CN114652280A - Sleep quality monitoring system and method - Google Patents
Sleep quality monitoring system and method Download PDFInfo
- Publication number
- CN114652280A CN114652280A CN202011535738.XA CN202011535738A CN114652280A CN 114652280 A CN114652280 A CN 114652280A CN 202011535738 A CN202011535738 A CN 202011535738A CN 114652280 A CN114652280 A CN 114652280A
- Authority
- CN
- China
- Prior art keywords
- user
- sleep
- monitoring
- sleep quality
- quality monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4812—Detecting sleep stages or cycles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4815—Sleep quality
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/0826—Detecting or evaluating apnoea events
Abstract
The invention relates to a sleep quality monitoring method, which comprises the following steps: carrying out sleep monitoring on the user according to the received vital sign data to obtain a sleep quality monitoring result of the user; monitoring whether the user snores or not according to the trained snore audio model and the collected user audio information; monitoring whether a user speaks a dream or not during sleeping by a voice endpoint detection method; and storing and fusing the obtained sleep quality monitoring result of the user, whether the user snores and whether the user speaks a dream during sleeping, so that the vital signs of the user can be comprehensively monitored. The invention also relates to a sleep quality monitoring system. The invention can enable the user to more comprehensively know the health condition and the sleep condition of the user, reduce the cost and facilitate the deployment and the migration.
Description
Technical Field
The invention relates to a sleep quality monitoring system and a sleep quality monitoring method.
Background
At present, most of existing sleep quality monitoring schemes or methods simply use a vital sign acquisition sensor and a bracelet or use a mobile phone APP to monitor sleep quality of a user, and the single mode can only monitor a single health index of the user. However, for sleep quality monitoring, the aspects of existing sleep quality monitoring evaluations are relatively single.
The prior art monitors the sleep index and data in a single mode, and is obviously not comprehensive enough. For example, it is obviously impossible to check abnormal sounds of a user during sleeping, that is, to determine whether the user snores or sleeps or not during sleeping, which affects the sleeping quality of the user.
Disclosure of Invention
In view of the above, it is desirable to provide a sleep quality monitoring system and method, which can analyze and monitor sleep data and determine whether the user has problems affecting the sleep quality, such as snoring and talking a dream, while sleeping by using an abnormal sound detection method.
The invention provides a sleep quality monitoring system, which comprises a biological signal acquisition sensor, a mobile terminal and a cloud server which are electrically connected with each other, wherein: the biological signal acquisition sensor is a non-contact sensor, is arranged under a user bed or on a roof when a user sleeps, and is used for acquiring and obtaining 'vital sign' data of the user during sleeping, wherein the 'vital sign' data comprises: heartbeat, respiration, pulse; the mobile terminal is used for receiving the vital sign data acquired by the biological signal acquisition sensor when a user sleeps and uploading the vital sign data to a cloud server; the comprehensive monitoring condition of the user vital signs returned by the cloud server is convenient for the user to check; the cloud server is used for receiving the 'vital sign' data uploaded by the mobile terminal when the user sleeps, comprehensively processing and analyzing the data, comprehensively monitoring the vital signs of the user, returning the comprehensive monitoring condition of the vital signs of the user to the mobile terminal, and facilitating the user to check the data.
Wherein, the comprehensive monitoring condition of the user vital signs comprises: the sleep quality monitoring result of the user, whether the user snores or not and whether the user speaks a dream while sleeping or not.
The cloud server comprises: sleep quality monitoring module, snore monitoring module, dream monitoring module and storage fusion module, wherein:
the sleep quality monitoring module is used for monitoring the sleep of the user according to the received vital sign data to obtain a sleep quality monitoring result of the user;
the snoring monitoring module is used for monitoring whether the user snores according to the trained snoring audio model and the collected user audio information;
the dream monitoring module is used for monitoring whether the user speaks a dream or not during sleeping through a voice endpoint detection method;
the storage fusion module is used for storing and fusing the obtained sleep quality monitoring result of the user, whether the user snores and whether the user speaks a dream during sleeping, and therefore the comprehensive monitoring on the vital signs of the user is achieved.
