CN116035536A

CN116035536A - Method, system and device for detecting and quantifying sleep activity level

Info

Publication number: CN116035536A
Application number: CN202310240862.0A
Authority: CN
Inventors: 何将
Original assignee: Anhui Xingchen Zhiyue Technology Co ltd
Current assignee: Anhui Xingchen Zhiyue Technology Co ltd
Priority date: 2023-03-14
Filing date: 2023-03-14
Publication date: 2023-05-02
Anticipated expiration: 2043-03-14
Also published as: CN116035536B

Abstract

The invention provides a method, a system and a device for detecting and quantifying the activity level of sleep behaviors, which are used for generating physiological state time frame characteristics and behavior state time frame characteristics by carrying out acquisition monitoring, signal processing and time frame characteristic analysis on physiological state signals and behavior state signals in the sleep process of a user; analyzing the time frame characteristics to respectively generate a sleep central movement capacity level curve, a sleep myotonia level curve and a sleep behavior movement level curve; according to the curve, carrying out baseline change analysis and extremum harmonic analysis, quantifying the behavior ability states and behavior actions of the user in different sleep states, and generating a sleep behavior activity level curve; and extracting phase behavior activity correlation coefficients through the combination of the sleep phase curves and the sleep behavior activity level curves, and generating a sleep behavior activity level report. The invention realizes scientific detection, analysis quantification and evaluation of the activity or inhibition level of sleep behavior.

Description

Method, system and device for detecting and quantifying sleep activity level

Technical Field

The invention relates to the field of sleep behavior activity level detection and quantification, in particular to a method, a system and a device for sleep behavior activity level detection and quantification.

Background

While healthy sleep is a process of turning off the sensory function, relaxing the rhythmicity of muscles and extremely reducing the motor behavior, people can cause abnormal sensory function and abnormal muscle control function during sleep due to various factors such as aging, diseases, pain, tiredness, mental stress, and mutation of sleep environment, thereby generating abnormal sleep behavior level and sleep motor behavior. Meanwhile, the human sleep is in a non-rapid eye movement sleep stage, a rapid eye movement sleep stage and the like, and is alternately circulated in equal periods, while the light sleep stage 1, the light sleep stage 2, the deep sleep stage 3, the deep sleep stage 4, the rapid eye movement sleep stage and the like, and different sleep behaviors are active or inhibited in different sleep phase stages.

Accurate assessment of sleep activity or inhibition levels is critical to health management and physiological analysis. At present, research and evaluation on the activity or inhibition level of the sleep behavior at home and abroad are relatively crude and simple, and most of the research and evaluation are trace analysis of sleep electromyography and counting statistics of sleep video behavior, but a more comprehensive and deeper unified analysis framework is lacking for detecting, quantifying and evaluating the activity or inhibition level of the sleep behavior. In the face of different sexes, different ages and different sleep phases, how to evaluate the activity or inhibition level of sleep behavior in the sleep process becomes a difficult problem which is still unsolved in neuroscience and clinical medicine.

Disclosure of Invention

Aiming at the defects and improvement demands of the existing method, the invention aims to provide a method for detecting and quantifying the activity level of sleep behaviors, which is used for analyzing the activity level of a sleep center, the activity level of sleep muscle and the activity level of sleep behaviors through collecting and processing physiological state signals and behavior state signals in the sleep process and analyzing time frame characteristics, quantifying the behavior states and behavior behaviors of a user in different sleep states, obtaining a sleep activity level index and a sleep activity level curve, further analyzing by combining with a sleep time phase curve to obtain a time phase activity correlation coefficient, and generating a sleep activity level report, thereby realizing scientific detection, analysis quantification and evaluation of the activity or inhibition level of the sleep behaviors in different sexes, different ages and different sleep phases and assisting health management and physiological analysis. The invention also provides a system for detecting and quantifying the sleep activity level, which is used for realizing the method. The invention also provides a device for detecting and quantifying the sleep activity level, which is used for realizing the system.

According to the object of the present invention, the present invention proposes a method for detecting and quantifying the activity level of sleep behavior, comprising the following steps:

The physiological state signals and behavior state signals of the sleeping process of the user are subjected to acquisition monitoring, signal processing and time frame feature analysis, and physiological state time frame features and behavior state time frame features are generated;

performing central movement capability analysis, myotonia level analysis and behavior movement level analysis on the physiological state time frame characteristics and the behavior state time frame characteristics to respectively generate a sleep central movement capability level curve, a sleep myotonia level curve and a sleep behavior movement level curve;

according to the sleep center movement capability level curve, the sleep myotonic level curve and the sleep behavior movement level curve, baseline change analysis and extremum harmonic analysis are carried out, the behavior capability states and behavior movement performances of a user in different sleep states are quantified, and a sleep behavior activity level curve is generated;

and identifying sleep time phase stage according to the physiological state time frame characteristics and the behavior state time frame characteristics, obtaining a sleep time phase curve, combining the sleep behavior activity level curve, extracting a time phase behavior activity correlation coefficient, and generating a sleep behavior activity level report.

More preferably, the specific steps of collecting and monitoring the physiological state signal and the behavior state signal in the sleeping process of the user, processing the signals and analyzing the time frame characteristics, and generating the physiological state time frame characteristics and the behavior state time frame characteristics further comprise:

The physiological state and the behavior state of the sleeping process of the user are collected and monitored, and the physiological state signal and the behavior state signal are generated;

the physiological state signal and the behavior state signal are subjected to the signal processing to generate physiological state data and behavior state data respectively;

and carrying out the time frame characteristic analysis on the physiological state data and the behavior state data to generate the physiological state time frame characteristic and the behavior state time frame characteristic.

More preferably, the physiological status signals include at least central nervous physiological signals, autonomic physiological signals and muscular system physiological signals.

More preferably, the central nervous physiological signal at least comprises an electroencephalogram signal, a magnetoencephalic signal and a blood oxygen level dependent signal; the autonomic nerve physiological signals at least comprise an electrocardiosignal, a pulse signal, a respiratory signal, an oximetry signal, a body temperature signal and a skin electric signal; the muscle system physiological signals include at least blood oxygen level dependent signals, myoelectric signals, skin electric signals, and acceleration signals.

More preferably, the behavior state signal at least comprises a sleep posture position signal and a limb movement signal.

More preferably, the signal processing at least comprises a/D digital-to-analog conversion, resampling, re-referencing, noise reduction, artifact removal, power frequency notch, low-pass filtering, high-pass filtering, band-stop filtering, band-pass filtering, correction processing and time frame division; the correction processing specifically comprises signal correction and prediction smoothing processing for signal data segments containing artifacts or distortion in physiological state signals, and the time frame division refers to moving interception processing for target signals according to a preset time window and a preset time step.

More preferably, the time frame feature analysis includes at least numerical feature, physical feature analysis, time frequency feature analysis, envelope feature, and nonlinear feature analysis; wherein the numerical features include at least mean, root mean square, maximum, minimum, variance, standard deviation, coefficient of variation, kurtosis, and skewness; the physical characteristics at least comprise time information, duration information, amplitude characteristics, intensity characteristics and frequency characteristics; the time-frequency characteristics at least comprise total power, characteristic frequency band power duty ratio, characteristic frequency band central frequency, heart rate and heart rate variability; the envelope features at least comprise an original signal, an envelope signal, a normalized envelope signal, an envelope mean value, an envelope root mean square, an envelope maximum value, an envelope minimum value, an envelope variance, an envelope standard deviation, an envelope variation coefficient, an envelope kurtosis and an envelope skewness; the nonlinear features include at least entropy features, fractal features, and complexity features.

