Feature Information Extraction Method and System for Sleep State Monitoring Model

Abstract

The present invention relates to the technical field of sleep assistance, and particularly to a method and system for extracting characteristic information of a sleep state monitoring model. The present invention includes the following steps: collecting multi-modal physiological signals of a subject to obtain original sleep monitoring data; performing noise removal and signal enhancement processing on the original sleep monitoring data, and performing signal segmentation to obtain multi-channel sleep signal segment data; extracting features based on electroencephalogram, electrooculogram, electromyogram, electrocardiogram, and accelerometer signals from the multi-channel sleep signal segment data to obtain multi-dimensional feature data; extracting ultrasonic features and acoustic features from the multi-channel sleep signal segment data to generate acoustic wave feature data. The present invention dynamically models and predicts trends in the process of sleep state transition, can accurately identify potential sleep disorder events, and evaluates their impacts through deep learning, providing support for personalized sleep diagnosis.

Description

Technical Field

[0001] The present invention relates to the technical field of assisted sleep, and particularly to a method and system for extracting characteristic information of a sleep state monitoring model. Background Art

[0002] The extraction of characteristic information in a sleep state monitoring model is a key step in achieving accurate monitoring. By extracting rich time-domain, frequency-domain, time-frequency domain, and non-linear characteristics from various sensor data, the model can comprehensively describe and distinguish different sleep stages and evaluate sleep quality. With the continuous progress of sensor technology and data processing methods, the accuracy and diversity of feature extraction will be further improved, providing more powerful support for personalized health management and precision medicine.

[0003] However, the methods for extracting characteristic information in traditional sleep state monitoring models often have the following problems. During the sleep state monitoring process, physiological signals are easily affected by noise (such as electromagnetic interference, breathing, and body movement), resulting in a decline in the quality of monitoring data, which in turn affects the accuracy of feature extraction. How to remove noise and extract effective features from multi-modal signals has always been a technical problem. Sleep disorders (such as insomnia, sleep apnea, etc.) often occur during sleep, and different disorders have different manifestations on different physiological signals. Therefore, it is difficult for traditional models to achieve real-time identification and monitoring of these events. In addition, the accuracy and efficiency of sleep monitoring also cannot meet the needs of real-time health management. Summary of the Invention

[0004] Based on this, it is necessary for the present invention to provide a method and system for extracting characteristic information of a sleep state monitoring model to solve at least one of the above technical problems.

[0005] To achieve the above object, a method for extracting characteristic information of a sleep state monitoring model includes the following steps:

[0006] Step S1: Collect multi-modal physiological signals of the object to be measured to obtain original sleep monitoring data; perform noise removal and signal enhancement processing on the original sleep monitoring data, and perform signal segmentation to obtain multi-channel sleep signal segment data;

[0007] Step S2: Extract features based on electroencephalogram, electrooculogram, electromyogram, electrocardiogram, and accelerometer signals from the multi-channel sleep signal segment data to obtain multi-dimensional feature data; extract ultrasonic features and acoustic features from the multi-channel sleep signal segment data to generate acoustic wave feature data;

[0008] Step S3: Extract non-linear dynamic features based on the multi-dimensional feature data to generate non-linear feature data; perform complementary fusion processing on the acoustic wave feature data through the non-linear feature data to generate mixed sleep feature data;

[0009] Step S4: Perform spatio-temporal evolution processing and event impact assessment on the mixed sleep feature data to generate sleep event assessment data; screen potential sleep disorder events based on the sleep event assessment data, and collect real-time physiological indicators to generate sleep real-time monitoring indicator data; perform sleep stage fluctuation analysis and physiological perturbation correlation processing on the multi-channel sleep signal segment data through the sleep real-time monitoring indicator data to generate physiological sleep perturbation correlation data;

[0010] Step S5: Identify the sleep environment impact area for the sleep stage fluctuation data to generate sleep environment impact area data; perform physiological-environment impact mode coupling on the sleep environment impact area data to obtain physiological-environment coupling mode data; merge the mixed sleep feature data, physiological sleep perturbation correlation data, and physiological-environment coupling mode data into feature information extraction data.

[0011] Through the acquisition of multi-modal physiological signals (EEG, EOG, EMG, ECG, accelerometer), the present invention comprehensively covers the sleep state of the subject to be measured and enhances the perception ability of sleep state changes from multiple dimensions. The preprocessing of the original sleep monitoring data eliminates noise and enhances key signals, ensuring the accuracy and robustness of subsequent processing. The segmentation of multi-channel signals enables feature extraction and analysis to be carried out on a finer-grained time period, accurately capturing short-term dynamic changes. The multi-dimensional feature extraction of EEG, EOG, EMG, ECG, and body movement can comprehensively reveal the changes in the brain, muscles, heart, and body posture during sleep, while acoustic features and ultrasonic features further enhance the detection of abnormal breathing and body movements. The extraction of non-linear dynamics features can capture complex sleep physiological changes, and through the fusion with acoustic wave features, more accurately identify abnormal events such as sleep apnea. The system reveals the dynamic changes of the sleep state through spatio-temporal evolution analysis, evaluates and identifies potential sleep disorder events in real time, and provides dynamic monitoring of important events during sleep. The fluctuation analysis of multi-channel sleep signals combined with physiological perturbation correlation deeply analyzes the correlation between physiological signal changes and sleep stages. Through physiological-environment coupling analysis, it reveals the impact of external environmental factors such as light, noise, and temperature on sleep quality, thereby constructing a more comprehensive sleep state assessment framework. Finally, based on the fusion of multi-source signals and multi-dimensional features, the system can achieve a full-range dynamic assessment of individual sleep quality, provide personalized intervention suggestions, and help more accurately identify and improve potential sleep problems.

[0012] The present invention also provides a feature information extraction system for a sleep state monitoring model, which is used to execute the feature information extraction method of the sleep state monitoring model described above. The feature information extraction system for the sleep state monitoring model includes:

[0013] A signal preprocessing module for collecting multi-modal physiological signals of the object under test to obtain original sleep monitoring data; removing noise and enhancing the signals from the original sleep monitoring data, and performing signal segmentation to obtain multi-channel sleep signal segment data;

[0014] A multi-dimensional feature extraction module for extracting features based on electroencephalogram, electrooculogram, electromyogram, electrocardiogram, and accelerometer signals from the multi-channel sleep signal segment data to obtain multi-dimensional feature data; extracting ultrasonic features and acoustic features from the multi-channel sleep signal segment data to generate acoustic wave feature data;

[0015] A feature fusion module for extracting non-linear dynamic features based on the multi-dimensional feature data to generate non-linear feature data; performing complementary fusion processing on the acoustic wave feature data through the non-linear feature data to generate mixed sleep feature data;

[0016] A sleep dynamic analysis module for performing spatio-temporal evolution processing and event impact assessment on the mixed sleep feature data to generate sleep event assessment data; screening potential sleep disorder events based on the sleep event assessment data, and collecting real-time physiological indicators to generate sleep real-time monitoring index data; performing sleep stage fluctuation analysis and physiological perturbation correlation processing on the multi-channel sleep signal segment data through the sleep real-time monitoring index data to generate physiological sleep perturbation correlation data;

[0017] An environment-physiology coupling module for identifying the sleep environment impact areas from the sleep stage fluctuation data to generate sleep environment impact area data; coupling the physiological-environment impact patterns for the sleep environment impact area data to obtain physiological-environment coupling pattern data; combining the mixed sleep feature data, physiological sleep perturbation correlation data, and physiological-environment coupling pattern data into feature information extraction data.

[0018] The present invention improves the accuracy of the original signal through noise removal and signal enhancement, ensuring the reliability of feature extraction. Signal segmentation makes the processing of long-term monitoring data more efficient, and multi-channel synchronous processing ensures the temporal consistency of physiological signals, facilitating the fusion of multi-dimensional features. The extracted multi-dimensional physiological features comprehensively reflect the sleep state, including information such as electroencephalogram, heart rate, eye movement, electromyogram, and body movement. Combining ultrasonic and acoustic features can detect external influences such as breathing and snoring, enriching the dimensions of sleep assessment. By extracting non-linear dynamic features, the system improves its sensitivity to complex physiological changes and abnormal events. The fusion of multi-dimensional features and acoustic wave features generates comprehensive hybrid sleep feature data, enhancing the comprehensiveness of sleep assessment. Spatiotemporal evolution analysis dynamically monitors changes in the sleep state and identifies potential sleep disorders or abnormal events. Real-time physiological monitoring combined with physiological perturbation analysis enables the system to detect physiological abnormalities in a timely manner and adjust the monitoring strategy. In addition, the system identifies the impact of environmental factors on sleep and optimizes the sleep environment and personalized intervention strategies through physiological-environmental coupling analysis, ultimately improving the accuracy and reliability of sleep quality assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Other features, objects, and advantages of the present invention will become more apparent by reading the detailed description of the non-limiting embodiments with reference to the following drawings:

[0020] Figure 1 It is a schematic flowchart of the steps for the method of extracting feature information of the sleep state monitoring model of the present invention;

[0021] Figure 2 is Figure 1 a detailed schematic flowchart of step S1 in

[0022] Figure 3 is Figure 1 a detailed schematic flowchart of step S2 in DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] The following clearly and completely describes the technical method of the present invention with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art within the scope of the present invention without creative efforts belong to the scope of protection of the present invention.

[0024] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0025] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0026] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a method for extracting characteristic information of a sleep state monitoring model, and the method includes the following steps:

[0027] Step S1: Collect multi-modal physiological signals of the object to be measured to obtain original sleep monitoring data; perform noise removal and signal enhancement processing on the original sleep monitoring data, and perform signal segmentation to obtain multi-channel sleep signal segment data;

[0028] Step S2: Extract features based on electroencephalogram, electrooculogram, electromyogram, electrocardiogram, and accelerometer signals from the multi-channel sleep signal segment data to obtain multi-dimensional feature data; extract ultrasonic features and acoustic features from the multi-channel sleep signal segment data to generate acoustic wave feature data;

[0029] Step S3: Extract non-linear dynamic features based on the multi-dimensional feature data to generate non-linear feature data; perform complementary fusion processing on the acoustic wave feature data through the non-linear feature data to generate mixed sleep feature data;

[0030] Step S4: Perform spatio-temporal evolution processing and event impact evaluation on the mixed sleep feature data to generate sleep event evaluation data; screen potential sleep disorder events based on the sleep event evaluation data, and collect real-time physiological indicators to generate sleep real-time monitoring index data; perform sleep stage fluctuation analysis and physiological perturbation correlation processing on the multi-channel sleep signal segment data through the sleep real-time monitoring index data to generate physiological sleep perturbation correlation data;

[0031] Step S5: Identify the sleep environment impact areas for the sleep stage fluctuation data to generate sleep environment impact area data; perform physiological-environment impact pattern coupling on the sleep environment impact area data to obtain physiological-environment coupling pattern data; merge the mixed sleep feature data, physiological sleep perturbation correlation data, and physiological-environment coupling pattern data into feature information extraction data.

[0032] In the embodiment of the present invention, referring to Figure 1 as described, it is a schematic diagram of the step flow of a method for extracting feature information of a sleep state monitoring model of the present invention. In this example, the method for extracting feature information of the sleep state monitoring model includes the following steps:

[0033] Step S1: Collect multi-modal physiological signals from the object to be measured to obtain original sleep monitoring data; perform noise removal and signal enhancement processing on the original sleep monitoring data, and perform signal segmentation to obtain multi-channel sleep signal segment data;

[0034] In the embodiment of the present invention, a multi-modal physiological signal collection device, such as a polysomnograph, is used to continuously collect physiological signals from the object to be measured. These signals include electroencephalogram (EEG), electrooculogram (EOG), electromyogram (EMG), electrocardiogram (ECG), and accelerometer signals to comprehensively record the physiological state of the object to be measured during sleep. During the collection process, the sampling rates of the device are set to 500Hz for EEG and EOG, 1000Hz for EMG and ECG, and 100Hz for the accelerometer to ensure high-precision and high-resolution signals. The collected original sleep monitoring data will be subjected to noise removal through a digital filter, and band-pass filtering (such as the 0.5 - 50Hz range for EEG signals) is used to remove environmental noise and power interference. Subsequently, the empirical mode decomposition (EMD) method is applied for signal enhancement processing to improve the signal-to-noise ratio. The processed signals are segmented according to a preset time window (such as 30 seconds) to generate multi-channel sleep signal segment data, which is convenient for subsequent feature extraction and analysis.

