CN115153444A - Multi-equipment multi-sensor sleep monitoring system - Google Patents
Multi-equipment multi-sensor sleep monitoring system Download PDFInfo
- Publication number
- CN115153444A CN115153444A CN202210898365.5A CN202210898365A CN115153444A CN 115153444 A CN115153444 A CN 115153444A CN 202210898365 A CN202210898365 A CN 202210898365A CN 115153444 A CN115153444 A CN 115153444A
- Authority
- CN
- China
- Prior art keywords
- data
- sleep
- respiratory
- processing module
- time
- 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
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
-
- 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
- A61B5/4815—Sleep quality
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Cardiology (AREA)
- Physiology (AREA)
- Pulmonology (AREA)
- Anesthesiology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a multi-equipment multi-sensor sleep monitoring system, which comprises: data acquisition module and data processing module, data acquisition module includes bracelet acquisition element, radar acquisition element and sound acquisition element, bracelet acquisition element gathers the first data that include first dynamic data, blood oxygen data, rhythm of the heart data and first breathing data of target in real time. The invention discloses a multi-equipment multi-sensor sleep monitoring system, which fully utilizes the advantages of various equipment and various sensors, extracts more accurate original data detected by each equipment and sensor for sleep analysis, and evaluates the same type of data according to the accuracy of the data and gives different weights to the same type of data, and the different types of data are used for analyzing and judging the sleep state according to the respective characteristics of the data, so that the accuracy of the original data is improved while the original detection data quantity is improved, and the accuracy of the sleep detection analysis is improved.
Description
Technical Field
The invention belongs to the technical field of sleep monitoring, and particularly relates to a multi-device multi-sensor sleep monitoring system.
Background
Sleep monitoring in daily use currently relies on a single monitoring device. For example, bracelet monitoring is carried out, body movement information and vital sign information at night are recorded through a body movement sensor, an optical heart rate sensor and an optical blood oxygen sensor which are arranged in a bracelet, and sleep conditions are analyzed; the mobile phone sleep monitoring APP generally utilizes a built-in body movement sensor and a built-in microphone to record the body movement and sound conditions of the sleep all night, and analyzes the information to obtain the sleep state analysis all night; the radar sleep monitoring can monitor the human body movement, respiration and heart rate in a non-contact and long-distance manner, and analyze the sleep by utilizing the information, so that the detection method avoids the discomfort caused by the contact of detection equipment and the human body, and does not influence the daily sleep of the human body; in addition, the sleep monitoring equipment available for families also comprises an intelligent mattress, a camera and the like.
The sleep monitoring equipment uses various data in the monitoring process, and the sleep state analysis result is obtained through comprehensive analysis. However, it is difficult to accurately monitor various data with a single monitoring device. The daily sleep monitoring equipment cannot be the same as professional sleep monitoring equipment, and various physiological signals can be comprehensively collected by the most suitable sensor and the most suitable using method, such as a polysomnography system. At present, the number of sensors in common sleep monitoring equipment is limited, the types of collected original signals are few, and the signal quality is uneven.
In the sleep analysis algorithm of bracelet, can use information such as body motion, breathing, rhythm of the heart usually, wherein hand motion and rhythm of the heart can be directly obtained by the built-in body motion sensor of bracelet and PPG sensor, and because wear next to the shin, think these two kinds of data relatively accurate usually, respiratory signal generally is derived by PPG signal or body motion signal indirect, and the accuracy is influenced by detection condition and algorithm greatly to influence sleep state analysis.
The mobile phone sleep monitoring APP usually needs the mobile phone to be placed at a place close to a tested person, the human body activity is presumed by detecting the vibration of the mattress, and the sleep sound is recorded through the microphone. However, the vibration of the mattress is related to the body shape of the tested person and the structure material of the mattress, so the body movement information obtained by the method is inaccurate. Common radar sleep monitoring equipment also utilizes body movement, breathing and heart rate information to carry out sleep state analysis, and the principle of its detection breathing, heart rate is based on the small action of the human body that human breathing heartbeat can drive, and the radar catches these small actions and carries out further analysis, processing, just can extract people's breathing, heartbeat information. The heartbeat drives the body to move very weakly, and the irradiation position of the radar can generate great influence on the detection result. In the actual sleeping process, the position and the posture of a person are random, so that the accuracy of heart rate data is difficult to ensure.
Other sleep monitoring devices also have similar problems, with some data being more accurately detected and others being less accurately detected. These less accurate raw data become short plates for sleep analysis, limiting the accuracy of sleep analysis.
