Employing device sensor data to determine user characteristics

• US 9,411,780 B1
• Filed: 06/03/2013
• Issued: 08/09/2016
• Est. Priority Date: 06/03/2013
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Awad, Nadim, Sridharan, Srinivasan, Kiraly, Kenneth Paul, Keljo, Jonathan White, Dolbakian, Levon, Froment, Arnaud Marie
• Primary Examiner(s): Le, John H
• Application Number:
  US13/908,795
• Time in Patent Office: 1,163 Days
• Field of Search: 702/127, 702/138, 702/141, 702/146, 702/149, 702/155, 702/158, 702/166, 702/179, 702/75, 702/116, 345/173, 345/440, 434/238, 434/257, 482/9, 600/300, 600/301, 707/731, 707/737
• US Class Current: 1/1
• CPC Class Codes: A41H 1/02 Devices for taking measurements on the human body
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G06Q 50/10 Services
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/62 of area, perimeter, diameter or volume
• CPC Class Codes: G06V 20/647 by matching two-dimensional images to three-dimensional objects

Abstract

Techniques are described for determining height, weight, or other characteristics of a user based on processed sensor data. The sensor data may include data collected by sensors on the user'"'"'s computing device or other computing devices, or data collected by stationary, external sensors. Different types of sensor data may be processed to estimate at least one physical characteristic of the user, such as the user'"'"'s height, weight, apparel size, age, and so forth. The estimated characteristics may be employed to perform actions based on the user'"'"'s identity or category, to customize content delivery for the user, or for other purposes.

Claims

1. A computer-implemented method, comprising:

receiving sensor data from a user device, the sensor data comprising;

image data depicting at least a portion of a user of the user device, the image data provided by an image capture device included in the user device; and

motion data describing a motion of the user device, the motion data provided by a motion sensor device included in the user device;

determining a first estimate of a physical characteristic of the user based on the image data, the physical characteristic comprising at least one of a height or an apparel size of the user;

determining a second estimate of the physical characteristic of the user based on the motion data;

processing the first estimate and the second estimate to determine a processed estimate of the physical characteristic of the user; and

based on the processed estimate, determining content to present through an application executed on the user device, wherein the content comprises at least one item recommended for the user based on the physical characteristic of the user.

2. The method of claim 1, wherein the determining of the first estimate further comprises:

identifying a reference object depicted in the image data;

retrieving size information that describes a predetermined size of at least one dimension of the reference object;

based on the image data, determining a proportion of the physical characteristic of the user to the at least one dimension of the reference object; and

determining the first estimate as a multiplicative product of the predetermined size and the proportion.

3. The method of claim 1, wherein the determining of the second estimate further comprises:

determining a vertical distance traveled by the user device during the motion, based at least partly on the motion data;

receiving device usage data indicating an activity performed on the user device, the activity performed during a time period that at least partly coincides with the motion;

based on the device usage data indicating that the activity comprises engaging in a telephone call, determining that the vertical distance corresponds to a difference between a first elevation of the user device and a second elevation of the user device, the first elevation corresponding to a resting position of the user device prior to the telephone call, and the second elevation corresponding to an ear of the user; and

determining the second estimate based on the vertical distance.

4. The method of claim 1, wherein processing the first estimate and the second estimate to determine the processed estimate further comprises calculating the processed estimate as an average of the first estimate and the second estimate.

19. The method of claim 1, wherein the item comprises one or more of apparel or accessories.

5. A system, comprising:

a memory storing computer-executable instructions; and

a processor in communication with the memory, the processor configured to execute the computer-executable instructions to cause the processor to;

receive first sensor data from a first sensor device included in a user device;

receive second sensor data from a second sensor device included in the user device, the second sensor device being different than the first sensor device;

determine a first estimate of a physical characteristic of a user associated with the user device, based at least partly on the first sensor data;

determine a second estimate of the physical characteristic of the user, based at least partly on the second sensor data;

process the first estimate and the second estimate to determine a third estimate of the physical characteristic of the user;

perform one or more actions that are customized based at least partly on the third estimate of the physical characteristic; and

wherein the one or more actions comprise;

identifying one or more products having a size that corresponds to the third estimate of the physical characteristic of the user; and

presenting content describing the one or more products.

6. The system of claim 5, wherein the physical characteristic includes one or more of a weight, an apparel size, an age, a gender, a height, a width, a size of at least one body part of the user, an item of apparel worn by the user, or a physical capability of the user.

