Granted Patent B2

US 12,357,233 · App. 17/269,200 · Granted Jul 15, 2025

Inventors: Nithin O. Rajan (Austin, TX); Byron P. Olson (Boone, IA); Dustin M. Freckleton (Austin, TX); David E. Clift-Reaves (Austin, TX); Paulo E. Xavier Da Silveira (Boulder, CO); Namita Lokare (Austin, TX); Mandy Marie Salinas (Austin, TX)

Assignee: ELECTRICITY NORTH WEST PROPERTY LIMITED

A61B5/4875A61B5/0002A61B5/0205A61B5/0537A61B5/1124A61B5/14551A61B5/6802A61B5/7264A61B5/742G06N20/00A61B2562/0219

Abstract

Claims (106)

1. A system for contextual drink detection for a user wearing one or more body-worn sensors, the system comprising:

a memory; and

at least one processor to:

receive data from the one or more body-worn sensors;

determine if the received data includes motion data or biological data;

wherein when the received data includes motion data, the processor to:

classify the motion data as a pre-determined motion pattern;

determine if the classified pre-determined motion pattern corresponds to a drink;

wherein when the classified pre-determined motion pattern is identified as the drink, the processor to tally the drink, transmit a notification to a computing device of a user wearing the body-worn sensors, and poll the body-worn sensors for additional data; and

wherein when the classified pre-determined motion pattern is not identified as the drink, the processor to poll the body-worn sensors for the additional data; and

wherein when the received data includes biological data, the processor to:

determine at least one of a respiration rate, heart rate, or heart rate variability of the user;

determine if the at least one respiration rate, heart rate, or heart rate variability of the user corresponds to the drink;

wherein when the at least one respiration rate, heart rate, or heart rate variability of the user corresponds to the drink, the processor to tally the drink, transmit a notification to a computing device of a user wearing the body-worn sensors, and poll the body-worn sensors for the additional data; and

wherein when the at least one respiration rate, heart rate, or heart rate variability of the user does not correspond to the drink, the processor to poll the body-worn sensors for the additional data;

record the tally of the drink to an input log for drink events;

determine, based on a balancing of the input log for recorded drinks and an output log for expelled fluids, each of the input log and the output log being based on data received from the one or more body-worn sensors, a net hydration balance for the user;

determine whether the net hydration balance is within a predetermined hydration range; and

when the net balance of hydration is not within the predetermined hydration range, transmit a notification to the user.

2. The system of claim 1 , wherein the determination of the drink motion is informed by contextual data and the system further comprising:

the processor to:

receive contextual data;

generate a variable contextual threshold based on the contextual data;

wherein the received data is more likely to be identified as the drink motion when the contextual threshold is lower than a baseline value; and

wherein the received data is less likely to be identified as the drink motion when the contextual threshold is greater than a baseline value.

3. The system of claim 2 , further comprising:

the processor to:

determine if the user of the body-worn sensors is sleeping; and

determine if the motion data corresponds to a known non-drink motion.

4. The system of claim 1 , wherein the motion data is pre-processed using dynamic time warping.

5. The system of claim 1 , wherein the one or more body-worn sensors comprises at least one motion sensor and one or more biological sensors.

6. The system of claim 5 , wherein the at least one motion sensor includes at least one of an inertial motion unit, an accelerometer, a magnetometer, and a gyroscope.

7. The system of claim 5 , wherein the one or more biological sensors includes a photoplethysmography monitor, and the biological data comprises at least one of blood oxygen saturation data, heart rate data, heart rate variation data, blood pressure data, and respiration rate data.

8. The system of claim 1 , wherein at least one of the motion data and the biological data is processed by a machine learning classification technique.

9. The system of claim 1 , wherein the transmitted notification to the user comprises a graphic display.

10. The system of claim 9 , wherein the graphic display indicates a number of drinks taken by the user.

11. The system of claim 9 , wherein the graphic display indicates the user hydration level over time.

12. The system of claim 1 , wherein motion data, biological data, or both motion data and biological data are used to identify the drink.

13. A method for contextual drink detection of a user wearing one or more body-worn sensors; the method comprising:

receiving, by at least one processor, data from the one or more body-worn sensors;

determining, by the at least one processor, if the received data includes motion data or biological data;

wherein when the received data includes motion data:

classifying, by at least one processor, the motion data as a pre-determined motion pattern;

determining, by the at least one processor, if the classified pre-determined motion pattern corresponds to a drink;

wherein when the classified pre-determined motion pattern is identified as the drink by the at least one processor, tallying the drink, transmitting a notification to a computing device of a user wearing the body-worn sensors, and polling the body-worn sensors for additional data; and

wherein the classified pre-determined motion pattern is not identified as the drink by the at least one processor, polling the body-worn sensors for the additional data; and

wherein when the received data includes biological data:

determining, by the at least one processor, at least one of a respiration rate, heart rate, or heart rate variability of the user;

determining, by the at least one processor, if the at least one of a respiration rate, heart rate, or heart rate variability corresponds to the drink motion;

wherein when the at least one respiration rate, heart rate, or heart rate variability of the user is determined to correspond to the drink by the at least one processor, tallying the drink, transmitting a notification to a computing device of a user wearing the body-worn sensors, and polling the body-worn sensors for the additional data; and

wherein when the at least one respiration rate, heart rate, or heart rate variability of the user is determined not to correspond to the drink by the at least one processor, polling the body-worn sensors for the additional data;

recording the tally of the drink to an input log for drink events;

determining, based on a balancing of the input log for recorded drinks and an output log for expelled fluids, each of the input log and the output log being based on data received from the one or more body-worn sensors, a net hydration balance for the user;

determining whether the net hydration balance is within a predetermined hydration range; and

when the net balance of hydration is not within the predetermined hydration range, transmitting a notification to the user.

