Detecting outdoor walking workouts on a wearable device

Patent metadata

Field	Value
Publication number	US-12109453-B2
Application number	US-202017032933-A
Country	US
Kind code	B2
Filing date	Sep 25, 2020
Priority date	Sep 27, 2019
Publication date	Oct 8, 2024
Grant date	Oct 8, 2024

Abstract

Disclosed embodiments include wearable devices and techniques for detecting walking workouts. By accurately and promptly detecting the start of walking workouts activities and automatically distinguishing between walking workout and causal walking activities, the disclosure enables wearable devices to accurately calculate user performance information when users forget to start and/or stop recording walking workouts.

First claim

The invention claimed is:

1. A method for improving performance of a wearable device while recording a walking workout, the method comprising:
training, by a processor, a predictive model to detect start and end points of a walking workout, the training based on training data that includes motion data indicative of casual walking activities and walking workouts;
measuring, by a motion sensing module of the wearable device, motion data of a user;
determining, by the processor circuit of the wearable device, a number of steps performed by the user based on the motion data;
detecting, by the processor circuit, a bout based on the number of steps performed by the user during a predetermined period of time, the bout including a plurality of continuous steps performed by the user;
detecting, by the processor circuit, a step rate based on the number of steps performed by the user during the predetermined period of time;
determining, by the processor circuit, mechanical work performed by the user during the bout, wherein the mechanical work is based on a pedestrian work model that is a function of at least the step rate and a load;
detecting, by the processor circuit, a start of the walking workout based on the mechanical work, wherein detecting the start of the walking workout includes:
comparing the mechanical work performed by the user to a mechanical work threshold;
detecting a value for the mechanical work performed by the user that is below the mechanical work threshold;
in response to detecting the value for the mechanical work performed by the user that is below the mechanical work threshold, determining, with the trained predictive model, a patterned movement indicative of walking based on the motion data;
in response to determining the patterned movement indicative of walking, starting the walking workout and

recording, by the processor circuit, the walking workout.

2. The method of claim 1 , wherein the detecting the start of the walking workout includes:
comparing the mechanical work to a mechanical work threshold; and
starting the walking workout in response to detecting a value for the mechanical work that exceeds the mechanical work threshold.

3. The method of claim 1 , wherein the patterned movement is a straight movement pattern or a repetitive movement pattern, wherein the straight movement pattern has a number of changes in user direction below a change in direction threshold and one or more changes in user direction do not repeat at regular time or distance intervals; and the repetitive movement pattern has a number of changes in user direction below the change in direction threshold and one or more changes in user direction that repeat at regular time or distance intervals.

4. The method of claim 1 , comprising:
sending, by the processor circuit, a notification to the user requesting confirmation of the start of the walking workout.

5. The method of claim 4 , wherein the notification is a notification user interface displayed on a display screen of the wearable device.

6. The method of claim 1 , comprising:
measuring, by a pressure sensor of the wearable device, pressure data;
measuring, by a GPS module of the wearable device, location data of the user;
determining, by the processor circuit, a grade for each step included in the number of steps based on the pressure data, the grade measuring steepness of terrain traversed during the bout;
determining, by the processor circuit, a step distance for each step included in the bout based on the motion data and the location data;
determining, by the processor circuit, a bout time describing a duration of the bout; and
determining, by the processor circuit, the mechanical work performed during the bout based on the step distance, the grade, and the bout time.

7. The method of claim 6 , comprising:
calculating, by the processor circuit, a load based on the grade and the number of steps performed by the user, the load estimating a force required to perform the number of steps over the grade; and
improving, by the processor circuit, an accuracy of the mechanical work by estimating the mechanical work using the load.

8. The method of claim 1 , comprising:
estimating, by the processor circuit, a device heading at every continuous step included in the bout based on the motion data, the device heading describing an orientation of the wearable device relative to a frame of reference;
determining, by the processor circuit, a number of changes in user direction based on the device heading and the number of steps; and
classifying a walking movement performed during the bout based on the number of changes in user direction.

9. The method of claim 8 , comprising:
measuring, by a magnetic field sensor of the wearable device, magnetic field data; and
the estimating the device heading including:
determining rotational data based on the magnetic field data;
selecting a first yaw component of the rotational data determined based on the magnetic field data;
determining rotational data based on the motion data;
selecting a second yaw component of the rotational data determined based on the motion data; and
improving accuracy of the device heading by determining the device heading based on a combination of the first yaw component and the second yaw component.

10. The method of claim 9 , wherein at least one of the first yaw component of the rotational data determined based the magnetic field data and the second yaw component of the rotational data determined based on the motion data is a rotational angle in a fixed body frame of reference, wherein the rotational angle describes angular motion relative to an axis of rotation that is parallel to a display screen of the wearable device.

11. The method of claim 1 , wherein the motion data comprises acceleration data obtained from an accelerometer and gyroscope data obtained from a gyroscope.

12. The method of claim 1 , comprising:
distinguishing, by a processor circuit, between a walking workout and a casual walking activity based on comparing the mechanical work to a mechanical work threshold and classifying a walking movement performed by the user.

13. The method of claim 1 , comprising:
in response to recording the walking workout, calculating, by the processor circuit, user performance information during the walking workout; and
detecting, by the processor circuit, an end of the walking workout based the user performance information.

14. A system for improving performance of a wearable device while recording a walking workout, the system comprising:
a motion sensing module configured to measure motion data of a user; and
a processor circuit in communication with the motion sensing module and configured to execute instructions causing the processor circuit to:
train a predictive model to detect start and end points of a walking workout, the training based on training data that includes motion data indicative of casual walking activities and walking workouts;
determine a number of steps performed by the user based on the motion data;
detect, by the processor circuit, a bout based on the number of steps performed by the user during a predetermined period of time, the bout including a plurality of continuous steps performed by the user;
detect a step rate based on the number of steps performed by the user during the predetermined period of time;
determine mechanical work performed by the user during the bout, wherein the mechanical work is based on a pedestrian work model that is a function of at least the step rate and a load;
compare the mechanical work performed by the user to a mechanica

Assignees

• Apple Inc

Inventors

• Dervisoglu Gunes
• Pham Hung A
• Rao Bharath Narasimha
• Beard Jonathan M
• Huet Lucie A
• Phan Anh N
• Majjigi Vinay R
• Ochs James P
• Jayaraman Raghuram Karthik

Classifications

• A63B2220/836

  Sensors arranged on the body of the user · CPC title

• A63B2220/89

  Field sensors, e.g. radar systems · CPC title

• G16H40/67

  for remote operation · CPC title

• G16H20/30 Primary

  relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising · CPC title

• A63B24/0062 Primary

  Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance · CPC title