Therefore, the above problems are further improved.
Disclosure of Invention
The invention mainly aims to provide a multi-equipment multi-sensor sleep monitoring system, which fully utilizes the advantages of various equipment and various sensors, extracts more accurate original data detected by each equipment and sensor for sleep analysis, gives different weights to the same type of data according to the accuracy evaluation of the same type of data, and is used for analyzing and judging the sleep state according to the respective characteristics of the different types of data, so that the accuracy of the original data is improved while the original detection data quantity is improved, and the accuracy of the sleep detection analysis is improved.
To achieve the above object, the present invention provides a multi-device multi-sensor sleep monitoring system for comprehensively analyzing a sleep condition of a target (person), comprising: data acquisition module and data processing module, data acquisition module includes bracelet collection element, radar acquisition element and sound acquisition element, wherein:
the bracelet acquisition unit acquires first data of a target, including first motion data, blood oxygen data, heart rate data and first respiratory data, in real time and transmits the acquired first data to the data processing module in real time;
the radar acquisition unit acquires second data of a target in real time, wherein the second data comprises second body movement data and second breathing data, and transmits the acquired second data to the data processing module in real time;
the sound acquisition unit acquires sound data of a target in real time and transmits the acquired sound data to the data processing module in real time;
the data processing module respectively obtains the first data, the second data and the third data and then carries out real-time processing and comprehensive processing on the data, so that a real-time sleep analysis report and a comprehensive sleep analysis report are respectively output.
As a further preferred technical solution of the above technical solution, for the instant processing, the data processing module performs instant analysis on the first data, the second data, and the third data, so as to make a display or an alarm responding in time, wherein:
for blood oxygen data, a data processing module analyzes the blood oxygen data of first data, if the current blood oxygen data is in a blood oxygen normal range, the data processing module outputs a target normal blood oxygen signal, if the current blood oxygen data is lower than a first blood oxygen threshold (preferably lower than 95%), the data processing module outputs a target hypoxia situation signal, if the current blood oxygen data is lower than a second blood oxygen threshold (preferably lower than 80%), the data processing module outputs a target hypoxia danger signal and outputs a blood oxygen alarm signal to a target person (through sound-light or vibration alarm and the like) or a third party (relatives and the like);
for heart rate data, a data processing module analyzes the heart rate data of first data, if the current heart rate data is in a heart rate normal range, the data processing module outputs a target normal heart rate signal, and if the current heart rate data is lower than a first heart rate threshold (preferably lower than 30 bps), the data processing module outputs a target bradycardia or stops a danger signal and outputs a heart rate alarm signal to a target person (through acousto-optic or vibration alarm and the like) or a third party (relatives and the like);
for the body movement data, the data processing module analyzes through the first body movement data of the first data and the second body movement data of the second data, so as to obtain each sleep state of the target, wherein:
for the time of getting to bed, a target exists in the monitoring range of the radar acquisition unit;
for the sleep starting time, counting the number n of micro-motion and large motion detected in unit time (such as 10 minutes) from the time of getting on bed, and determining that the sleep starts if the number n is lower than a certain threshold nth 1;
for the sleep ending time, counting the number n of micro-motion or large motion in unit time (such as 10 minutes) from the sleep starting time, and determining that a period of sleep is ended if the number n of micro-motion or large motion is higher than a certain threshold nth 2;
for the time of leaving the bed, whether a target exists in the monitoring range of the radar acquisition unit or not is judged;
counting the times n1 and n2 of occurrence of fine actions in unit time monitored by a bracelet acquisition unit and a radar acquisition unit in the sleep from the sleep starting time to the sleep ending time, and when n1 + alpha + n2 (1-alpha) is lower than a certain threshold nth3, determining that the current sleep state is deep sleep and marking (otherwise, shallow sleep), wherein alpha is a weight of first movement data in signal evaluation, the range is greater than 0 and less than 1, and the larger the value is, the larger the specific gravity of the first movement data is, the larger the influence on the judgment of the sleep depth is;
for the respiratory data, the data processing module analyzes through first respiratory data of the first data and second respiratory data of the second data so as to obtain each respiratory state of the target, wherein:
the data processing module takes the second respiratory data as priority, simultaneously checks the signal quality of the first respiratory data and the signal quality of the second respiratory data in real time, timely switches the respiratory data, takes the respiratory data with high signal quality as analysis, takes the second respiratory data in unit time, carries out frequency domain transformation to obtain frequency spectrum information, the frequency corresponding to a peak point of the frequency spectrum is recorded as f0, the frequency spectrum energy in (f 0-delat _ f, f0+ delta _ f) is recorded as P0 comprehensively, the total energy of the whole frequency spectrum is recorded as Ps, when P0/(Ps-P0) is lower than a certain threshold value, the second respiratory data collected by the radar collecting unit is determined to be poor in quality, and is switched to the first respiratory data collected by the bracelet collecting unit, and if the peak value of the first respiratory data collected by the bracelet collecting unit is lower than the certain threshold value, the first respiratory data is determined to be too weak, the data reliability is lower, and the second respiratory data is switched to;
for the sound data, the data processing module analyzes the sound data of the third data, calculates the frequency, the intensity and the peak value change of the sound data in unit time in real time, if the sound fluctuation is uniform, the corresponding wave peaks are periodic and the intensity change is small, the snore marking is performed on the corresponding time, if the sound fluctuation is large, the interval difference of the corresponding wave peaks is large, the peak value difference is large, the snore emphasis marking is required, and a snore alarm signal is output to the target;
and outputting an instant sleep analysis report by the data processing module through each data.
