Assist device and system

• US 10,687,193 B2
• Filed: 07/30/2018
• Issued: 06/16/2020
• Est. Priority Date: 09/19/2013
• Status: Active Grant

• Current Assignee: UnaliWear, Inc.
• Original Assignee: UnaliWear, Inc.
• Inventors: Booth, Jean Anne, Kircher, Brian, Potts, Davin, Ahmed, Syed Sajjad
• Primary Examiner(s): Trieu, Van T
• Application Number:
  US16/049,361
• Publication Number:
  US 20190069154A1
• Time in Patent Office: 687 Days
• CPC Class Codes: G06F 1/163 Wearable computers, e.g. on a belt
• CPC Class Codes: G06F 1/1635 Details related to the integration of battery packs and other power supplies such as fuel cells or integrated AC adapter
• CPC Class Codes: G06F 1/3231 Monitoring the presence, absence or movement of users
• CPC Class Codes: G06F 1/3287 by switching off individual functional units in the computer system
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/024 Guidance services
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/90 Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A wearable device monitors a wearer'"'"'s physical activity and provides assistance to the wearer. The device includes physiologic sensors that provide sensor data of the wearer to a processor, a user interface that provides information to the wearer, a network interface that provides a network connection between the device and a remote computer, and a memory that stores instructions. The processor executes the instructions to collect physical activity data of the wearer using the sensors, to provide the collected activity data to the remote computer via the network interface to create or update a parameterized rule-based custom data model for the wearer, to receive the custom data model for comparison to collected activity data, and to communicate with the wearer via the user interface when a check of the wearer'"'"'s activity data against the custom data model indicates that the wearer'"'"'s activity is not consistent with the custom data model.

Claims

1. A wearable device adapted to monitor a wearer'"'"'s physical activity patterns and to provide assistance to the wearer, comprising:

a power source;

a processor;

at least one physiologic sensor that provides sensor data of the wearer to the processor;

a user interface connected to the processor and adapted to interact with the wearer and to provide information to the wearer;

a network interface configured to provide a network connection between the device and a remote computer; and

a memory coupled to the processor, the memory storing program instructions that, upon execution by the processor, cause the device to collect, from the at least one physiologic sensor, physical activity data related to times and locations of physical activity of the wearer over time, to provide the collected physical activity data to the remote computer via the network interface for processing to create or update a parameterized rule-based custom data model for the wearer, the parameterized rule-based custom data model being representative of an activity profile of the times and locations of physical activity of the wearer over time, to receive the parameterized rule-based custom data model from the remote computer for comparison to collected physical activity data, and to communicate with the wearer via the user interface when a comparison of the wearer'"'"'s physical activity data against the parameterized rule-based custom data model indicates that the wearer'"'"'s physical activity is not consistent with the parameterized rule-based custom data model.

2. The wearable device according to claim 1, wherein the at least one physiologic sensor passively gathers sensor data about the wearer and the processor executes instructions to compare the gathered sensor data against the parameterized rule-based custom data model to detect a deviation.

3. The wearable device according to claim 2, wherein the processor executes instructions to provide a communication to the wearer via the user interface when the deviation is detected, the communication offering assistance to the wearer.

4. The wearable device according to claim 3, wherein the processor executes instructions to contact a caregiver or call center when the assistance offered to the wearer is accepted b wearer.

5. The wearable device according to claim 1, further comprising a location detection device, wherein the processor executes instructions to compare the wearer'"'"'s location to the parameterized rule-based custom data model to determine if the wearer is in an unexpected location, and upon detection that the wearer is in an unexpected location, communicates with the wearer via the user interface to offer directions.

6. The wearable device according to claim 5, wherein upon detection that the wearer is in an unexpected location, the processor executes instructions to determine whether the wearer is traveling and, when the wearer is determined to be traveling, disables the communications with the wearer via the user interface to offer directions until the wearer returns from traveling.

7. The wearable device according to claim 6, wherein upon determining that the wearer is traveling, the processor executes instructions to reduce sensitivity of non-critical monitoring by the at least one physiologic sensor until the wearer returns from traveling.

8. The wearable device according to claim 6, wherein upon detection that the wearer is traveling, the processor executes instructions to increase sensitivity of fall detection by the at least one physiologic sensor until the wearer returns from traveling.

