Performing an operation during inferred periods of non-use of a wearable device

Patent metadata

Field	Value
Publication number	US-9864955-B2
Application number	US-201715437130-A
Country	US
Kind code	B2
Filing date	Feb 20, 2017
Priority date	Jun 24, 2014
Publication date	Jan 9, 2018
Grant date	Jan 9, 2018

Abstract

A wearable computing device is described that predicts, based on movement detected, over time, by the wearable computing device, one or more future periods of time during which the wearable computing device will not be used. Responsive to determining that the wearable computing device is not being used at a current time, the wearable computing device determines whether the current time coincides with at least one period of time from the one or more future periods of time. Responsive to determining that the current time coincides with the at least one period of time, the wearable computing device performs an operation.

First claim

What is claimed is:

1. A method comprising:
determining, based on a movement of a wearable computing device being detected during multiple days of a sample period, a recurring period of time of day during which a frequency or a magnitude of the movement satisfies a threshold that indicates the wearable computing device was not being used;
determining, at a time after the sample period and by the wearable computing device, whether a current period of time of day, coincides with the recurring period of time of day; and
responsive to determining that the current period of time of day coincides with the recurring period of time of day and responsive to determining that an operation can be completed during the recurring period of time of day, performing, by the wearable computing device, the operation during the current period of time of day.

2. The method of claim 1 , wherein a machine learning system of the wearable computing device determines the recurring period of time of day when the wearable computing device is not being used.

3. The method of claim 2 , further comprising:
receiving, from at least one sensor of the wearable computing device, first movement data indicating a lack of movement of the wearable computing device being detected during a first period of time of a first day of the multiple days of the sample period;
receiving, from at least one sensor of the wearable computing device, second movement data indicating a lack of movement of the wearable computing device being detected during a second period of time of a second day of the multiple days of the sample period, the second day being different than the first day, wherein the second period of time of the second day corresponds to the first period of time of the first day;
identifying, by the machine learning system, based on the first movement data and the second movement data, the first period of time of the first day and the second period of time of the second day as being the recurring period of time of day when the wearable computing device is not being used; and
generating, by the machine learning system, a rule that predicts the current period of time of day to be when the wearable computing device will not be used.

4. The method of claim 3 , wherein the machine learning system of the wearable computing device determines, using the rule, whether the current period of time of day coincides with the recurring period of time of day.

5. The method of claim 3 , further comprising:
determining, by the machine learning system, based on the first movement data and the second movement data, one or more changes in a frequency or a magnitude of acceleration of wearable computing device during the first period of time of the first day and during the second period of time of the second day; and
responsive to determining that the one or more changes in the frequency or the magnitude of acceleration of wearable computing device during the first period of time of the first day and during the second period of time of the second day satisfy a threshold, identifying, by the machine learning system, the first period of time of the first day and the second period of time of the second day as coinciding with the recurring period of time of day when the wearable computing device is not being used.

6. The method of claim 1 , wherein determining the recurring period of time of day when the wearable computing device is not being used comprises determining the recurring period of time of day when the wearable computing device is not being worn.

7. The method of claim 1 , wherein performing the operation comprises outputting, for display, a security challenge graphical user interface in response to detecting future movement of the wearable computing device during the recurring period of time of day.

8. A wearable computing device comprising:
at least one sensor configured to detect movement associated with the computing device;
at least one processor;
a memory comprising instructions that, when executed, cause the at least one processor to:
determine, based on a movement of detected by the at least one sensor during multiples days of a sample period, a recurring period of time of day during which a frequency or a magnitude of the movement satisfies a threshold that indicates the wearable computing device is not being used;
determine, at a time after the sample period, whether a current period of time of day coincides with the recurring period of time of day; and
responsive to determining that the current period of time of day coincides with the recurring period of time of day and responsive to determining that an operation can be completed during the recurring period of time of day, perform the operation during the current period of time of day.

9. The wearable computing device of claim 8 , wherein the instructions, when executed, cause the at least one processor to execute a machine learning system to determine the recurring period of time of day when the wearable computing device is not being used.

10. The wearable computing device of claim 9 , wherein the instructions, when executed, further cause the at least one processor to execute the machine learning system to:
receive, from the at least one sensor, first movement data indicating a lack of movement of the wearable computing device being detected during a first period of time of a first day from the multiple days of the sample period;
receive, from the at least one sensor, second movement data indicating a lack of movement of the wearable computing device being detected during a second period of time of a second day from the multiple days of the sample period, the second day being different than the first day, wherein the second period of time of the second day corresponds to the first period of time of the first day;
identify, based on the first movement data and the second movement data, the first period of time of the first day and the second period of time of the second day as coinciding with the recurring period of time of day when the wearable computing device is not being used; and
generate a rule that predicts the current period of time of day to be when the wearable computing device will not be used.

11. The wearable computing device of claim 10 , wherein the instructions, when executed, further cause the at least one processor to execute the machine learning system to determine, using the rule, whether the current period of time of day coincides with the recurring period of time of day.

12. The wearable computing device of claim 10 , wherein the instructions, when executed, further cause the at least one processor to execute the machine learning system to:
determine, based on the first movement data and the second movement data, one or more changes in a frequency or a magnitude of acceleration of wearable computing device during the first period of time of the first day and during the second period of time of the second day; and
responsive to determining that the one or more changes in the frequency or the magnitude of acceleration of wearable computing device during the first period of time of the first day and during the second period of time of the second day satisfy a threshold, identify the first period of time of the first day and the second period of time of the second day as coinciding with the recurring period of time of day when the wearable computing device is not being used.

13. The wearable computing device of claim 8 , wherein the instructions, when executed, cause the at least one processor to determine the recurring period of time of day when the wearable computing device is not being used by determining the recurr

Assignees

• Google Inc
• Google Llc

Inventors

• Faaborg Alexander
• Chang Jeffrey Albert

Classifications

• G06F9/4843

  by program, e.g. task dispatcher, supervisor, operating system · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G06F8/65 Primary

  Updates (security arrangements therefor G06F21/57) · CPC title

• G06F1/163

  Wearable computers, e.g. on a belt · CPC title

• G06F9/46

  Multiprogramming arrangements · CPC title