14. The method of claim 13 , wherein the determination of the drink motion is informed by contextual data; method further comprising:

receiving, by the at least one processor, contextual data;

generating, by the at least one processor, a variable contextual threshold based on the contextual data;

identifying, by the at least one processor, the received data as the drink motion when the contextual threshold is lower than a baseline value; and

identifying, by the at least one processor, the received data as a non-drink motion when the contextual threshold is greater than a baseline value.

15. The method of claim 14 , further comprising:

determining, by the at least one processor, if the user of the body-worn sensors is sleeping; and

determining, by the at least one processor, if the motion data corresponds to a known non-drink motion.

16. The method of claim 13 , further comprising pre-processing, by the at least one processor, the motion data using dynamic time warping.

17. The method of claim 13 , wherein the one or more body-worn sensors comprises at least one motion sensor and one or more biological sensors.

18. The method of claim 17 , wherein the at least one motion sensor includes at least one of an inertial motion unit, an accelerometer, a magnetometer, and a gyroscope.

19. The method of claim 17 , wherein the one or more biological sensors includes a photoplethysmography monitor, and the biological data comprises at least one of blood oxygen saturation data, heart rate data, heart rate variation data, blood pressure data, and respiration rate data.

20. The method of claim 13 , further comprising processing, by the at least one processor, at least one of the motion data and the biological data using a machine learning classification technique.

21. The method of claim 13 , wherein the transmitted notification to the user comprises generating, by the at least one processor, a graphic display.

22. The method of claim 21 , wherein the graphic display indicates a number of drinks taken by the user.

23. The method of claim 21 , wherein the graphic display indicates the user hydration level over time.

24. The method of claim 13 , wherein motion data, biological data, or both motion data and biological data are used to identify the drink.

25. A non-transitory computer-readable storage medium, having instructions for contextual drink detection stored thereon that, when executed by a computing device cause the computing device to perform operations, the operations comprising:

receiving data from one or more body-worn sensors;

determining if the received data includes motion data or biological data;

wherein when the received data includes motion data:

classifying the motion data as a pre-determined motion pattern;

determining if the classified pre-determined motion pattern corresponds to a drink;

wherein the classified pre-determined motion pattern is identified as the drink by at least one processor, tallying the drink, transmitting a notification to a computing device of a user wearing the body-worn sensors, and polling the body-worn sensors for additional data; and

wherein when the classified pre-determined motion pattern is not identified as the drink by the at least one processor, polling the body-worn sensors for the additional data; and

wherein when the received data includes biological data:

determining at least one of a respiration rate, heart rate, or heart rate variability of the user;

determining if the at least one of a respiration rate, heart rate, or heart rate variability corresponds to the drink motion;

wherein when the at least one respiration rate, heart rate, or heart rate variability of the user is determined to correspond to the drink, transmitting a notification to a computing device of a user wearing the body-worn sensors, and polling the body-worn sensors for the additional data; and

wherein when the at least one respiration rate, heart rate, or heart rate variability of the user does not correspond to the drink, polling the body-worn sensors for the additional data;

recording the tally of the drink to an input log for drink events;

determining, based on a balancing of the input log for recorded drinks and an output log for expelled fluids, each of the input log and the output log being based on data received from the one or more body-worn sensors, a net hydration balance for the user;

determining whether the net hydration balance is within a predetermined hydration range; and

when the net balance of hydration is not within the predetermined hydration range, transmitting a notification to the user.

26. The non-transitory computer-readable storage medium of claim 25 , wherein the determination of the drink motion is informed by contextual data; method further comprising:

receiving contextual data;

generating a variable contextual threshold based on the contextual data;

identifying the received data as the drink motion when the contextual threshold is lower than a baseline value; and

identifying the received data as a non-drink motion when the contextual threshold is greater than a baseline value.

27. The non-transitory computer-readable storage medium of claim 26 , further comprising:

determining if the user of the body-worn sensors is sleeping; and

determining if the motion data corresponds to a known non-drink motion.

28. The non-transitory computer-readable storage medium of claim 25 , further comprising pre-processing the motion data using dynamic time warping.

29. The non-transitory computer-readable storage medium of claim 25 , wherein the one or more body-worn sensors comprises at least one motion sensor and one or more biological sensors.

30. The non-transitory computer-readable storage medium of claim 29 , wherein the at least one motion sensor includes at least one of an inertial motion unit, an accelerometer, a magnetometer, and a gyroscope.

31. The non-transitory computer-readable storage medium of claim 29 , wherein the one or more biological sensors includes a photoplethysmography monitor, and the biological data comprises at least one of blood oxygen saturation data, heart rate data, heart rate variation data, blood pressure data, and respiration rate data.

32. The non-transitory computer-readable storage medium of claim 25 , further comprising processing at least one of the motion data and the biological data using a machine learning classification technique.

33. The non-transitory computer-readable storage medium of claim 25 , wherein the transmitted notification to the user comprises generating a graphic display.

34. The non-transitory computer-readable storage medium of claim 33 , wherein the graphic display indicates a number of drinks taken by the user.

35. The non-transitory computer-readable storage medium of claim 33 , wherein the graphic display indicates the user hydration level over time.

36. The non-transitory computer-readable storage medium of claim 25 , wherein motion data, biological data, or both motion data and biological data are used to identify the drink.

Assignments (3)

Continuity (2)

References Cited (17)