As a further preferred technical solution of the above technical solution, for the comprehensive processing, the data processing module performs comprehensive analysis on the first data, the second data and the third data, so as to make respiratory quality assessment and sleep quality analysis, wherein:
for respiratory quality assessment, when respiratory waveforms obviously fluctuate and show that frequency or intensity changes greatly compared with historical data and indicate the occurrence of respiratory disturbance or apnea, the number of times of apnea occurrence is counted through data monitoring all night, the worse respiratory quality is shown as the number of times of apnea occurrence and respiratory disturbance occurrence is more, a respiratory quality score is set as Soc _ resp, a full score is 100, every time respiratory abnormality occurrence is deducted by a certain score, the severity of apnea is comprehensively assessed through sound waveform characteristics and blood oxygen data, sound data are compared at the same time, time periods with apnea and snore marks occurring at the same time are checked and marked, and the number of times is counted;
for sleep quality analysis, the sleep quality is related to deep sleep (deep sleep) proportion, sleep interruption times and turnover times, and a sleep quality comprehensive score is calculated, wherein the used data are as follows:
deep sleep ratio a1: counting sleep data all night, calculating the proportion of deep sleep time to total sleep time, and recording as a deep sleep proportion a1, wherein a1 is a value which is more than 0 and less than 1;
turning-over times a2: turning over is a large motion which is continuous in a short time, and the turning over motion is accurately judged and marked through the first motion data and the second motion data;
waking number a3: the more waking times at night, the worse the sleep;
respiratory quality score a4: if the respiratory quality assessment score is low, the respiratory quality during the sleep process is poor;
based on the above four data, the sleep score Soc _ sleep is calculated as follows:
Soc_sleep＝SocA1+SocA2+SocA3+SocA4；
SocA1＝100*α1*(0.5+a1)；
SocA2＝100*α2*cur(a2)；
SocA3＝100*α3*(1-0.2*a3)；
SocA4＝100*α4*a4；
the cur is a centrosymmetric distribution curve (the center is located at x =25, the peak value is 1), the larger the deviation from the center is, the smaller the value of cur (x) is, the more alpha 1, alpha 2, alpha 3 and alpha 4 are the weight values of all parameters occupying the sleep evaluation, the larger the weight value is, the larger the influence of the parameters on the sleep quality evaluation is, and finally, the comprehensive sleep analysis report is output by combining the respiratory quality evaluation and the sleep quality analysis.
As a further preferred technical solution of the above technical solution, before monitoring, self-checking is respectively performed on the data acquisition module and the data processing module, so as to ensure that the data acquisition module and the data processing module work normally in a monitoring period.
As a further preferable technical solution of the above technical solution, the data processing module transmits the timely sleep analysis report and the comprehensive sleep analysis report to an equipment terminal (including a mobile phone, etc.).
Drawings
Fig. 1 is a schematic structural diagram of a multi-device multi-sensor sleep monitoring system of the present invention.
Fig. 2 is a schematic diagram of the cur (x) parameter in the sleep quality analysis of a multi-device multi-sensor sleep monitoring system of the present invention.
Detailed Description
The following description is presented to disclose the invention so as to enable any person skilled in the art to practice the invention. The preferred embodiments in the following description are given by way of example only, and other obvious variations will occur to those skilled in the art. The basic principles of the invention, as defined in the following description, may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the invention.
In the preferred embodiments of the present invention, those skilled in the art should note that the objects and the like referred to in the present invention can be regarded as the prior art.
Preferred embodiments.