The sleep quality monitoring module is specifically configured to:
the method comprises the steps of taking 'vital sign' data acquired by a received biological signal acquisition sensor as an original data sample, conducting sleep staging on a user according to a sleep staging correlation principle, training a corresponding model through a machine learning method, and outputting a corresponding sleep quality monitoring result.
The snoring monitoring module is specifically configured to:
the microphone on the mobile terminal is used for collecting user audio information, when a person under guardianship sleeps, whether the user snores or not is monitored, and when the user snores, the user is reminded of sleep apnea syndrome cautiously.
The dream monitoring module is specifically used for:
when the monitored person sleeps, whether a voice signal is generated when the user sleeps is monitored to judge whether the monitored person speaks the dream.
The storage fusion module is specifically configured to:
make the user know the sleep state of oneself through different modes to with the sleep state is preserved simultaneously on high in the clouds server, thereby conveniently manages and analyzes user's health condition, the sleep form includes: sleep quality monitoring, snoring monitoring and dream recording.
The invention also provides a sleep quality monitoring method, which comprises the following steps: carrying out sleep monitoring on the user according to the received vital sign data to obtain a sleep quality monitoring result of the user; monitoring whether the user snores or not according to the trained snore audio model and the collected user audio information; monitoring whether a user speaks a dream or not during sleeping by a voice endpoint detection method; and storing and fusing the obtained sleep quality monitoring result of the user, whether the user snores and whether the user speaks a dream during sleeping, so that the vital signs of the user can be comprehensively monitored.
The invention uses a 'biological signal acquisition' sensor to acquire 'vital signs' of a user to monitor the user and the sleep quality; when the user sleeps, the snoring condition of the user can be monitored, the dream of the person under guardianship is recorded, and the user can know the health condition and the sleeping condition of the user more comprehensively. The invention not only can carry out more comprehensive health and sleep quality monitoring, but also has the advantages of convenient deployment and migration, reduces the cost, and has wide application fields and scenes, such as the fields of medical treatment, nursing and accompanying, personal families and the like.
Drawings
FIG. 1 is a diagram of the hardware architecture of the sleep quality monitoring system of the present invention;
fig. 2 is a schematic diagram of a comprehensive monitoring situation of a user vital sign of the mobile terminal 11 according to the embodiment of the present invention;
FIG. 3 is a schematic diagram of sleep staging performed on a user according to the principle related to sleep staging by using "vital sign" data as an original data sample according to an embodiment of the present invention;
fig. 4 is a flowchart of a sleep quality monitoring method according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Fig. 1 is a hardware architecture diagram of a sleep quality monitoring system 1 according to the present invention. The sleep quality monitoring system 1 includes: a biological signal acquisition sensor 10, a mobile terminal 11 and a cloud server 12 electrically connected to each other. Wherein:
the biological signal acquisition sensor 10 is a non-contact sensor, and is installed under a user bed or on a roof when a user sleeps, and is used for acquiring and obtaining 'vital sign' data of the user during sleeping. The "vital signs" data include: heartbeat, respiration, pulse.
The mobile terminal 11 is configured to receive the data of the "vital signs" of the user during sleep, which is acquired by the biological signal acquisition sensor 10, and upload the data of the "vital signs" to the cloud server 12; and facilitating the user to view the comprehensive monitoring condition of the user vital signs returned by the cloud server 12, please refer to fig. 2.
The mobile terminal 11 is an intelligent electronic device used by a user, and may be a smart phone, a tablet computer, or the like. The comprehensive monitoring condition of the vital signs of the user comprises the following steps: the sleep quality monitoring result of the user, whether the user snores or not and whether the user speaks a dream while sleeping or not.
The cloud server 12 is configured to receive the 'vital sign' data uploaded by the mobile terminal 11 during sleep of the user, perform comprehensive processing and analysis on the data, realize comprehensive monitoring on the vital sign of the user, return the comprehensive monitoring condition of the vital sign of the user to the mobile terminal 11, and facilitate the user to check the data.
The cloud server 12 includes: a sleep quality monitoring module 101, a snoring monitoring module 102, a dream monitoring module 103, and a memory fusion module 104.
