Method and apparatus for voice interaction control of smart device

Patent metadata

Field	Value
Publication number	US-11037561-B2
Application number	US-201716325635-A
Country	US
Kind code	B2
Filing date	Jul 20, 2017
Priority date	Aug 15, 2016
Publication date	Jun 15, 2021
Grant date	Jun 15, 2021

Abstract

A method and apparatus for voice interaction control of a smart device, wherein the method comprises: monitoring and collecting in real time a voice signal emitted by a user of the smart device (S 11 ); conducting voice recognition to the collected voice signal (S 12 ); and according to a result of the voice recognition to the voice signal by the smart device, wakening a corresponding function of the smart device and judging whether to control the smart device to move, and if yes, acquiring a position of the user and controlling the smart device to move toward the user, to shorten a distance between the smart device and the user, and then recognizing a voice signal that the user again emits; and if not, directly according to the result of the voice recognition controlling the smart device to execute a corresponding operation (S 13 ).

First claim

What is claimed is:

1. A method for voice interaction control of a smart device, wherein the method comprises:
monitoring and collecting in real time a voice signal emitted by a user of the smart device;
conducting voice recognition to the collected voice signal; and
according to a result of the voice recognition to the voice signal by the smart device, wakening a corresponding function of the smart device and judging whether to control the smart device to move, and if yes, acquiring a position of the user and controlling the smart device to move toward the user, to shorten a distance between the smart device and the user, and then recognizing a voice signal that the user again emits; and if not, directly according to the result of the voice recognition controlling the smart device to execute a corresponding operation;
acquiring a position of the user and controlling the smart device to move toward the user comprises:
according to the collected voice signal, calculating by sound source localization to obtain position information of a sound source relative to the smart device, and according to the position information determining a distance and direction of the user relative to the smart device; and
by using the determined distance and direction of the user relative to the smart device, controlling the smart device to move toward the user.

2. The method according to claim 1 , wherein the step of acquiring a position of the user and controlling the smart device to move toward the user comprises:
controlling the smart device to move toward the user to a first preset position, wherein a distance between the first preset position and the user is less than a first distance threshold.

3. The method according to claim 2 , wherein the method further comprises:
according to a result of the voice recognition to the voice signal that the user again emits by the smart device, judging whether to control the smart device to move again, and if yes, controlling the smart device to move toward the user to a second preset position, wherein a distance between the second preset position and the user is less than a second di stance threshold.

4. The method according to claim 1 , wherein the step of conducting voice recognition to the collected voice signal comprises: recognizing out a wake-up word from the collected voice signal; and
the step of according to a result of the voice recognition to the voice signal by the smart device, wakening a corresponding function of the smart device and judging whether to control the smart device to move comprises:
when the recognized-out wake-up word matches a saved preset wake-up word, wakening a corresponding function of the smart device and controlling the smart device to move.

5. The method according to claim 1 , wherein the step of by using the determined distance and direction of the user relative to the smart device, controlling the smart device to move toward the user comprises:
determining by distance localization position coordinates of the user and current position coordinates of the smart device in an indoor space,
according to the determined position coordinates of the user and a preset first distance threshold, calculating to obtain corresponding position coordinates of the first preset position, and
by indoor navigation, generating a preset path that uses the current position coordinates of the smart device as a starting point and the corresponding position coordinates of a first preset position as an end point, and controlling in real time the smart device to move to the first preset position along the preset path and with a preset constant step length.

6. The method according to claim 1 , wherein the step of conducting voice recognition to the collected voice signal comprises: recognizing out a wake-up word and a commanding word from the collected voice signal; and
the step of according to a result of the voice recognition to the voice signal by the smart device, wakening a corresponding function of the smart device and judging whether to control the smart device to move comprises:
when the recognized-out wake-up word matches a saved preset wake-up word and the recognized-out commanding word does not match a saved preset commanding word, wakening a corresponding function of the smart device and controlling the smart device to move; and
when the recognized-out wake-up word matches a saved preset wake-up word and the recognized-out commanding word matches a saved preset commanding word, wakening a corresponding function of the smart device and according to an instruction of the commanding word controlling the smart device to execute the corresponding operation.

7. An apparatus for voice interaction control of a smart device, wherein the apparatus comprises: a processor and a computer readable medium, wherein the computer readable medium stores a computer readable code that is readable by the processor, and the processor executes the computer readable code to perform the following steps:
monitoring and collecting in real time a voice signal emitted by a user of the smart device;
conducting voice recognition to the collected voice signal; and
according to a result of the voice recognition to the voice signal by the smart device, wakening a corresponding function of the smart device and judging whether to control the smart device to move, and if yes, acquiring a position of the user and controlling the smart device to move toward the user, to shorten a distance between the smart device and the user, and then recognizing a voice signal that the user again emits; and if not, directly according to the result of the voice recognition controlling the smart device to execute a corresponding operation;
acquiring a position of the user and controlling the smart device to move toward the user further comprises:
according to the collected voice signal, calculating by sound source localization to obtain position information of a sound source relative to the smart device, and according to the position information determining a distance and direction of the user relative to the smart device; and by using the determined distance and direction of the user relative to the smart device, controlling the smart device to move toward the user.

8. The apparatus according to claim 7 , wherein acquiring a position of the user and controlling the smart device to move toward the user comprises:
controlling unit is for controlling the smart device to move toward the user to a first preset position, wherein a distance between the first preset position and the user is less than a first distance threshold.

9. The apparatus according to claim 8 , wherein the processor executes the machine executable instructions further to implement steps:
according to a result of the voice recognition to the voice signal that the user again emits by the smart device, judging whether to control the smart device to move again, and if yes, controlling the smart device to move toward the user to a second preset position, wherein a distance between the second preset position and the user is less than a second distance threshold.

10. The apparatus according to claim 7 , wherein conducting voice recognition to the collected voice signal comprises: recognizing out a wake-up word from the collected voice signal; and
according to a result of the voice recognition to the voice signal by the smart device, wakening a corresponding function of the smart device and judging whether to control the smart device to move comprises:
when the recognized-out wake-up word matches a saved preset wake-up word, wakening a corresponding function of the smart device and controlling the smart device to move.

11. The appa

Assignees

• Goertek Inc

Inventors

• Ma Honglong
• Chen Chuan
• Liu Cui

Classifications

• G06F3/167 Primary

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

• G05D1/02

  Control of position or course in two dimensions · CPC title

• G10L15/08

  Speech classification or search · CPC title

• G05D1/0242

  using non-visible light signals, e.g. IR or UV signals · CPC title

• G10L15/22 Primary

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