality of optional elements that are output in a consecutive sequence of turns;
when a second voice input is received through the microphone during output of the response so that two or more of the plurality of optional elements are output, interrupting the output of the response and continuing to receive the second voice input; and
based on the second voice input, selecting one of a first optional element currently being output upon the second voice input being received and a second optional element as a last optional element output before the first optional element among the two or more of the plurality of optional elements, and determining whether selection of the one of the first optional element and the second optional element is successful;
when the selection of the one of the first optional element and the second optional element is successful, outputting a response for notifying one optional element to be executed among the two or more of the plurality of optional elements;
when the selection of the one of the first optional element and the second optional element is not successful, outputting an audio prompt comprising at least part of the first optional element and the second optional element for requesting to specify one optional element to be executed, and receiving a third voice input for specifying the one optional element;
executing the function on an object associated with the one optional element.

9. The method of claim 8 , wherein, when text data generated from the second voice input lacks text data related to the function, the output of the response through the speaker is maintained.

10. The method of claim 8 , further comprising:
receiving, through the microphone, a fourth voice input at a time point prior to a time point when the second voice input was initially received, while a first optional element among the plurality of optional elements is output at a designated turn in the consecutive sequence of turns;
interrupting output of the response at the time point when the fourth voice input is received;
when text data generated from the fourth voice input indicates a previous turn rather than the designated turn, outputting the second optional element; and
when the text data generated from the fourth voice input indicates a next turn rather than the designated turn, outputting a third optional element corresponding to the next turn in the consecutive sequence of turns from among the plurality of optional elements.

11. The method of claim 8 , wherein the response includes a request for information related to executing the function, the method further comprising:
when text data generated from the second voice input includes the requested information, configuring the information using at least a part of the generated text data.

12. The method of claim 8 , wherein the response includes a request to confirm execution of the function, the method further comprising:
executing the function when text data generated from the second voice input indicates confirmation of the execution of the function.

13. The method of claim 8 , further comprising:
when text data generated from the second voice input includes text data requesting execution of a connected function associated with the function, executing the connected function.

14. The method of claim 8 , further comprising:
outputting, through the speaker, an audio prompt requesting c

Assignees

• Samsung Electronics Co Ltd

Inventors

• Choo Heeyoung
• Cho Hyunduk
• Hong Yeseul
• Lee Dayoung
• Lee Boram

Classifications

• G10L15/04 Primary

  Segmentation; Word boundary detection · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G10L15/222

  Barge in, i.e. overridable guidance for interrupting prompts · CPC title

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title