9. The wearable device according to claim 1, wherein the parameterized rule-based custom data model represents at least one of a level of physical activity of the wearer, an activity profile of the wearer over time, an activity profile of the wearer relative to a location, and an activity profile of the wearer relative to a location over time.

10. The wearable device according to claim 9, wherein the processor executes instructions to compare the collected physical activity data to the parameterized rule-based custom data model to determine if the wearer has missed a physical activity and, if so, communicates a query to the wearer via the user interface.

11. The wearable device according to claim 9, wherein the processor executes instructions to compare the collected physical activity data to the parameterized rule-based custom data model to determine if the wearer'"'"'s physical activity level is decreasing and, if so, increases sensitivity of fall detection by the at least one physiologic sensor.

12. The wearable device according to claim 1, wherein the at least one physiologic sensor comprises a microphone that collects vocal patterns of the wearer for comparison to previously acquired recordings of the vocal patterns of the wearer to identify changes representative of changes in at least one of mental and physical state of the wearer.

13. The wearable device according to claim 1, wherein the processor executes instructions to compare the collected physical activity data to previously acquired physical activity data of the wearer to identify changes representative of changes in at least one of mental and physical state of the wearer.

14. The wearable device according to claim 1, wherein the processor executes instructions to compare sleep data collected by the at least one physiologic sensor to previously acquired sleep data of the wearer to identify changes representative of changes in at least one of mental and physical state of the wearer.

15. The wearable device according to claim 1, wherein the processor executes instructions to compare the collected physical activity data to the parameterized rule-based custom data model to determine if the wearer'"'"'s movements are unusual and, if so, communicates a query to the wearer via the user interface requesting that the user record a speech sample for comparison to a previously recorded speech sample to identify changes indicative of a need for medical attention.

16. The wearable device according to claim 1, wherein the processor executes instructions to communicate with another medical device via the network interface, to extract sharable data from the other medical device, and to prompt the wearer to take an action when the extracted sharable data indicates that the wearer requires medical attention.

17. The wearable device according to claim 16, wherein the extracted sharable data from the other medical device includes a telemedicine reminder for the wearer to take an action.

18. The wearable device according to claim 1, wherein when the at least one physiologic sensor indicates that the wearer is inactive, the processor executes instructions to monitor a microphone to determine if a low volume of sound is detected and, if so, executes instructions to monitor ambient light to determine if low ambient light conditions are present and, if so, determines that the wearer is sleeping and turns off non-critical monitoring features.

19. The wearable device according to claim 1, further comprising a location detection device and, the processor executing instructions to compare location data from the location detection device to stored location data to determine if the wearer is entering a building and, if so, accessing a pressure baseline for the building to offset pressure readings while the wearer is in the building.

20. The wearable device according to claim 19, further comprising a location detection device and, the processor executing instructions to enter a pressure sensing mode to monitor pressure changes for a predetermined period of time to establish a pressure baseline, wherein the pressure baseline is used to offset pressure readings while the wearer is in the building.

21. The wearable device according to claim 1, wherein the network interface receives data indicative of the wearer'"'"'s home location and data indicative of another location, wherein the processor executes instructions to determine whether data indicative of the other location has been received in the last predetermined period of time and, if not, determines whether data indicative of the wearer'"'"'s home location has been received and, if so, the network interface ends monitoring for location data.

22. The wearable device according to claim 21, wherein the processor executes instructions to query the wearer when the data indicative of the wearer'"'"'s home location has not been received in a predetermined period of time since data indicative of the other location was last received.

23. The wearable device according to claim 1, wherein the wearable device is configured to be worn on the wrist of the wearer.

24. The wearable device according to claim 1, wherein the network interface is a wireless interface.

25. The wearable device according to claim 1, wherein the at least one physiologic sensor comprises at least one of an accelerometer and a gyrometer configured to detect a potential falling incident and a location sensor to determine a location of the wearer.

26. The wearable device according to claim 1, wherein the user interface comprises a continuous speech recognition interface configured to enable speech interaction by the wearer with the device.

27. The wearable device according to claim 26, wherein the speech recognition interface is configured to receive and to transmit a request for assistance by the wearer to the remote computer via the network interface and to audibilize instructions and queries that offer assistance to the wearer.