The invention discloses a multi-equipment multi-sensor sleep monitoring system, which is used for comprehensively analyzing the sleep condition of a target (personnel), and comprises the following steps: data acquisition module and data processing module, data acquisition module includes bracelet collection element, radar acquisition element and sound acquisition element, wherein:
the bracelet acquisition unit acquires first data of a target, including first motion data, blood oxygen data, heart rate data and first respiratory data, in real time and transmits the acquired first data to the data processing module in real time;
the radar acquisition unit acquires second data of a target in real time, wherein the second data comprises second body movement data and second breathing data, and transmits the acquired second data to the data processing module in real time;
the sound acquisition unit acquires sound data of a target in real time and transmits the acquired sound data to the data processing module in real time;
the data processing module respectively obtains the first data, the second data and the third data and then carries out real-time processing and comprehensive processing on the data, so that a real-time sleep analysis report and a comprehensive sleep analysis report are respectively output.
Specifically, for the instant processing, the data processing module performs instant analysis on the first data, the second data and the third data, so as to make a display or alarm responding in time, wherein:
for blood oxygen data, a data processing module analyzes the blood oxygen data of first data, if the current blood oxygen data is in a blood oxygen normal range (95% -100%), the data processing module outputs a target normal blood oxygen signal, if the current blood oxygen data is lower than a first blood oxygen threshold (preferably lower than 95%), the data processing module outputs a target hypoxia situation signal, and if the current blood oxygen data is lower than a second blood oxygen threshold (preferably lower than 80%), the data processing module outputs a target hypoxia danger signal and outputs a blood oxygen alarm signal to a target person (through sound-light or vibration alarm, etc.) or a third party (relatives, etc.);
for heart rate data, a data processing module analyzes the heart rate data of first data, if the current heart rate data is in a heart rate normal range (60-100 bps), the data processing module outputs a target normal heart rate signal, and if the current heart rate data is lower than a first heart rate threshold (preferably lower than 30 bps), the data processing module outputs a target bradycardia or stops a danger signal and outputs a heart rate alarm signal to a target person (through acousto-optic or vibration alarm and the like) or a third party (relatives and the like);
blood oxygen and heart rate's data all derive from bracelet acquisition element, however bracelet acquisition element's detection effect rather than wearing whether laminating relevant, if heart rate and blood oxygen data that the bracelet uploaded are low or zero excessively, and radar acquisition element indicates that someone exists and respiratory data is normal, is probably that the bracelet detects inefficacy, and its upload data no longer are used as sleep analysis.
For the body movement data, the data processing module analyzes through first body movement data of the first data and second body movement data of the second data so as to obtain each sleep state of the target, wherein:
and displaying whether the target is in the bed or not and whether the target is in a sleeping state or not in real time. The first motion data in the hand ring can only be used for detecting the motion of the hand, and the radar has a wide detection range and can detect the motion condition of the whole body, so that the time when a tester gets in or out of bed and starts or ends sleeping can be more accurately reflected.
For the bed-climbing time, a target exists in the monitoring range of the radar acquisition unit;
for the sleep starting time, counting the number n of micro-motion and large motion detected in unit time (such as 10 minutes) from the time of getting to bed, and determining that the sleep starts if the number n is lower than a certain threshold nth 1;
for the sleep ending time, counting the number n of micro-motion or large motion in unit time (such as 10 minutes) from the sleep starting time, and determining that a period of sleep is ended if the number n of micro-motion or large motion is higher than a certain threshold nth 2;
for the time of leaving the bed, whether a target exists in the monitoring range of the radar acquisition unit or not is judged;
counting the times n1 and n2 of occurrence of fine actions in unit time monitored by a bracelet acquisition unit and a radar acquisition unit in the sleep from the sleep starting time to the sleep ending time, and when n1 + alpha + n2 (1-alpha) is lower than a certain threshold nth3, determining that the current sleep state is deep sleep and marking (otherwise, shallow sleep), wherein alpha is a weight of first movement data in signal evaluation, the range is greater than 0 and less than 1, and the larger the value is, the larger the specific gravity of the first movement data is, the larger the influence on the judgment of the sleep depth is;
for the respiratory data, the data processing module analyzes the first respiratory data of the first data (the respiratory data can be indirectly derived through the collected PPG signal of the bracelet collecting unit, and the signal quality of the respiratory data is related to the original signal quality of the PPG) and the second respiratory data of the second data, so as to obtain each respiratory state of the target, wherein:
the respiratory data that the radar was gathered is closely related with the position of human for the radar, when people's thorax was just facing to the radar detection face, can obtain clear, the better respiratory data of signal noise, when human thorax was far away from the radar detection face or when being back of the body to the radar, respiratory data quality is relatively poor.