The sleep quality monitoring module 101 is configured to perform sleep monitoring on the user according to the received vital sign data to obtain a sleep quality monitoring result of the user. Specifically, the method comprises the following steps:
in this embodiment, the sleep quality monitoring module 101 uses "vital sign" data collected by the received biological signal collecting sensor as an original data sample, performs sleep stages on the user according to the correlation principle of the sleep stages, trains a corresponding model by a machine learning method, and outputs a corresponding sleep quality monitoring result, so that the user can better know the sleep condition of the user.
Wherein the "vital signs" data comprises: heartbeat, respiration, pulse. The sleep staging is carried out on the user, and the result of the sleep staging comprises: stages and information of whether to sleep, light sleep, deep sleep, and rapid eye movement.
Further, sleep staging a user according to principles related to sleep staging includes:
the different stages in the sleep process are classified according to the different sleep depths, and the sleep process is divided into three stages, namely an awakening period, a rapid eye movement period and a non-rapid eye movement period. The Non Rapid Eye Movement (NREM) period is divided into 1, 2, 3 and 4 periods, wherein the 1 and 2 periods are light sleep periods, and the 3 and 4 periods are deep sleep periods.
Taking the 'vital sign' data as an original data sample, and performing sleep staging on the user according to the sleep staging correlation principle, including physiological signal acquisition, sleep condition judgment, sleep feature extraction and sleep staging, as shown in fig. 3. Firstly, acquiring three physiological signals of heart rate, respiration and body movement of a human body by using a Doppler sensor; secondly, judging whether to fall asleep or awake according to the amplitude and frequency characteristics of the body movement signals; then, extracting sleep characteristics by using the change relation of the heart rate and the respiration along with the sleep stage; and finally, realizing stages of different sleep stages in the sleep process based on the decision tree to obtain sleep stage data.
Carrying out preprocessing operations such as cleaning and labeling on the obtained sleep stage data to obtain a data format conforming to machine learning; and continuously training and adjusting the data by a machine learning method to obtain a final model.
The snoring monitoring module 102 is configured to monitor whether the user snores according to the trained snoring audio model and the collected user audio information. Specifically, the method comprises the following steps:
various snore audios are collected in advance to serve as snore samples, and corresponding snore audio models are trained through a deep learning method.
Furthermore, snore monitoring refers to monitoring the snore data of a person in a sleeping process by using a non-contact and non-invasive sound acquisition means and analyzing the acoustic characteristics of the snore signals, so as to obtain rapid and accurate identification of the snore signals.
The method and the device utilize the deep neural network to identify and classify the characteristics of the snore candidates. And sending all the extracted snore candidate feature maps into a deep neural network for feature extraction operation, combining the convolution result sequences to be used as a feature sequence with a time dimension, sending the feature sequence into a nonlinear sampling layer and a smooth layer of the next layer for processing, and finally obtaining the snore or non-snore classification results. That is, the corresponding snore audio model is trained.
In the embodiment, the microphone on the mobile terminal 11 is used for collecting the audio information of the user, and when a person under guardianship sleeps, the user is monitored to snore or not, so that the user is reminded of sleep apnea syndrome carefully, the health condition of the user is better monitored, and the sleep quality of the user is improved.
The dream monitoring module 103 is configured to monitor whether the user speaks a dream while sleeping through a voice endpoint detection method. Specifically, the method comprises the following steps:
voice endpoint Detection, also called Voice Activity Detection (VAD), aims to distinguish between speech and non-speech areas.
Based on the voice endpoint detection method, the microphone on the mobile terminal 11 is used for collecting the user audio information, the starting point and the ending point of the voice are accurately positioned from the voice with noise, the mute part is removed, the noise part is removed, and a segment of really effective content of the voice is found. When the monitored person sleeps, whether a voice signal is generated when the monitored person sleeps is monitored, and whether the monitored person speaks the dream is judged according to the principle so that the monitored person can know the sleeping condition of the monitored person.
The voice endpoint detection refers to the time for collecting voice signals, and the voice signals from the beginning of speaking to the end of speaking are collected and processed.
The storage fusion module 104 is used for storing and fusing the obtained sleep quality monitoring result of the user, whether the user snores or not and whether the user speaks a dream during sleeping or not, so as to realize comprehensive monitoring of the vital signs of the user. Specifically, the method comprises the following steps:
the storage fusion module 104 fuses the above various schemes together, so as to monitor the vital signs of the user, and enable the user to know the sleep state of the user in various ways, including: the sleep state information is simultaneously stored in the cloud server 12, so that the health condition of the user can be conveniently managed and analyzed.