28. The wearable device according to claim 27, wherein the speech recognition interface audibilizes reminders for the user to take medication.

29. A system adapted to monitor the physical activity patterns of a wearer and to provide assistance to the wearer when a need for assistance is indicated, comprising:

the wearable device of claim 1 adapted to be worn by the wearer; and

at least one remote computer connectable to the device via the network interface, the remote computer adapted to receive the collected physical activity data from the device via the network interface for processing to create a parameterized rule-based custom data model for the wearer during a training mode, the parameterized rule-based custom data model being representative of an activity profile of times and locations of physical activity of the wearer over time, to provide the parameterized rule-based custom data model to the device for comparison to collected physical activity data during an active mode, and to update parameters of the parameterized rule-based custom data model during the active mode.

30. The system according to claim 29, wherein the at least one remote computer collects physical activity data from multiple wearers and clusters the data from multiple wearers to create peer groups to wearers.

31. The system according to claim 30, wherein a peer group of a wearer is used to establish an initial parameterized rule-based data model for the wearer that is updated by the at least one remote computer over time as new physical activity data is collected to create the parameterized rule-based custom data model for the wearer.

32. The system according to claim 31, wherein deviation sensitivity of the initial parameterized rule-based data model is increased as the initial parameterized rule-based data model becomes more customized to the wearer.

33. The system according to claim 30, wherein fall data for the wearer is compared to fall data from multiple wearers and if the fall data of the wearer is significantly different from the fall data from multiple wearers, the at least one remote computer uses the fall data of the wearer to train a wearer-specific fall detection algorithm for implementation by the device.

34. The system according to claim 30, wherein fall data for the wearer is compared to fall data from multiple wearers and if the fall data of the wearer is not significantly different from the fall data from multiple wearers, the at least one remote computer trains a generic fall detection algorithm for implementation by the device.

35. A method for monitoring physical activity patterns of a wearer of a wearable assist device and to provide assistance to the wearer, comprising:

at least one physiologic sensor collecting physical activity data related to times and locations of physical activity of the wearer over time;

providing the collected physical activity data to a remote computer;

the remote computer processing the collected physical activity data to create or update a parameterized rule-based custom data model for the wearer, the parameterized rule-based custom data model being representative of an activity profile of the times and locations of physical activity of the wearer over time;

the assist device receiving the parameterized rule-based custom data model from the remote computer;

the assist device comparing newly collected physical activity data to the parameterized rule-based custom data model; and

communicating with the wearer via a user interface of the assist device when the comparing of the wearer'"'"'s newly collected physical activity data against the parameterized rule-based custom data model indicates that the wearer'"'"'s physical activity is not consistent with the parameterized rule-based custom data model.

36. The method of claim 35, further comprising the assist device communicating with a medical device to extract sharable data from the medical device and prompting the wearer to take an action when the extracted sharable data indicates that the wearer requires medical attention.

37. The method of claim 36, wherein the extracted sharable data from the other medical device includes a telemedicine reminder for the wearer to take an action.

38. The method of claim 35, wherein the remote computer creates the parameterized rule-based custom data model for the wearer during a training mode of the assist device, further comprising the remote computer providing updated parameters of the parameterized rule-based custom data model during an active mode of the assist device.

39. The method of claim 35, further comprising the remote computer collecting physical activity data from multiple wearers and clustering the data from multiple wearers to create peer groups to wearers.

40. The method of claim 39, further comprising using a peer group of a wearer to establish an initial parameterized rule-based data model for the wearer and updating the initial parameterized rule-based data model for the wearer over time as new physical activity data is collected to create the parameterized rule-based custom data model for the wearer.

41. The method of claim 40, further comprising increasing deviation sensitivity of the initial parameterized rule-based data model as the initial parameterized rule-based data model becomes more customized to the wearer.

42. The method of claim 39, further comprising comparing fall data for the wearer to fall data from multiple wearers and if the fall data of the wearer is significantly different from the fall data from multiple wearers, using the fall data of the wearer to train a wearer-specific fall detection algorithm for implementation by the assist device.

43. The method of claim 39, further comprising comparing fall data for the wearer to fall data from multiple wearers and if the fall data of the wearer is not significantly different from the fall data from multiple wearers, training a generic fall detection algorithm for implementation by the assist device.