Contactless cough detection and attribution

Patent metadata

Field	Value
Publication number	US-11406281-B2
Application number	US-202016990720-A
Country	US
Kind code	B2
Filing date	Aug 11, 2020
Priority date	Aug 11, 2020
Publication date	Aug 9, 2022
Grant date	Aug 9, 2022

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;
a radar sensor housed by the housing; 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 such that, separately for each user of a plurality of users within a bed, a state is selected from a plurality of states;
attribute the detected cough to a particular user of the plurality of users within the bed based at least in part on the state selected for each user of the plurality of states based on the received radar data;
receive a spoken command from the microphone;
output data based on the spoken command, via the wireless network interface, to a cloud-based server system;
receive an instruction from the cloud-based server system via the wireless network interface in response to the output data; and
output stored cough data in response to the received instruction 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 pre-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 attribute the detected cough to the particular user comprises the processing system being configured to determine that the only user being monitored is attributed with the detected cough.

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

6. 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 particular user has moved more than other users of the plurality of users within the bed within a time period of the detected cough.

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

8. The contactless cough detection device of claim 7 , further comprising:
a speaker housed by the housing and in communication with the processing system.

9. The contactless cough detection device of claim 1 , wherein the processing system is further configured to output a report that indicates a number of times that the particular user coughed during sleep.

10. The contactless cough detection device of claim 9 , wherein the electronic display outputs the report for presentation.

11. The contactless cough detection device of claim 1 , wherein the processing system is further configured to create, over a plurality of days, a trend report indicating whether an amount of coughing by the particular user is increasing, decreasing, or staying constant.

12. 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.

13. The contactless cough detection device of claim 12 , 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.

14. 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 particular user coughed during a night.

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

16. The contactless cough detection device of claim 15 , 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 particular user coughed that woke the particular user from sleep.

17. 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 based on the state analysis process for the particular user.

18. A method for performing contactless cough detection, the method comprising:
receiving an audio data stream from a microphone;
detecting that a cough has occurred based on the received audio data stream;
receiving a radar data stream indicative of reflected radio waves from a radar sensor;
performing a state analysis process based on the received radar data such that, separately for each user of a plurality of users within a bed, a state is selected from a plurality of states;
attributing the detected cough to a particular user of the plurality of users within the bed based at least in part on the state selected for each user of the plurality of states based on the received radar data;
receiving a spoken command via the microphone;
outputting data based on the spoken command, via a wireless network interface, to a cloud-based server system;
receiving an instruction from the cloud-based server system via the wireless network interface in response to the output data; and
outputting stored cough data in response to the received instruction via an electronic display.

19. The method for performing contactless cough detection of claim 18 , 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.

20. The method for performing contactless cough detection of claim 18 , the method further comprising: deleting the received audio data stream after detecting that the cough has occurred.

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

22. The method for performing contactless cough detection of claim 18 , wherein:
performing the state analysis process comprises determining that the particular user has moved more than one or more other users within the bed within a time period of the detected cough; and
attributing the detected cough to the particular

Assignees

• Google Llc

Inventors

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

Classifications

• G06N3/045

  Combinations of networks · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title