Methods and electronic devices for determining context while minimizing high-power sensor usage

Patent metadata

Field	Value
Publication number	US-11301022-B2
Application number	US-201815913467-A
Country	US
Kind code	B2
Filing date	Mar 6, 2018
Priority date	Mar 6, 2018
Publication date	Apr 12, 2022
Grant date	Apr 12, 2022

Abstract

An electronic device includes one or more low-power context sensors, one or more high-power context sensors, and one or more processors operable with the one or more low-power context sensors and the one or more high-power context sensors. The one or more processors, working with context engines associated with the sensors, minimize usage of the high-power context sensors when determining a context of the electronic device, where that determined context has a confidence score above a predefined confidence level threshold.

First claim

What is claimed is:

1. A method in an electronic device comprising one or more low-power context sensors, one or more high-power context sensors, and one or more processors operable with the one or more low-power context sensors and the one or more high-power context sensors, the method comprising minimizing, with the one or more processors, usage of the one or more high-power context sensors when determining a context of the electronic device, where the context has a confidence score above a predefined confidence level threshold, wherein the minimizing comprises:
selecting, with the one or more processors, a set of at least two of the one or more low-power context sensors;
receiving input from each low-power context sensor of the set of at least two of the one or more low-power context sensors; and
determining, with a context engine operable with the one or more processors, a sensor context determination confidence score for the context from the input for each low-power context sensor of the set of at least two of the one or more low-power context sensors; and
determining, with the context engine, at least one other sensor context determination confidence score for at least one other context from the input for each low-power context sensor of the one or more low-power context sensors;
determining whether the sensor context determination confidence score from a first low-power context sensor and from a second low-power context sensor are above the predefined confidence level threshold; and
also determining whether a difference of the sensor context determination confidence score from the first low-power context sensor and from the second low-power context sensor is within a predefined confidence level difference threshold;
wherein the predefined confidence level threshold is defined by a first percentage and the predefined conference level difference threshold is defined by a second percentage that is less than the first percentage; and
further comprising identifying, with the one or more processors, the input and as indicating a correctly identified context when both:
the sensor context determination confidence score from the first low-power context sensor and from the second low-power context sensor are both above seventy-five percent; and
the difference of the sensor context determination confidence score from the first low-power context sensor and from the second low- power context sensor is within ten percent the predefined confidence level difference threshold.

2. The method of claim 1 , wherein the minimizing further comprises:
aggregating each sensor context determination score to obtain the confidence score; and
determining whether the confidence score exceeds the predefined confidence level threshold.

3. The method of claim 2 , further comprising identifying, with the one or more processors, the input as indicating a correctly identified context when the confidence score exceeds the predefined confidence level threshold.

4. The method of claim 2 , wherein when the confidence score is below the predefined confidence level threshold the minimizing further comprises:
actuating, with the one or more processors, at least one high-power context sensor of the one or more high-power context sensors;
receiving additional input from each high-power context sensor of the one or more high-power context sensors;
determining, with the context engine, an additional sensor context determination confidence score for each high-power context sensor of the one or more high-power context sensors;
aggregating the additional sensor context determination confidence score into the confidence score; and
again determining whether the confidence score exceeds the predefined confidence level threshold.

5. The method of claim 4 , further comprising identifying, with the one or more processors, the input and the additional input as indicating a correctly identified context when the confidence score exceeds the predefined confidence level threshold.

6. The method of claim 5 , further comprising refining a confidence score determination model at the context engine by supplementing the confidence score determination model with the confidence score of the correctly identified context.

7. The method of claim 6 , wherein the supplementing results in the context engine generating a higher sensor context determination confidence score when receiving the input.

8. The method of claim 2 , further comprising, when the confidence score fails to exceed the predefined confidence level threshold:
selecting, with the one or more processors, another low-power context sensor to increase a number of low-power context sensors of the set of the at least two of the one or more low-power context sensors;
receiving another input from the another low-power context sensor; and
determining, with the context engine, another sensor context determination confidence score for another context from the another input.

9. The method of claim 8 , wherein the minimizing further comprises:
again aggregating each sensor context determination score to again obtain the confidence score; and
again determining whether the confidence score exceeds the predefined confidence level threshold.

10. The method of claim 8 , further comprising repeating the selecting the another low-power context sensor to increase the number of low-power context sensors of the set of the at least two of the one or more low-power context sensors until all low-power sensors of the electronic device are included in the set of the at least two of the one or more low-power context sensors.

11. The method of claim 10 , further comprising actuating a high-power context sensor.

12. The method of claim 11 , wherein the high-power context sensor comprises an imager.

13. The method of claim 1 , wherein the set of the at least two of the one or more low-power context sensors comprises three or more low-power context sensors.

14. The method of claim 1 , wherein the set of at least two of the one or more low-power context sensors comprises a proximity detector.

15. The method of claim 1 , further comprising refining a confidence score determination model at the context engine by supplementing the confidence score determination model with the confidence score of the correctly identified context to improve the confidence score determination model.

16. The method of claim 1 , wherein the set of at least two of the one or more low-power context sensors comprises a geolocator.

17. The method of claim 1 , wherein the set of at least two of the one or more low-power context sensors comprises a proximity sensor.

18. The method of claim 1 , wherein the set of at least two of the one or more low-power context sensors comprises a microphone.

19. The method of claim 1 , wherein the set of at least two of the one or more low-power context sensors comprises an accelerometer.

20. The method of claim 1 , wherein the set of at least two of the one or more low-power context sensors comprises a light sensor.

Assignees

• Motorola Mobility Llc

Inventors

• Alameh Rachid
• Ji Zhengping
• Simerson Jarrett

Classifications

• G06F9/461

  Saving or restoring of program or task context · CPC title

• G06F1/1684

  Constructional details or arrangements related to integrated I/O peripherals not covered by groups G06F1/1635 - G06F1/1675 · CPC title

• H04M2250/10

  including a GPS signal receiver · CPC title

• G06F3/011

  Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00) · CPC title

• G06F3/013

  Eye tracking input arrangements (G06F3/015 takes precedence) · CPC title