Monitoring routines and providing reminders

Patent metadata

Field	Value
Publication number	US-10942833-B2
Application number	US-201916245855-A
Country	US
Kind code	B2
Filing date	Jan 11, 2019
Priority date	Jan 11, 2019
Publication date	Mar 9, 2021
Grant date	Mar 9, 2021

Abstract

A computer system, computer program product and computer-implemented method for performing a task. The computer system includes a sensor and a processor. The sensor is attachable to an article and is sensitive to a parameter indicative of a pattern of use of the article. The processor is configured to: determine a standard pattern of use of the article from a measurement of the parameter obtained during a training period, determine a tracked pattern of use of the article from a measurement of the parameter obtained during a tracking period, and generate a reminder to perform the task when the tracked pattern of use deviates from the standard pattern of use. A device receives the reminder in order to presenting the reminder to a user.

First claim

What is claimed is:

1. A computer-implemented method for performing a task, the computer-implemented method comprising:
measuring, via a sensor attached to an article, a parameter during a training period using a processor, the parameter indicative of a pattern of use of the article;
determining, from the parameter, a standard pattern of use of the article from a measurement of the parameter during the training period using the processor, the standard pattern of use determined based, at least in part on, executing a machine learning algorithm that learns the standard pattern via mapping of the measurement of the parameter during the training period;
measuring, via the processor, the parameter during a tracking period;
determining, via the processor, a tracked pattern of use of the article during the tracking period from a measurement of the parameter during the tracking period;
determining, via the processor, the tracked pattern deviates from the standard pattern of use and a deviation time period during which the tracked pattern remains deviated from the standard pattern;
generating, via the processor, a reminder to perform the task in response to determining that the tracked pattern of use deviates from the standard pattern of use and the deviation time period exceeds a time threshold; and
continuing to monitor, via the processor, measurements related to the tracked pattern of use after the reminder is provided to determine compliance of a user with reminder,
wherein the processor learns the time threshold being based on a time period at which the user achieves the compliance following deviation from the standard pattern of use.

2. The computer-implemented method of claim 1 , wherein the standard pattern of use is a routine established by the user with respect to the article during the training period.

3. The computer-implemented method of claim 1 , further comprising using machine learning to determine the standard pattern of use.

4. The computer-implemented method of claim 3 further comprising changing the standard pattern of use to a new pattern of use based on results of the machine learning.

5. The computer-implemented method of claim 1 , further comprising cancelling the reminder upon instruction from the user.

6. The computer-implemented method of claim 1 , wherein the standard pattern of use is a pattern that is expected to occur at least one of: (i) hourly; (ii) daily; (iii) weekly; and (iv) monthly.

7. The computer-implemented method of claim 1 , wherein the standard pattern of use is a pattern that is expected to occur at least one of: (i) hourly; (ii) daily; (iii) weekly; and (iv) monthly.

8. The computer-implemented method of claim 1 , wherein the article is different from the user.

9. A computer system for performing a task, the system comprising:
a sensor coupled to an article, the sensor sensitive to a parameter indicative of a pattern of use of the article;
a processor configured to:
determine a standard pattern of use of the article from a measurement of the parameter obtained during a training period based, at least in part on, executing a machine learning algorithm that learns the standard pattern via mapping of the measurement of the parameter during the training period;
determine a tracked pattern of use of the article from a measurement of the parameter obtained during a tracking period;
determine the tracked pattern deviates from the standard pattern of use and a deviation time period during which the tracked pattern remains deviated from the standard pattern;
generate a reminder to perform the task in response to determining that the tracked pattern of use deviates from the standard pattern of use and the deviation time period exceeds a time threshold; and
continue to monitor measurements related to the tracked pattern of use after the reminder is provided to determine compliance of a user with reminder; and
a device receptive to the reminder for presenting the reminder to a user,
wherein the processor learns the time threshold being based on a time period at which the user achieves the compliance following deviation from the standard pattern of use.

10. The system of claim 9 , wherein the standard pattern of use is a routine established by the user with respect to the article during the training period.

11. The system of claim 9 , wherein the processor determines the standard pattern of use via a machine learning module.

12. The system of claim 11 , wherein the processor is further configured to change the standard pattern of use to a new pattern based on results obtained at the machine learning module.

13. The system of claim 9 , wherein the processor is further configured to cancel the reminder upon instruction from the user.

14. A computer program product for performing a task, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform:
measuring, via a sensor attached to an article, a parameter during a training period, the parameter indicative of a pattern of use of the article using the processor;
determining, from the parameter, a standard pattern of use of the article from a measurement of the parameter during the training period using the processor, the standard pattern of use determined based, at least in part on, executing a machine learning algorithm that learns the standard pattern via mapping of the measurement of the parameter during the training period;
measuring, via the processor, the parameter during a tracking period;
determining, via the processor, a tracked pattern of use of the article during the training period from a measurement of the parameter during the tracking period;
determining, via the processor, the tracked pattern deviates from the standard pattern of use and a deviation time period during which the tracked pattern remains deviated from the standard pattern;
generating a reminder to perform the task in response to determining that the tracked pattern of use deviates from the standard pattern of use and the deviation time period exceeds a time threshold; and
continuing, via the processor, to monitor measurements related to the tracked pattern of use after the reminder is provided to determine compliance of a user with reminder,
wherein the processor learns the time threshold being based on a time period at which the user achieves the compliance following deviation from the standard pattern of use.

15. The computer program product of claim 14 , wherein the standard pattern of use is a routine established by the user with respect to the article during the training period.

16. The computer program product of claim 14 further comprising using a machine learning process to determine the standard pattern of use.

17. The computer program product of claim 16 further comprising changing the standard pattern of use to a new pattern of use based on results of the machine learning.

18. The computer program product of claim 14 , further comprising cancelling the reminder upon instruction from the user.

Assignees

• IBM

Inventors

• Eberbach Adam
• Andres Josh
• Mehedy Lenin

Classifications

• G06F11/3072 Primary

  where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting · CPC title

• G06Q10/06311 Primary

  Scheduling, planning or task assignment for a person or group · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• H04L67/535

  Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34) · CPC title

• G06F1/163

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