[0035] Step S2: Extract features based on electroencephalogram, electrooculogram, electromyogram, electrocardiogram, and accelerometer signals from the multi-channel sleep signal segment data to obtain multi-dimensional feature data; extract ultrasonic features and acoustic features from the multi-channel sleep signal segment data to generate acoustic wave feature data;

[0036] In the embodiments of the present invention, based on the multi-channel sleep signal segment data after signal segmentation, feature extraction is performed on various physiological signals respectively. For electroencephalogram signals, energy features in the δ (0.5 - 4 Hz), θ (4 - 8 Hz), α (8 - 13 Hz), β (13 - 30 Hz), and γ (30 - 50 Hz) bands are extracted, and waveform features of K complexes and sleep spindles are detected. For electrooculogram signals, frequency and amplitude features are extracted by identifying rapid and slow eye movements. Electromyogram signals are used to evaluate muscle tension by analyzing the intensity and frequency features of electromyographic activity. Electrocardiogram signals adopt heart rate variability analysis to extract time-domain and frequency-domain indicators. Accelerometer signals are used for body movement analysis to extract features such as body movement frequency, intensity, and duration. After integrating these multi-dimensional feature data, they are combined with the micro body movement features collected by ultrasonic sensors and the environmental sound features collected by high-sensitivity microphones to generate comprehensive acoustic wave feature data. In specific applications, feature extraction algorithms such as wavelet transform and fast Fourier transform (FFT) are applied to signal processing to ensure the accuracy and effectiveness of feature extraction.

[0037] Step S3: Perform non-linear dynamics feature extraction based on the multi-dimensional feature data to generate non-linear feature data; perform complementary fusion processing on the acoustic wave feature data through the non-linear feature data to generate mixed sleep feature data;

[0038] After obtaining the multi-dimensional feature data in the embodiments of the present invention, a non-linear dynamics method is used to further extract features from it. For example, the phase space reconstruction technique is used to process the multi-dimensional feature data, and the maximum Lyapunov exponent is calculated to evaluate the stability of the system; recurrence quantification analysis (RQA) is used to extract recurrence rate and determinism features; sample entropy and approximate entropy are used to measure the complexity of the signal. In addition, fluctuation features are extracted through detrended fluctuation analysis and long-range correlation analysis. The non-linear feature data and the acoustic wave feature data are subjected to complementary fusion processing, usually using a feature fusion method based on a deep neural network, to enhance the expression ability and discriminant performance of the features. Finally, mixed sleep feature data is generated, which plays a key role in subsequent sleep event evaluation and perturbation correlation analysis. In specific applications, the structure of the deep neural network can be selected as a multi-layer perceptron (MLP) or a convolutional neural network (CNN), and the network parameters are optimized through cross-validation to achieve the best feature fusion effect.

[0039] Step S4: Perform spatio-temporal evolution processing and event impact evaluation on the mixed sleep feature data to generate sleep event evaluation data; screen potential sleep disorder events based on the sleep event evaluation data, and collect real-time physiological indicators to generate real-time sleep monitoring indicator data; perform sleep stage fluctuation analysis and physiological perturbation correlation processing on the multi-channel sleep signal segment data through the real-time sleep monitoring indicator data to generate physiological sleep perturbation correlation data;

[0040] In the embodiment of the present invention, the mixed sleep characteristic data is processed through spatio-temporal evolution. By using methods such as time series analysis and hidden Markov model (HMM), the spatio-temporal evolution event data of the sleep state is generated. These data are used to identify potential sleep interruptions or abnormal events, and the impact of the events is evaluated through a feature importance evaluation method (such as gradient-based importance scoring) to generate sleep event evaluation data. Then, based on the evaluation data, potential sleep disorder events are screened out, and the acquisition parameters of the multi-modal sensors are configured to collect key physiological indicators in real time, such as heart rate, respiratory rate, etc., to generate real-time sleep monitoring index data. By performing sleep stage fluctuation analysis on these real-time sleep monitoring index data and multi-channel sleep signal segment data, and using methods such as the dynamic time warping (DTW) algorithm, the volatility of the sleep stage is analyzed, and the physiological disturbances are correlated to generate physiological sleep disturbance correlation data. In a specific application scenario, the acquisition frequency of the real-time monitoring indicators is set to once per second for heart rate and respiratory rate to ensure the real-time and accuracy of the data.

[0041] Step S5: Identify the sleep environment impact area for the sleep stage fluctuation data to generate sleep environment impact area data; perform physiological-environment impact mode coupling on the sleep environment impact area data to obtain physiological-environment coupling mode data; merge the mixed sleep characteristic data, physiological sleep disturbance correlation data, and physiological-environment coupling mode data into feature information extraction data.

[0042] The physiological sleep disturbance correlation data in the embodiment of the present invention is used to identify the impact area of the sleep environment. An algorithm based on spatial clustering (such as DBSCAN) is used for area identification to generate sleep environment impact area data. Then, by using a multi-variable coupling analysis method, the physiological data and environmental data (such as temperature, noise level) are coupled to establish a physiological-environment impact mode to generate physiological-environment coupling mode data. In actual applications, the acquisition of environmental parameters is realized through smart home devices. The temperature is set between 18-22 °C, and the noise level is controlled at 30-40 decibels to optimize sleep quality. Finally, the mixed sleep characteristic data, physiological sleep disturbance correlation data, and physiological-environment coupling mode data are integrated to form comprehensive feature information extraction data. These comprehensive data can be used for further sleep quality assessment, sleep disorder diagnosis, and the formulation of personalized sleep intervention programs. The application scenarios cover fields such as home sleep monitoring, medical diagnosis, and sleep research.

[0043] Preferably, step S1 includes the following steps:

[0044] Step S11: Continuously collect the sleep physiological data of the object to be measured by using a polysomnograph, where the sleep physiological data includes electroencephalogram, electrooculogram, electromyogram, electrocardiogram, and accelerometer signal;

[0045] Step S12: Collect body movement signals through an ultrasonic sensor and collect environmental sounds through a high-sensitivity microphone, so as to obtain body movement environmental acoustic data;

[0046] Step S13: Combine the sleep physiological data and the body movement environmental acoustic data into original sleep monitoring data;

[0047] Step S14: Perform signal quality assessment on the original sleep monitoring data to obtain signal quality assessment data, where the signal quality assessment includes signal-to-noise ratio calculation and electrode detachment detection; remove electrooculogram and electromyogram artifacts from the original sleep monitoring data, and use wavelet transform to remove baseline drift, so as to obtain sleep monitoring data;

[0048] Step S15: Perform signal enhancement based on empirical mode decomposition on the sleep monitoring data according to the signal quality assessment data, so as to obtain enhanced sleep monitoring data;

[0049] Step S16: Perform signal segmentation on the enhanced sleep monitoring data to obtain multi-channel sleep signal segment data.

[0050] As an embodiment of the present invention, referring to Figure 2 shown, it is Figure 1 a detailed step flow diagram of step S1 in

[0051] Step S11: Continuously collect data from the object to be measured using a polysomnograph to obtain sleep physiological data, where the sleep physiological data includes electroencephalogram, electrooculogram, electromyogram, electrocardiogram, and accelerometer signals;

[0052] In the embodiment of the present invention, a polysomnograph is used to continuously collect data from the object to be measured, and the collected data includes electroencephalogram (EEG), electrooculogram (EOG), electromyogram (EMG), electrocardiogram (ECG), and accelerometer signals. In specific operations, the electrodes for collecting electroencephalogram signals are placed on the scalp according to the international 10-20 electrode placement system, and the electrode contact resistance is controlled within 5 kΩ. The sampling rates of EEG and EOG are set to 500 Hz, the sampling rates of EMG and ECG are 1000 Hz, and the accelerometer signals are recorded at a frequency of 100 Hz. During the collection process, ensure good electrode contact and monitor the signal stability in real time to avoid artifact interference. The collection process lasts throughout the sleep cycle, recording the physiological data of each sleep stage, providing a complete sleep physiological basis for subsequent analysis.

[0053] Step S12: Collect body movement signals through an ultrasonic sensor and collect environmental sounds through a high-sensitivity microphone, so as to obtain body movement environmental acoustic data;

[0054] In order to more comprehensively evaluate the sleep state, the embodiment of the present invention uses an ultrasonic sensor to collect body motion signals, and combines it with a high-sensitivity microphone to collect environmental sounds. In a specific application scenario, the ultrasonic sensor is installed at the head of the bed or under the mattress, and the operating frequency is set to 40kHz to detect tiny body movements of the subject, such as breathing and turning over. The high-sensitivity microphone is placed in the sleeping environment, 1.5 meters away from the noise source, with a frequency response range of 20Hz to 20kHz, to collect external noise and the subject's snoring, etc. By synchronously recording body motion signals and environmental acoustic data, we can better understand the interference factors in the sleep process, and provide data support for subsequent body movement and environmental impact analysis.

[0055] Step S13: merging the sleep physiological data and the body motion environment acoustic data into original sleep monitoring data;

[0056] The embodiment of the present invention merges the sleep physiological data collected in step S11 and the body movement and environmental acoustic data obtained in step S12 to generate original sleep monitoring data. When merging data, it is necessary to ensure that the timestamps of various signals are synchronized so that the physiological and environmental data of the same time period can be accurately corresponded in subsequent analysis. The data storage format is a multi-channel time series, and all signals are uniformly recorded with a time resolution of 1ms. By integrating body movement and environmental sound information with physiological data, a global sleep monitoring data set is constructed to facilitate subsequent feature extraction and analysis.

[0057] Step S14: performing signal quality assessment on the original sleep monitoring data to obtain signal quality assessment data, wherein the signal quality assessment includes signal-to-noise ratio calculation and electrode detachment detection; performing electrooculography and electromyography artifact removal on the original sleep monitoring data, and removing baseline drift using wavelet transform, thereby obtaining sleep monitoring data;

[0058] The embodiment of the present invention performs signal quality assessment on the original sleep monitoring data, and first calculates the signal-to-noise ratio of each channel signal. In the specific operation, the signal-to-noise ratio is calculated based on the ratio of noise variance and signal power using the background noise level estimation formula in the signal. The ideal signal-to-noise ratio of EEG and EOG signals is usually maintained above 20 dB. In addition, the contact impedance of the EEG electrode is monitored in real time to detect whether the electrode has fallen off. If the impedance suddenly rises by more than 10 kΩ, it is marked as electrode detachment. Then, the adaptive filter method is used to remove EOG and EMG artifacts to ensure the purity of sleep physiological signals. In order to solve the problem of baseline drift, the wavelet transform method is applied to remove it. In particular, for electroencephalogram signals, the db4 wavelet basis is used to process the low-frequency drift, thereby obtaining sleep monitoring data after artifact removal and baseline correction.

[0059] Step S15: Perform signal enhancement based on empirical mode decomposition on the sleep monitoring data according to the signal quality evaluation data, so as to obtain enhanced sleep monitoring data;

[0060] In the embodiment of the present invention, according to the signal quality evaluation data, for the sleep monitoring data with relatively low signal-to-noise ratio or containing artifacts, the empirical mode decomposition (EMD) algorithm is applied for signal enhancement. First, the original signal is decomposed into a series of intrinsic mode functions (IMFs), and the main components are retained and the noise components are removed through screening and reconstruction. In specific operations, for EEG signals, usually only the first 3-4 order IMFs are retained to capture the main physiological fluctuations during sleep. The EMD processing can enhance the detailed part of the signal, especially the weak signal part, improve the usability of the signal, and thus generate enhanced sleep monitoring data to ensure higher credibility in subsequent analysis.

[0061] Step S16: Perform signal segmentation on the enhanced sleep monitoring data to obtain multi-channel sleep signal segment data.

[0062] In the embodiment of the present invention, after signal enhancement, signal segmentation is performed on the enhanced sleep monitoring data. The segmentation is based on a standard sleep time window, usually set to 30 seconds for each time period to ensure that each segment can completely contain a complete physiological change cycle. For accelerometer signals and body movement signals, the time window can be shortened to 10 seconds to capture more subtle movement changes. The segmented data will be marked as multi-channel sleep signal segments and saved according to the channel type and time sequence. These segment data are convenient for subsequent feature extraction and sleep state classification analysis. In actual scenarios, these segments will be used as inputs in machine learning models or deep learning models for predicting and classifying different sleep stages or states.