More preferably, the physiological state time frame characteristic comprises at least the numerical characteristic, the time frequency characteristic, the envelope characteristic, the nonlinear characteristic of the physiological state signal.

More preferably, the behavioral state timeframe characteristics include at least the numerical characteristics, the physical characteristics, and the time-frequency characteristics of the behavioral state signals.

More preferably, the specific steps of performing central exercise capability analysis, myotonic level analysis and behavioral action level analysis on the physiological state time frame feature and the behavioral state time frame feature to generate a sleep central exercise capability level curve, a sleep myotonic level curve and a sleep behavioral action level curve respectively further include:

analyzing the central movement capacity of the physiological state time frame characteristics, extracting central movement capacity indexes of all time frames, and generating the sleep central movement capacity level curve;

performing myotensor level analysis on the physiological state time frame characteristics, extracting myotensor level indexes of all time frames, and generating the sleep myotensor level curve;

and carrying out behavior action level analysis on the behavior state time frame characteristics, extracting a behavior action level index, and generating the sleep behavior action level curve.

More preferably, the calculation and generation method of the central movement capacity index and the central movement capacity curve comprises the following steps:

1) Collecting the central nervous physiological signals and the autonomic nervous physiological signals in a resting state when the current user wakes up, and carrying out time frame feature analysis and feature value average value calculation to obtain a nerve resting movement capacity baseline feature index set;

2) Extracting the time frame characteristics corresponding to the central nervous physiological signals and the autonomic nervous physiological signals from the physiological state time frame characteristics to generate central physiological state time frame characteristics;

3) Calculating the relative variation of the characteristic value in the central physiological state time frame characteristic and the baseline characteristic index value in the nerve resting exercise capacity baseline characteristic index set to obtain a central exercise capacity characterization characteristic relative variation index set;

4) Performing weighted fusion calculation on all indexes in the central movement capacity characterization characteristic relative change index set to obtain the central movement capacity index under the current time frame;

5) And obtaining the central movement capacity index of all time frames according to time sequence, and generating and obtaining the central movement capacity curve.

More preferably, the calculation and generation method of the myopic level index and the myopic level curve comprises the following steps:

1) Collecting physiological signals of the muscle system in a resting state when a current user wakes up, and carrying out time frame characteristic analysis and characteristic value average value calculation to obtain a muscle resting behavior baseline characteristic index set;

2) Extracting the time frame characteristics corresponding to the physiological signals of the muscle system from the physiological state time frame characteristics to generate muscle physiological state time frame characteristics;

3) Calculating the relative variation of the characteristic value in the time frame characteristic of the physiological state of the muscle and the baseline characteristic index value in the baseline characteristic index set of the nerve rest behavior of the muscle to obtain a relative variation index set of the characteristic of the tension of the muscle;

4) Performing weighted fusion calculation on all indexes in the relative change index set of the muscle tension characterization characteristics to obtain the muscle tension level index under the current time frame;

5) And obtaining the myotonic level indexes of all time frames according to time sequence, and generating and obtaining the myotonic level curve.

More preferably, the calculation and generation method of the behavioral action level index and the behavioral action level curve comprises the following steps:

1) Acquiring the behavior state time frame characteristics, analyzing and quantifying time distribution, duration, motion amplitude, motion frequency, motion intensity and motion regularity of behavior motion, and generating a behavior action level characterization index set;

2) Performing weighted fusion calculation on all indexes in the behavior action level representation index set to obtain the behavior action level index under the current time frame;

3) And obtaining the behavior action level index of all time frames according to time sequence, and generating and obtaining the behavior action level curve.

More preferably, the step of analyzing the baseline variation and extremum harmony according to the sleep central movement capability level curve, the sleep myotonia level curve and the sleep behavior movement level curve to quantify the behavior capability states and behavior movement performances of the user in different sleep states, and the step of generating the sleep behavior activity level curve further includes:

acquiring, analyzing and calculating to acquire the physiological state time frame characteristics and the behavior state time frame characteristics of healthy user groups with different sexes, different age groups and large scale numbers in a awake period resting state and an awake period motion task state, acquiring a central motion capability curve, a myopic level curve and a behavior motion level curve in different states through central motion capability analysis, myopic level analysis and behavior motion level analysis, acquiring resting baseline values and task baseline values of the central motion capability curve, the myopic level curve and the behavior motion level curve through multi-sample fusion calculation, and establishing a standard behavior active curve characteristic baseline index set;

and carrying out baseline variation analysis and extremum harmonic analysis according to the standard behavior activity curve characteristic baseline index set, the sleep central movement capacity level curve, the sleep myotonia level curve and the sleep behavior movement level curve, calculating according to time sequence to obtain sleep behavior activity level indexes of all time frames, and generating the sleep behavior activity level curve.

More preferably, the method for generating the sleep activity level index and the sleep activity level curve specifically comprises the following steps:

1) Acquiring the standard behavior active curve characteristic baseline index sets of healthy user groups with different sexes, different age groups and different scale numbers under the state of rest in the awake period and the state of motion task in the awake period;

2) Acquiring the sleep central movement capacity level curve, the sleep myotonic level curve and the sleep behavior movement level curve of the current user, and calculating a baseline variation value of a rest baseline value and a task baseline value in the standard behavior activity curve characteristic baseline index set of the healthy crowd in the same age layer, namely obtaining a sleep behavior activity curve characteristic variation set through baseline variation analysis;

3) Carrying out extremum harmonic analysis on all indexes in the characteristic change quantity set of the sleep behavior activity curve to obtain extremum harmonic values, namely the sleep behavior activity level index under the current time frame;

4) And obtaining the sleep behavior activity level index of all time frames according to time sequence, and generating and obtaining the sleep behavior activity level curve.

More preferably, the specific calculation mode of the baseline variation analysis is as follows:

For real-valued variables

And its non-zero base line sequence +.>

For the baseline variation value of

；

wherein ,

respectively real value variable +.>

The base line change value of (2), the ith base line value and the corresponding weight, and N is a positive integer.

More preferably, the extremum harmonic analysis is a data analysis method which uses the maximum value, the minimum value, the maximum value and the minimum value of the numerical value array as observation base points, uses the mean value, the median, the quantile, the variance, the variation coefficient, the kurtosis, the skewness, the absolute value mean value, the absolute value median, the absolute value quantile, the absolute value variance, the absolute value variation coefficient, the absolute value mean value, the absolute value kurtosis and the absolute value skewness of the numerical value array as main analysis harmonic items to observe and analyze the extremum fluctuation state and the general trend change of the numerical value array.

More preferably, a specific calculation mode of the extremum harmonic analysis is as follows:

for numerical value arrays

For example, the extremum harmonic value is calculated by

；

wherein ,

is a numerical value array +.>

Extremum harmonic value of->

To take the absolute value operator, N is a positive integer.