Fig. 4 is a flowchart illustrating the operation of the sleep quality monitoring method according to the preferred embodiment of the present invention.
And step S1, carrying out sleep monitoring on the user according to the received vital sign data to obtain a sleep quality monitoring result of the user. Specifically, the method comprises the following steps:
in this embodiment, the cloud server 12 takes "vital sign" data collected by the received biological signal collecting sensor as an original data sample, performs sleep staging on the user according to the principle related to the sleep staging, trains a corresponding model by a machine learning method, and outputs a corresponding sleep quality monitoring result, so that the user can better know the sleep condition of the user.
Wherein the "vital signs" data comprises: heartbeat, respiration, pulse. The sleep stage is carried out on the user, and the result of the sleep stage comprises: stages and information of whether to sleep, light sleep, deep sleep, and rapid eye movement.
Further, sleep staging a user according to principles related to sleep staging includes:
the different stages in the sleep process are classified according to the different sleep depths, and the sleep process is divided into three stages, namely an awakening period, a rapid eye movement period and a non-rapid eye movement period. The Non Rapid Eye Movement (NREM) period is divided into 1, 2, 3 and 4 periods, wherein the 1 and 2 periods are light sleep periods, and the 3 and 4 periods are deep sleep periods.
Taking the 'vital sign' data as an original data sample, and performing sleep staging on the user according to the sleep staging correlation principle, including physiological signal acquisition, sleep condition judgment, sleep feature extraction and sleep staging, as shown in fig. 3. Firstly, acquiring three physiological signals of heart rate, respiration and body movement of a human body by using a Doppler sensor; secondly, judging whether to fall asleep or awake according to the amplitude and frequency characteristics of the body movement signals; then, extracting sleep characteristics by using the change relation of the heart rate and the respiration along with the sleep stage; and finally, realizing stages of different sleep stages in the sleep process based on the decision tree to obtain sleep stage data.
Carrying out preprocessing operations such as cleaning and labeling on the obtained sleep stage data to obtain a data format conforming to machine learning; and continuously training and adjusting the data by a machine learning method to obtain a final model.
And step S2, monitoring whether the user snores or not according to the trained snore audio model and the collected user audio information. Specifically, the method comprises the following steps:
various snore audios are collected in advance to serve as snore samples, and corresponding snore audio models are trained through a deep learning method.
Furthermore, snore monitoring refers to monitoring the snore data of a person in a sleeping process by using a non-contact and non-invasive sound acquisition means and analyzing the acoustic characteristics of the snore signals, so as to obtain rapid and accurate identification of the snore signals.
The method and the device utilize the deep neural network to identify and classify the features of the snore candidates. And sending all the extracted snore candidate feature maps into a deep neural network for feature extraction operation, combining the convolution result sequences to be used as a feature sequence with a time dimension, sending the feature sequence into a nonlinear sampling layer and a smooth layer of the next layer for processing, and finally obtaining the snore or non-snore classification results. That is, the corresponding snore audio model is trained.
In the embodiment, the microphone on the mobile terminal 11 is used for collecting the audio information of the user, and when a person under guardianship sleeps, the user is monitored to snore or not, so that the user is reminded of sleep apnea syndrome carefully, the health condition of the user is better monitored, and the sleep quality of the user is improved.
Step S3, monitoring whether the user speaks the dream while sleeping through the voice endpoint detection method. Specifically, the method comprises the following steps:
voice endpoint Detection, also called Voice Activity Detection (VAD), aims to distinguish between Voice and non-Voice areas.
Based on the voice endpoint detection method, the microphone on the mobile terminal 11 is used for collecting the user audio information, the starting point and the ending point of the voice are accurately positioned from the voice with noise, the mute part is removed, the noise part is removed, and a segment of really effective content of the voice is found. When the monitored person sleeps, whether a voice signal is generated when the monitored person sleeps is monitored, and whether the monitored person speaks the dream is judged according to the principle so that the monitored person can know the sleeping condition of the monitored person.