[0063] The present invention comprehensively collects electroencephalogram (EEG), electrooculogram (EOG), electromyogram (EMG), electrocardiogram (ECG) and accelerometer signals through a polysomnography monitor, covering multi-dimensional monitoring of the brain, heart, muscle activities and body postures, ensuring an all-round perception of the sleep state. Combining the collection of ultrasonic waves and environmental sounds further enhances the detection ability of respiration, body movement and the impact of the external environment on sleep. By removing artifacts, correcting baseline drift and enhancing signals from the original data, the purity and signal-to-noise ratio of the signals are effectively improved, ensuring the accuracy and robustness of subsequent data analysis. Signal segmentation divides long-time data into short-time segments, enabling the system to analyze the sleep characteristics in each time period in fine granularity and capture the subtle dynamic changes during sleep. This process not only improves the recognition accuracy of sleep stages but also helps identify abnormal events such as sleep apnea. The fusion of multi-dimensional features and acoustic wave features increases the data diversity. Combining with non-linear dynamics feature analysis, the system can more accurately capture complex sleep state changes. Overall, the present invention improves the accuracy and comprehensiveness of sleep state assessment through rich physiological data, diverse feature extraction and fusion methods, providing a solid foundation for personalized sleep monitoring and intervention.

[0064] Preferably, step S16 includes the following steps:

[0065] Step S161: Segment the enhanced sleep monitoring data according to the preset time window data to obtain initial sleep signal segment data;

[0066] In the embodiment of the present invention, the enhanced sleep monitoring data is segmented according to a preset time window. The commonly used time window is 30 seconds, which is the standard time period for classifying different sleep stages in sleep research. In specific implementation, signals such as electroencephalogram, electrooculogram, and electromyogram are divided into continuous time period segments to ensure that each segment contains synchronous data of all channels. To reduce boundary effects, an overlapping window processing method is adopted, and the window overlap rate is set to 50%, that is, half of the data in each time window segment is shared with the front and back segments to ensure the continuity of signal features. The initial sleep signal segment data obtained through this processing method will be used for further multi-channel synchronous processing.

[0067] Step S162: Perform multi-channel time synchronization and alignment processing on the initial sleep signal segment data to obtain aligned sleep signal segment data;

[0068] In the embodiments of the present invention, multi-channel time synchronization and alignment processing are performed on the initial sleep signal segment data. Since the sampling rates of different devices may be different, it is necessary to first unify the sampling frequencies of each channel. For example, the sampling rate of electroencephalogram may be 500 Hz, while the sampling rate of the accelerometer signal is 100 Hz. The data of each channel needs to be synchronized to a unified 500 Hz through interpolation and resampling. Then, the cross-correlation algorithm is used to align the signals of each channel to ensure that the data points at the same moment on the time axis correspond to the same physiological state and environmental factors. The aligned sleep signal segment data will more accurately reflect the coordinated changes of various physiological signals during sleep.

[0069] Step S163: Perform data integrity check on the aligned sleep signal segment data, identify and mark the missing or distorted data segments to obtain integrity check data;

[0070] In the embodiments of the present invention, data integrity check is performed on the aligned sleep signal segment data, and the missing or distorted data segments are identified and marked. In specific operations, data loss or signal distortion is detected by checking the continuity of the signal and the voltage amplitude range. For example, if the voltage amplitude of a certain segment of electroencephalogram signal abnormally exceeds the normal physiological range (such as ±100 μV), it can be marked as a distorted data segment. For the missing data segments, they can be identified through the data blanks on the time axis. These marked missing or distorted data segments will be used for subsequent data repair or processing, and corresponding integrity check data will be generated to ensure the accuracy and reliability of subsequent data analysis.

[0071] Step S164: Perform amplitude normalization processing on the aligned sleep signal segment data according to the integrity check data, and perform fast Fourier transform to obtain sleep signal spectrum data;

[0072] In the embodiments of the present invention, based on the integrity check data, amplitude normalization processing is performed on the aligned sleep signal segment data. In specific operations, by normalizing the data of each channel, the signal amplitude range is mapped between 0 and 1 to eliminate the amplitude differences between different channels, facilitating subsequent frequency domain analysis. Then, fast Fourier transform (FFT) is used to perform spectrum analysis on the normalized data to convert the time domain signal into a frequency domain signal. The specific operation parameters of FFT are: the spectrum resolution is set to 0.1 Hz, the frequency band range is from 0.5 Hz to 50 Hz, and the spectrum information of common slow waves (such as δ waves, 0.5 - 4 Hz) and fast waves (such as α waves, 8 - 13 Hz) during sleep is extracted. The generated sleep signal spectrum data will be used to analyze the physiological activity characteristics of different frequency bands during sleep.

[0073] Step S165: performing multi-channel integration and synchronous processing on the sleep signal spectrum data to obtain multi-channel sleep signal segment data, wherein the multi-channel includes electroencephalogram, oculogram, electromyogram, electrocardiogram, accelerometer signal, ultrasonic signal and acoustic signal.

[0074] The embodiment of the present invention performs multi-channel integration and synchronization processing on the sleep signal spectrum data to generate the final multi-channel sleep signal segment data. This step first aligns and integrates the spectrum data of the electroencephalogram (EEG), oculogram (EOG), electromyogram (EMG), electrocardiogram (ECG), accelerometer signal, ultrasonic signal and acoustic signal in the time and frequency domain through a multi-channel synchronization algorithm. In the specific operation, the linear weighted average method is used to fuse the spectrum information of each channel at the same time point to ensure that the correlation between the signals of each channel is maintained. In practical applications, multi-channel data integration can better capture the overall physiological state and sleep behavior of the subject. Ultimately, the obtained multi-channel sleep signal segment data will be used for subsequent feature extraction and sleep stage classification analysis, which can more comprehensively and accurately reflect the sleep quality and potential problems of the subject.

[0075] The present invention divides the enhanced sleep monitoring data into preset time windows to accurately capture sleep activities in each time segment, ensure fine-grained analysis of signals, and improve the efficiency of real-time monitoring and parallel processing. The time synchronization and alignment processing of multi-channel data ensures the time consistency of signals from different sensors and reduces the time deviation in the analysis. Through data integrity check, the system can identify and process abnormal data to ensure the reliability of the analysis results. Amplitude normalization eliminates the dimensional differences between different sensors and enhances the comparability of cross-channel analysis. Fast Fourier transform (FFT) provides frequency domain features to reveal sleep physiological activities in different frequency bands. The integrated analysis of multi-channel signals enhances the ability to capture complex physiological changes, improves the comprehensive understanding of sleep status and the detection accuracy of abnormal events. On the whole, the system achieves accurate assessment of sleep status and effective identification of sleep disorders through high-quality data processing, multi-dimensional feature extraction and spectrum analysis.

[0076] Preferably, step S2 comprises the following steps:

[0077] Step S21: extracting energy features of the δ, θ, α, β and γ bands from the EEG signals in the multi-channel sleep signal segment data, and performing waveform detection based on K complexes and sleep spindles to obtain EEG feature data;

[0078] Step S22: performing fast and slow eye movement identification on the eye movement signal in the multi-channel sleep signal segment data, and extracting the eye movement frequency and amplitude characteristics in the rapid eye movement and non-rapid eye movement states to obtain eye movement feature data;

[0079] Step S23: Perform muscle tension analysis on the electromyogram signals in the multi-channel sleep signal segment data based on the electromyogram activity intensity and frequency characteristics to obtain electromyogram feature data;

[0080] Step S24: Perform heart rate variability analysis on the electrocardiogram signals in the multi-channel sleep signal segment data, extract time-domain and frequency-domain heart rate variability indexes to obtain electrocardiogram feature data;

[0081] Step S25: Perform body movement analysis on the accelerometer signals in the multi-channel sleep signal segment data, extract body movement frequency, intensity, and duration characteristics to obtain body movement feature data;

[0082] Step S26: Combine the electroencephalogram feature data, eye movement feature data, electromyogram feature data, electrocardiogram feature data, and body movement feature data into multi-dimensional feature data;

[0083] Step S27: Perform Doppler frequency shift analysis on the ultrasonic signals in the multi-channel sleep signal segment data, extract minute body movement characteristics to obtain ultrasonic feature data;

[0084] Step S28: Perform sound event detection and classification on the environmental sound signals in the multi-channel sleep signal segment data, extract sleep sound characteristics based on breath sounds and snoring sounds to obtain acoustic feature data; combine the ultrasonic feature data and the acoustic feature data into acoustic wave feature data.

[0085] As an embodiment of the present invention, refer to Figure 3 shown in Figure 1 is a detailed step flow schematic diagram of step S2 in

[0086] Step S21: Extract the energy characteristics of the δ, θ, α, β, and γ bands from the electroencephalogram signals in the multi-channel sleep signal segment data, and perform waveform detection based on K complexes and sleep spindles to obtain electroencephalogram feature data;

[0087] In the embodiments of the present invention, in the multi-channel sleep signal segment data, the electroencephalogram (EEG) signal is analyzed in detail to extract the energy characteristics of the δ (0.5 - 4 Hz), θ (4 - 8 Hz), α (8 - 13 Hz), β (13 - 30 Hz), and γ (30 - 50 Hz) bands. In the specific operation, first, band-pass filters are applied to filter out the signals of each frequency band respectively, and then the power spectral density (PSD) of each frequency band is calculated to quantify the energy characteristics. Subsequently, an automatic detection algorithm is used to identify the waveform characteristics of K-complexes and sleep spindles. The detection of K-complexes adopts a method based on template matching and is identified by comparing the correlation with a predefined K-complex template; the detection of sleep spindles adopts a method combining wavelet transform and threshold determination to capture its unique frequency and duration characteristics. In a specific application scenario, the sampling rate of the EEG signal is set to 500 Hz, and the bandwidths of the filters are δ (0.5 - 4 Hz), θ (4 - 8 Hz), α (8 - 13 Hz), β (13 - 30 Hz), and γ (30 - 50 Hz) respectively, ensuring the accurate extraction of the energy characteristics of each frequency band. Finally, electroencephalogram feature data including the energy values of each frequency band and the detection results of K-complexes and sleep spindles is generated for subsequent sleep stage classification and analysis.

[0088] Step S22: Perform rapid and slow eye movement recognition on the electrooculogram signal in the multi-channel sleep signal segment data, and extract the eye movement frequency and amplitude characteristics in the rapid eye movement and non-rapid eye movement states to obtain electrooculogram feature data;

[0089] In the embodiments of the present invention, the electrooculogram (EOG) signal in the multi-channel sleep signal segment data is recognized for rapid and slow eye movements, and the eye movement frequency and amplitude characteristics in the rapid eye movement (REM) and non-rapid eye movement (NREM) states are extracted. In the specific operation, first, a low-pass filter (such as 30 Hz) is applied to remove high-frequency noise, and then methods based on the time domain and frequency domain are used to identify rapid and slow eye movements. The recognition of rapid eye movements adopts short-time energy and zero-crossing rate analysis, and slow eye movements are detected through signal fluctuations with a long time span. After the recognition is completed, the eye movement frequency (times / minute) and amplitude (μV) within each time window are calculated to quantify the eye movement characteristics. In practical applications, the sampling rate of the EOG signal is set to 500 Hz, the time window for rapid eye movement detection is 2 seconds, and the time window for slow eye movement detection is 10 seconds. Finally, electrooculogram feature data including the eye movement frequency and amplitude in the REM and NREM states is generated for evaluating the sleep stage and monitoring sleep abnormalities related to eye movements.

[0090] Step S23: Perform muscle tension analysis on the electromyogram signal in the multi-channel sleep signal segment data based on the electromyogram activity intensity and frequency characteristics to obtain electromyogram feature data;

[0091] In an embodiment of the present invention, muscle tension analysis based on the intensity and frequency characteristics of electromyogram (EMG) signals in multi-channel sleep signal segment data is performed to obtain EMG feature data. In specific operations, first, the EMG signal is subjected to high-pass filtering (such as 20 Hz) to remove the DC component and low-frequency noise. Then, the root mean square (RMS) value is used to calculate the intensity of EMG activity, and the frequency domain characteristics, such as the dominant frequency and the frequency band energy distribution, are extracted through fast Fourier transform (FFT). Next, the threshold determination method is used to identify changes in muscle tension, such as sudden muscle activity or continuous muscle relaxation. In a specific application scenario, the sampling rate of the EMG signal is set to 1000 Hz, the RMS calculation window is 1 second, and the spectral resolution of the FFT is set to 1 Hz. Finally, EMG feature data including the intensity of EMG activity, the dominant frequency, and the frequency domain distribution is generated for analyzing muscle activity during sleep and evaluating muscle-related sleep disorders.