The data processing module takes the second respiratory data as priority, simultaneously checks the signal quality of the first respiratory data and the second respiratory data in real time, timely switches the respiratory data, takes the respiratory data with high signal quality as analysis, takes the second respiratory data in unit time, carries out frequency domain transformation to obtain frequency spectrum information, the frequency corresponding to a peak point of the frequency spectrum is recorded as f0, the frequency spectrum energy in (f 0-delat _ f, f0+ delta _ f) is recorded as P0 comprehensively, the total energy of the whole frequency spectrum is recorded as Ps, when P0/(Ps-P0) is lower than a certain threshold value, the second respiratory data collected by the radar collection unit is determined to be poor in quality, the first respiratory data collected by the bracelet collection unit is switched, and if the signal peak value of the first respiratory data collected by the bracelet collection unit is lower than a certain threshold value, the first respiratory data is determined to be too weak, the data is low in reliability, and the second respiratory data is switched;
for the sound data, the data processing module analyzes the sound data of the third data, calculates the frequency, the intensity and the peak value change of the sound data in unit time in real time, if the sound fluctuation is uniform, the corresponding wave peaks are periodic and the intensity change is small, the target is only snored, snore marking is carried out on the corresponding time, if the sound fluctuation is large, the corresponding wave peak interval difference is large, the peak value difference is large, snore key marking is needed, and a snore alarm signal is output to the target;
and outputting an instant sleep analysis report by the data processing module through each data.
Further, for the integrated processing, the data processing module performs integrated analysis on the first data, the second data and the third data to thereby make a respiratory quality assessment and a sleep quality analysis, wherein:
for respiratory quality assessment, when respiratory waveforms obviously fluctuate and show that frequency or intensity changes greatly compared with historical data and indicate the occurrence of respiratory disturbance or apnea, the number of times of apnea occurrence is counted through data monitoring all night, the worse respiratory quality is shown as the number of times of apnea occurrence and respiratory disturbance occurrence is more, a respiratory quality score is set as Soc _ resp, a full score is 100, every time respiratory abnormality occurrence is deducted by a certain score, the severity of apnea is comprehensively assessed through sound waveform characteristics and blood oxygen data, sound data are compared at the same time, time periods with apnea and snore marks occurring at the same time are checked and marked, and the number of times is counted;
for sleep quality analysis, the sleep quality is related to deep sleep (deep sleep) proportion, sleep interruption times and turnover times, and a sleep quality comprehensive score is calculated, wherein the used data are as follows:
deep sleep ratio a1: counting sleep data all night, calculating the proportion of deep sleep time to total sleep time, and recording as a deep sleep proportion a1, wherein a1 is a value which is more than 0 and less than 1;
turning-over times a2: turning over is a large motion which is continuous in a short time, and the turning over motion is accurately judged and marked through the first body motion data and the second body motion data; in the normal sleeping process, people can have the action of turning over, the times are usually about 20-30 times, and excessive or insufficient turning over times indicate that the sleeping quality is not good.
Waking number a3: the more waking times at night, the worse the sleep;
respiratory quality score a4: if the respiratory quality assessment score is low, the respiratory quality assessment score indicates that the respiratory quality is poor in the sleep process;
based on the above four data, the sleep score Soc _ sleep is calculated as follows:
Soc_sleep＝SocA1+SocA2+SocA3+SocA4；
SocA1＝100*α1*(0.5+a1)；
SocA2＝100*α2*cur(a2)；
SocA3＝100*α3*(1-0.2*a3)；
SocA4＝100*α4*a4；
the cur is a centrosymmetric distribution curve (the center is located at x =25, the peak value is 1), as shown in fig. 2, the larger the deviation from the center is, the smaller the value of cur (x) is, α 1, α 2, α 3 and α 4 are weights of parameters occupying sleep evaluation, the larger the weight is, the larger the influence of the parameter on sleep quality evaluation is, and finally, a comprehensive sleep analysis report is output by combining respiration quality evaluation and sleep quality analysis.
Further, before monitoring, self-checking is respectively carried out on the data acquisition module and the data processing module, so that the data acquisition module and the data processing module are ensured to normally work in a monitoring period.
Furthermore, the data processing module transmits the timely sleep analysis report and the comprehensive sleep analysis report to the equipment terminal (including a mobile phone and the like).
