US 11,229,369 B2Granted

Detecting and measuring snoring

AssigneeFitbit, Inc.

InventorsHao-Wei Su, Logan Niehaus, Conor Joseph Heneghan, Jonathan David Charlesworth, Subramaniam Venkatraman, Shelten Gee Jao Yuen

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

Approaches described herein can determine one or more breathing phase patterns over a period of time using audio data captured by at least one microphone. The audio data can include one or more snores. A breathing phase pattern included within the period of time can be determined based at least in part on sensor data captured by one or more sensors in the electronic device. A determination can be made that a first breathing phase pattern represented by the audio data and a second breathing phase pattern represented by the sensor data are correlated. A determination can be made that the first breathing phase pattern represented by the audio data and the second breathing phase pattern represented by the sensor data both correspond to a user wearing the electronic device.

Claims20

Dependent claims

An electronic device comprising:

at least one processor;
and
a memory storing instructions that, when executed by the at least one processor, cause the electronic device to perform:
obtaining audio data comprising one or more snores captured over a period of time by at least one microphone, wherein the audio data includes spectral features associated with the one or more snores of multiple entities comprising a user of the electronic device;
generating, based at least in part on the spectral features associated with the one or more snores, clusters of snoring activity associated with the multiple entities, wherein the clusters comprise a cluster of snoring activity associated with the user;
determining one or more breathing phase patterns based at least in part on the clusters of snoring activity associated with the multiple entities, wherein the one or more breathing phase patterns comprise a breathing phase pattern associated with the user;
determining a second breathing phase pattern included within the period of time, based at least in part on sensor data captured by one or more sensors in the electronic device;
determining an amount of correlation between each of the one or more breathing phase patterns associated with the clusters of snoring activity and the second breathing phase pattern associated with the sensor data, wherein the amount of correlation is associated with whether a breathing phase pattern is associated with the user and not associated with another entity;
determining that a first breathing phase pattern of the one or more breathing phase patterns is associated with the user and not associated with another entity when the amount of correlation between the first breathing phase pattern and the second breathing phase pattern meets at least a threshold amount of correlation;
and
generating snore metrics for the user based at least in part on the audio data captured by the at least one microphone.

8 more elements

A method of determining breathing phase patterns, the method comprising:

obtaining, by computing system comprising one or more processors, audio data comprising a recording of one or more snores captured over a period of time by at least one microphone, wherein the audio data includes spectral features associated with the one or more snores of multiple entities comprising a user of an electronic device;
generating, by the computing system, based at least in part on the spectral features associated with the one or more snores, clusters of snoring activity associated with the multiple entities, wherein the clusters comprise a cluster of snoring activity associated with the user;
determining, by the computing system, one or more breathing phase patterns based at least in part on the clusters of snoring activity associated with the multiple entities, wherein the one or more breathing phase patterns comprise a breathing phase pattern associated with the user;
determining, by the computing system, a second breathing phase pattern included within the period of time, based at least in part on sensor data captured by one or more sensors in the electronic device;
determining, by the computing system, an amount of correlation between each of the one or more breathing phase patterns associated with the clusters of snoring activity and the second breathing phase pattern associated with the sensor data, wherein the amount of correlation is associated with whether a breathing phase pattern is associated with the user and not associated with another entity;
determining, by the computing system, that a first breathing phase pattern of the one or more breathing phase patterns is associated with the user and not associated with another entity when the amount of correlation between the first breathing phase pattern and the second breathing phase pattern meets at least a threshold amount of correlation;
and
generating, by the computing system, snore metrics for the user based at least in part on the audio data captured by the at least one microphone.

5 more elements

A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of an electronic device, cause the electronic device to perform operations comprising:

obtaining audio data comprising a recording of one or more snores captured over a period of time by at least one microphone, wherein the audio data includes spectral features associated with the one or more snores of multiple entities comprising a user of the electronic device;
generating, based at least in part on the spectral features associated with the one or more snores, clusters of snoring activity associated with the multiple entities, wherein the clusters comprise a cluster of snoring activity associated with the user;
determining one or more breathing phase patterns based at least in part on the clusters of snoring activity associated with the multiple entities, wherein the one or more breathing phase patterns comprise a breathing phase pattern associated with the user;
determining a second breathing phase pattern included within the period of time, based at least in part on sensor data captured by one or more sensors in the electronic device;
determining an amount of correlation between each of the one or more breathing phase patterns associated with the clusters of snoring activity and the second breathing phase pattern associated with the sensor data, wherein the amount of correlation is associated with whether a breathing phase pattern is associated with the user and not associated with another entity;
determining that a first breathing phase pattern of the one or more breathing phase patterns is associated with the user and not associated with another entity when the amount of correlation between the first breathing phase pattern and the second breathing phase pattern meets at least a threshold amount of correlation;
and
generating snore metrics for the user based at least in part on the audio data captured by the at least one microphone.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/431,576Filed 4 Jun 2019
Published: US 2020/0383581 A110 Dec 2020
Granted: 25 Jan 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification16 codes

A61B 5/0205
Detecting, measuring or recording for evaluating the cardiovascular system, e.g. pulse, heart rate, blood pressure or blood flow: simultaneously…
A61B 5/1102
Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb: ballistocardiography
A61B 5/1116
Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb: determining posture transitions
A61B 5/4809
Sleep evaluation: sleep detection, i.e. determining whether a subject is asleep or not