[0092] Step S24: Perform heart rate variability analysis on the electrocardiogram signal in the multi-channel sleep signal segment data, extract time-domain and frequency-domain heart rate variability indexes, and obtain electrocardiogram feature data;

[0093] In an embodiment of the present invention, heart rate variability (HRV) analysis is performed on the electrocardiogram (ECG) signal in the multi-channel sleep signal segment data, and time-domain and frequency-domain heart rate variability indexes are extracted to obtain electrocardiogram feature data. In specific operations, first, QRS wave detection is performed on the ECG signal, and the Pan-Tompkins algorithm is used to accurately identify the heart beat interval (RR interval). In time-domain analysis, indexes such as standard deviation of NN intervals (SDNN) and root mean square of successive differences (RMSSD) are calculated; in frequency-domain analysis, the fast Fourier transform (FFT) or power spectral density estimation method is applied to extract the low-frequency (LF, 0.04 - 0.15 Hz) and high-frequency (HF, 0.15 - 0.40 Hz) powers and the LF / HF ratio. In a specific application scenario, the sampling rate of the ECG signal is set to 1000 Hz, and the threshold for QRS detection is dynamically adjusted according to the heart rate range of the measured object to ensure accurate identification of heart beats. Finally, electrocardiogram feature data including time-domain and frequency-domain HRV indexes is generated for evaluating the activity of the autonomic nervous system and the cardiac health status.

[0094] Step S25: Perform body movement analysis on the accelerometer signal in the multi-channel sleep signal segment data, extract body movement frequency, intensity, and duration characteristics, and obtain body movement feature data;

[0095] The embodiment of the present invention performs body motion analysis on the accelerometer signal in the multi-channel sleep signal segment data, extracts the body motion frequency, intensity and duration characteristics, and obtains body motion feature data. In the specific operation, the accelerometer signal is first low-pass filtered (such as 5Hz) to remove high-frequency noise, and then the amplitude and change rate of the signal are calculated to quantify the body motion intensity. The time domain analysis method is used to identify the frequency and duration of body motion events, such as the number of body movements per minute and the duration of a single body movement. Further, a detection algorithm based on statistical thresholds is applied to distinguish normal body movements from abnormal body movements (such as frequent turning over or violent movements). In a specific application scenario, the sampling rate of the accelerometer signal is set to 100Hz, and the threshold of body motion detection is adjusted individually according to the activity habits of the subject. Finally, body motion feature data including body motion frequency, intensity and duration are generated for monitoring body motion patterns during sleep and identifying abnormal body motion behaviors.

[0096] Step S26: merging the EEG feature data, the eye movement feature data, the myoelectric feature data, the electrocardiographic feature data, and the body movement feature data into multi-dimensional feature data;

[0097] The embodiment of the present invention integrates the EEG feature data, eye movement feature data, electromyographic feature data, electrocardiographic feature data and body movement feature data extracted in steps S21-S25 to form multidimensional feature data. In the specific operation, each type of feature data is first standardized (such as Z-score standardization) to eliminate the dimensional differences between different features. Then, the various types of feature data are arranged in order according to the time window (such as 30 seconds) to form a multidimensional vector containing all feature dimensions. For example, within a 30-second time window, the EEG features include the energy value and waveform detection results of each frequency band, the eye movement features include frequency and amplitude, the electromyographic features include activity intensity and frequency, the electrocardiographic features include HRV indicators, and the body movement features include frequency, intensity and duration. Finally, a comprehensive multidimensional feature data set is generated as an input for subsequent sleep stage classification and abnormality detection to ensure the comprehensive analysis and evaluation of various physiological signals.

[0098] Step S27: performing Doppler frequency shift analysis on the ultrasonic signal in the multi-channel sleep signal segment data, extracting micro-body motion features, and obtaining ultrasonic feature data;

[0099] In the embodiments of the present invention, Doppler frequency shift analysis is performed on the ultrasonic signals in the multi-channel sleep signal segment data to extract micro-body movement features and obtain ultrasonic feature data. In specific operations, first, the ultrasonic signals are band-pass filtered (such as 20 kHz to 40 kHz) to remove background noise, and then the Doppler frequency shift algorithm is applied to detect the micro-movements of the object under test, such as breathing and slight turning over. By comparing the frequency changes of the transmitted and received ultrasonic signals, the speed and direction of the body movement are calculated, thereby quantifying the frequency and amplitude of the micro-body movement. In a specific application scenario, the operating frequency of the ultrasonic sensor is set to 40 kHz, and the signal sampling rate is 100 kHz to ensure high-precision body movement detection. Finally, ultrasonic feature data including the frequency and amplitude of the micro-body movement is generated, which is used to supplement and enhance the body movement information in traditional physiological signals and improve the accuracy of overall sleep monitoring.

[0100] Step S28: Perform sound event detection and classification on the environmental sound signals in the multi-channel sleep signal segment data, extract sleep sound features based on breath sounds and snoring sounds, and obtain acoustic feature data; merge the ultrasonic feature data and the acoustic feature data into acoustic wave feature data.

[0101] In the embodiments of the present invention, sound event detection and classification are performed on the environmental sound signals in the multi-channel sleep signal segment data, and sleep sound features based on breath sounds and snoring sounds are extracted to obtain acoustic feature data; subsequently, the ultrasonic feature data in step S27 is merged with the acoustic feature data to generate acoustic wave feature data. In specific operations, first, the environmental sound signals are preprocessed, including noise reduction and normalization processing, and then a machine learning-based sound event detection algorithm (such as support vector machine SVM or deep neural network DNN) is applied to identify and classify different sound events, such as normal breathing, snoring, and environmental noise. For breath sounds and snoring sounds, feature parameters such as frequency, amplitude, and duration are further extracted. In a specific application scenario, the sampling rate of the microphone is set to 44.1 kHz, and the sound event classification model is trained with a large amount of sleep environment data to improve the recognition accuracy. Finally, the extracted acoustic feature data is fused with the ultrasonic feature data obtained through Doppler frequency shift analysis, and methods such as feature splicing or weighted averaging are used to generate comprehensive acoustic wave feature data for further analyzing the impact of the environment on sleep and identifying sleep-related sound abnormal events.

[0102] By extracting the energy characteristics of frequency bands such as δ, θ, α, β, and γ, the present invention can accurately analyze the quality changes in each stage of sleep. Combining the detection of K complexes and sleep spindles, it can identify the key events in the deep sleep and rapid eye movement (REM) stages. The analysis of eye movement characteristics helps to distinguish between the REM and NREM stages, and evaluate the sleep depth, dream activities, and physical function recovery. The intensity and frequency characteristics of electromyogram activities can effectively identify the muscle states in different sleep stages, help to judge the muscle relaxation degree in deep sleep, and detect sleep disorders such as periodic limb movements. The extraction of heart rate variability (HRV) characteristics evaluates the balance of the autonomic nervous system and reveals the activity changes of the sympathetic and parasympathetic nerves during sleep. The analysis of body movement characteristics can monitor the number of awakenings and the nocturnal activity level, providing a basis for judging light sleep and deep sleep. The multi-channel signal fusion, including electroencephalogram, eye movement, electromyogram, electrocardiogram, and body movement characteristic data, forms a comprehensive perspective to comprehensively analyze the physiological changes during sleep and improve the analysis ability of complex sleep states. By detecting minute body movements through ultrasonic signals, especially in deep sleep, and analyzing breath sounds and snoring sounds to identify respiratory disorders such as sleep apnea syndrome. The acoustic signals can also detect the impact of environmental noise on sleep quality. Through the comprehensive analysis of various physiological signals and external interferences, the system improves the accuracy of sleep quality assessment and enhances the ability to identify sleep disorders.

[0103] Preferably, step S3 includes the following steps:

[0104] Step S31: Perform phase space reconstruction on the multi-dimensional feature data to obtain reconstructed phase space data; calculate the largest Lyapunov exponent based on the reconstructed phase space data to obtain system stability characteristic data;

[0105] In the embodiment of the present invention, phase space reconstruction is performed on the multi-dimensional feature data. The reconstruction method is based on the Takens theorem. By selecting appropriate time delays and embedding dimensions, the time series data is mapped into a high-dimensional phase space. The time delay is usually determined by the autocorrelation function or mutual information method, and the embedding dimension can be estimated by the false nearest neighbor algorithm. In practical applications, for the reconstruction of multi-dimensional feature data including electroencephalogram, electrocardiogram, and body movement, the time delay is set to 10 sampling points and the embedding dimension is 3. After phase space reconstruction, the largest Lyapunov exponent is calculated based on the reconstructed phase space data to measure the chaos and stability of the system. The calculation of the Lyapunov exponent uses the Wolf algorithm to measure the exponential divergence rate of the trajectory in the phase space. Finally, system stability characteristic data is obtained, which reflects the dynamic stability characteristics of physiological signals in the sleep state.

[0106] Step S32: Perform recurrence quantification analysis on the multi-dimensional feature data, and extract the recurrence rate and determinism characteristics to obtain recurrence characteristic data;

[0107] In the embodiments of the present invention, recursive quantitative analysis (RQA) is performed on multi-dimensional feature data. First, the feature data is normalized to adapt it to the construction of the recurrence plot. The recurrence plot is generated by calculating the distance matrix between the phase space trajectory points, and a fixed distance threshold (such as 0.1) is used to determine the recurrence of points. Based on the recurrence plot, the recurrence rate (i.e., the frequency of the trajectory returning to the previous state) and the determinism feature (i.e., the proportion of the continuous recurrence line) are extracted, and these features quantify the complexity and determinism of the system. In actual operation, the distance threshold and the recurrence plot resolution are adjusted according to the data characteristics. Finally, recurrence feature data containing the recurrence rate and the determinism feature is generated for further evaluating the periodicity and stability of the multi-dimensional feature data.

[0108] Step S33: Calculate the sample entropy and approximate entropy according to the multi-dimensional feature data to obtain entropy feature data; perform detrended fluctuation analysis on the multi-dimensional feature data and extract long-range correlation features to obtain fluctuation feature data;

[0109] In the embodiments of the present invention, the sample entropy (SampEn) and approximate entropy (ApEn) of the multi-dimensional feature data are calculated. The sample entropy measures the complexity and randomness of the data by comparing the similarities of subsequences with different lengths in the time series; the approximate entropy is used to detect the predictability of the signal. In practical applications, the embedding dimension of the sample entropy and the approximate entropy is set to 2, and the tolerance is set to 20% of the standard deviation of the data. Subsequently, detrended fluctuation analysis (DFA) is performed on the multi-dimensional feature data. This method segments the time series and calculates the fluctuation amplitude of each segment to extract long-range correlation features, reflecting the self-similarity of the signal. In the application scenario, the segment length is set to a multiple of 4 seconds to 16 seconds. Finally, feature data containing entropy features and fluctuation features is obtained for identifying the complexity and long-term correlation of physiological signals in the sleep state.

[0110] Step S34: Fuse the system stability feature data, recurrence feature data, entropy feature data, and fluctuation feature data to obtain non-linear feature data;

[0111] In the embodiments of the present invention, the system stability feature data, recurrence feature data, entropy feature data, and fluctuation feature data extracted in steps S31 - S33 are subjected to feature fusion. In the specific operation, first, all the feature data is standardized to ensure the dimensional consistency of different types of features. Then, dimensionality reduction methods such as the weighted average method or principal component analysis (PCA) are used to combine different features into a non-linear feature vector. In practical applications, the number of principal components of PCA is set to the number that can explain more than 90% of the variance to maximize information retention. Finally, the fused non-linear feature data is generated, reflecting the overall non-linear dynamic characteristics of the system and serving as the input for the subsequent steps.