Preferably, the invention is not only suitable for the case of single person detection, but also can be used in the scene of multiple persons. The specific implementation method can refer to the following two methods:
one method is to increase the number of sensors, reasonably arrange in a detection range, limit the detection range and spatially distinguish a multi-person scene.
Another method is to directly detect information of multiple persons by using the existing sensor, match signals detected by different devices with a person to be detected (target) through signal correlation analysis, and analyze the sleep state according to the sleep detection analysis method (data processing module processes and analyzes data). When the bracelet acquisition unit is used, a tester (target) needs to be worn next to the skin for testing, so that bracelet detection data (first data) and the tester have a clear one-to-one relationship and can be used as a reference for distinguishing different testers; the millimeter wave radar (radar acquisition unit) can realize high-precision, high-resolution and multi-target detection, and can effectively distinguish the motion condition and the breathing condition of multiple targets in the detection area; the microphone (sound collection unit) can simultaneously collect the sound information of a plurality of persons in the environment, and the sound information of different testers is separated by sound identification technologies such as voiceprint identification and the like. For the same tester, the respiratory data obtained by the bracelet acquisition unit and the radar acquisition unit and the snore signal (sound data) analyzed and obtained by the sound acquisition unit have higher correlation. Therefore, through signal correlation analysis, detection signals of different testers separated by each acquisition unit can be matched and grouped to obtain detection data sets of the testers, and the sleep analysis processing is performed on each data set to obtain the sleep analysis condition of each tester.
It should be noted that technical features such as objects related to the present patent application should be regarded as the prior art, and specific structures, operation principles, control modes and spatial arrangement modes that may be related to the technical features should be selected conventionally in the field, and should not be regarded as the points of the present patent, and the present patent is not further specifically described in detail.
It will be apparent to those skilled in the art that modifications and equivalents can be made to the embodiments described above, or some features of the embodiments described above, and any modifications, equivalents, improvements, and the like, which fall within the spirit and principle of the present invention, are intended to be included within the scope of the present invention.
Claims (5)
1. A multi-device multi-sensor sleep monitoring system for integrated analysis of sleep status of a target, comprising: data acquisition module and data processing module, data acquisition module includes bracelet collection element, radar acquisition element and sound acquisition element, wherein:
the bracelet acquisition unit acquires first data of a target, including first motion data, blood oxygen data, heart rate data and first respiratory data, in real time and transmits the acquired first data to the data processing module in real time;
the radar acquisition unit acquires second data of a target in real time, wherein the second data comprises second body movement data and second breathing data, and transmits the acquired second data to the data processing module in real time;
the sound acquisition unit acquires sound data of a target in real time and transmits the acquired sound data to the data processing module in real time;
the data processing module respectively obtains the first data, the second data and the third data and then carries out real-time processing and comprehensive processing on the data, so that a real-time sleep analysis report and a comprehensive sleep analysis report are respectively output.
2. The multi-device multi-sensor sleep monitoring system of claim 1, wherein for the immediate processing, the data processing module performs an immediate analysis of the first data, the second data and the third data to provide a timely responsive display or alarm, wherein:
for blood oxygen data, a data processing module analyzes the blood oxygen data of first data, if the current blood oxygen data is in a blood oxygen normal range, the data processing module outputs a target normal blood oxygen signal, if the current blood oxygen data is lower than a first blood oxygen threshold value, the data processing module outputs a target oxygen deficiency condition signal, and if the current blood oxygen data is lower than a second blood oxygen threshold value, the data processing module outputs a target oxygen deficiency danger signal and outputs a blood oxygen alarm signal to the target person or a third party;
for heart rate data, a data processing module analyzes the heart rate data of first data, if the current heart rate data is in a heart rate normal range, the data processing module outputs a target normal heart rate signal, and if the current heart rate data is lower than a first heart rate threshold, the data processing module outputs a target bradycardia or stop danger signal and outputs a heart rate alarm signal to a target person or a third party;
for the body movement data, the data processing module analyzes through first body movement data of the first data and second body movement data of the second data so as to obtain each sleep state of the target, wherein:
for the time of getting to bed, a target exists in the monitoring range of the radar acquisition unit;
