Method for responding to user utterance and electronic device for supporting same

Patent metadata

Field	Value
Publication number	US-11631406-B2
Application number	US-201916960764-A
Country	US
Kind code	B2
Filing date	Jan 21, 2019
Priority date	Jan 25, 2018
Publication date	Apr 18, 2023
Grant date	Apr 18, 2023

Abstract

In an embodiment of the disclosure, disclosed is an electronic device including a communication module, a microphone, a first and a second wake-up recognition module, a memory, and a processor. The processor is configured to receive a first user utterance through the microphone, recognize the first user utterance based on at least one of the first or the second wake-up recognition module, when the recognized first user utterance includes specified at least one first trigger information, record at least part of the first user utterance by activating the recording function, transmit recorded data to an external device, and receive at least one of second user utterance information, which is predicted to occur at a time after the function of the speech recognition service is activated by the first wake-up recognition module, or at least one response information associated with the second user utterance from the external device.

First claim

The invention claimed is:

1. An electronic device supporting a speech recognition service, the electronic device comprising:
a communication module configured to communicate with at least one external device;
a microphone configured to receive a voice input according to a user utterance;
a first wake-up recognition module configured to activate a function of the speech recognition service;
a second wake-up recognition module configured to activate a recording function for the user utterance;
a memory configured to store at least one trigger information associated with activation of the function of the speech recognition service or the recording function; and
a processor electrically connected to the communication module, the microphone, the first wake-up recognition module, the second wake-up recognition module, and the memory,
wherein the processor is configured to:
receive a first user utterance through the microphone,
recognize the first user utterance based on at least one of the first wake-up recognition module or the second wake-up recognition module,
when the recognized first user utterance includes at least one first trigger information, record at least part of the first user utterance by activating the recording function, transmit recorded data through the communication module to a first external device supporting an operation of the speech recognition service, and receive at least one of second user utterance information, which is predicted to occur at a time after the function of the speech recognition service is activated by the first wake-up recognition module, or at least one response information associated with the second user utterance from the first external device through the communication module,
when receiving a third user utterance at the time after the function of the speech recognition service is activated, compare the third user utterance with the second user utterance information received from the first external device,
when the third user utterance corresponds to the second user utterance information received from the first external device by more than a specified ratio, output the at least one response information, and
receive at least one parameter information required to perform a task associated with the second user utterance, from the first external device through the electronic device, and obtain at least one content associated with execution of the task based on the at least one parameter information from at least one second external device.

2. The electronic device of claim 1 , wherein the processor is configured to:
store at least one of the second user utterance information, the at least one response information, or the at least one content in a specified cache memory.

3. The electronic device of claim 2 , wherein the processor is configured to:
when the third user utterance does not correspond to the second user utterance information received from the first external device by more than a specified ratio, delete at least one of the second user utterance information, the at least one response information, or the at least one content from the cache memory.

4. The electronic device of claim 1 , further comprising:
a display; and
at least one speaker,
wherein the processor is configured to:
output at least one of the at least one response information or the at least one content through at least one of the display or the at least one speaker.

5. The electronic device of claim 1 , wherein the processor is configured to:
set the first trigger information in response to user control; or
set information, which is included on a history of the recorded user utterance by more than a specified threshold quantity, as the first trigger information to store the first trigger information.

6. The electronic device of claim 1 , wherein the processor is configured to:
perform talker recognition on the first user utterance; and
maintain or stop recording for at least part of the first user utterance, based on the result of performing the talker recognition.

7. The electronic device of claim 1 , wherein the processor is configured to:
in the recording of at least part of the first user utterance, when receiving a sound output from at least one third external device, stop recording for at least part of the first user utterance.

8. A user utterance response method of an electronic device supporting a speech recognition service, the method comprising:
receiving a first user utterance;
recognizing the first user utterance;
when the recognized first user utterance includes at least one first trigger information, recording at least part of the first user utterance, by activating a recording function included in the electronic device;
transmitting recorded data to a first external device supporting an operation of the speech recognition service;
receiving at least one of second user utterance information, which is predicted to occur at a time after a function of the speech recognition service is activated on the electronic device, or at least one response information associated with the second user utterance from the first external device;
receiving a third user utterance at the time after the function of the speech recognition service is activated;
comparing the third user utterance with the second user utterance information received from the first external device;
when the third user utterance corresponds to the second user utterance information received from the first external device by more than a specified ratio, outputting the at least one response information,
receiving at least one parameter information required to perform a task associated with the second user utterance, from the first external device through the electronic device; and
obtaining at least one content associated with execution of the task based on the at least one parameter information from at least one second external device.

9. The method of claim 8 , further comprising at least one of:
setting the first trigger information in response to user control; or
setting information, which is included on a history of the recorded user utterance by more than a specified threshold quantity, as the first trigger information.

10. The method of claim 8 , wherein recognizing the first user utterance includes:
performing talker recognition on the first user utterance; and
maintaining or stopping recording for at least part of the first user utterance based on the result of performing the talker recognition.

11. The method of claim 8 , wherein recording the at least part of the first user utterance includes:
when receiving a sound output from at least one third external device, stopping recording for at least part of the first user utterance.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Kim Yongho
• Chun Taeksoo
• Kim Sunah
• Lee Boram
• Cho Kyoungsun
• Joo Gahyun

Classifications

• G06F3/167

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

• G10L15/22 Primary

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

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• Y02D30/70

  in wireless communication networks · CPC title