[0112] Step S35: Perform wavelet packet transform on the acoustic wave feature data, extract time-frequency domain features, and obtain time-frequency acoustic wave feature data;

[0113] In the embodiment of the present invention, wavelet packet transform is performed on the acoustic wave feature data extracted in step S28, and the signal is decomposed into different time-frequency domains. First, a suitable mother wavelet (such as Daubechies wavelet) is selected, and the decomposition level is determined (usually 3 levels). Then, the original signal is decomposed into sub-signals of different frequency bands through multi-level wavelet packet decomposition. Time-domain and frequency-domain features of each sub-signal are extracted, such as energy, frequency center, and time-frequency energy distribution. In an actual application scenario, the sampling rate of the acoustic wave signal is 44.1 kHz, the number of wavelet packet decomposition levels is 3, and the extracted time-frequency features include the energy ratio of each frequency band and the frequency change trend. Finally, time-frequency acoustic wave feature data is generated, accurately reflecting the variation law of the acoustic wave signal in different time and frequency dimensions.

[0114] Step S36: Use the non-linear feature data to perform feature weighting on the time-frequency acoustic wave feature data to obtain weighted acoustic wave feature data;

[0115] In the embodiment of the present invention, the non-linear feature data in step S34 is used to perform feature weighting on the time-frequency acoustic wave feature data in step S35. In specific operations, first, the non-linear feature data and the time-frequency acoustic wave feature data are feature-matched to ensure their alignment in the time dimension. Then, a feature weighting algorithm (such as the weighted average method based on correlation) is applied, and by applying the weight of the non-linear feature to the time-frequency acoustic wave feature, the acoustic wave features sensitive to the sleep state are highlighted. In an actual application scenario, the weight calculation uses a linear regression model, and the weight is dynamically adjusted according to the correlation between the non-linear feature and the time-frequency feature. Finally, weighted acoustic wave feature data is generated, enhancing the acoustic wave signal features related to the change of the sleep state.

[0116] Step S37: Perform feature fusion based on a deep neural network on the non-linear feature data and the weighted acoustic wave feature data to obtain hybrid sleep feature data.

[0117] In the embodiment of the present invention, the non-linear feature data in step S34 and the weighted acoustic wave feature data in step S36 are subjected to feature fusion based on a deep neural network (DNN). First, a deep neural network model is constructed. The model includes an input layer, multiple hidden layers, and an output layer. The number of neurons in the hidden layer is set according to the dimension and complexity of the feature data (for example, 128 neurons in each layer). The input layer receives the non-linear feature and the weighted acoustic wave feature respectively, and feature fusion is performed through the non-linear activation function (such as ReLU) of the hidden layer. The model is trained by the backpropagation algorithm, the mean square error (MSE) is used as the loss function, and the Adam optimizer is selected. In practical applications, the training data is divided into a training set and a validation set through cross-validation. During the training process, the learning rate is set to 0.001, and the number of iterations is 1000 times. Finally, the fused hybrid sleep feature data is generated, which is used to more accurately describe the sleep state and its related physiological and environmental features, providing input for subsequent sleep quality assessment and anomaly detection.

[0118] The present invention reveals the complex dynamic behavior during sleep through phase space reconstruction, and uses the largest Lyapunov exponent to measure the stability of the sleep system, especially showing outstanding performance in detecting sleep disorders such as apnea. Recurrence quantification analysis (RQA) effectively identifies repeated sleep stages and abnormal events, such as body movements and apnea, enhancing the analysis of the stability of the sleep structure. Non-linear features such as sample entropy and approximate entropy quantify the complexity of physiological signals, and detrended fluctuation analysis reveals long-range dependence to identify potential sleep problems. Wavelet packet transform extracts the time-frequency features of breath sounds and snoring, which helps to detect sleep apnea at an early stage. The combination of non-linear features, time-frequency features, and a deep neural network (DNN) further improves the detection accuracy of sleep events. The DNN automatically extracts the key patterns in complex data, optimizing the identification and classification of abnormal sleep events. Overall, the present invention provides an efficient and accurate sleep monitoring solution, especially showing superiority in sleep disorder detection and sleep quality assessment.

[0119] Preferably, step S4 includes the following steps:

[0120] Step S41: Perform spatio-temporal evolution processing on the sleep state according to the hybrid sleep feature data to generate sleep state spatio-temporal evolution event data;

[0121] In an embodiment of the present invention, spatio-temporal evolution processing of the sleep state is performed based on the hybrid sleep feature data to generate spatio-temporal evolution event data of the sleep state. In specific operations, first, the hybrid sleep feature data is input into a spatio-temporal evolution model, which adopts a deep learning architecture such as a long short-term memory network (LSTM) or a graph convolutional network (GCN) to capture the dynamic changes of the sleep state in time and space. The model analyzes the feature changes within consecutive time windows to identify the transition trends and patterns of the sleep state. For example, in an actual application scenario, the number of hidden layer units of the LSTM network is set to 128, the learning rate is 0.001, and it is trained using the Adam optimizer for 200 iterations to ensure that the model can effectively capture the temporal features of the sleep state. During the processing, the model generates event data including sleep state transitions, durations, and spatial distributions, which reflect the evolution dynamics of different stages during sleep and provide a basis for subsequent abnormal event recognition.

[0122] Step S42: Identify potential sleep interruptions or abnormal events in the hybrid sleep feature data through the spatio-temporal evolution event data of the sleep state, and perform an event impact assessment based on feature importance to generate sleep event assessment data;

[0123] In an embodiment of the present invention, the spatio-temporal evolution event data of the sleep state generated in step S41 is used to identify potential sleep interruptions or abnormal events in the hybrid sleep feature data, and an event impact assessment based on feature importance is performed to generate sleep event assessment data. In specific operations, first, an anomaly detection algorithm (such as Isolation Forest or Support Vector Machine SVM) is applied to identify events in the spatio-temporal evolution event data that are significantly different from the normal sleep pattern, such as frequent sleep interruptions or abnormal sleep stage transitions. Subsequently, an evaluation method based on feature importance (such as SHAP values or feature importance scores) is used to analyze the impact degree of these abnormal events on the overall sleep quality. For example, in actual applications, the number of trees of the Isolation Forest algorithm is set to 100, and the maximum number of features is 5 to improve the accuracy and efficiency of detection. Through these methods, sleep event assessment data including the types of abnormal events, occurrence frequencies, and their impact degrees on sleep quality is generated, providing a basis for further sleep disorder screening and intervention.

[0124] Step S43: Screen potential sleep disorder events based on the sleep event assessment data, and collect real-time physiological indicators to generate real-time sleep monitoring index data;

[0125] Embodiment of the present invention: According to the sleep event evaluation data generated in step S42, potential sleep disorder events are screened out, and real-time physiological indicators are collected to generate sleep real-time monitoring indicator data. In the specific operation, the sleep event evaluation data is first clustered (such as K-means or spectral clustering) to identify potential sleep disorder patterns with similar characteristics. Then, a screening threshold is set based on these patterns, for example, the event frequency exceeds 3 times per hour or the score of a specific abnormal event exceeds a certain threshold (such as 0.8) as a screening criterion. After screening out potential disorder events, the acquisition parameters of the multimodal sensor are configured, focusing on monitoring physiological indicators related to these disorders, such as heart rate, respiratory rate and blood oxygen saturation. In a specific application, the real-time acquisition parameters are set to heart rate once per second, respiratory rate twice per second, and blood oxygen saturation once per second. Data is transmitted in real time through wireless sensors, and edge computing devices are used for real-time signal processing and analysis. Finally, real-time sleep monitoring indicator data containing key physiological indicators is generated for dynamic monitoring and timely intervention in sleep disorder events.

[0126] Step S44: performing sleep stage fluctuation analysis on the multi-channel sleep signal segment data to generate sleep stage fluctuation data; and performing physiological disturbance association processing on the sleep stage fluctuation data through the real-time sleep monitoring index data to generate physiological sleep disturbance association data.

[0127] The embodiment of the present invention performs a sleep stage fluctuation analysis on the multi-channel sleep signal segment data to generate sleep stage fluctuation data; and performs physiological disturbance association processing on the sleep stage fluctuation data through the sleep real-time monitoring index data to generate physiological sleep disturbance association data. In the specific operation, the dynamic time warping (DTW) algorithm is first applied to perform fluctuation analysis on the sleep stages in the multi-channel sleep signal segment data to identify the frequent conversion of sleep stages and the change of duration. For example, the window length of DTW is set to 30 seconds, and a time offset within a certain range is allowed to match the sleep stage pattern of different time periods. Then, in combination with the sleep real-time monitoring index data generated in step S43, correlation analysis or causal inference methods (such as Granger causality test) are used to evaluate the correlation between physiological index changes and sleep stage fluctuations. For example, in practical applications, the correlation threshold is set to 0.6, and significantly associated physiological disturbance factors are identified, such as frequent conversion of heart rate sudden changes and REM stages. Through this association processing, physiological sleep disturbance association data containing sleep stage fluctuation patterns and related physiological disturbance factors are generated, providing data support for in-depth understanding of sleep quality and formulating personalized intervention strategies.

[0128] Through spatio-temporal evolution processing of the mixed sleep characteristic data, the present invention can monitor the changes in the sleep state in real time and capture the dynamic evolution during the entire sleep cycle. Especially during the transition between different sleep stages such as rapid eye movement (REM) and non-rapid eye movement (NREM), spatio-temporal evolution analysis can reveal the duration, occurrence frequency, and pattern of each stage. Spatio-temporal evolution processing can sensitively identify sleep interruptions or minor abnormal changes, such as brief awakenings or micro-movements. This is particularly useful for identifying phenomena that affect sleep quality, such as frequent micro-awakenings and periodic limb movements at night. Through spatio-temporal evolution event data, potential interruptions or abnormal events that may occur during sleep, such as apnea, sleep interruptions, and night awakenings, can be automatically identified. Combining the multi-dimensional features in the mixed sleep characteristic data can more accurately locate the occurrence time and intensity of sleep events. Using the feature importance evaluation method, the system can automatically analyze which features have an important impact on the occurrence of sleep interruptions or abnormal events. For example, abnormal changes in heart rate fluctuations, apnea, or electromyogram activity. Through such evaluations, the system can identify key physiological factors to help further screen for potential sleep disorders. After analyzing the sleep event evaluation data, possible sleep disorder events, such as sleep apnea syndrome, insomnia, or periodic limb movements, can be automatically screened out. This automatic screening can reduce human intervention and help more efficiently discover potential problems during sleep. During the sleep monitoring process, the system can perform dynamic evaluations based on real-time collected physiological indicators (such as heart rate, respiratory rate, body movement, etc.). This real-time feedback mechanism can immediately respond to new abnormal events to ensure immediate adjustment and warning of the sleep state. Through real-time physiological indicator collection, the system can perform personalized monitoring according to the sleep characteristics of individuals and identify potential health risks based on their specific physiological conditions. Sleep stage fluctuation analysis can identify and track the fluctuations during different stages (such as light sleep, deep sleep, and REM stage) of the sleep process. This analysis helps to understand the duration of each stage, the regularity of mutual transformation, and the fluctuation characteristics between stages, which is crucial for studying the stability and quality of different sleep stages. By correlating and processing the sleep real-time monitoring indicator data with the sleep stage fluctuation data, the system can identify the correlation between physiological disturbances (such as apnea, heart rate disorders) and specific sleep stages. This helps to reveal the impact of specific physiological events on sleep stage changes, thereby further evaluating whether these disturbances may lead to a decline in sleep quality or the occurrence of disorders. By analyzing the relationship between sleep stage fluctuations and physiological disturbances, the system can effectively integrate multi-channel sleep signal data (such as EEG, EMG, ECG, accelerometer data, etc.) to generate high-precision physiological sleep disturbance correlation data. This data can be used to diagnose complex sleep disorders, such as sleep apnea syndrome, REM behavior disorder, etc.

[0129] Preferably, step S4 includes the following steps:

[0130] Step S411: Extract the sleep state transition features based on time series from the mixed sleep feature data, so as to obtain the state transition sequence data;

[0131] In the embodiment of the present invention, the sleep state transition features based on time series are extracted from the mixed sleep feature data, so as to obtain the state transition sequence data. In the specific operation, first, the mixed sleep feature data is sorted in chronological order, and the sleep features in each time period are labeled as the corresponding sleep states (such as NREM, REM or awake). Then, the sliding window method (such as the window size is set to 30 seconds and the step size is 10 seconds) is used to process the data segment by segment, extract the state transition features in each time window, and record the start time, end time of the sleep state and the transition frequency. The transition features of each time window are recorded as the state transition sequence data through timestamps for subsequent modeling and analysis.