More preferably, the specific steps of identifying sleep time phase stage according to the physiological state time frame feature and the behavior state time frame feature, obtaining a sleep time phase curve, extracting a time phase behavior activity correlation coefficient in combination with the sleep behavior activity level curve, and generating a sleep behavior activity level report further include:

Identifying sleep phase stages according to the physiological state time frame characteristics and the behavior state time frame characteristics to obtain the sleep phase curve;

analyzing and calculating relation features of the sleep time phase curve and the sleep behavior activity level curve, extracting the time phase behavior activity correlation coefficient, wherein the relation features at least comprise association features and distance features;

and analyzing, calculating and generating the sleep behavior activity level report according to the sleep time phase curve, the sleep behavior activity level curve and the time phase activity correlation coefficient.

More preferably, the extraction method of the sleep phase curve specifically comprises the following steps:

1) Performing learning training and data modeling on the physiological state time frame characteristics, the behavior state time frame characteristics and the corresponding sleep stage data of the scale sleep user sample through a deep learning algorithm to obtain a sleep time phase automatic stage model;

2) Inputting the physiological state time frame characteristics and the behavior state time frame characteristics of the current user into the sleep time phase automatic stage model to obtain corresponding sleep time phase stage values;

3) And acquiring the sleep time phase stage values of the physiological state time frame characteristics and the behavior state time frame characteristics of all time frames according to a time sequence, and generating the sleep time phase curve.

More preferably, the method for calculating the phase behavior activity correlation coefficient specifically comprises the following steps:

1) Acquiring the sleep time phase curve and the sleep behavior activity level curve;

2) Analyzing and calculating the relation characteristic of the sleep time phase curve and the sleep behavior activity level curve to obtain a time phase behavior activity level relation characteristic index set;

3) And carrying out weighted fusion calculation on the time phase behavior activity level relation characteristic index set to obtain the time phase behavior activity correlation coefficient.

More preferably, the relationship features include at least an association feature and a distance feature; the correlation features at least comprise a coherence coefficient, a pearson correlation coefficient, a Jacquard similarity coefficient, a linear mutual information coefficient and a linear correlation coefficient, and the distance features at least comprise an Euclidean distance, a Manhattan distance, a Chebyshev distance, a Minkowski distance, a normalized Euclidean distance, a Mahalanobis distance, a Papanic distance, a Hamming distance and an included angle cosine.

More preferably, the sleep activity level report at least comprises the sleep phase curve, the sleep activity level curve, the phase activity correlation coefficient, a phase activity level distribution statistic, a peak activity period minor knot, a low peak activity period minor knot, an abnormal activity period minor knot, and a sleep activity level report summary.

More preferably, the behavioural activity level phase distribution statistics are in particular an average behavioural activity level, a maximum behavioural activity level and a minimum behavioural activity level of different sleep phases.

More preferably, the peak activity time summary is a peak time distribution corresponding to a segment exceeding a preset peak threshold in the sleep behavior activity level curve, a time numerical sum of the peak time distribution, and a duty ratio.

More preferably, the low-peak activity period summary is a low-peak period distribution corresponding to a segment exceeding a preset low-peak threshold in the sleep behavior activity level curve, a time-value sum and a duty ratio of the low-peak period distribution.

More preferably, the abnormal activity period summary is an abnormal period distribution corresponding to an abnormal segment deviating from a curve baseline trend in the sleep behavior activity level curve, a time numerical sum of the abnormal period distribution, and a duty ratio.

According to the object of the present invention, the present invention proposes a system for detecting and quantifying the activity level of sleep behavior, comprising the following modules:

the signal acquisition processing module is used for carrying out acquisition monitoring, signal processing and time frame characteristic analysis on physiological state signals and behavior state signals in the sleeping process of the user to generate physiological state time frame characteristics and behavior state time frame characteristics;

The ability state analysis module is used for carrying out central movement ability analysis, myotonia level analysis and behavior action level analysis on the physiological state time frame characteristics and the behavior state time frame characteristics to respectively generate a sleep central movement ability level curve, a sleep myotonia level curve and a sleep behavior action level curve;

the behavior activity quantification module is used for carrying out baseline variation analysis and extremum harmonic analysis according to the sleep central movement capacity level curve, the sleep myotonic level curve and the sleep behavior movement level curve, quantifying the behavior capacity states and behavior movement performances of the user in different sleep states and generating a sleep behavior activity level curve;

and the sleep behavior reporting module is used for identifying sleep time phase stages according to the physiological state time frame characteristics and the behavior state time frame characteristics to obtain a sleep time phase curve, extracting time phase behavior activity correlation coefficients by combining the sleep behavior activity level curve, and generating a sleep behavior activity level report.

And the data operation center module is used for visual display, data storage and unified management of data operation of all data in the system.

More preferably, the signal acquisition processing module further comprises the following functional units:

The system comprises a signal acquisition monitoring unit, a control unit and a control unit, wherein the signal acquisition monitoring unit is used for acquiring and monitoring the physiological state and the behavior state of a sleeping process of a user and generating a physiological state signal and a behavior state signal, the physiological state signal at least comprises a central nervous physiological signal, an autonomic nervous physiological signal and a muscle system physiological signal, and the behavior state signal at least comprises a sleeping posture position signal and a limb movement signal;

the signal data processing unit is used for performing signal processing on the physiological state signal and the behavior state signal to generate physiological state data and behavior state data respectively, wherein the signal processing at least comprises A/D digital-to-analog conversion, resampling, re-referencing, noise reduction, artifact removal, power frequency notch, low-pass filtering, high-pass filtering, band-stop filtering, band-pass filtering, correction processing and time frame division;

the time frame feature analysis unit is used for carrying out time frame feature analysis on the physiological state data and the behavior state data to generate the physiological state time frame feature and the behavior state time frame feature, and the time frame feature analysis at least comprises numerical feature, physical feature analysis, time frequency feature analysis, envelope feature and nonlinear feature analysis.

More preferably, the capability state analysis module further comprises the following functional units:

the central movement capacity analysis unit is used for analyzing the central movement capacity of the physiological state time frame characteristics, extracting central movement capacity indexes of all time frames and generating the sleep central movement capacity level curve;

the myotonic level analysis unit is used for carrying out myotonic level analysis on the physiological state time frame characteristics, extracting myotonic level indexes of all time frames and generating the sleep myotonic level curve;

the behavior level analysis unit is used for performing behavior action level analysis on the behavior state time frame characteristics, extracting a behavior action level index and generating the sleep behavior action level curve.

More preferably, the behavioral activity quantization module further comprises the following functional units:

the baseline index set unit is used for acquiring, analyzing and calculating the physiological state time frame characteristics and the behavior state time frame characteristics of healthy user groups with different sexes, different age groups and large scale numbers in a awake period resting state and an awake period motion task state, obtaining the central motion capability curve, the myopic level curve and the behavior action level curve in different states through central motion capability analysis, myopic level analysis and behavior action level analysis, obtaining the resting baseline value and the task baseline value of the central motion capability curve, the myopic level curve and the behavior action level curve through multi-sample fusion calculation, and establishing a standard behavior active curve characteristic baseline index set;

And the sleep behavior quantification unit is used for obtaining sleep behavior activity level indexes of all time frames according to time sequence calculation and generating the sleep behavior activity level curve according to the standard behavior activity curve characteristic baseline index set, the sleep center movement capacity level curve, the sleep myotonia level curve and the sleep behavior movement level curve.