for the sleep starting time, counting the number n of times of monitoring micro-motion and large motion in unit time from the time of getting on bed to be lower than a certain threshold nth1, and determining that the sleep starts;
for the sleep ending time, counting the number n of micro-motion or large motion higher than a certain threshold nth2 in unit time from the sleep starting time, and determining that a period of sleep is ended;
for the time of leaving the bed, whether a target exists in the monitoring range of the radar acquisition unit or not is judged;
counting the times n1 and n2 of occurrence of fine actions in unit time monitored by a bracelet acquisition unit and a radar acquisition unit in the sleep from the sleep starting time to the sleep ending time, and when n1 + alpha + n2 (1-alpha) is lower than a certain threshold nth3, determining that the current sleep state is deep sleep and marking, wherein alpha is the weight of first movement data in signal evaluation, the range is greater than 0 and less than 1, and the larger the value is, the larger the proportion of the first movement data is, the larger the influence on sleep depth judgment is;
for the respiratory data, the data processing module analyzes through first respiratory data of the first data and second respiratory data of the second data so as to obtain each respiratory state of the target, wherein:
the data processing module takes the second respiratory data as priority, simultaneously checks the signal quality of the first respiratory data and the second respiratory data in real time, timely switches the respiratory data, takes the respiratory data with high signal quality as analysis, takes the second respiratory data in unit time, carries out frequency domain transformation to obtain frequency spectrum information, the frequency corresponding to a peak point of the frequency spectrum is recorded as f0, the frequency spectrum energy in (f 0-delat _ f, f0+ delta _ f) is recorded as P0 comprehensively, the total energy of the whole frequency spectrum is recorded as Ps, when P0/(Ps-P0) is lower than a certain threshold value, the second respiratory data collected by the radar collection unit is determined to be poor in quality, the first respiratory data collected by the bracelet collection unit is switched, and if the signal peak value of the first respiratory data collected by the bracelet collection unit is lower than a certain threshold value, the first respiratory data is determined to be too weak, the data is low in reliability, and the second respiratory data is switched;
for the sound data, the data processing module analyzes the sound data of the third data, calculates the frequency, the intensity and the peak value change of the sound data in unit time in real time, if the sound fluctuation is uniform, the corresponding wave peaks are periodic and the intensity change is small, the target is only snored, snore marking is carried out on the corresponding time, if the sound fluctuation is large, the corresponding wave peak interval difference is large, the peak value difference is large, snore key marking is needed, and a snore alarm signal is output to the target;
and outputting an instant sleep analysis report by the data processing module through each data.
3. The multi-device multi-sensor sleep monitoring system as claimed in claim 2, wherein for the integrated processing, the data processing module performs integrated analysis on the first data, the second data and the third data to make the respiratory quality assessment and the sleep quality analysis, wherein:
for respiratory quality assessment, when respiratory waveforms obviously fluctuate and show that frequency or intensity changes greatly compared with historical data and indicate the occurrence of respiratory disturbance or apnea, the number of times of apnea occurrence is counted through data monitoring all night, the worse respiratory quality is shown as the number of times of apnea occurrence and respiratory disturbance occurrence is more, a respiratory quality score is set as Soc _ resp, a full score is 100, every time respiratory abnormality occurrence is deducted by a certain score, the severity of apnea is comprehensively assessed through sound waveform characteristics and blood oxygen data, sound data are compared at the same time, time periods with apnea and snore marks occurring at the same time are checked and marked, and the number of times is counted;
for sleep quality analysis, the sleep quality is related to deep sleep proportion, sleep interruption times and turnover times, and a sleep quality comprehensive score is calculated, wherein the used data are as follows:
deep sleep ratio a1: counting the sleep data of the whole night, calculating the proportion of the deep sleep time to the total sleep time, and recording as a deep sleep proportion a1, wherein a1 is a value which is more than 0 and less than 1;
turning-over times a2: turning over is a large motion which is continuous in a short time, and the turning over motion is accurately judged and marked through the first motion data and the second motion data;
waking number a3: the more waking times at night, the worse the sleep;
respiratory quality score a4: if the respiratory quality assessment score is low, the respiratory quality during the sleep process is poor;
based on the above four data, the sleep score Soc _ sleep is calculated as follows:
Soc_sleep＝SocA1+SocA2+SocA3+SocA4；
SocA1＝100*α1*(0.5+a1)；
SocA2＝100*α2*cur(a2)；
SocA3＝100*α3*(1-0.2*a3)；
SocA4＝100*α4*a4；
the cur is a centrosymmetric distribution curve, the larger the deviation from the center is, the smaller the value of cur (x) is, the greater the weight values of the parameters alpha 1, alpha 2, alpha 3 and alpha 4 account for sleep evaluation, the greater the weight values are, the greater the influence of the parameters on the sleep quality evaluation is, and finally, the respiration quality evaluation and the sleep quality analysis are combined to output a comprehensive sleep analysis report.
