Activating voice assistant based on at least one of user proximity and context

• US 10,621,992 B2
• Filed: 07/22/2016
• Issued: 04/14/2020
• Est. Priority Date: 07/22/2016
• Status: Active Grant

• Current Assignee: Lenovo PC International Limited (Lenovo Group Ltd.)
• Original Assignee: Lenovo Singapore Pte Limited (Lenovo Group Ltd.)
• Inventors: Qian, Ming, Wang, Song, Nicholson, John Weldon
• Primary Examiner(s): Kim, Jonathan C
• Application Number:
  US15/217,426
• Publication Number:
  US 20180025733A1
• Time in Patent Office: 1,362 Days
• Field of Search: None
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10

Abstract

In one aspect, a device includes a processor, a microphone accessible to the processor, and storage accessible to the processor. The storage bears instructions executable by the processor to, without receiving a user command to enter voice recognition mode, automatically activate the microphone responsive to a determination based on a proximity signal that a user is proximate to the device.

Claims

1. A device, comprising:

at least one processor;

a microphone accessible to the at least one processor; and

storage accessible to the at least one processor and bearing instructions executable by the at least one processor to;

without receiving a user command to enter voice recognition mode and based on a setting being enabled to activate the microphone and a voice assistant module (VAM) based on biometric information related to a user, automatically activate the microphone and the VAM based on predicted sleep times and predicted wake up times determined from the biometric information, the biometric information indicating at least one respective sleep time and/or at least one respective wake up time of the user;

wherein the instructions are executable to;

predict a first sleep time and a first wake up time of the user using a machine learning algorithm and data from a biometric sensor in communication with the device, the data related to a biometric of the user;

based on the setting being enabled, automatically deactivate the microphone and the VAM based on the first sleep time of the user; and

based on the setting being enabled, automatically activate the microphone and the VAM based on the first wake up time of the user.

2. The device of claim 1, wherein the instructions are executable by the at least one processor to:

without receiving a user command to enter voice recognition mode, automatically activate the microphone based on a determination that the user is proximate to the device.

3. The device of claim 2, wherein the instructions are executable by the at least one processor to:

without receiving a user command to enter voice recognition mode, automatically activate the microphone based on the determination that the user is proximate to the device and that a user context test is satisfied, the user context test being satisfied at least in part based on input to launch an application.

4. The device of claim 3, wherein the instructions are executable by the at least one processor to:

without receiving a user command to enter voice recognition mode, automatically deactivate the microphone and/or maintain deactivated the microphone based on the determination that the user is proximate to the device and that the user context test is not satisfied.

5. The device of claim 1, wherein the instructions are executable to:

without receiving a user command to enter voice recognition mode, automatically activate the microphone based on identification of a first entry in an electronic calendar; and

decline to automatically activate the microphone based on identification of a second entry in the electronic calendar, the second entry being different from the first entry.

6. The device of claim 5, wherein the second entry relates to a meeting or workout.

7. The device of claim 6, wherein the first entry relates to work or study.

8. The device of claim 5, wherein the first entry relates to work or study.

9. The device of claim 1, wherein the instructions are executable to:

without receiving a user command to enter voice recognition mode, automatically activate the microphone responsive to input to send a text message.

10. The device of claim 1, wherein the instructions are executable to:

present a user interface (UI) on a display accessible to the at least one processor, the UI comprising a selector that is selectable to enable the setting.

11. A computer readable storage medium (CRSM) that is not a transitory signal, the computer readable storage medium comprising instructions executable by a processor of a device to:

based on a setting being enabled to activate at least one microphone and a voice assistant module (VAM) not by a key word being spoken or button press but based on biometric information related to a user, automatically activate the at least one microphone and the VAM based on predicted sleep times and predicted wake up times determined from the biometric information, the biometric information indicating at least one respective sleep time and/or at least one respective wake up time of the user;

wherein the instructions are executable to;

predict a first sleep time and a first wake up time of the user using a machine learning algorithm and data from a biometric sensor, the data related to a biometric of the user;

based on the setting being enabled, automatically deactivate the at least one microphone and the VAM based on the first sleep time of the user; and

based on the setting being enabled, automatically activate the at least one microphone and the VAM based on the first wake up time of the user.

12. The CRSM of claim 11, wherein the instructions are executable to:

present a user interface (UI) on a display accessible to the at least one processor, the UI comprising a selector that is selectable to enable the setting.

13. The CRSM of claim 11, wherein the instructions are executable to:

activate the at least one microphone, not by a key word being spoken or button press, but based on identification of a first entry in an electronic calendar; and

decline to activate the at least one microphone based on identification of a second entry in the electronic calendar, the second entry being different from the first entry.

14. The CRSM of claim 13, wherein the second entry relates to a meeting or workout.

15. The CRSM of claim 14, wherein the first entry relates to work or study.

16. The CRSM of claim 11, wherein the instructions are executable to:

activate the at least one microphone, not by a key word being spoken or button press, but responsive to input to send a text message.

17. A method, comprising:

based on a setting of a device being enabled to activate at least one microphone and a voice assistant module (VAM) based on biometric information related to a user, automatically activating the at least one microphone and the VAM based on predicted sleep times and predicted wake up times determined from the biometric information, the biometric information indicating at least one respective sleep time and/or at least one respective wake up time of the user;

wherein the method comprises;

predicting a first sleep time and a first wake up time of the user using a machine learning algorithm and data from a biometric sensor, the data related to a biometric of the user;

based on the setting being enabled, automatically deactivating the at least one microphone and the VAM based on the first sleep time of the user; and

based on the setting being enabled, automatically activating the at least one microphone and the VAM based on the first wake up time of the user.

18. The method of claim 17, comprising:

presenting a user interface (UI) on a display, the UI comprising a selector that is selectable to enable the setting.

19. The method of claim 17, comprising:

without receiving a user command to enter voice recognition mode, automatically activating the microphone based on identification of a first entry in an electronic calendar; and

declining to automatically activate the microphone based on identification of a second entry in the electronic calendar, the second entry being different from the first entry.

20. The method of claim 17, comprising:

without receiving a user command to enter voice recognition mode, automatically activating the microphone responsive to input to send a text message.