More preferably, the sleep behavior reporting module further comprises the following functional units:

the sleep phase stage unit is used for identifying sleep phase stages according to the physiological state time frame characteristics and the behavior state time frame characteristics to obtain the sleep phase curve;

the correlation coefficient calculation unit is used for analyzing and calculating the relation characteristics of the sleep time phase curve and the sleep behavior activity level curve, extracting the time phase behavior activity correlation coefficient, and the relation characteristics at least comprise correlation characteristics and distance characteristics;

the activity report generating unit is used for analyzing, calculating and generating the sleep activity level report according to the sleep time phase curve, the sleep activity level curve and the time phase activity correlation coefficient, wherein the sleep activity level report at least comprises the sleep time phase curve, the sleep activity level curve, the time phase activity correlation coefficient, a behavior activity level time phase distribution statistic, a peak activity time period minor knot, a low peak activity time period minor knot, an abnormal activity time period minor knot and a sleep activity level report summary;

And the report output management unit is used for uniformly managing the format output and the presentation form of the sleep behavior activity level report.

More preferably, the data operation center module further comprises the following functional units:

a user information management unit for registering input, editing, inquiry, output and deletion of user basic information;

the data visual management unit is used for visual display management of all data in the system;

and the data operation management unit is used for storing, backing up, migrating and exporting all data in the system.

According to the purpose of the invention, the invention provides a sleep behavior activity level detection and quantification device, which comprises the following modules:

the sleep behavior reporting module is used for identifying sleep time phase stages according to the physiological state time frame characteristics and the behavior state time frame characteristics to obtain a sleep time phase curve, extracting time phase behavior activity correlation coefficients in combination with the sleep behavior activity level curve, and generating a sleep behavior activity level report;

the data visualization module is used for carrying out unified visual display management on all data in the device;

and the data operation center module is used for visual display, data storage and unified management of data operation of all the data in the device.

According to the method, the system and the device for detecting and quantifying the activity level of the sleep behavior, the physiological state signals and the behavior state signals of the sleep process are collected and processed, the time frame characteristic analysis is carried out, the movement capacity level of the sleep center, the sleep myotonia level and the sleep behavior action level are analyzed, the behavior capacity states and the behavior actions performances of a user in different sleep states are quantified, the sleep behavior activity level index and the sleep behavior activity level curve are obtained, the time phase activity correlation coefficient is further obtained by analyzing the sleep time phase curve, and the sleep behavior activity level report is generated, so that the sleep behavior activity or inhibition levels of different sexes, different ages and different sleep time phases are scientifically detected, analyzed, quantified and evaluated, and the health management and the physiological analysis are assisted.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate and do not limit the invention.

FIG. 1 is a flowchart illustrating a method for detecting and quantifying sleep activity level according to an embodiment of the present invention;

FIG. 2 is a schematic block diagram of a system for detecting and quantifying sleep activity level according to an embodiment of the present invention;

fig. 3 is a schematic diagram of a module configuration of an apparatus for detecting and quantifying sleep activity level according to an embodiment of the present invention.

Detailed Description

In order to more clearly illustrate the objects and technical solutions of the present invention, the present invention will be further described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the embodiments described below are only some, but not all, embodiments of the invention. Other embodiments, which are derived from the embodiments of the invention by a person skilled in the art without creative efforts, shall fall within the protection scope of the invention. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be arbitrarily combined with each other.

In an actual use scene, the method, the system and the device for detecting and quantifying the activity level of the sleep behavior can combine, energize or embed sleep related products and services, and provide a detecting and quantifying scheme for the activity level of the sleep behavior for different crowd scenes such as children, teenagers, middle aged people, elderly people, athletes, sub-health and the like.

As shown in fig. 1, a method for detecting and quantifying sleep activity level according to an embodiment of the present invention includes the following steps:

p100: and (3) carrying out acquisition monitoring, signal processing and time frame feature analysis on the physiological state signals and the behavior state signals of the sleeping process of the user to generate physiological state time frame features and behavior state time frame features.

The method comprises the first step of collecting and monitoring physiological states and behavior states of a sleeping process of a user to generate physiological state signals and behavior state signals.

In this embodiment, the physiological status signals include at least central nervous physiological signals, autonomic physiological signals, and muscular system physiological signals. Wherein, the central nervous physiological signal at least comprises an electroencephalogram signal, a magnetoencephalic signal and a blood oxygen level dependent signal; the autonomic nerve physiological signals at least comprise electrocardiosignals, pulse signals, respiratory signals, blood oxygen signals, body temperature signals and skin electric signals; the physiological signals of the muscular system at least comprise blood oxygen level dependent signals, myoelectric signals, skin electric signals and acceleration signals.

In this embodiment, the behavior state signal at least includes a sleep posture position signal and a limb movement signal.

In this embodiment, an electroencephalogram signal is used as a central nerve physiological signal, an electrocardiosignal, a respiratory signal and a blood oxygen signal are used as autonomic nerve physiological signals, and the central nerve physiological signal and the autonomic nerve physiological signal are collected and monitored by a polysomnography recorder. The sampling rate of the electroencephalogram signals and the electrocardiosignals is 512Hz, the recording electrodes of the electroencephalogram signals are F3, F4, C3, C4, O1 and O2, the reference electrodes are M1 and M2, and the electrocardiosignals are collected to be left chest V6 leads. The sampling rate of the respiratory signal and the blood oxygen signal is 128Hz, the respiratory signal is from the chest and abdomen belt, and the blood oxygen signal is from the fingertip.

In this embodiment, the myoelectric signal is used as a physiological signal of the muscular system, the limb movement signal is used as a behavior state signal, the myoelectric signal and the limb movement signal are collected and recorded by using a myoelectric and triaxial acceleration composite sensor with multiple positions, the sampling rate of the myoelectric signal is 512Hz, the sampling rate of the triaxial acceleration signal is 128Hz, and the collecting positions are respectively the outer middle parts of the lower arms and the upper arms of the left hand and the right hand, the outer middle parts of the lower legs and the thighs of the left leg and the right chest.

And secondly, performing signal processing on the physiological state signal and the behavior state signal to generate physiological state data and behavior state data respectively.

In this embodiment, the signal processing at least includes a/D digital-to-analog conversion, resampling, re-referencing, noise reduction, artifact removal, power frequency notch, low-pass filtering, high-pass filtering, band-stop filtering, band-pass filtering, correction processing, and time frame division. The correction processing specifically comprises the steps of carrying out signal correction and predictive smoothing processing on signal data fragments containing artifacts or distortion in physiological state signals; the time frame division refers to performing mobile interception processing on the target signal according to a preset time window and a preset time step.