[0132] Step S412: Use the hidden Markov model to model the state transition sequence data, so as to obtain the sleep state probability distribution data;

[0133] In the embodiment of the present invention, the hidden Markov model (HMM) is used to model the state transition sequence data, so as to obtain the sleep state probability distribution data. In the specific operation, first, the parameters of the hidden Markov model are initialized, including the number of states (set to 3, corresponding to the NREM, REM and awake states), and the transition probability matrix and the initial state probability distribution between states. Then, the state transition sequence data extracted in step S411 is input into the model, and the Baum-Welch algorithm is used for parameter estimation and model training. After the training is completed, the model can output the sleep state probability distribution at each time point according to the input feature sequence. In practical applications, the number of hidden states of the HMM is set to 3, and the maximum number of iterations is 100 times to ensure that the model can accurately capture the state transition characteristics of different sleep stages. The generated sleep state probability distribution data is used for further state transition analysis.

[0134] Step S413: Construct a sleep state transition matrix based on the sleep state probability distribution data to obtain the state transition feature data;

[0135] In an embodiment of the present invention, a sleep state transition matrix is constructed based on sleep state probability distribution data to obtain state transition feature data. In specific operations, first, the sleep state probability distribution for each time period is statistically analyzed to calculate the transition frequencies between states. For example, the probability of transitioning from the NREM state to the REM state is determined by the transition frequency in the state probability distribution. Through this statistical analysis, a sleep state transition matrix is constructed, where each element in the matrix represents the transition probability between two sleep states. To ensure the accuracy of the matrix, a large amount of historical data can be used for estimation. In practical applications, the rows of the matrix represent the current state (such as NREM, REM), the columns represent the next state, and the data of the transition matrix is used as the basis for subsequent time series modeling.

[0136] Step S414: Extract local time features based on a sliding time window for the mixed sleep feature data to obtain time window feature data;

[0137] In an embodiment of the present invention, local time features are extracted based on a sliding time window for the mixed sleep feature data to obtain time window feature data. In specific operations, first, the length and step size of the sliding time window are defined. For example, the window size is set to 60 seconds and the step size is set to 20 seconds, and the data of the entire sleep cycle is segmented. Statistical analysis is performed on the feature data (such as heart rate, eye movement, electromyogram, etc.) within each time window to extract local time features, such as the mean, standard deviation, maximum value, minimum value, etc. of the features. Then, the local time features within each time window are saved as time window feature data for use in time series modeling in combination with state transition features. In practical applications, for different physiological signals, the feature extraction strategies will be different. For example, the feature extraction of the heart rate signal will focus on variability, while for the eye movement signal, the frequencies of fast and slow eye movements will be emphasized.

[0138] Step S415: Perform time series modeling based on the long short-term memory network according to the state transition feature data and the time window feature data to generate a sleep state spatio-temporal evolution model, where the sleep state spatio-temporal evolution model includes the transition probabilities and duration distributions of different sleep stages;

[0139] In an embodiment of the present invention, based on the state transition feature data and the time window feature data, a long short-term memory network (LSTM) is used for time series modeling to generate a spatio-temporal evolution model of the sleep state. In specific operations, first, the state transition feature data and the time window feature data are input into the LSTM model. The input layer of the model is multi-dimensional feature data, and the hidden layer is set to 128 neurons to capture the time series dependence of the sleep state. During the training process, LSTM adjusts the weight parameters through backpropagation so that the model can accurately predict the sleep state at the next moment. In practical applications, the training dataset of the LSTM model is divided in a ratio of 80% for training and 20% for validation. The optimizer uses Adam, and the learning rate is set to 0.001. After training is completed, the generated spatio-temporal evolution model of the sleep state includes the transition probabilities and duration distributions of different sleep stages, providing a basis for predicting the evolution trend of the sleep state.

[0140] Step S416: Predict the evolution trend of the sleep state according to the spatio-temporal evolution model of the sleep state and the non-linear feature data, and perform event classification and marking to generate spatio-temporal evolution event data of different types of sleep states, where the spatio-temporal evolution event data of the sleep state includes normal sleep events, abnormal sleep events, and external environment influence events.

[0141] In an embodiment of the present invention, according to the spatio-temporal evolution model of the sleep state and the non-linear feature data, the evolution trend of the sleep state is predicted, and event classification and marking are performed to generate spatio-temporal evolution event data of different types of sleep states. In specific operations, first, the spatio-temporal evolution model generated in step S415 is used to perform time series prediction on the future sleep state, and the prediction results include the sleep state and its transition probability at each moment. Then, in combination with the non-linear feature data (such as the largest Lyapunov exponent, recurrence features, etc.), trend analysis is performed to judge the stability of the sleep state and possible abnormal changes. Based on these analysis results, the system will classify and mark different types of events (such as normal sleep events, abnormal sleep events, or external environment influence events). For example, abnormal events can be frequent sleep interruptions or abnormal sleep state transitions. Finally, the spatio-temporal evolution event data of the sleep state generated by the system can be used for further sleep quality assessment and intervention decision-making.

[0142] The present invention can finely depict the changes and transition processes of different sleep stages, such as the sequence and duration of light sleep, deep sleep and rapid eye movement (REM) stages, by extracting time series features from mixed sleep feature data. This information is the basis for subsequent sleep state transition modeling. The extracted state transition sequence provides accurate time series data for subsequent modeling, so that changes in sleep states can be dynamically monitored and evaluated. Hidden Markov model (HMM) is a probability-based time series modeling method that can effectively capture the randomness and implicit laws of sleep states. By modeling state transition sequence data, the probability distribution of sleep stages can be obtained, such as the transition probability of light sleep, deep sleep and REM sleep. HMM helps to reveal the sleep stage transition process that is difficult to observe directly and model it, which can greatly improve the understanding of complex sleep states. By constructing a sleep state transition matrix, the transition rules between different sleep stages, such as the probability of transitioning from the REM stage to light sleep, can be clearly displayed. This helps to better understand the overall structure of the sleep cycle. Transition matrix data can be used to evaluate the stability and predictability of sleep states. For example, a higher probability of continuous deep sleep indicates a more stable sleep state, which helps to evaluate sleep quality. By extracting local time features from mixed sleep feature data using a sliding time window, changes in sleep state over a shorter period of time can be captured. This is important for identifying short sleep events or stage changes, especially when detecting sudden abnormal sleep events. The sliding time window method enables the system to perform more sophisticated time series analysis to avoid ignoring short but important sleep fluctuations or anomalies. Long short-term memory networks (LSTMs) are powerful tools for processing time series data, and are particularly good at modeling long-term dependent sequences. By using LSTM to perform time series modeling on state transition features and time window feature data, the system can capture the long-term dependencies of different sleep stages and their transition trends, and build an accurate spatiotemporal evolution model of sleep states. This spatiotemporal evolution model can not only describe the transition probability of each sleep stage, but also predict the duration distribution of each stage, thereby providing a strong basis for evaluating the integrity of the sleep cycle. By combining nonlinear feature data and the spatiotemporal evolution model of sleep states, the system can predict trends in future sleep states. This feature is particularly helpful for early warning of potential sleep interruptions or abnormal events, such as apnea or sudden awakening. The system can classify and label different types of sleep states based on the prediction results, including normal sleep events, abnormal sleep events (such as frequent micro-awakenings or sleep disorders), and external environmental influences (such as noise, light, etc.). This helps users or doctors better understand the root causes of sleep problems. For abnormal events that may cause health risks (such as apnea or abnormal heart rate), the system can detect and issue warnings early through spatiotemporal evolution predictions, which can help to intervene in time and improve sleep safety.

[0143] Preferably, step S43 includes the following steps:

[0144] Step S431: Perform a clustering analysis on the sleep event evaluation data to identify potential sleep disorder patterns, and obtain sleep disorder pattern data;

[0145] In the embodiment of the present invention, a clustering analysis is performed on the sleep event evaluation data to identify potential sleep disorder patterns, and sleep disorder pattern data is obtained. In specific operations, first, the sleep event evaluation data is standardized to ensure that the ranges of different feature data are consistent. Then, the K-means clustering algorithm of unsupervised learning is used to perform clustering analysis on the data. The initial number of clusters is set to 5, and the positions of the cluster centers are optimized through iteration to group similar sleep disorder events into one category. The optimal number of clusters is determined by the elbow method. The results of the clustering generate multiple sleep disorder patterns, and the main features in each cluster (such as abnormal sleep interruption frequency, abnormal rapid eye movement, etc.) are recorded. The finally generated sleep disorder pattern data is used for subsequent event screening and threshold setting, and can be used to analyze the personalized sleep disorder patterns of different users in the application scenario.

[0146] Step S432: Set the screening threshold for sleep disorder events based on the sleep disorder pattern data, so as to obtain screening threshold data; screen the sleep disorder events from the sleep event evaluation data according to the screening threshold data, and obtain potential disorder event data;

[0147] In the embodiment of the present invention, the screening threshold for sleep disorder events is set based on the sleep disorder pattern data, so as to obtain screening threshold data. In specific operations, first, each sleep disorder pattern is analyzed to determine the abnormal value range of specific physiological signals (such as heart rate, respiratory rate) under each type of disorder pattern. Through statistical analysis of historical data, the abnormal range of each physiological signal is calculated, and the screening threshold is set. For example, for heart rate variability, a heart rate variability coefficient exceeding 90% of the standard range is set as the screening threshold for sleep disorder events. Then, according to these thresholds, the new sleep event evaluation data is screened, and the events with abnormalities exceeding the set thresholds are retained as potential disorder events. The screening threshold data provides a standard for efficiently screening potential sleep disorders.

[0148] Step S433: Determine the physiological indicators that need to be monitored key points according to the potential disorder event data, and generate a monitoring indicator list;

[0149] In the embodiment of the present invention, physiological indicators that need to be monitored with emphasis are determined based on potential obstacle event data, and a monitoring indicator list is generated. In specific operations, first, the selected potential obstacle event data is analyzed to identify physiological characteristics that may cause sleep disorders. For example, heart rate, respiratory rate, eye movement frequency, etc. may be indicators highly correlated with potential obstacles. Then, through correlation analysis and expert system recommendation, physiological indicators most relevant to a specific obstacle pattern are determined. In an application scenario, abnormal rapid eye movement frequency may indicate certain neurological problems, so eye movement frequency will be included in the monitoring indicator list. The generated monitoring indicator list contains all physiological indicators that need to be monitored with emphasis and serves as the basis for subsequent sensor collection.

[0150] Step S434: Configure the acquisition parameters of the multi-modal sensor according to the monitoring indicator list, so as to obtain sensor configuration data;

[0151] In the embodiment of the present invention, the acquisition parameters of the multi-modal sensor are configured according to the monitoring indicator list, so as to obtain sensor configuration data. In specific operations, first, according to the monitoring indicator list generated in step S433, a suitable multi-modal sensor is selected for physiological data acquisition. For example, an electrocardiogram sensor is selected for heart rate monitoring, an acceleration sensor is selected for body movement, and an electrooculogram sensor is selected for eye movement. Then, according to the characteristics of different sensors, acquisition parameters are set, such as sampling frequency, transmission interval, etc. For electrocardiogram data, the sampling frequency can be set to 500 Hz, while the sampling frequency of acceleration data can be set to 50 Hz. The sensor configuration data contains the acquisition parameters of all devices and is used to ensure that the devices can efficiently and accurately acquire physiological data.

[0152] Step S435: Use the sensor configuration data to perform real-time physiological indicator acquisition on the object to be measured and perform real-time signal processing, so as to obtain sleep real-time monitoring indicator data.

[0153] In the embodiment of the present invention, the sensor configuration data is used to perform real-time physiological indicator acquisition on the object to be measured and perform real-time signal processing, so as to obtain sleep real-time monitoring indicator data. In specific operations, first, the configured sensor device is worn on the object to be measured, and the sensor starts to acquire physiological signals in real time according to the set parameters. The acquired data is transmitted wirelessly to the data processing terminal, and real-time signal processing is performed on the terminal. The processing process includes operations such as filtering, denoising, and feature extraction. For example, the electrocardiogram signal can be filtered by a low-pass filter to remove high-frequency noise, and then the heart rate data can be extracted through the QRS wave detection algorithm. The finally generated sleep real-time monitoring indicator data contains the real-time changes of multiple physiological signals, such as heart rate variability, respiratory rate, eye movement frequency, etc., and is used for further sleep quality analysis and intervention.

