Meal-based medication reminder system

• US 9,847,012 B2
• Filed: 07/07/2014
• Issued: 12/19/2017
• Est. Priority Date: 07/07/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Zomet, Asaf, Shynar, Michael
• Primary Examiner(s): PHAM, QUANG
• Application Number:
  US14/324,769
• Publication Number:
  US 20160005299A1
• Time in Patent Office: 1,261 Days
• CPC Class Codes: G08B 21/24 Reminder alarms, e.g. anti-loss alarms
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients

Abstract

In general, this disclosure is directed to techniques for generating, by a computing device, at approximately a time that a user is eating, at least one computer-generated indication. Based at least in part on the at least one computer-generated indication and pre-defined activity data that are indicative of a human consuming an ingestible substance, the computing device determines whether the user is currently consuming an ingestible substance. Responsive to determining that the user is currently consuming the ingestible substance, the computing device outputs a reminder to consume at least one particular ingestible substance, such as a medication.

Claims

1. A computing device for reminding a user to consume at least one particular ingestible substance based on a determination that the user is currently eating, the computing device comprising:

at least one processor; and

at least one module, operable by the at least one processor to;

generate, based on motion data received from one or more sensors operably coupled to the computing device, and at a time that the user is eating, at least one indication of user activity indicating one or more motions of an arm of the user, wherein the one or more sensors are located on the arm of the user;

determine, based on pre-defined motion data that is indicative of an act of a human consuming an ingestible substance and the at least one indication of user activity, a degree of confidence that indicates a confidence that the user is currently consuming the ingestible substance;

compare the degree of confidence to a threshold to determine whether the degree of confidence satisfies the threshold;

responsive to determining that the degree of confidence satisfies the threshold, determine that the user is currently consuming the ingestible substance; and

responsive to determining that the user is currently consuming the ingestible substance, output a reminder to consume the at least one particular ingestible substance.

2. The computing device of claim 1, wherein the at least one indication of user activity comprises a first indication of user activity, wherein the one or more sensors comprise a first set of one or more sensors, and wherein the at least one module is operable by the at least one processor to:

determine a first difference between the first indication of user activity and the pre-defined motion data;

generate, by a second set of one or more sensors operably coupled to the computing device, based on data received from the second set of one or more sensors, a second indication of user activity, wherein the second set of one or more sensors are different from the first set of one or more sensors;

determine a second difference between the second indication of user activity and pre-defined activity data;

apply a first weight, corresponding to the first indication of user activity, to the first difference to generate a first weighted difference value;

apply a second weight, corresponding to the second indication of user activity, to the second difference to generate a second weighted difference value;

aggregate the first and second weighted difference values to generate an aggregated weighted difference value; and

determine, based on the aggregated weighted difference value, whether the user is currently consuming the ingestible substance.

3. The computing device of claim 1, wherein the at least one module is operable by the at least one processor to:

responsive to determining that the user is consuming the ingestible substance, generate at least one difference between the at least one indication of user activity and the pre-defined motion data; and

update the pre-defined motion data based on the difference to generated updated pre-defined motion data,

wherein the at least one module is operable by the at least one processor to determine, based on the at least one indication of user activity and the updated pre-defined motion data, whether the user is currently consuming the ingestible substance.

4. The computing device of claim 1, wherein the computing device comprises a wearable computing device configured to be worn on the arm of the user.

5. The computing device of claim 1, wherein the one or more sensors are physically attached to the computing device.

6. A method for reminding a user to consume at least one particular ingestible substance based on a determination that the user is currently eating, the method comprising:

generating, by one or more sensors of a computing device, based on motion data received from the one or more sensors, and at a time that a user is eating, at least one indication of user activity indicating one or more motions of an arm of the user, wherein the one or more sensors are located on the arm of the user;

determining, by the computing device and based on pre-defined motion data that is indicative of an act of a human consuming an ingestible substance and the at least one indication of user activity, a degree of confidence that indicates a confidence that the user is currently consuming the ingestible substance;

comparing, by the computing device, the degree of confidence to a threshold to determine whether the degree of confidence satisfies the threshold;

responsive to determining that the degree of confidence satisfies the threshold, determining, by the computing device that the user is currently consuming the ingestible substance; and

responsive to determining that the user is currently consuming the ingestible substance, outputting, by the computing device, a reminder to consume the at least one particular ingestible substance.