The voice endpoint detection refers to the time for collecting voice signals, and the voice signals from the beginning of speaking to the end of speaking are collected and processed.
And step S4, storing and fusing the obtained sleep quality monitoring result of the user, whether the user snores and whether the user speaks a dream during sleeping, and realizing comprehensive monitoring of the vital signs of the user. Specifically, the method comprises the following steps:
fuse above multiple scheme together, realize the monitoring to user's vital sign to make the user know oneself sleep state through multiple mode, include: the sleep state information is simultaneously stored on a cloud server, so that the health condition of a user can be conveniently managed and analyzed.
The invention provides a set of solution scheme comprising a series of modules and algorithms, such as a 'biological signal acquisition' sensor, an acquisition program, a sleep quality monitoring algorithm, snoring monitoring, dream monitoring and the like; the user can conveniently carry out comprehensive health monitoring and evaluation on the monitored person, and the user can more comprehensively know the health condition of the monitored person. Compared with the method for monitoring the sleep quality or managing the health by using a single mode, the method can know the sleep condition of the person under guardianship besides the vital sign information (including heartbeat, respiration and pulse) collected by the sensor. Therefore, the system is helpful for helping the user to know the physical state of the person under guardianship more comprehensively, and is convenient for monitoring and managing the health condition.
Although the present invention has been described with reference to the presently preferred embodiments, it will be understood by those skilled in the art that the foregoing description is illustrative only and is not intended to limit the scope of the invention, as claimed.
Claims (8)
1. The utility model provides a sleep quality monitoring system, its characterized in that, this system includes mutual electric connection's biological signal acquisition sensor, removes end and high in the clouds server, wherein:
the biological signal acquisition sensor is a non-contact sensor, is arranged under a user bed or on a roof when a user sleeps, and is used for acquiring and obtaining 'vital sign' data of the user during sleeping, wherein the 'vital sign' data comprises: heartbeat, respiration, pulse;
the mobile terminal is used for receiving the 'vital sign' data acquired by the biological signal acquisition sensor when the user sleeps and uploading the 'vital sign' data to a cloud server; the comprehensive monitoring condition of the user vital signs returned by the cloud server is convenient for the user to check;
the cloud server is used for receiving the 'vital sign' data uploaded by the mobile terminal when the user sleeps, comprehensively processing and analyzing the data, comprehensively monitoring the vital signs of the user, returning the comprehensive monitoring condition of the vital signs of the user to the mobile terminal, and facilitating the user to check the data.
2. The sleep quality monitoring system according to claim 1, characterized in that the comprehensive monitoring of the user's vital signs comprises: the sleep quality monitoring result of the user, whether the user snores or not and whether the user speaks a dream while sleeping or not.
3. The sleep quality monitoring system of claim 2, wherein the cloud server comprises: sleep quality monitoring module, snore monitoring module, dream monitoring module and storage fusion module, wherein:
the sleep quality monitoring module is used for monitoring the sleep of the user according to the received vital sign data to obtain a sleep quality monitoring result of the user;
the snoring monitoring module is used for monitoring whether the user snores according to the trained snoring audio model and the collected user audio information;
the dream monitoring module is used for monitoring whether the user speaks a dream or not during sleeping through a voice endpoint detection method;
the storage fusion module is used for storing and fusing the obtained sleep quality monitoring result of the user, whether the user snores or not and whether the user speaks a dream during sleeping or not, and therefore the comprehensive monitoring of the vital signs of the user is achieved.
4. The sleep quality monitoring system according to claim 3, wherein the sleep quality monitoring module is specifically configured to:
the method comprises the steps of taking 'vital sign' data acquired by a received biological signal acquisition sensor as an original data sample, conducting sleep staging on a user according to a sleep staging correlation principle, training a corresponding model through a machine learning method, and outputting a corresponding sleep quality monitoring result.
5. The sleep quality monitoring system according to claim 4, wherein the snoring monitoring module is specifically configured to:
the microphone on the mobile terminal is used for collecting user audio information, when a person under guardianship sleeps, whether the user snores or not is monitored, and when the user snores, the user is reminded of sleep apnea syndrome cautiously.