4. The multi-device multi-sensor sleep monitoring system according to claim 3, wherein before monitoring, self-checking is performed on the data acquisition module and the data processing module respectively, so as to ensure that the data acquisition module and the data processing module work normally in a monitoring period.
5. The multi-device multi-sensor sleep monitoring system as recited in claim 4, wherein the data processing module transmits the timely sleep analysis report and the comprehensive sleep analysis report to the device terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210898365.5A CN115153444A (en) | 2022-07-28 | 2022-07-28 | Multi-equipment multi-sensor sleep monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210898365.5A CN115153444A (en) | 2022-07-28 | 2022-07-28 | Multi-equipment multi-sensor sleep monitoring system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115153444A true CN115153444A (en) | 2022-10-11 |
Family
ID=83477014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210898365.5A Pending CN115153444A (en) | 2022-07-28 | 2022-07-28 | Multi-equipment multi-sensor sleep monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115153444A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115607122A (en) * | 2022-10-26 | 2023-01-17 | 广州和普乐健康科技有限公司 | Portable sleep of non-contact prescreening appearance |
| CN116649917A (en) * | 2023-07-24 | 2023-08-29 | 北京中科心研科技有限公司 | Sleep quality monitoring method and device and wearable equipment |
| CN117370769A (en) * | 2023-12-08 | 2024-01-09 | 深圳市光速时代科技有限公司 | Intelligent wearable device data processing method suitable for sleep environment |
-
2022
- 2022-07-28 CN CN202210898365.5A patent/CN115153444A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115607122A (en) * | 2022-10-26 | 2023-01-17 | 广州和普乐健康科技有限公司 | Portable sleep of non-contact prescreening appearance |
| CN116649917A (en) * | 2023-07-24 | 2023-08-29 | 北京中科心研科技有限公司 | Sleep quality monitoring method and device and wearable equipment |
| CN116649917B (en) * | 2023-07-24 | 2023-10-24 | 北京中科心研科技有限公司 | Sleep quality monitoring method and device and wearable equipment |
| CN117370769A (en) * | 2023-12-08 | 2024-01-09 | 深圳市光速时代科技有限公司 | Intelligent wearable device data processing method suitable for sleep environment |
| CN117370769B (en) * | 2023-12-08 | 2024-02-23 | 深圳市光速时代科技有限公司 | Intelligent wearable device data processing method suitable for sleep environment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115153444A (en) | Multi-equipment multi-sensor sleep monitoring system | |
| EP2055235B1 (en) | Fetal movement information processing device and fetal movement information processing method | |
| JP5991388B2 (en) | Safety monitoring device | |
| Alaziz et al. | Motion scale: A body motion monitoring system using bed-mounted wireless load cells | |
| EP2858556B1 (en) | Method and system of detecting seizures | |
| CN105051799A (en) | Method for detecting falls and a fall detector. | |
| CN104107037A (en) | Physiological information acquiring and processing system | |
| Kagawa et al. | Sleep stage classification by body movement index and respiratory interval indices using multiple radar sensors | |
| CN106175770B (en) | The judgement system of apnea during a kind of sleep | |
| CN106344034A (en) | Sleep quality evaluation system and method | |
| US20170265801A1 (en) | Bruxism Detection System With Chin-Mounted Accelerometer Sensor | |
| US11141096B2 (en) | Method for predicting future change in physical condition of person from sleep-state history | |
| US10238330B2 (en) | Method of indicating the probability of psychogenic non-epileptic seizures | |
| Walsh et al. | Identification of nocturnal movements during sleep using the non-contact under mattress bed sensor | |
| Liu et al. | Non-contact human fatigue assessment system based on millimeter wave radar | |
| Febriana et al. | Sleep monitoring system based on body posture movement using Microsoft Kinect sensor | |
| Pouyan et al. | Sleep state classification using pressure sensor mats | |
| EP3918997A3 (en) | Methods, systems, and devices for detecting apnea events and sleep | |
| Gilakjani et al. | Movement detection with adaptive window length for unobtrusive bed-based pressure-sensor array | |
| CN204246115U (en) | A kind of physiology information detecting and blood processor | |
| Ahmed et al. | Classification of sleep-wake state in ballistocardiogram system based on deep learning | |
| CN210990210U (en) | Non-inductive sleep monitoring device and monitoring system | |
| Bobrova et al. | Mathematical methods of fetal activity signal processing | |
| Gilakjani et al. | Improved sensor selection method during movement for breathing rate estimation with unobtrusive pressure sensor arrays | |
| Zhang et al. | A novel accelerometer-based method for the real-time assessment of Parkinson's tremor |
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 |