In this embodiment, the physiological status signal and the behavioral status signal are first preprocessed: the preprocessing of the brain electric physiological signals mainly comprises the steps of removing artifacts, correcting, reducing wavelet noise and 50 percent

Power frequency notch filtering, 0.5-70->

Band-pass filtering; the pretreatment of the electrocardiosignal mainly comprises artifact removal, correction treatment, wavelet noise reduction, 0.1-40%>

Band-pass filtering; the pretreatment of the electromyographic signals mainly comprises artifact removal, correction treatment, wavelet noise reduction and 50>

and 100/>

Power frequency notch filtering, 20-150- >

Band-pass filtering; the preprocessing of the triaxial acceleration signal mainly comprises the steps of removing artifacts, correcting and processing, and waveletNoise reduction of 0.1 to 40%>

Band-pass filtering; pretreatment of respiratory signals and blood oxygen signals is mainly carried out to remove artifacts, correct signals and enable the signals to be 2 +.>

And (5) low-pass filtering. And secondly, carrying out sliding segmentation on the signals by using a preset time window of 5 seconds and a preset time step of 10 seconds to respectively obtain physiological state data and behavior state data.

Thirdly, performing time frame feature analysis on the physiological state data and the behavior state data to generate physiological state time frame features and behavior state time frame features.

In this embodiment, the time frame feature analysis at least includes numerical feature, physical feature analysis, time frequency feature analysis, envelope feature, and nonlinear feature analysis; wherein the numerical features include at least mean, root mean square, maximum, minimum, variance, standard deviation, coefficient of variation, kurtosis, and skewness; the physical characteristics at least comprise time information, duration information, amplitude characteristics, intensity characteristics and frequency characteristics; the time-frequency characteristics at least comprise total power, characteristic frequency band power duty ratio, characteristic frequency band center frequency, heart rate and heart rate variability; the envelope features at least comprise an original signal, an envelope signal, a normalized envelope signal, an envelope mean, an envelope root mean square, an envelope maximum, an envelope minimum, an envelope variance, an envelope standard deviation, an envelope variation coefficient, an envelope kurtosis and an envelope skewness; the nonlinear features include at least entropy features, fractal features, and complexity features.

In this embodiment, the physiological state time frame features at least include a numerical feature, a time-frequency feature, an envelope feature, and a nonlinear feature of the physiological state signal. The behavior state time frame features include at least a numerical feature, a physical feature, and a time-frequency feature of the behavior state signal.

In this embodiment, root mean square, variation coefficient, total power, characteristic frequency band power duty ratio, characteristic frequency band center frequency, envelope deviation, sample entropy, heart rate and heart rate variability are taken as physiological state time frame characteristics, and average value, time information, duration information, amplitude characteristics, intensity characteristics and frequency characteristics are taken as behavioral state time frame characteristics to perform subsequent further analysis and calculation of characteristic indexes and characteristic curves. These metrics can in most cases meet the assessment and measurement of central motor capacity, myotonic level and behavioural action level.

P200: and carrying out central movement capability analysis, myotonia level analysis and behavior movement level analysis on the physiological state time frame characteristics and the behavior state time frame characteristics to respectively generate a sleep central movement capability level curve, a sleep myotonia level curve and a sleep behavior movement level curve.

Analyzing central movement capacity of physiological state time frame features, extracting central movement capacity indexes of all time frames, and generating a sleep central movement capacity level curve.

In this embodiment, the calculation and generation method of the central movement capability index and the central movement capability curve is as follows:

1) Collecting central nerve physiological signals and autonomic nerve physiological signals in a resting state when a current user wakes up, and carrying out time frame feature analysis and feature value average calculation to obtain a nerve resting motor ability baseline feature index set;

2) Extracting time frame characteristics corresponding to central nervous physiological signals and autonomic nervous physiological signals from the physiological state time frame characteristics, and generating central physiological state time frame characteristics;

3) Calculating the relative variation of the characteristic value in the central physiological state time frame characteristic and the baseline characteristic index value in the nerve resting motor capacity baseline characteristic index set to obtain a central motor capacity characterization characteristic relative variation index set;

4) Carrying out weighted fusion calculation on all indexes in the central movement capability characterization characteristic relative change index set to obtain a central movement capability index under the current time frame;

5) And obtaining the central movement capacity index of all time frames according to the time sequence, and generating and obtaining a central movement capacity curve.

And secondly, performing myotensor level analysis on the physiological state time frame characteristics, extracting the myotensor level indexes of all time frames, and generating a sleep myotensor level curve.

In this embodiment, the calculation and generation method of the myotonic level index and the myotonic level curve is as follows:

1) Collecting physiological signals of a muscle system in a resting state when a current user wakes up, and carrying out time frame characteristic analysis and characteristic value mean value calculation to obtain a muscle resting behavior baseline characteristic index set;

2) Extracting time frame characteristics corresponding to physiological signals of a muscle system from the physiological state time frame characteristics to generate muscle physiological state time frame characteristics;

4) Carrying out weighted fusion calculation on all indexes in the relative change index set of the muscle tension characterization characteristics to obtain a muscle tension level index under the current time frame;

5) And obtaining the myotonic level indexes of all time frames according to the time sequence, and generating and obtaining a myotonic level curve.

Thirdly, performing behavior action level analysis on the behavior state time frame characteristics, extracting a behavior action level index, and generating a sleep behavior action level curve.

In this embodiment, the calculation and generation method of the behavioral action level index and the behavioral action level curve is as follows:

1) Acquiring behavior state time frame characteristics, analyzing and quantifying time distribution, duration, motion amplitude, motion frequency, motion intensity and motion regularity of behavior motion, and generating a behavior action level representation index set;

2) Carrying out weighted fusion calculation on all indexes in the behavior action level representation index set to obtain a behavior action level index under the current time frame;

3) And obtaining the behavior action level indexes of all time frames according to the time sequence, and generating and obtaining a behavior action level curve.

In this embodiment, the time distribution is a time distribution of occurrence time points of limb movement; the duration is the duration of each occurrence of limb movement and the total duration; the motion amplitude comes from the statistical analysis of the amplitude characteristics; the motion frequency comes from the statistical analysis of the frequency characteristics; the intensity of motion comes from statistical analysis of the intensity features; the movement regularity comes from the comprehensive consideration of the time sequence distribution and the movement intensity of the limb movement occurrence time point, namely the time sequence distribution regularity of the movement intensity.

In this embodiment, the weighted fusion calculation adopts an averaging method.

P300: and carrying out baseline change analysis and extremum harmonic analysis according to the sleep center movement capability level curve, the sleep myotonic level curve and the sleep behavior movement level curve, quantifying the behavior capability states and behavior movement performances of the user in different sleep states, and generating a sleep behavior activity level curve.

The method comprises the steps of firstly, collecting, analyzing and calculating physiological state time frame characteristics and behavior state time frame characteristics of healthy user groups with different sexes, different age groups and different scale numbers in a wake period resting state and a wake period motion task state, obtaining a central motion capability curve, a muscle tension level curve and a behavior motion level curve in different states through central motion capability analysis, muscle tension level analysis and behavior motion level analysis, obtaining a resting base line value and a task base line value of the central motion capability curve, the muscle tension level curve and the behavior motion level curve through multi-sample fusion calculation, and establishing a standard behavior active curve characteristic base line index set.

And step two, carrying out baseline change analysis and extremum harmonic analysis according to a standard behavior activity curve characteristic baseline index set, a sleep central movement capacity level curve, a sleep myotonia level curve and a sleep behavior movement level curve, obtaining sleep behavior activity level indexes of all time frames according to time sequence calculation, and generating a sleep behavior activity level curve.