6. The sleep quality monitoring system of claim 4, wherein the dream monitoring module is specifically configured to:
when the monitored person sleeps, whether a voice signal is generated when the user sleeps is monitored to judge whether the monitored person speaks the dream.
7. The sleep quality monitoring system according to claim 4, wherein the memory fusion module is specifically configured to:
make the user know the sleep state of oneself through different modes to with the sleep state is preserved simultaneously on high in the clouds server, thereby conveniently manages and analyzes user's health condition, the sleep form includes: monitoring sleep quality, monitoring snoring and recording dream.
8. A sleep quality monitoring method is characterized by comprising the following steps:
carrying out sleep monitoring on the user according to the received vital sign data to obtain a sleep quality monitoring result of the user;
monitoring whether the user snores or not according to the trained snore audio model and the collected user audio information;
monitoring whether a user speaks a dream or not during sleeping by a voice endpoint detection method;
and storing and fusing the obtained sleep quality monitoring result of the user, whether the user snores and whether the user speaks a dream during sleeping, so that the vital signs of the user can be comprehensively monitored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011535738.XA CN114652280A (en) | 2020-12-23 | 2020-12-23 | Sleep quality monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011535738.XA CN114652280A (en) | 2020-12-23 | 2020-12-23 | Sleep quality monitoring system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114652280A true CN114652280A (en) | 2022-06-24 |
Family
ID=82025594
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011535738.XA Pending CN114652280A (en) | 2020-12-23 | 2020-12-23 | Sleep quality monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114652280A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115581435A (en) * | 2022-08-30 | 2023-01-10 | 湖南万脉医疗科技有限公司 | Sleep monitoring method and device based on multiple sensors |
-
2020
- 2020-12-23 CN CN202011535738.XA patent/CN114652280A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115581435A (en) * | 2022-08-30 | 2023-01-10 | 湖南万脉医疗科技有限公司 | Sleep monitoring method and device based on multiple sensors |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bi et al. | AutoDietary: A wearable acoustic sensor system for food intake recognition in daily life | |
| US11172909B2 (en) | Sensor fusion to validate sound-producing behaviors | |
| Matos et al. | An automated system for 24-h monitoring of cough frequency: the leicester cough monitor | |
| US20220007964A1 (en) | Apparatus and method for detection of breathing abnormalities | |
| CN105765656A (en) | Controlling speech recognition process of computing device | |
| Shuzo et al. | Wearable eating habit sensing system using internal body sound | |
| CN110811647B (en) | Multi-channel hidden lie detection method based on ballistocardiogram signal | |
| AU2021250913B2 (en) | Localized collection of biological signals, cursor control in speech-assistance interface based on biological electrical signals and arousal detection based on biological electrical signals | |
| WO2006059325A1 (en) | Method and system of indicating a condition of an individual | |
| Cohen-McFarlane et al. | Comparison of silence removal methods for the identification of audio cough events | |
| Fattah et al. | Stetho-phone: Low-cost digital stethoscope for remote personalized healthcare | |
| CN112869716B (en) | Pulse feature identification system and method based on two-channel convolutional neural network | |
| CN108392201B (en) | Brain training method and related equipment | |
| CN114587288A (en) | Sleep monitoring method, device and equipment | |
| Nguyen et al. | A potential approach for emotion prediction using heart rate signals | |
| CN114652280A (en) | Sleep quality monitoring system and method | |
| CN116057627A (en) | Computer-implemented method for providing data for automatic assessment of infant crying | |
| Sofwan et al. | Normal and Murmur Heart Sound Classification Using Linear Predictive Coding and k-Nearest Neighbor Methods | |
| CN103186701A (en) | Method, system and equipment for analyzing eating habits | |
| Sivanjaneyulu et al. | Cnn based ppg signal quality assessment using raw ppg signal for energy-efficient ppg analysis devices in internet of medical things | |
| CN115770043A (en) | Dream emotion recognition method and device, electronic equipment and storage medium | |
| CN215349053U (en) | Congenital heart disease intelligent screening robot | |
| CN113764099A (en) | Psychological state analysis method, device, equipment and medium based on artificial intelligence | |
| CN113178195A (en) | Speaker identification method based on sound-induced electroencephalogram signals | |
| CN113208621A (en) | Dreaming interaction method and system based on EEG signal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |