IP Library › Granted Patent US 12,433,533
Granted Patent B2
US 12,433,533 · App. 18/287,969 · Granted Oct 7, 2025

Method, computing apparatus, and computer program for analyzing sleeping state of user through sound information

Inventors: Junki Hong (Daejeon, KR); Hong Hai Tran (Seoul, KR); Jinhwan Jung (Daejeon, KR); Dongheon Lee (Seongnam-si, KR)
Assignee: ASLEEP CO., LTD
A61B5/4812A61B5/7267A61B7/04G10L25/18G10L25/66H04R19/04H04R2201/003
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,433,533
App. No.
18/287,969
Granted
Oct 7, 2025
Kind
B2
Abstract

A method for analyzing a user's sleep state based on sound information for realizing the above-described tasks is disclosed. The method comprises the steps of acquiring sleep sound information related to the user's sleep, pre-processing the sleep sound information, and acquiring sleep state information by analyzing the pre-processed sleep sound information, wherein the sleep state information may include sleep stage information related to the user's sleep depth.

Claims (53)

1. A method for analyzing a sleep state of a user based on sleep sound information, comprising the steps of:

acquiring the sleep sound information including a sound related to breathing and a body movement of the user through a microphone module provided in a user terminal;

pre-processing, via a processor, the sleep sound information;

converting, via the processor, the pre-processed sleep sound information to a plurality of spectrograms;

acquiring, via the processor, sleep state information by processing the plurality of spectrograms as an input of a sleep analysis model including a feature extraction model and a feature classification model, wherein the feature extraction model includes one or more neural networks including an encoder pre-trained through an autoencoder and the feature classification model includes one or more neural networks including a fully connected layer in at least one of the one or more neural networks, and wherein the sleep analysis model has been trained with a learning data set including a plurality of training spectrograms each of which is tagged with sleep stage information;

generating, via the processor, external environment adjustment information based on the sleep state information; and

transmitting the external environment adjustment information to one or more environment adjustment units, the one or more environment adjustment units is configured to adjust a sleep environment of the user by operating one or more environment adjustment modules based on the external environment adjustment information,

wherein the acquired sleep state information includes sleep stage information related to a sleep depth of the user,

wherein each of the plurality of spectrograms corresponds to a predetermined epoch,

wherein the one or more neural networks included in the feature extraction model are configured to extract a plurality of features each of which is based on each of the plurality of spectrograms, and

wherein the one or more neural networks included in the feature classification model are configured to estimate a plurality of sleep stages which are based on the plurality of the features as the sleep stage information.

2. The method of claim 1 , wherein at least one of the one or more neural networks of the feature extraction model and the one or more neural networks of the feature classification model includes at least one of: a convolutional neural network (CNN) model, recurrent neural networks (RNNs), generative adversarial networks (GANs), and a restricted Boltzmann machines (RBMs), deep belief network (DBN), a Q network, a U network or a Siamese network.

3. The method of claim 1 , wherein the plurality of features are extracted by the one or more neural networks of the feature extraction model based on one or more patterns related to at least one of breathing sounds, breathing patterns, and movement patterns in each of the plurality of spectrograms.

4. The method of claim 1 , wherein each of the plurality of sleep stages is estimated based on at least a sequence of features which comprises a plurality of sequential features among the plurality of features.

5. The method of claim 1 , wherein the one or more environment adjustment modules is related to at least one of temperature, a wind direction, humidity, a sound and illuminance of the sleep environment of the user.

6. A device configured for analyzing a sleep state of a user based on sleep sound information, the device comprising:

a memory;

a microphone module configured to acquire the sleep sound information including a sound related to breathing and a body movement of the user; and

a processor configured to:

pre-process the sleep sound information;

convert the pre-processed sleep sound information to a plurality of spectrograms;

acquire sleep state information by processing the plurality of spectrograms as an input of a sleep analysis model including a feature extraction model and a feature classification model, wherein the feature extraction model includes one or more neural networks including an encoder pre-trained through an autoencoder and the feature classification model includes one or more neural networks including a fully connected layer in at least one of the one or more neural networks, and wherein the sleep analysis model has been trained with a learning data set including a plurality of training spectrograms each of which is tagged with sleep stage information;

generate external environment adjustment information based on the sleep state information; and

transmit the external environment adjustment information to one or more environment adjustment units, the one or more environment adjustment units is configured to adjust a sleep environment of the user by operating one or more environment adjustment modules based on the external environment adjustment information,

wherein the acquired sleep state information includes sleep stage information related to a sleep depth of the user,

wherein each of the plurality of spectrograms corresponds to a predetermined epoch,

wherein the one or more neural networks included in the feature extraction model are configured to extract a plurality of features each of which is based on each of the plurality of spectrograms, and

wherein the one or more neural networks included in the feature classification model are configured to estimate a plurality of sleep stages which are based on the plurality of the features as the sleep stage information.

7. The device of claim 6 , wherein at least one of the one or more neural networks of the feature extraction model and the one or more neural networks of the feature classification model includes at least one of: a convolutional neural network (CNN) model, recurrent neural networks (RNNs), generative adversarial networks (GANs), and a restricted Boltzmann machines (RBMs), deep belief network (DBN), a Q network, a U network or a Siamese network.

8. The device of claim 6 , wherein the plurality of features are extracted by the one or more neural networks of the feature extraction model based on one or more patterns related to at least one of breathing sounds, breathing patterns, and movement patterns in each of the plurality of spectrograms.

9. The device of claim 6 , wherein each of the plurality of sleep stages is estimated based on at least a sequence of features which comprises a plurality of sequential features among the plurality of features.

10. The device of claim 6 , wherein the one or more environment adjustment modules is related to at least one of temperature, a wind direction, humidity, a sound and illuminance of the sleep environment of the user.

11. A server comprising a sleep analysis model for analyzing a sleep state of a user based on sleep sound information including a sound related to breathing and a body movement of the user acquired through a microphone module provided in a user terminal, the server comprising:

a memory; and

a processor configured to:

pre-process the sleep sound information;

convert the pre-processed sleep sound information to a plurality of spectrograms;

acquire sleep state information by processing the plurality of spectrograms as an input of a sleep analysis model including a feature extraction model and a feature classification model, wherein the feature extraction model includes one or more neural networks including an encoder pre-trained through an autoencoder and the feature classification model includes one or more neural networks including a fully connected layer in at least one of the one or more neural networks, and wherein the sleep analysis model has been trained with a learning data set including a plurality of training spectrograms each of which is tagged with sleep stage information;

generate external environment adjustment information based on the sleep state information; and

transmit the external environment adjustment information to one or more environment adjustment units, the one or more environment adjustment units is configured to adjust a sleep environment of the user by operating one or more environment adjustment modules based on the external environment adjustment information,

wherein the acquired sleep state information includes sleep stage information related to a sleep depth of the user,

wherein each of the plurality of spectrograms corresponds to a predetermined epoch,

wherein the one or more neural networks included in the feature extraction model are configured to extract a plurality of features each of which is based on each of the plurality of spectrograms, and

wherein the one or more neural networks included in the feature classification model are configured to estimate a plurality of sleep stages which are based on the plurality of the features as the sleep stage information.

12. The server of claim 11 , wherein at least one of the one or more neural networks of the feature extraction model and the one or more neural networks of the feature classification model includes at least one of: a convolutional neural network (CNN) model, recurrent neural networks (RNNs), generative adversarial networks (GANs), and a restricted Boltzmann machines (RBMs), deep belief network (DBN), a Q network, a U network or a Siamese network.

13. The server of claim 11 , wherein the plurality of features are extracted by the one or more neural networks of the feature extraction model based on one or more patterns related to at least one of breathing sounds, breathing patterns, and movement patterns in each of the plurality of spectrograms.

14. The server of claim 11 , wherein each of the plurality of sleep stages is estimated based on at least a sequence of features which comprises a plurality of sequential features among the plurality of features.

15. The server of claim 11 , wherein the one or more environment adjustment modules is related to at least one of temperature, a wind direction, humidity, a sound and illuminance of the sleep environment of the user.

16. A computer-readable recording medium recording a computer program for executing the method for analyzing the sleep state of the user based on the sound information according to claim 1 .

17. A computer-readable recording medium recording a computer program for executing the method for analyzing the sleep state of the user based on the sound information according to claim 2 .

18. A computer-readable recording medium recording a computer program for executing the method for analyzing the sleep state of the user based on the sound information according to claim 3 .

19. A computer-readable recording medium recording a computer program for executing the method for analyzing the sleep state of the user based on the sound information according to claim 4 .

20. A computer-readable recording medium recording a computer program for executing the method for analyzing the sleep state of the user based on the sound information according to claim 5 .

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 24, 2023
From: HONG, JUNKI; TRAN, HONG HAI; JUNG, JINHWAN; LEE, DONGHEON
To: ASLEEP CO., LTD
Reel/Frame 065323/0738 →
Priority Claims (1)
KR 10-2021-0194186 · Dec 31, 2021 · national
Continuity (1)
Related Publication 20240081730A1 · Mar 14, 2024
References Cited (37)
US 6290654B1 · Karakasoglu · 2001 [cited by examiner]
US 20020106091A1 · Furst · 2002 [cited by examiner]
US 20040240699A1 · Hasegawa · 2004 [cited by examiner]
US 20060017558A1 · Albert · 2006 [cited by examiner]
US 20070041596A1 · Pan · 2007 [cited by examiner]
US 20150315013A1 · Hsieh · 2015 [cited by examiner]
US 20160187856A1 · Vilermo et al. · 2016 [cited by applicant]
US 20160212542A1 · Wang · 2016 [cited by examiner]
US 20190320972A1 · Tribble et al. · 2019 [cited by applicant]
US 20200054289A1 · Shimol · 2020 [cited by examiner]
US 20200138366A1 · Low · 2020 [cited by examiner]
US 20200296513A1 · Littrell · 2020 [cited by examiner]
US 20200315368A1 · Tsern · 2020 [cited by examiner]
US 20210275056A1 · McMahon · 2021 [cited by examiner]
US 20220134050A1 · Moriyasu · 2022 [cited by examiner]
US 20220322998A1 · Wang · 2022 [cited by examiner]
US 20230190140A1 · Tiron · 2023 [cited by examiner]
CN 111904424A · 2020 [cited by applicant]
JP 5662373B2 · 2015 [cited by applicant]
KR 20030032529A · 2003 [cited by applicant]
KR 20160096905A · 2016 [cited by applicant]
KR 20170057038A · 2017 [cited by applicant]
KR 20180014417A · 2018 [cited by applicant]
KR 1020180075832A · 2018 [cited by applicant]
KR 20180096176A · 2018 [cited by applicant]
KR 20190114925A · 2019 [cited by applicant]
KR 102081241A · 2020 [cited by applicant]
KR 20200129426A · 2020 [cited by applicant]
KR 20200139049A · 2020 [cited by applicant]
KR 102429256B1 · 2022 [cited by applicant]
WO 2011010384A1 · 2011 [cited by applicant]
Jung Kyung Hong et at. “Confidence-Based Framework Using Deep Learning for Automated Sleep Stage Scoring” Nature and Science of Sleep, Published: Dec. 24, 2021, Nature and Science of Sleep 2021:13 2239-2250. [cited by applicant]
Korean Office Action10-2022-0095338 Issued Dec. 2, 2022. [cited by applicant]
Korean Office Action 10-2023-0089780, Issued on Oct. 18, 2023. [cited by applicant]
Japanese Office Action 2023-557252, Issued Jun. 5, 2024. [cited by applicant]
Japanese Office Action 2023-169644, Issued Jul. 9, 2024. [cited by applicant]
Japanese Office Action 2023-169644 , Issued on Dec. 24, 2024. [cited by applicant]