[0154] Through cluster analysis, the present invention performs pattern recognition on sleep event assessment data, and can discover different sleep disorder patterns (such as apnea, frequent awakenings, REM behavior disorder, etc.). This pattern recognition not only helps to automatically classify different types of sleep disorders, but also reveals the potential associations among various disorders. Cluster analysis helps to generate personalized sleep disorder patterns based on the sleep data of different individuals, thereby providing a basis for individualized diagnosis of sleep problems. Based on the results of cluster analysis, the system can set screening thresholds to screen events for specific sleep disorder patterns. For example, for sleep apnea, specific thresholds for the frequency of respiratory interruptions or the amplitude of heart rate fluctuations can be set to ensure that the screened events are highly relevant. The setting of the screening threshold can be adaptively adjusted according to the different sleep characteristics of each person, avoiding the limitations of a single threshold and improving the screening accuracy. Determination of key physiological indicators to be monitored: Based on the potential disorder events screened out, the system can automatically generate a list of key physiological indicators to be monitored. By selectively monitoring key physiological indicators, unnecessary monitoring items are reduced, the monitoring process is optimized, and the monitoring efficiency and the accuracy of data processing are improved. According to the generated list of monitoring indicators, the system can dynamically configure the acquisition parameters of multi-modal sensors to ensure that the sensors can accurately collect the key physiological indicators to be monitored. This not only optimizes the use of sensors, but also improves the effectiveness of data acquisition. Through precise parameter configuration, the system can avoid unnecessary data redundancy and acquisition noise, ensure the clarity and accuracy of signals, and thus improve the effect of subsequent data processing and analysis. Using the optimized sensor configuration, the system can collect real-time physiological indicators of the object being measured to ensure that when potential sleep disorder events are detected, the relevant physiological data can be accurately captured, thereby improving the detection and confirmation rate of events. The system can perform real-time signal processing on the collected physiological data to quickly identify abnormal conditions. This real-time processing ability is crucial for dealing with sudden sleep disorders (such as sleep apnea, arrhythmia, etc.) and can provide effective support for timely intervention. The real-time collected and processed data can provide feedback for subsequent sleep state monitoring and sleep disorder assessment, forming a closed-loop monitoring mechanism to ensure that the system continuously optimizes the monitoring strategy and configuration.

[0155] Preferably, step S44 includes the following steps:

[0156] Step S441: Perform analysis on the change of sleep cycles on the multi-channel sleep signal segment data based on the dynamic time warping algorithm to obtain sleep cycle data; based on the sleep cycle data, statistically analyze the duration and transition frequency of each sleep stage to obtain sleep structure data;

[0157] In the embodiments of the present invention, the multi-channel sleep signal segment data is subjected to sleep cycle change analysis based on the dynamic time warping algorithm to obtain sleep cycle data. In specific operations, first, multi-channel sleep signal segments are obtained, including electroencephalogram (EEG), electrooculogram (EOG), electromyogram (EMG), etc. Then, the dynamic time warping (DTW) algorithm is used to align and analyze the cycles of these multi-dimensional signals, calculate the similarities and differences between different channels, and further identify the boundaries and change rules of each sleep cycle. By analyzing the signal characteristics within multiple consecutive sleep cycles, accurate sleep cycle data is obtained. Then, based on this cycle data, statistical analysis is performed on the duration and transition frequency of each sleep stage to generate sleep structure data. In the application scenario, this method is applicable to identifying multiple sleep cycles and their characteristic changes of a user during a night, such as the transition from rapid eye movement (REM) to deep sleep (NREM).

[0158] Step S442: Perform a prediction on the sleep stage change trend of the sleep structure data based on time series to obtain sleep stage fluctuation data;

[0159] In the embodiments of the present invention, the sleep structure data is subjected to a prediction on the sleep stage change trend based on time series to obtain sleep stage fluctuation data. In specific operations, first, time series modeling is performed on the previously obtained sleep structure data, and prediction models such as autoregressive integrated moving average (ARIMA) model or long short-term memory (LSTM) network are used to predict the change trend of each future sleep stage based on historical data. By analyzing the periodic characteristics and volatility in the time series, the sleep stage fluctuations of the user in a future period are predicted. The finally generated sleep stage fluctuation data reflects the change trend of different possible stages (such as light sleep, deep sleep, REM) in future sleep. This step is particularly suitable for monitoring the long-term sleep stage changes of users to identify potential sleep quality problems in advance.

[0160] Step S443: Perform a physiological perturbation correlation analysis on the sleep stage fluctuation data according to the sleep real-time monitoring index data, identify the association between the sleep stage and the physiological signal changes, and generate physiological perturbation association data;

[0161] In an embodiment of the present invention, physiological perturbation correlation analysis is performed on sleep stage fluctuation data based on real-time sleep monitoring index data, the association between sleep stages and physiological signal changes is identified, and physiological perturbation association data is generated. In specific operations, first, real-time sleep monitoring index data (such as heart rate, respiratory rate, blood oxygen saturation, etc.) is obtained, and then the correlation analysis is performed on these data and the sleep stage fluctuation data obtained in the previous step. The relationship between the changes in each physiological index and specific sleep stages is analyzed through statistical methods such as Pearson correlation coefficient and mutual information to identify patterns such as whether an increase in heart rate is related to the REM stage or whether a change in respiratory rate is related to the light sleep stage. The finally generated physiological perturbation association data reflects the specific association between sleep stages and key physiological signal changes, facilitating subsequent risk assessment.

[0162] Step S444: Perform pattern classification on the physiological perturbation association data according to a preset perturbation pattern library to generate perturbation pattern data; perform physiological perturbation risk assessment on the physiological signal perturbations in each sleep stage according to the perturbation pattern data, so as to obtain physiological perturbation assessment data;

[0163] In an embodiment of the present invention, pattern classification is performed on the physiological perturbation association data according to a preset perturbation pattern library to generate perturbation pattern data. In specific operations, first, a physiological perturbation pattern library is established, which contains common physiological signal perturbation patterns (such as waking up corresponding to an increase in heart rate, sleep apnea corresponding to irregular breathing, etc.). Then, a pattern matching algorithm is used to match the physiological perturbation association data with the templates in the pattern library to identify the type of the current physiological perturbation and generate corresponding perturbation pattern data. According to the perturbation pattern data, risk assessment is performed on the physiological signal perturbations occurring in each sleep stage. The assessment method can be based on a weighted scoring system, combined with the frequency, duration, and severity of the perturbation, to generate physiological perturbation assessment data. In an application scenario, this step can identify high-risk sleep problems, such as frequent apnea or excessive heart rate fluctuations.

[0164] Step S445: Generate physiological sleep perturbation association data including the influence weight of physiological indexes, the sleep stage transition probability, and the perturbation degree according to the physiological perturbation assessment data.

[0165] Embodiments of the present invention generate physiological sleep disturbance correlation data including the influence weights of physiological indicators, the sleep stage transition probabilities, and the degree of disturbance based on physiological disturbance assessment data. In specific operations, first, weighted analysis is performed on the physiological disturbance assessment data, and the influence weights of each physiological indicator are set (for example, the influence weight of heart rate may be higher, while the weight of body movement is lower). Then, based on the sleep stage transition probability data and in combination with the degree of disturbance, the disturbance events that may occur in each sleep stage are evaluated. The finally generated physiological sleep disturbance correlation data includes the influence degrees of different physiological indicators in different sleep stages and provides the transition probabilities of disturbances in each stage. These data can be used to further optimize sleep intervention measures to help users improve sleep quality and reduce potential health risks.

[0166] The dynamic time warping (DTW) algorithm of the present invention can process asynchronous time series data and is suitable for processing sleep signals of different time periods or different individuals. By analyzing the multi-channel sleep signal segment data through this algorithm, the subtle changes in the sleep cycle can be accurately captured, and the reliability of the sleep cycle data can be improved. By statistically analyzing the duration and transition frequency of each sleep stage (such as light sleep, deep sleep, REM, etc.), the sleep structure of the measured object can be more comprehensively reflected, providing basic data for subsequent sleep quality assessment. Through time series analysis, the system can predict the change trend of sleep stages. For example, the system can identify whether the light sleep state is about to transition to the deep sleep or REM stage. This prediction ability can help users or doctors understand the fluctuations of the sleep state in advance and provide a head start for intervening in sleep problems. Predicting the fluctuation trend of sleep stages allows the system to respond in a timely manner when an abnormal fluctuation is detected, thereby dynamically adjusting the monitoring strategy to avoid data loss or monitoring delay caused by sudden problems. By correlatively analyzing the physiological indicators monitored in real time with the sleep stage fluctuation data, the potential relationship between specific physiological signals (such as heart rate, respiratory rate, etc.) and sleep stage changes can be revealed. For example, the system can identify the phenomenon that the heart rate variability significantly increases during the REM stage, providing a reference for subsequent intervention measures. Each person's physiological disturbances may have a unique correlation pattern with sleep stages. This analysis step can identify individualized physiological disturbance characteristics through correlative analysis, providing support for personalized sleep monitoring. By classifying the patterns of physiological disturbance correlation data, the system can quickly identify common or abnormal physiological disturbance patterns in sleep stages based on a disturbance pattern library. For example, the system can identify physiological signal disturbances based on apnea patterns. This standardized pattern classification helps improve the recognition efficiency and accuracy of the system. By assessing the risks of the identified disturbance patterns, the system can quantify the potential impact of different physiological disturbances on sleep health. This assessment mechanism can not only provide users with a clear risk level (such as low risk, medium risk, or high risk), but also provide further diagnostic basis for doctors. This step combines the influence weight of physiological signals, the transition probability of sleep stages, and the degree of disturbance to generate a complete set of physiological sleep disturbance correlation data. Through this comprehensive analysis, the system can more accurately quantify the impact of physiological signals on different sleep stages and provide a comprehensive and quantitative assessment result for sleep health. The physiological sleep disturbance correlation data provides a reliable basis for subsequent intervention measures. Doctors can determine which abnormal fluctuations in physiological indicators may have a significant impact on specific sleep stages based on this data, and thus formulate more targeted treatment or monitoring plans. Through the dynamic time warping algorithm and time series analysis, the system can accurately track the changes in the sleep cycle and predict the fluctuations of sleep stages. This comprehensive analysis helps to comprehensively understand the health status of the sleep structure.Through the correlation analysis and pattern classification of physiological perturbations, the system can identify potential sleep disorders and physiological abnormalities, which is crucial for the early detection and prevention of sleep-related diseases. Since the sleep and physiological characteristics of each person are different, the design of steps S441 to S445 can generate personalized risk assessment reports based on individual data, thereby providing a scientific basis for precise intervention. The physiological sleep perturbation correlation data can not only provide comprehensive diagnostic information for doctors, but also support the real-time monitoring system to help doctors adjust the monitoring plan or take intervention measures in a timely manner when needed.

[0167] The present invention also provides a feature information extraction system for a sleep state monitoring model, which is used to execute the above-mentioned feature information extraction method for the sleep state monitoring model. The feature information extraction system for the sleep state monitoring model includes:

[0168] A signal preprocessing module, which is used to collect multi-modal physiological signals of the object to be measured to obtain original sleep monitoring data; perform noise removal and signal enhancement processing on the original sleep monitoring data, and perform signal segmentation to obtain multi-channel sleep signal segment data;

[0169] A multi-dimensional feature extraction module, which is used to extract features based on electroencephalogram, electrooculogram, electromyogram, electrocardiogram, and accelerometer signals from the multi-channel sleep signal segment data to obtain multi-dimensional feature data; extract ultrasonic features and acoustic features from the multi-channel sleep signal segment data to generate acoustic wave feature data;

[0170] A feature fusion module, which is used to extract non-linear dynamic features based on the multi-dimensional feature data to generate non-linear feature data; perform complementary fusion processing on the acoustic wave feature data through the non-linear feature data to generate mixed sleep feature data;

[0171] A sleep dynamic analysis module, which is used to perform spatio-temporal evolution processing and event impact assessment on the mixed sleep feature data to generate sleep event assessment data; screen potential sleep disorder events based on the sleep event assessment data, and collect real-time physiological indicators to generate sleep real-time monitoring index data; perform sleep stage fluctuation analysis and physiological perturbation correlation processing on the multi-channel sleep signal segment data through the sleep real-time monitoring index data to generate physiological sleep perturbation correlation data;

[0172] An environment-physiology coupling module, which is used to identify the sleep environment impact area of the sleep stage fluctuation data to generate sleep environment impact area data; perform physiology-environment impact pattern coupling on the sleep environment impact area data to obtain physiology-environment coupling pattern data; merge the mixed sleep feature data, physiological sleep perturbation correlation data, and physiology-environment coupling pattern data into feature information extraction data.