In this embodiment, the method for generating the sleep behavior activity level index and the sleep behavior activity level curve specifically includes:

1) Acquiring standard behavior active curve characteristic baseline index sets of healthy user groups with different sexes, different age groups and different scale numbers in a rest state of a waking period and a motion task state of the waking period;

2) Acquiring a sleep central movement capacity level curve, a sleep myotonic level curve and a sleep behavior movement level curve of a current user, and calculating a rest baseline value and a baseline variation value of a task baseline value in a standard behavior activity curve characteristic baseline index set of healthy people of the same age group, namely obtaining a sleep behavior activity curve characteristic variation set through baseline variation analysis;

3) Carrying out extremum harmonic analysis on all indexes in the characteristic change quantity set of the sleep behavior activity curve to obtain extremum harmonic values, namely sleep behavior activity level indexes under the current time frame;

4) And obtaining sleep behavior activity level indexes of all time frames according to time sequences, and generating and obtaining a sleep behavior activity level curve.

In this embodiment, the specific calculation method of the baseline variation analysis is as follows:

for real-valued variables

And its non-zero base line sequence +. >

For the baseline variation value of

；

wherein ,

respectively real value variable +.>

In an actual use scene, the weight coefficient related to the task baseline value is at least 2-4 times larger than the weight coefficient related to the rest baseline value.

In this embodiment, the extremum harmonic analysis is a data analysis method that uses the maximum value, the minimum value, the maximum value of the absolute value and the minimum value of the absolute value as the observation base point, uses the average value, the median, the quantile, the variance, the variation coefficient, the kurtosis, the skewness, the absolute value average value, the absolute value median, the absolute value quantile, the absolute value variance, the absolute value variation coefficient, the absolute value average value, the absolute value kurtosis and the absolute value skewness of the numerical value array as the main analysis harmonic items to observe and analyze the extremum fluctuation state and the overall trend change of the numerical value array.

In this embodiment, a specific calculation method of extremum harmonic analysis is as follows:

for numerical value arrays

For the extreme value harmonic value thereof is

；

wherein ,

is a numerical value array +.>

Extremum harmonic value of->

To take the absolute value operator, N is a positive integer.

In an actual use scene, the extremum harmonic value is obtained by taking the maximum fluctuation observed value as a basis and taking the mean value and the absolute value mean value as the harmonic mantissa, so that the maximum fluctuation observation and the average trend observation of the sleep behavior level can be achieved.

P400: and identifying sleep time phase stage according to the physiological state time frame characteristics and the behavior state time frame characteristics, obtaining a sleep time phase curve, combining the sleep behavior activity level curve, extracting a time phase behavior activity correlation coefficient, and generating a sleep behavior activity level report.

The first step, the sleep time phase stage is identified according to the physiological state time frame characteristics and the behavior state time frame characteristics, and a sleep time phase curve is obtained.

In this embodiment, the method for extracting the sleep phase curve specifically includes:

1) The physiological state time frame characteristics, the behavior state time frame characteristics and the corresponding sleep stage data of the scale sleep user sample are subjected to learning training and data modeling through a deep learning algorithm, and a sleep time phase automatic stage model is obtained;

2) Inputting the physiological state time frame characteristics and the behavior state time frame characteristics of the current user into a sleep time phase automatic stage model to obtain corresponding sleep time phase stage values;

3) And acquiring sleep phase stage values of physiological state time frame characteristics and behavior state time frame characteristics of all time frames according to the time sequence, and generating a sleep phase curve.

And secondly, analyzing and calculating the relation characteristics of the sleep time phase curve and the sleep behavior activity level curve, extracting the time phase behavior activity correlation coefficient, wherein the relation characteristics at least comprise correlation characteristics and distance characteristics.

In this embodiment, the method for calculating the phase behavior activity correlation coefficient specifically includes:

1) Acquiring a sleep time phase curve and a sleep behavior activity level curve;

3) And carrying out weighted fusion calculation on the phase behavior activity level relation characteristic index set to obtain a phase behavior activity correlation coefficient.

In this embodiment, the relationship features include at least an association feature and a distance feature; the correlation features at least comprise a coherence coefficient, a pearson correlation coefficient, a Jacquard similarity coefficient, a linear mutual information coefficient and a linear correlation coefficient, and the distance features at least comprise an Euclidean distance, a Manhattan distance, a Chebyshev distance, a Minkowski distance, a standardized Euclidean distance, a Mahalanobis distance, a Papanic distance, a Hamming distance and an included angle cosine.

In this embodiment, the pearson correlation coefficient and the euclidean distance are selected as the relational features. For the sameTwo sets of lengths

and />

Pirson correlation coefficient->

The calculation formula of (2) is as follows:

；/>

wherein ,

for array->

Average value of>

For array->

Average value of (2).

Euclidean distance

The calculation formula of (2) is as follows:

。

thirdly, according to the sleep time phase curve, the sleep behavior activity level curve and the time phase activity correlation coefficient, analyzing, calculating and generating a sleep behavior activity level report.

In this embodiment, the sleep activity level report at least includes a sleep phase curve, a sleep activity level curve, a phase activity correlation coefficient, a phase distribution statistic of activity levels, a peak activity period summary, a low peak activity period summary, an abnormal activity period summary, and a sleep activity level report summary.

In this embodiment, the statistics of the phase distribution of the behavioural activity level are specifically the average behavioural activity level, the maximum behavioural activity level and the minimum behavioural activity level of different sleep phases.

In this embodiment, the peak activity period summary is specifically a peak period distribution, a time-value sum of the peak period distribution, and a duty ratio corresponding to a segment exceeding a preset peak threshold in the sleep behavior activity level curve.

In this embodiment, the summary of the low peak activity period is the low peak period distribution corresponding to the segment exceeding the preset low peak threshold in the sleep activity level curve, the sum of time and value of the low peak period distribution, and the duty ratio.

In this embodiment, the summary of abnormal activity periods is an abnormal period distribution corresponding to an abnormal segment that deviates from a curve baseline trend in the sleep behavior activity level curve, a time-value sum and a duty ratio of the abnormal period distribution.

As shown in fig. 2, a system for detecting and quantifying sleep activity level is provided according to an embodiment of the present invention, and is configured to perform the above-described method steps. The system comprises the following modules:

the signal acquisition processing module S100 is used for carrying out acquisition monitoring, signal processing and time frame characteristic analysis on physiological state signals and behavior state signals in the sleeping process of a user to generate physiological state time frame characteristics and behavior state time frame characteristics;

the ability state analysis module S200 is configured to perform central movement ability analysis, myotonic level analysis and behavior action level analysis on the physiological state time frame feature and the behavior state time frame feature, and generate a sleep central movement ability level curve, a sleep myotonic level curve and a sleep behavior action level curve respectively;

the behavior activity quantification module S300 is used for carrying out baseline variation analysis and extremum harmonic analysis according to the sleep central movement capability level curve, the sleep myotonia level curve and the sleep behavior movement level curve, quantifying the behavior capability states and behavior movement performances of the user in different sleep states, and generating a sleep behavior activity level curve;

The sleep behavior reporting module S400 is configured to identify sleep phase stages according to the physiological status time frame features and the behavior status time frame features, obtain a sleep phase curve, extract phase behavior activity correlation coefficients in combination with the sleep behavior activity level curve, and generate a sleep behavior activity level report.

And the data operation center module S500 is used for visual display, data storage and unified management of data operation of all data in the system.

In this embodiment, the signal acquisition processing module S100 further includes the following functional units:

the signal acquisition monitoring unit is used for acquiring and monitoring the physiological state and the behavior state of the sleeping process of the user and generating physiological state signals and behavior state signals, wherein the physiological state signals at least comprise central nervous physiological signals, autonomic nervous physiological signals and muscle system physiological signals, and the behavior state signals at least comprise sleeping posture position signals and limb movement signals;

The time frame feature analysis unit is used for performing time frame feature analysis on the physiological state data and the behavior state data to generate physiological state time frame features and behavior state time frame features, and the time frame feature analysis at least comprises numerical features, physical feature analysis, time frequency feature analysis, envelope features and nonlinear feature analysis.

In this embodiment, the capability status analysis module S200 further includes the following functional units:

the central movement capacity analysis unit is used for analyzing the central movement capacity of the physiological state time frame characteristics, extracting the central movement capacity indexes of all time frames and generating a sleep central movement capacity level curve;

the myotonic level analysis unit is used for carrying out myotonic level analysis on the physiological state time frame characteristics, extracting myotonic level indexes of all time frames and generating a sleep myotonic level curve;

the behavior level analysis unit is used for performing behavior action level analysis on the behavior state time frame characteristics, extracting a behavior action level index and generating a sleep behavior action level curve.

In this embodiment, the active behavior quantification module S300 further includes the following functional units:

the baseline index set unit is used for acquiring, analyzing and calculating physiological state time frame characteristics and behavior state time frame characteristics of healthy user groups with different sexes, different age groups and large scale numbers in a rest state in a wake period and a motion task state in the wake period, acquiring a central motion capability curve, a muscle tension level curve and a behavior action level curve in different states through central motion capability analysis, muscle tension level analysis and behavior action level analysis, acquiring rest baseline values and task baseline values of the central motion capability curve, the muscle tension level curve and the behavior action level curve through multi-sample fusion calculation, and establishing a standard behavior active curve characteristic baseline index set;

The sleep behavior quantification unit is used for obtaining sleep behavior activity level indexes of all time frames according to time sequence calculation and generating a sleep behavior activity level curve according to a standard behavior activity curve characteristic baseline index set, a sleep central movement capacity level curve, a sleep myotonia level curve and a sleep behavior movement level curve.

In this embodiment, the sleep behavior reporting module S400 further includes the following functional units:

the sleep time phase stage unit is used for identifying sleep time phase stages according to the physiological state time frame characteristics and the behavior state time frame characteristics to obtain a sleep time phase curve;

the activity report generation unit is used for analyzing, calculating and generating a sleep activity level report according to the sleep time phase curve, the sleep activity level curve and the time phase activity correlation coefficient, wherein the sleep activity level report at least comprises a sleep time phase curve, a sleep activity level curve, the time phase activity correlation coefficient, a behavior activity level time phase distribution statistic, a peak activity time period minor knot, a low peak activity time period minor knot, an abnormal activity time period minor knot and a sleep activity level report summary;

In this embodiment, the data operation center module S500 further includes the following functional units:

As shown in fig. 3, an apparatus for detecting and quantifying sleep activity level according to an embodiment of the present invention includes the following modules:

the signal acquisition processing module M100 is used for carrying out acquisition monitoring, signal processing and time frame characteristic analysis on physiological state signals and behavior state signals in the sleeping process of a user to generate physiological state time frame characteristics and behavior state time frame characteristics;

the ability state analysis module M200 is used for carrying out central movement ability analysis, myotonic level analysis and behavior action level analysis on the physiological state time frame characteristics and the behavior state time frame characteristics to respectively generate a sleep central movement ability level curve, a sleep myotonic level curve and a sleep behavior action level curve;

The behavior activity quantification module M300 is used for carrying out baseline variation analysis and extremum harmonic analysis according to the sleep central movement capability level curve, the sleep myotonia level curve and the sleep behavior movement level curve, quantifying the behavior capability states and behavior movement performances of the user in different sleep states, and generating a sleep behavior activity level curve;

the sleep behavior reporting module M400 is used for identifying sleep time phase stage according to the physiological state time frame characteristics and the behavior state time frame characteristics, obtaining a sleep time phase curve, extracting time phase behavior activity correlation coefficients in combination with the sleep behavior activity level curve, and generating a sleep behavior activity level report.

The data visualization module M500 is used for unified visual display management of all data in the device;

the data operation center module M600 is used for visual display, data storage and unified management of data operation of all data in the device.

The apparatus is configured to correspondingly perform the steps of the method clock of fig. 1, and will not be described in detail herein.

The present invention also provides various types of programmable processors (FPGA, ASIC or other integrated circuit) for running a program, wherein the program when run performs the steps of the embodiments described above.

The invention also provides corresponding computer equipment, comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the memory realizes the steps in the embodiment when the program is executed.

Although the embodiments of the present invention are described above, the embodiments are only used for facilitating understanding of the present invention, and are not intended to limit the present invention. Any person skilled in the art to which the present invention pertains may make any modifications, changes, equivalents, etc. in form and detail of the implementation without departing from the spirit and principles of the present invention disclosed herein, which are within the scope of the present invention. Accordingly, the scope of the invention should be determined from the following claims.

Claims

1. A method of sleep activity level detection quantification comprising the steps of:

2. The method of claim 1, wherein the specific steps of performing acquisition monitoring, signal processing and time frame feature analysis on the physiological state signal and the behavioral state signal of the sleep process of the user to generate the physiological state time frame feature and the behavioral state time frame feature further comprise:

3. The method of claim 1, wherein: the physiological status signal includes at least one of a central nervous physiological signal, an autonomic nervous physiological signal, and a musculature physiological signal.

4. A method as claimed in claim 3, wherein: the central nervous physiological signal comprises at least one of an electroencephalogram signal, a magnetoencephalic signal and a blood oxygen level dependent signal; the autonomic nerve physiological signal comprises at least one of an electrocardiosignal, a pulse signal, a respiratory signal, an oximetry signal, a body temperature signal and a skin electric signal; the muscle system physiological signal includes at least one of a blood oxygen level dependent signal, a myoelectric signal, a skin electric signal, and an acceleration signal.

5. The method of claim 1, wherein: the behavioral state signals include at least one of sleep posture position signals and limb movement signals.

6. The method of claim 1, wherein: the signal processing at least comprises A/D digital-to-analog conversion, resampling, re-referencing, noise reduction, artifact removal, power frequency notch, low-pass filtering, high-pass filtering, band-stop filtering, band-pass filtering, correction processing and time frame division; the correction processing specifically comprises signal correction and prediction smoothing processing for signal data segments containing artifacts or distortion in physiological state signals, and the time frame division refers to moving interception processing for target signals according to a preset time window and a preset time step.