7. The system of claim 5, wherein the first sensor device and the second sensor device comprise one or more of a camera, an accelerometer, a gyroscope, a magnetometer, a geolocation device, a barometer, an altimeter, or a touch-sensitive display.

8. The system of claim 5, wherein the one or more actions comprise:

identifying the user based at least partly on the third estimate of the physical characteristic, and

customizing at least one feature of the user device, based on a stored preference of the identified user.

9. The system of claim 5, wherein:

the physical characteristic includes an age of the user; and

the one or more actions comprise controlling access to at least one of a function, an application, or a content item on the user device based on the third estimate of the physical characteristic including the age of the user.

10. The system of claim 5, wherein the one or more actions comprise:

based at least partly on the third estimate of the physical characteristic, determining content to present on the user device.

11. The system of claim 5, wherein:

at least one of the first sensor data and the second sensor data comprises image data that depicts an object and at least a portion of the user;

the physical characteristic includes a dimension of at least the portion of the user depicted in the image data; and

the one or more actions comprise;

based on the image data, determining a proportion between a size of the object and at least the portion of the user;

estimating the size of the object, based on the proportion and the third estimate of the dimension of at least the portion of the user; and

identifying a type of the object depicted in the image data, based at least partly on the size of the object.

12. A computer-implemented method, comprising:

receiving sensor data from at least two sensor devices;

processing the sensor data from the at least two sensor devices to determine at least two independent estimates of a physical dimension of a user of a user device;

processing the at least two independent estimates of the physical dimension, to determine a processed estimate of the physical dimension of the user;

performing one or more actions that are customized based at least in part on the processed estimate of the physical dimension of the user; and

wherein the one or more actions comprise;

selecting, from a plurality of items, at least one item that is recommended for the user based at least partly on the processed estimate of the physical dimension of the user; and

presenting, on the user device, content describing the at least one item recommended for the user.

13. The method of claim 12, further comprising:

processing the processed estimate with at least one previously determined estimate of the physical dimension, to update the processed estimate of the physical dimension.

14. The method of claim 12, wherein the physical dimension of the user comprises a height, a weight, a width, an apparel size, an age, a gender, a body part dimension of the user, an item of apparel worn by the user, or a physical capability of the user.

15. The method of claim 12, further comprising:

receiving the sensor data comprising image data that depicts a reference object and at least a portion of the user, wherein the reference object has at least one predetermined dimension; and

determining one of the at least two independent estimates of the physical dimension of the user, based at least partly on a comparison of the predetermined dimension of the reference object depicted in the image data to the physical dimension of the user depicted in the image data.

16. The method of claim 12, further comprising:

receiving the sensor data comprising motion data describing a motion of the user device;

determining a vertical distance traveled by the user device during the motion, based at least partly on the motion data;

receiving device usage data indicating an activity performed on the user device, the activity occurring during a time period that at least partly coincides with the motion, the activity being characterized by a characteristic motion performed during the activity; and

determining one of the at least two independent estimates of the physical dimension of the user, based on associating the characteristic motion with the vertical distance traveled by the user device.

17. The method of claim 12, further comprising:

receiving the sensor data comprising atmospheric pressure data describing an atmospheric pressure change at the user device;

receiving device usage data indicating an activity performed on the user device, the activity including a motion of the user device during a time period that at least partly coincides with the atmospheric pressure change, the activity being characterized by a characteristic motion performed during the activity;

determining an altitude change of the user device during the motion, based at least partly on the atmospheric pressure change; and

determining one of the at least two independent estimates of the physical dimension of the user, based on associating the characteristic motion with the altitude change.

18. The method of claim 12, further comprising:

receiving the sensor data comprising touch input data describing a tactile pressure placed on the user device by the user while interacting with the user device; and

determining one of the at least two independent estimates of the physical dimension of the user based at least partly on the tactile pressure placed on the user device by the user.

20. The method of claim 12, further comprising:

receiving the sensor data comprising motion data and acceleration data, determining a distance traveled by the user of the user device during a time period;

during the time period, determining a number of strides of the user during the distance traveled, based at least partly on the acceleration data;

during the time period, determining a length and frequency of the strides based at least partly on the number of strides and the distance traveled; and

determining one of the at least two independent estimates of the physical dimension of the user based at least partly on the length and frequency of the strides.