[0173] Therefore, in whatever aspect, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0174] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A method for extracting feature information of a sleep state monitoring model, characterized in that: The following steps are involved: Step S1: collecting multimodal physiological signals of the subject to obtain original sleep monitoring data; The original sleep monitoring data is subjected to noise removal and signal enhancement processing, and signal segmentation is performed to obtain multi-channel sleep signal segment data; Step S2: extracting features of the multi-channel sleep signal segment data based on electroencephalogram, oculogram, electromyogram, electrocardiogram and accelerometer signals to obtain multi-dimensional feature data; extracting ultrasonic features and acoustic features of the multi-channel sleep signal segment data to generate sound wave feature data; Step S3: extracting nonlinear dynamic features according to the multidimensional feature data to generate nonlinear feature data; The nonlinear characteristic data is used to perform complementary fusion processing on the acoustic characteristic data to generate mixed sleep characteristic data. Step S3 includes: Step S31: reconstructing the multidimensional characteristic data in phase space to obtain reconstructed phase space data; calculating the maximum Lyapunov exponent based on the reconstructed phase space data to obtain system stability characteristic data; Step S32: performing recursive quantitative analysis on the multi-dimensional feature data, and extracting the recursive rate and deterministic features to obtain recursive feature data; Step S33: performing sample entropy and approximate entropy calculations on the multidimensional feature data to obtain entropy feature data; performing detrending fluctuation analysis on the multidimensional feature data and extracting long-range correlation features to obtain fluctuation feature data; Step S34: fusing the system stability characteristic data, the recursive characteristic data, the entropy characteristic data and the fluctuation characteristic data to obtain nonlinear characteristic data; Step S35: performing wavelet packet transformation on the sound wave characteristic data, and extracting time-frequency domain features to obtain time-frequency sound wave characteristic data; Step S36: using the nonlinear characteristic data to perform characteristic weighting on the time-frequency sound wave characteristic data to obtain weighted sound wave characteristic data; Step S37: performing feature fusion based on a deep neural network on the nonlinear feature data and the weighted sound wave feature data, thereby obtaining mixed sleep feature data; Step S4: performing spatiotemporal evolution processing and event impact assessment on the mixed sleep feature data to generate sleep event assessment data; screening potential sleep disorder events based on the sleep event assessment data, and collecting real-time physiological indicators to generate sleep real-time monitoring indicator data; performing sleep stage fluctuation analysis and physiological disturbance association processing on the multi-channel sleep signal segment data through the sleep real-time monitoring indicator data to generate physiological sleep disturbance association data. Step S4 includes: Step S41: performing a sleep state spatiotemporal evolution process according to the mixed sleep feature data to generate sleep state spatiotemporal evolution event data. Step S41 includes: Step S411: extracting sleep state transition features based on time series from the mixed sleep feature data, thereby obtaining state transition sequence data; Step S412: Modeling the state transition sequence data using a hidden Markov model to obtain sleep state probability distribution data; Step S413: constructing a sleep state transition matrix based on the sleep state probability distribution data to obtain state transition feature data; Step S414: extracting local time features of the mixed sleep feature data based on a sliding time window, thereby obtaining time window feature data; Step S415: performing time series modeling based on a long short-term memory network according to the state transition feature data and the time window feature data to generate a sleep state spatiotemporal evolution model, wherein the sleep state spatiotemporal evolution model includes transition probabilities and duration distributions of different sleep stages; Step S416: predicting the sleep state evolution trend according to the sleep state spatiotemporal evolution model and the nonlinear characteristic data, and classifying and marking events to generate different types of sleep state spatiotemporal evolution event data, wherein the sleep state spatiotemporal evolution event data includes normal sleep events, abnormal sleep events, and external environment impact events; Step S42: identifying potential sleep interruptions or abnormal events in the mixed sleep feature data through the sleep state spatiotemporal evolution event data, and performing event impact assessment based on feature importance to generate sleep event assessment data; Step S43: Screening potential sleep disorder events according to the sleep event evaluation data, and collecting real-time physiological indicators to generate real-time sleep monitoring indicator data; Step S44: performing sleep stage fluctuation analysis on the multi-channel sleep signal segment data to generate sleep stage fluctuation data; and performing physiological disturbance correlation processing on the sleep stage fluctuation data through the real-time sleep monitoring index data to generate physiological sleep disturbance correlation data; Step S5: Identify the sleep environment impact area of ​​the sleep stage fluctuation data to generate sleep environment impact area data; perform physiological-environmental impact pattern coupling on the sleep environment impact area data to obtain physiological-environmental coupling pattern data; merge the mixed sleep feature data, physiological sleep disturbance association data and physiological-environmental coupling pattern data into feature information extraction data.

2. The method for extracting characteristic information of a sleep state monitoring model according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: continuously collecting sleep data of the subject using a polysomnography monitor to obtain sleep physiological data, wherein the sleep physiological data includes electroencephalogram, oculogram, electromyogram, electrocardiogram and accelerometer signals; Step S12: collecting body motion signals through an ultrasonic sensor and collecting environmental sounds through a high-sensitivity microphone, thereby obtaining body motion environmental acoustic data; Step S13: merging the sleep physiological data and the body motion environment acoustic data into original sleep monitoring data; Step S14: performing signal quality assessment on the original sleep monitoring data to obtain signal quality assessment data, wherein the signal quality assessment includes signal-to-noise ratio calculation and electrode detachment detection; performing electrooculography and electromyography artifact removal on the original sleep monitoring data, and removing baseline drift using wavelet transform, thereby obtaining sleep monitoring data; Step S15: performing signal enhancement based on empirical mode decomposition on the sleep monitoring data according to the signal quality evaluation data, thereby obtaining enhanced sleep monitoring data; Step S16: performing signal segmentation on the enhanced sleep monitoring data to obtain multi-channel sleep signal segment data.

3. The method for extracting characteristic information of a sleep state monitoring model according to claim 2, characterized in that: Step S16 includes the following steps: Step S161: segmenting the enhanced sleep monitoring data according to the preset time window data to obtain initial sleep signal segment data; Step S162: performing multi-channel time synchronization and alignment processing on the initial sleep signal segment data to obtain aligned sleep signal segment data; Step S163: aligning the sleep signal segment data to perform data integrity check, identifying and marking missing or distorted data segments, and obtaining integrity check data; Step S164: performing amplitude normalization processing on the aligned sleep signal segment data according to the integrity check data, and performing fast Fourier transform to obtain sleep signal spectrum data; Step S165: performing multi-channel integration and synchronous processing on the sleep signal spectrum data to obtain multi-channel sleep signal segment data, wherein the multi-channel includes electroencephalogram, oculogram, electromyogram, electrocardiogram, accelerometer signal, ultrasonic signal and acoustic signal.

4. The method for extracting characteristic information of a sleep state monitoring model according to claim 3, characterized in that: Step S2 includes the following steps: Step S21: Extracting EEG signals from multi-channel sleep signal segment data , , , as well as The energy characteristics of the band are measured, and waveform detection based on K complex and sleep spindle is performed to obtain EEG characteristic data; Step S22: performing fast and slow eye movement identification on the eye movement signal in the multi-channel sleep signal segment data, and extracting the eye movement frequency and amplitude characteristics in the rapid eye movement and non-rapid eye movement states to obtain eye movement feature data; Step S23: performing muscle tension analysis based on the intensity and frequency characteristics of electromyographic activity on the electromyographic signals in the multi-channel sleep signal segment data to obtain electromyographic characteristic data; Step S24: performing heart rate variability analysis on the electrocardiogram signal in the multi-channel sleep signal segment data, extracting time domain and frequency domain heart rate variability indicators, and obtaining electrocardiogram feature data; Step S25: performing body motion analysis on the accelerometer signal in the multi-channel sleep signal segment data, extracting body motion frequency, intensity and duration characteristics, and obtaining body motion feature data; Step S26: merging the EEG feature data, the eye movement feature data, the myoelectric feature data, the electrocardiographic feature data, and the body movement feature data into multi-dimensional feature data; Step S27: performing Doppler frequency shift analysis on the ultrasonic signal in the multi-channel sleep signal segment data, extracting micro-body motion features, and obtaining ultrasonic feature data; Step S28: Detect and classify sound events on the ambient sound signals in the multi-channel sleep signal segment data, extract sleep sound features based on breathing sounds and snoring sounds, and obtain acoustic feature data; merge the ultrasonic feature data and the acoustic feature data into sound wave feature data.

5. The method for extracting characteristic information of a sleep state monitoring model according to claim 4, characterized in that: Step S43 includes the following steps: Step S431: performing cluster analysis on the sleep event assessment data to identify potential sleep disorder patterns, and obtaining sleep disorder pattern data; Step S432: setting a sleep disorder event screening threshold based on the sleep disorder pattern data, thereby obtaining screening threshold data; screening the sleep event assessment data for sleep disorder events according to the screening threshold data, thereby obtaining potential disorder event data; Step S433: determining the physiological indicators that need to be monitored based on the potential obstacle event data, and generating a monitoring indicator list; Step S434: configuring the acquisition parameters of the multimodal sensor according to the monitoring indicator list, thereby obtaining sensor configuration data; Step S435: using the sensor configuration data to collect real-time physiological indicators of the subject, and performing real-time signal processing, so as to obtain real-time sleep monitoring indicator data.

6. The method for extracting characteristic information of a sleep state monitoring model according to claim 5, characterized in that: Step S44 includes the following steps: Step S441: performing sleep cycle change analysis based on a dynamic time warping algorithm on the multi-channel sleep signal segment data to obtain sleep cycle data; and performing statistics on the duration and conversion frequency of each sleep stage based on the sleep cycle data to obtain sleep structure data; Step S442: predicting the sleep stage change trend based on the time series of the sleep structure data, thereby obtaining sleep stage fluctuation data; Step S443: performing physiological disturbance correlation analysis on the sleep stage fluctuation data according to the real-time sleep monitoring index data, identifying the correlation between the sleep stage and the physiological signal change, and generating physiological disturbance correlation data; Step S444: performing pattern classification on the physiological disturbance associated data according to a preset disturbance pattern library to generate disturbance pattern data; performing physiological disturbance risk assessment on the physiological signal disturbance of each sleep stage according to the disturbance pattern data, thereby obtaining physiological disturbance assessment data; Step S445: generating physiological sleep disturbance associated data including physiological index impact weights, sleep stage transition probabilities, and disturbance degrees according to the physiological disturbance assessment data.

7. A feature information extraction system for a sleep state monitoring model, characterized in that: Used to execute the feature information extraction method of the sleep state monitoring model according to claim 1, the feature information extraction system of the sleep state monitoring model comprises: The signal preprocessing module is used to collect multimodal physiological signals of the subject to obtain original sleep monitoring data; remove noise and enhance the signal of the original sleep monitoring data, and perform signal segmentation to obtain multi-channel sleep signal segment data; A multi-dimensional feature extraction module is used to extract features of multi-channel sleep signal fragment data based on electroencephalogram, oculogram, electromyogram, electrocardiogram and accelerometer signals to obtain multi-dimensional feature data; and to extract ultrasonic features and acoustic features of multi-channel sleep signal fragment data to generate sound wave feature data; A feature fusion module is used to extract nonlinear dynamic features based on multidimensional feature data to generate nonlinear feature data; and to perform complementary fusion processing on the sound wave feature data through the nonlinear feature data to generate mixed sleep feature data; The sleep dynamic analysis module is used to perform spatiotemporal evolution processing and event impact assessment on mixed sleep feature data to generate sleep event assessment data; screen potential sleep disorder events based on the sleep event assessment data, collect real-time physiological indicators, and generate real-time sleep monitoring indicator data; perform sleep stage fluctuation analysis and physiological disturbance correlation processing on multi-channel sleep signal fragment data through real-time sleep monitoring indicator data to generate physiological sleep disturbance correlation data; The environmental-physiological coupling module is used to identify the sleep environment impact area of ​​the sleep stage fluctuation data and generate sleep environment impact area data; to couple the sleep environment impact area data with the physiological-environment impact pattern to obtain the physiological-environment coupling pattern data; and to merge the mixed sleep feature data, the physiological sleep disturbance association data and the physiological-environment coupling pattern data into feature information extraction data.

Images