Contactless cough detection and attribution

Patent metadata

Field	Value
Publication number	US-11627890-B2
Application number	US-202217846438-A
Country	US
Kind code	B2
Filing date	Jun 22, 2022
Priority date	Aug 11, 2020
Publication date	Apr 18, 2023
Grant date	Apr 18, 2023

Abstract

Methods, devices, and systems for contactless cough detection and attribution are presented herein. Audio data may be received using a microphone. A cough may be identified as having occurred based on the received audio data. Radar data may be received indicative of reflected radio waves from a radar sensor. A state analysis process may be performed using the received radar data. The detected cough may be attributed to a particular user based at least in part on the state analysis process performed using the radar data.

First claim

What is claimed is:

1. A contactless cough detection device, comprising:
a housing;
a microphone housed by the housing;
a wireless network interface housed by the housing;
an electronic display housed by the housing, wherein the electronic display is visible through a screen;
a radar sensor housed by the housing, wherein the radar sensor emits radio waves through the screen; and
a processing system housed by the housing, comprising one or more processors, that receives data from the microphone and the radar sensor and is in communication with the wireless network interface and electronic display, wherein the processing system is configured to:
receive audio data from the microphone;
detect that a cough has occurred based on the received audio data;
receive radar data indicative of reflected radio waves from the radar sensor;
perform a state analysis process based on the received radar data for a user within a bed to select a state from a plurality of states;
attribute the detected cough to the user within the bed based at least in part on the state selected for the user based on the received radar data;
cause cough data for the user corresponding to the attributed detected cough to be stored; and
output the stored cough data via the electronic display.

2. The contactless cough detection device of claim 1 , wherein the processing system detects that the cough has occurred by analyzing the received audio data from the microphone using a trained cough detection machine learning model.

3. The contactless cough detection device of claim 1 , wherein the processing system is further configured to delete the audio data received from the microphone after detecting that the cough has occurred.

4. The contactless cough detection device of claim 1 , wherein the processing system being configured to perform the state analysis process comprises the processing system being configured to determine the user has moved within the bed within a time period of the detected cough.

5. The contactless cough detection device of claim 1 , wherein the processing system is further configured to cause sleep data indicative of the cough being attributed to the user to be stored.

6. The contactless cough detection device of claim 5 , wherein the processing system is further configured to transmit the sleep data to a remote server system via the wireless network interface.

7. The contactless cough detection device of claim 1 , wherein the processing system being configured to output the stored cough data via the electronic display comprises the processing system being configured to output a report indicating a number of times that the user coughed during sleep.

8. The contactless cough detection device of claim 1 , wherein:
the radar sensor is an integrated circuit (IC) distinct from the processing system; and
the radar sensor outputs frequency-modulated continuous wave (FMCW) radar into an environment of the contactless cough detection device.

9. The contactless cough detection device of claim 8 , wherein the FMCW radar has a frequency between 57 and 64 GHz and has a peak effective isotropically radiated power (EIRP) of 20 dBm or less.

10. The contactless cough detection device of claim 1 , wherein the radar sensor emits the radio waves through an opaque bezel of the screen.

11. The contactless cough detection device of claim 1 , wherein the processing system is further configured to determine that the detected cough woke the user from sleep based on a change in the state of the user.

12. The contactless cough detection device of claim 1 , wherein the processing system being configured to output the stored cough data comprises the processing system being configured to output a report indicative of a number of times the user coughed during a night to the electronic display for presentation.

13. The contactless cough detection device of claim 1 , wherein the processing system being configured to output the stored cough data comprises the processing system being configured to output the cough data with sleep data for the user to the electronic display for presentation.

14. The contactless cough detection device of claim 1 , further comprising a speaker housed by the housing.

15. A method for performing contactless cough detection, the method comprising:
receiving, by a contactless cough detection device, an audio data stream from a microphone;
detecting, by the contactless cough detection device, that a cough has occurred based on the received audio data stream;
receiving, by the contactless cough detection device, a radar data stream indicative of reflected radio waves from a radar sensor;
performing, by the contactless cough detection device, a state analysis process based on the received radar data such that a state is selected from a plurality of states for a user within a bed;
attributing, by the contactless cough detection device, the detected cough to the user within the bed based at least in part on the state selected based on the received radar data;
storing, by the contactless cough detection device, cough data indicating the attributed detected cough for the user; and
outputting, by the contactless cough detection device, the stored cough data via an electronic display, wherein:
the electronic display is visible through a screen of the contactless cough detection device; and
the radar sensor emits and senses radar waves through the screen of the contactless cough detection device.

16. The method for performing contactless cough detection of claim 15 , wherein detecting that the cough has occurred is performed by analyzing the received audio data stream using a pre-trained cough detection machine learning model.

17. The method for performing contactless cough detection of claim 16 , the method further comprising: deleting the received audio data stream after detecting that the cough has occurred.

18. The method for performing contactless cough detection of claim 15 , wherein performing the state analysis process comprises determining that the user has moved within the bed within a time period of the detected cough.

19. The method for performing contactless cough detection of claim 15 , further comprising:
determining that the detected cough woke the user from sleep based on a change in the state for the user.

20. The method for performing contactless cough detection of claim 15 , wherein outputting the stored cough data comprises outputting the cough data with sleep data for presentation.

Assignees

• Google Llc

Inventors

• Shin Dongeek
• Dixon Michael
• Garrison Jake
• Goldenson Andrew William

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• A61B2505/07

  Home care · CPC title

• A61B5/0022

  Monitoring a patient using a global network, e.g. telephone networks, internet · CPC title

• A61B5/7267

  involving training the classification device · CPC title