7. The method of claim 6, wherein the at least one indication of user activity comprises a first indication of user activity, wherein the one or more sensors comprise a first set of one or more sensors, wherein determining whether the user is currently consuming the ingestible substance comprises:

determining, by the computing device, a first difference between the first indication of user activity and the pre-defined motion data;

generating, by a second set of one or more sensors operably coupled to the computing device, based on data received from the second set of one or more sensors, a second indication of user activity, wherein the second set of one or more sensors are different from the first set of one or more sensors;

determining, by the computing device, a second difference between the second indication of user activity and pre-defined activity data;

applying, by the computing device, a first weight, corresponding to the first indication of user activity, to the first difference to generate a first weighted difference value;

applying, by the computing device, a second weight, corresponding to the second indication of user activity, to the second difference to generate a second weighted difference value;

aggregating, by the computing device, the first and second weighted difference values to generate an aggregated weighted difference value; and

determining, by the computing device and based on the aggregated weighted difference value, whether the user is currently consuming the ingestible substance.

8. The method of claim 7, wherein the pre-defined activity data comprises at least one of image data of portions of food, a motion profile, image data of portions of a cheekbone, image data of portions of utensils, a mapping service to look up a restaurant, an eating schedule, an eating time, ambient audio to determine co-presence of others who are eating, a blood sugar level, motion data, a database of coordinates of restaurants, and a trained classifier.

9. The method of claim 6, wherein the at least one particular ingestible substance is at least one medication.

10. The method of claim 6, wherein the one or more sensors comprise at least one of an accelerometer and a gyrometer.

11. The method of claim 6, further comprising:

responsive to determining that the user is consuming the ingestible substance, generating, by the computing device, at least one difference between the at least one indication of user activity and the pre-defined motion data; and

updating, by the computing device, the pre-defined motion data based on the at least one difference,

wherein determining whether the user is currently consuming the ingestible substance comprises determining, by the computing device and based on the at least one indication of user activity and the updated pre-defined motion data, whether the user is currently consuming the ingestible substance.

12. The method of claim 6,

wherein generating the at least one indication of user activity at the time that the user is eating comprises generating the at least one indication of user activity within a time duration, wherein the time duration comprises a range of time.

13. The method of claim 6, wherein the reminder comprises at least one of a text message, an email, a vibration on a watch, a user interface element for display on the computing device, a flashing light mounted on computing device, or an audio message.

14. The method of claim 6, wherein the received motion data comprises at least one of a speed of the one or more motions of the arm of the user or a set of one or more positions of the arm during the one or more motions of the arm of the user, wherein the received motion data is measured by one of an accelerometer or a gyrometer and converted into one or more motion vectors.

15. A non-transitory computer-readable storage medium encoded with instructions that, when executed, cause at least one processor of a computing device to:

generate, at a time that a user is eating and based on motion data received from one or more sensors operably coupled to the computing device and located on an arm of the user, at least one indication of user activity indicating one or more motions of the arm of the user;

determine, based on pre-defined motion data that is indicative of an act of a human consuming an ingestible substance and the at least one indication of user activity, a degree of confidence that indicates a confidence that the user is currently consuming the ingestible substance;

compare the degree of confidence to a threshold to determine whether the degree of confidence satisfies the threshold;

responsive to determining that the degree of confidence satisfies the threshold, determine that the user is currently consuming the ingestible substance; and

responsive to determining that the user is currently consuming the ingestible substance, output a reminder to consume the at least one particular ingestible substance.

16. The non-transitory computer readable storage medium of claim 15, wherein the at least one indication of user activity comprises a first indication of user activity, wherein the one or more sensors comprise a first set of one or more sensors, and wherein the instructions causing the at least one processor to determine whether the user is currently consuming the ingestible substance comprise instructions that, when executed, cause the at least one processor to:

determine a first difference between the first indication of user activity and the pre-defined motion data;

generate, by a second set of one or more sensors operably coupled to the computing device, based on data received from the second set of one or more sensors, a second indication of user activity, wherein the second set of one or more sensors are different from the first set of one or more sensors;

determine a second difference between the second indication of user activity and pre-defined activity data;

apply a first weight, corresponding to the first indication of user activity, to the first difference to generate a first weighted difference value;

apply a second weight, corresponding to the second indication of user activity, to the second difference to generate a second weighted difference value;

aggregate the first and second weighted difference values to generate an aggregated weighted difference value; and

determine, based on the aggregated weighted difference value, whether the user is currently consuming the ingestible substance.

17. The non-transitory computer-readable storage medium of claim 15, wherein the instructions, when executed, further cause the at least one processor to:

responsive to determining that the user is consuming the ingestible substance, generate at least one difference between the at least one indication of user activity and the pre-defined motion data; and

update the pre-defined motion data based on the difference to generated updated pre-defined motion data,

wherein the computer-readable storage medium further comprises instructions that, when executed, cause the one or more processors to determine, based on the at least one indication of user activity and the updated pre-defined motion data, whether the user is currently consuming the ingestible substance.