7. A method according to claim 1 or 2, characterized in that: the time frame characteristic analysis comprises at least one of numerical characteristic, physical characteristic analysis, time frequency characteristic analysis, envelope characteristic and nonlinear characteristic analysis; wherein the numerical features include at least one of mean, root mean square, maximum, minimum, variance, standard deviation, coefficient of variation, kurtosis, and skewness; the physical characteristics comprise at least one of time information, duration information, amplitude characteristics, intensity characteristics and frequency characteristics; the time-frequency characteristic comprises at least one of total power, characteristic frequency band power duty ratio, characteristic frequency band central frequency, heart rate and heart rate variability; the envelope features comprise at least one of an original signal, an envelope signal, a normalized envelope signal, an envelope mean, an envelope root mean square, an envelope maximum, an envelope minimum, an envelope variance, an envelope standard deviation, an envelope variation coefficient, an envelope kurtosis and an envelope skewness; the nonlinear features include at least one of entropy features, fractal features, and complexity features.

8. The method of claim 7, wherein: the physiological state timeframe characteristic comprises at least one of the numerical characteristic, the time-frequency characteristic, the envelope characteristic, and the nonlinear characteristic of the physiological state signal.

9. The method of claim 7, wherein: the behavioral state timeframe characteristics include at least one of the numerical characteristics, the physical characteristics, and the time-frequency characteristics of the behavioral state signals.

10. The method of claim 1 or 2, wherein the specific steps of performing a central motor capability analysis, a myotonic level analysis, and a behavioral action level analysis on the physiological state timeframe features and the behavioral state timeframe features to generate a sleep central motor capability level curve, a sleep myotonic level curve, and a sleep behavioral action level curve, respectively, further comprise:

11. The method of claim 10, wherein the method of computational generation of the hub athletic performance index and the hub athletic performance curve is:

1) Collecting central nerve physiological signals and autonomic nerve physiological signals in a resting state when a current user wakes up, and carrying out time frame feature analysis and feature value average value calculation to obtain a nerve resting motor capacity baseline feature index set;

12. The method of claim 10, wherein the calculation generating method of the myopic level index and the myopic level curve is:

1) Collecting physiological signals of the muscle system in a resting state when the current user wakes up, and carrying out time frame characteristic analysis and characteristic value mean value calculation to obtain a muscle resting behavior baseline characteristic index set;

13. The method of claim 10, wherein the behavioral action level index and the behavioral action level curve are calculated by:

14. The method of claim 1, wherein the step of generating a sleep activity level curve based on the sleep hub motor ability level curve, the sleep myopic level curve, and the sleep activity level curve by performing a baseline variation analysis and an extremum harmonic analysis to quantify the user's performance status and performance of the activity under different sleep states further comprises:

15. The method of claim 14, wherein the sleep activity level index and the sleep activity level curve are generated by:

16. The method of claim 1 or 15, wherein the baseline variation analysis is specifically calculated by:

for real-valued variables

And its non-zero base line sequence +.>

For the baseline variation value of

；/>

wherein ,

respectively real value variable +.>

17. The method according to claim 1 or 15, wherein the extremum harmonic analysis is a data analysis method for observing extremum fluctuation status and general trend change of the analysis value array based on at least one of maximum value, minimum value, absolute value maximum value, absolute value minimum value of the value array as observation base point and at least one of mean value, median value, quantile, variance, coefficient of variation, kurtosis, skewness, absolute value mean value, absolute value median, absolute value quantile, absolute value variance, absolute value coefficient of variation, absolute value mean value, absolute value kurtosis, absolute value skewness of the value array as main analysis harmonic item.

18. The method of claim 1 or 15, wherein one specific calculation of the extremum blending analysis is:

for numerical value arrays

The extremum harmonic value is calculated by the following steps:

；

wherein ,

is a numerical value array +.>

Extremum harmonic value of->

To take the absolute value operator, N is a positive integer.

19. The method of claim 1, wherein the specific steps of identifying sleep phase stages from the physiological state time frame features and the behavioral state time frame features, obtaining a sleep phase curve, extracting phase activity correlation coefficients in conjunction with the sleep behavioral activity level curve, and generating a sleep behavioral activity level report further comprise:

20. The method of claim 19, wherein the method for extracting the sleep phase curve specifically comprises:

21. The method of claim 19, wherein the method for calculating the phase activity correlation coefficient specifically comprises:

22. The method of any one of claims 19-21, wherein: the relationship features include at least one of an association feature and a distance feature; wherein the correlation characteristic comprises at least one of a coherence coefficient, a pearson correlation coefficient, a jaccard similarity coefficient, a linear mutual information coefficient, and a linear correlation coefficient, and the distance characteristic comprises at least one of a euclidean distance, a manhattan distance, a chebyshev distance, a minkowski distance, a normalized euclidean distance, a mahalanobis distance, a barbita distance, a hamming distance, and an angle cosine.

23. The method of claim 1 or 19, wherein the sleep behavior activity level report includes at least any one or more of the sleep phase profile, the sleep behavior activity level profile, the phase behavior activity correlation coefficient, behavior activity level phase distribution statistics, peak activity period summary, low peak activity period summary, abnormal activity period summary, sleep behavior activity level report summary.

24. The method of claim 23, wherein: the behavioural activity level phase distribution statistics are specifically an average behavioural activity level, a maximum behavioural activity level and a minimum behavioural activity level of different sleep phases.

25. The method of claim 23, wherein: the peak activity time section summary is specifically a peak time section distribution corresponding to a segment exceeding a preset peak threshold value in the sleep behavior activity level curve, a time numerical sum and a duty ratio of the peak time section distribution.

26. The method of claim 23, wherein: the low peak activity period summary is specifically low peak period distribution corresponding to a segment exceeding a preset low peak threshold value in the sleep behavior activity level curve, and time numerical sum and duty ratio of the low peak period distribution.

27. The method of claim 23, wherein: the abnormal activity period summary is specifically an abnormal period distribution corresponding to an abnormal segment which deviates from a curve baseline trend in the sleep behavior activity level curve, a time-value sum and a duty ratio of the abnormal period distribution.

28. A system for quantification of sleep activity level detection, comprising the following modules:

29. The system of claim 28, wherein the signal acquisition processing module further comprises the following functional units:

The system comprises a signal acquisition monitoring unit, a sleep state monitoring unit and a control unit, wherein the signal acquisition monitoring unit is used for acquiring and monitoring the physiological state and the behavior state of a sleeping process of a user and generating the physiological state signal and the behavior state signal, the physiological state signal comprises at least one of a central nervous physiological signal, an autonomic nervous physiological signal and a muscle system physiological signal, and the behavior state signal comprises at least one of a sleeping posture position signal and a limb movement signal;

the time frame feature analysis unit is used for carrying out time frame feature analysis on the physiological state data and the behavior state data, generating the physiological state time frame feature and the behavior state time frame feature, and the time frame feature analysis comprises at least one of numerical value feature, physical feature analysis, time frequency feature analysis, envelope feature and nonlinear feature analysis.

30. The system of claim 28 or 29, wherein the capability state analysis module further comprises the following functional units:

31. The system of claim 30, wherein the activity quantification module further comprises the following functional units:

32. The system of claim 31, wherein the sleep behavior reporting module further comprises the following functional units:

the correlation coefficient calculation unit is used for analyzing and calculating the relation characteristic of the sleep time phase curve and the sleep behavior activity level curve, extracting the time phase behavior activity correlation coefficient, and the relation characteristic comprises at least one of a correlation characteristic and a distance characteristic;

33. The system of claim 28, wherein the data operations center module further comprises the following functional units:

34. An apparatus for detecting and quantifying sleep activity level, comprising: