A sleep-aiding system and method based on neural oscillation phase locking and digital twin optimization

Abstract

The application discloses a sleep-aiding system and method based on neural oscillation phase-locked loop and digital twin optimization, which comprises a signal acquisition module, a signal processing and determination module, a neural oscillation phase-locked loop control module, a digital twin optimization module, a multi-modal collaborative scheduling module, a multi-modal stimulation synchronous output module and an effect evaluation and closed-loop feedback module. The neural oscillation phase-locked loop control module is used for generating a stimulation signal with the same frequency and phase as the target neural oscillation based on the principle of a phase-locked loop. The digital twin optimization module is used for predicting the future sleep state change trend based on the user's personalized sleep physiological digital twin, and generating the optimal stimulation parameter combination. The multi-modal collaborative scheduling module is used for coordinating the control parameters of the somatosensory shaking, somatosensory music, light pulse and temperature regulation according to the preset scheduling strategy, the current sleep staging and the phase-locked state. The application effectively shortens the sleep latency, improves the sleep efficiency and reduces the number of night awakenings.

Description

Technical Field

[0001] This invention relates to the fields of sleep medicine and biomedical engineering technology, specifically to a sleep aid system and method based on neural oscillation phase-locked loop and digital twin optimization. Background Technology

[0002] Sleep disorders have become a global public health problem. According to the World Health Organization, approximately 27% of the global population suffers from sleep disorders, and the incidence of insomnia among adults in China is as high as 38.2%. Chronic insomnia not only leads to daytime dysfunction and cognitive decline, but is also closely related to various diseases such as cardiovascular disease, metabolic syndrome, and depression.

[0003] Currently, existing sleep aid technologies mainly include the following categories:

[0004] First, medications for sleep: While benzodiazepines and non-benzodiazepine receptor agonists can shorten the time to fall asleep, they have side effects such as dependence, tolerance, and residual effects the next day, and long-term use carries significant risks.

[0005] Second, physical sleep aids: including white noise, single-frequency shaking, and tactile music. While these methods have no side effects, they have the following drawbacks: the stimulation parameters are fixed and cannot be adjusted in real time according to individual physiological states; the effect of single-modal stimulation is limited, failing to fully utilize the synergistic effect of multi-sensory channels, and failing to achieve synchronous coupling between external stimulation and neural oscillations.

[0006] Third, closed-loop feedback for sleep aid: Some existing technologies attempt to adjust stimulation parameters through EEG feedback, but most of them use simple threshold judgments or fixed rules, failing to achieve true phase locking and unable to predict changes in sleep state in advance and pre-adjust stimulation parameters.

[0007] The above shortcomings urgently need to be addressed. Summary of the Invention

[0008] To overcome the problems of fixed stimulation parameters, limited effects of single modality, lack of phase synchronization, and inability to predict changes in sleep state and pre-adjust stimulation parameters in existing sleep aid technologies, this invention provides a sleep aid system and method based on neural oscillation phase-locked loop and digital twin optimization.

[0009] The technical solution of this invention is as follows:

[0010] In a first aspect, the present invention provides a sleep aid system based on neural oscillation phase-locked loop and digital twin optimization, comprising:

[0011] The signal acquisition module is used to simultaneously acquire the user's electroencephalogram (EEG) signals, electrooculogram (EOG) signals, electromyogram (EMG) signals, heart rate signals, body movement signals, and ambient light signals.

[0012] The signal processing and determination module is used to filter, denoise, extract features, and determine sleep stages of the acquired signals.

[0013] The neural oscillation phase-locked control module is used to extract the instantaneous phase of the user's EEG signal in real time based on the phase-locked loop principle, generate a stimulation signal that is in phase and frequency with the target neural oscillation, and adjust the external stimulation phase and the neural oscillation phase to converge to the phase-locked state through phase error feedback.

[0014] The digital twin optimization module is used to predict future sleep state changes based on a user's personalized sleep physiological digital twin and generate the optimal combination of stimulation parameters.

[0015] The multimodal collaborative scheduling module is used to coordinate the control parameters of motion-sensing shaking, motion-sensing music, light pulses and temperature adjustment according to the current sleep stage and phase-locked state and a preset scheduling strategy.

[0016] The multimodal stimulus synchronous output module is used to convert the optimized stimulus parameters into physical output and apply them to the user;

[0017] The effect evaluation and closed-loop feedback module is used to monitor the user's physiological response in real time, evaluate the effect of stimulation, and make dynamic corrections when parameters deviate from the optimal or adverse response is detected. The updated data is then fed back to the digital twin optimization module for model iteration.

[0018] As a preferred embodiment of the present invention, the signal processing and determination module includes:

[0019] The EEG signal preprocessing unit is used to perform bandpass filtering and notch filtering preprocessing on the acquired user EEG signals.

[0020] The electrooculometry and electromyography noise filtering unit is used to combine the acquired user electrooculometry and electromyography signals to perform independent component analysis and noise reduction on the preprocessed user electroencephalogram signal.

[0021] The heart rate variability analysis unit is used to calculate the time-domain and frequency-domain indices of heart rate variability based on the collected user heart rate signals.

[0022] The sleep stage identification unit is used to determine sleep stages based on the user's denoised EEG signal, heart rate variability time-domain and frequency-domain indicators, collected user electrooculogram signal, user electromyogram signal, user body movement signal and ambient light signal, using an XGBoost classifier.

[0023] As a preferred embodiment of the present invention, the input features of the XGBoost classifier include the multi-band power spectrum of the user's electroencephalogram (EEG), the slow wave index of the electrooculogram (EOG), the activity of the electromyogram (EMG), the time-domain and frequency-domain indices of heart rate variability, body movement counts, and ambient light intensity. The output is a five-category system: wakefulness, non-rapid eye movement (NREM) sleep stage 1, NREM sleep stage 2, NREM sleep stage 3, and rapid eye movement (REM) sleep.

[0024] As a preferred embodiment of the present invention, the neural oscillation phase-locked control module includes:

[0025] The phase extraction unit uses Hilbert transform to extract the instantaneous phase of the user's EEG signal;

[0026] The phase-locked loop unit is used to compare the phase of the external stimulus reference signal with the instantaneous phase of the user's EEG signal, converge to the phase-locked state, and output the phase error.

[0027] The stimulation signal generation unit is used to generate a stimulation signal that is in phase and frequency with the target nerve oscillation based on the phase error of the output.

[0028] As a preferred embodiment of the present invention, the phase-locked loop unit is determined by the following conditions: the absolute value of the phase error is less than a preset degree and the duration is greater than a preset duration.

[0029] As a preferred embodiment of the present invention, the digital twin optimization module includes:

[0030] The digital twin construction unit constructs a personalized sleep physiology digital twin based on the user's historical EEG signals, historical EEG signals, historical EMG signals, historical heart rate signals, and historical body movement signals.

[0031] The sleep environment digital mapping unit is used to map the body shaking parameters, sound and light parameters, and temperature parameters into the environmental input variables of the user's personalized sleep physiological digital twin.

[0032] The real-time status synchronization update unit is used to perform real-time estimation and parameter correction of the status of the user's personalized sleep physiological digital twin using the Kalman filter algorithm.

[0033] The multi-objective optimization algorithm unit is used to solve for the optimal combination of stimulus parameters by minimizing sleep latency, maximizing sleep efficiency, and minimizing the number of awakenings, with the particle swarm optimization algorithm as the optimization objectives.

[0034] The predictive parameter adjustment unit pre-adjusts the stimulation parameters based on the state prediction of the user's personalized sleep physiological digital twin.

[0035] As a preferred embodiment of the present invention, the optimization objective function of the multi-objective optimization algorithm unit is: minimizing the objective function value equal to the first weight coefficient multiplied by the predicted sleep latency, plus the second weight coefficient multiplied by the complement of the predicted sleep efficiency, plus the third weight coefficient multiplied by the predicted number of awakenings, wherein the sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is equal to 1.

[0036] As a preferred embodiment of the present invention, the digital twin construction unit is described using a state-space model:

[0037] ;

[0038] Where x(k) is the sleep state vector, including EEG rhythm state, autonomic nervous system state, and sleep depth state; u(k) is the stimulus parameter vector, including somatosensory shaking parameters, somatosensory music parameters, light pulse parameters, and temperature regulation parameters; y(k) is the observation vector, including EEG signal features, electrooculography signal features, electromyography signal features, and heart rate signal features; w(k) is the process noise; v(k) is the observation noise; A is the state transition matrix; B is the input matrix; C is the observation matrix; and D is the direct transmission matrix.

[0039] As a preferred embodiment of the present invention, the multimodal stimulation synchronous output module includes a body-sensing shaking drive unit, a body-sensing music vibration unit, a light pulse stimulation unit, and a temperature adjustment unit.

[0040] Secondly, the present invention provides a sleep aid method based on neural oscillation phase-locking and digital twin optimization, and a sleep aid system based on neural oscillation phase-locking and digital twin optimization for executing any of the above schemes, comprising:

[0041] Simultaneously collect user's electroencephalogram (EEG), electrooculogram (EOG), electromyogram (EMG), heart rate, body movement, and ambient light signals;

[0042] The collected signals are filtered, denoised, feature extracted, and sleep stage determined.

[0043] Based on the phase-locked loop principle, the instantaneous phase of the user's EEG signal is extracted in real time to generate a stimulation signal that is in phase and frequency with the target neural oscillation. Through phase error feedback adjustment, the external stimulation phase and the neural oscillation phase converge to a phase-locked state.

[0044] Based on a user's personalized sleep physiological digital twin, predict future sleep state changes and generate the optimal combination of stimulation parameters;

[0045] Based on the current sleep stage and phase-locked state, and in accordance with the preset scheduling strategy, coordinate the control parameters of somatosensory shaking, somatosensory music, light pulses and temperature regulation.

[0046] The optimized stimulus parameters are converted into physical outputs and applied to the user;

[0047] The system monitors users' physiological responses in real time, assesses the effects of stimulation, and dynamically corrects parameters when they deviate from the optimal range or cause adverse reactions. The updated data is then fed back to the digital twin optimization module for model iteration.

[0048] According to the above-described solution, the beneficial effects of this invention are as follows:

[0049] This invention utilizes neural oscillation phase-locked loop technology to achieve precise phase synchronization between external rhythmic stimuli and the brain's internal neural oscillations, significantly enhancing neural plasticity, promoting the natural regulation of sleep-wake rhythms, and significantly shortening the sleep latency compared to the control group. Through a digital twin optimization module, a personalized sleep physiological digital twin is constructed for each user, enabling parameter pre-adjustment based on a predictive model, significantly improving the accuracy of sleep stage prediction and significantly reducing parameter optimization deviation. Through multimodal collaborative scheduling, the multi-channel temporal output of somatosensory shaking, somatosensory music, light pulses, and temperature regulation is coordinated, fully utilizing the synergistic effect of multiple sensory channels, significantly improving sleep efficiency. Through a closed-loop feedback mechanism, physiological responses are monitored in real time and stimulation parameters are dynamically corrected, ensuring the safety and effectiveness of stimulation, and significantly reducing the number of nighttime awakenings. It has no side effects or dependence and is suitable for the adjunctive treatment of various sleep disorders such as primary insomnia, anxiety-related insomnia, and circadian rhythm disorder insomnia. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of the structure of a sleep aid system based on neural oscillation phase-locked loop and digital twin optimization in one embodiment of the present invention;

[0051] Figure 2 This is a flowchart illustrating a sleep aid method based on neural oscillation phase-locked loop and digital twin optimization in one embodiment of the present invention.

[0052] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0053] To make the technical problems to be solved, the technical solutions, and the beneficial effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] It should be noted that the terms "comprising" and "having," and any variations thereof, in the specification and claims of this invention are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0055] like Figure 1 As shown, one embodiment of the present invention provides a sleep aid system based on neural oscillation phase-locked loop and digital twin optimization, including a signal acquisition module, a signal processing and judgment module, a neural oscillation phase-locked loop control module, a digital twin optimization module, a multimodal collaborative scheduling module, a multimodal stimulus synchronous output module, and an effect evaluation and closed-loop feedback module.

[0056] The signal acquisition module is used to simultaneously acquire the user's electroencephalogram (EEG) signals, electrooculogram (EOG) signals, electromyogram (EMG) signals, heart rate signals, body movement signals, and ambient light signals.

[0057] Specifically, the signal acquisition module includes an electroencephalogram (EEG) signal acquisition unit, an electrooculogram (EOG) signal acquisition unit, an electromyogram (EMG) signal acquisition unit, a heart rate signal acquisition unit, a body movement signal acquisition unit, and an ambient light acquisition unit. The EEG signal acquisition unit uses a dry electrode array with a sampling rate of 256 Hz and a resolution of 24 bits. The EOG signal acquisition unit uses bipolar leads placed above the outer canthus of the eye and the outer ear. The EMG signal acquisition unit uses mandibular EMG bipolar leads. The heart rate signal acquisition unit uses a photoplethysmography (PPG) sensor with wavelengths of 660 nm / 940 nm. The body movement signal acquisition unit uses a triaxial accelerometer with a range of ±4 g. The ambient light acquisition unit has a spectral range of 380 nm to 780 nm.

[0058] The signal processing and determination module is used to filter, denoise, extract features, and determine sleep stages of the acquired signals.

[0059] Specifically, the signal processing and judgment module includes an EEG signal preprocessing unit, an EOL and EMG noise filtering unit, a heart rate variability analysis unit, and a sleep stage recognition unit. The EEG signal preprocessing unit performs bandpass filtering and notch filtering on the acquired user EEG signals. The bandpass filtering range is 0.5Hz to 45Hz, preserving the effective EEG frequency band and removing high-frequency noise and low-frequency drift, as well as 50Hz power frequency and harmonic interference. The EOL and EMG noise filtering unit combines the acquired user EOL and EMG signals to perform independent component analysis (ICA) denoising on the preprocessed user EEG signals, removing EOL artifacts and EMG interference. The heart rate variability analysis unit calculates time-domain and frequency-domain indices of heart rate variability based on the acquired user heart rate signals. The time-domain indices include the standard deviation of the continuous heartbeat interval sequence (SDNN) and the root mean square of the difference between adjacent heartbeat intervals (RMSSD). The frequency-domain indices include low-frequency power (LF), high-frequency power (HF), and the low-frequency / high-frequency ratio (LF / HF). The sleep stage identification unit is used to determine sleep stages based on the user's denoised EEG signal, heart rate variability time-domain and frequency-domain indicators, collected user electrooculogram signal, user electromyogram signal, user body movement signal and ambient light signal, using an XGBoost classifier.

[0060] The input features of the XGBoost classifier include the power spectrum of the user's EEG signal in multiple frequency bands (alpha, theta, and beta waves), the slow wave index of the EEG signal, the activity of the EMG signal, the time-domain and frequency-domain indices of heart rate variability, body movement counts, and ambient light intensity. The output is a five-category system: wakefulness, non-rapid eye movement (NREM) sleep stage 1, NREM sleep stage 2, NREM sleep stage 3, and rapid eye movement (REM) sleep.

[0061] The neural oscillation phase-locked control module is used to extract the instantaneous phase of the user's EEG signal in real time based on the phase-locked loop principle, generate a stimulation signal that is in phase and frequency with the target neural oscillation, and adjust the external stimulation phase and the neural oscillation phase to converge to the phase-locked state through phase error feedback.

[0062] Specifically, the neural oscillation phase-locked control module includes a phase extraction unit, a phase-locked loop unit, and a stimulation signal generation unit.

[0063] The phase extraction unit, targeting the alpha wave (8-13Hz), uses Hilbert transform to extract the instantaneous phase of the user's EEG signal: first, bandpass filtering (8-13Hz) is applied to the user's EEG signal x(t) to obtain x_α(t); then, an analytic signal is constructed. Where H[·] is the Hilbert transform operator, and j is the imaginary unit. Used to construct complex analytic signals; instantaneous phase , To analyze the imaginary part of the signal (output of Hilbert transform). To analyze the real part of the signal, It is the arctangent function.

[0064] The phase-locked loop (PLL) unit compares the phase of the external stimulus reference signal with the instantaneous phase of the user's EEG signal, converges to a phase-locked state, and outputs the phase error. The PLL unit includes a reference oscillator, a phase detector, a loop filter, and a voltage-controlled oscillator (VCO). The reference oscillator generates the external stimulus reference signal. ,in The peak value of the sine wave is usually normalized to 1, t is a continuous time variable, and f_0 = 10Hz (center frequency of the α wave). The phase change rate is φ_0, and the initial phase is φ_0. The phase detector calculates the phase error based on the phase of the external stimulus reference signal φ_ref(t) and the instantaneous phase of the user's EEG signal φ_eeg(t). The loop filter is used to perform low-pass smoothing on the calculated phase error using a proportional-integral (PI) controller, filtering out high-frequency noise and outputting a smooth control quantity u(t) to the voltage-controlled oscillator. ,in , A voltage-controlled oscillator is used to adjust the frequency of the external stimulus reference signal according to u(t) so that the phase error converges to near zero. ,in The phase-locked loop (PLL) unit's phase-locking criteria are: the absolute value of the phase error is less than a preset degree (e.g., 10 degrees) and the duration is greater than a preset duration (e.g., 30 seconds). The stimulation signal generation unit is used to generate a stimulation signal that is in phase and frequency with the target nerve oscillation based on the output phase error.

[0065] The digital twin optimization module is used to predict future sleep state changes and generate the optimal combination of stimulation parameters based on the user's personalized sleep physiological digital twin.

[0066] Specifically, the digital twin optimization module includes a digital twin construction unit, a sleep environment digital mapping unit, a real-time status synchronization update unit, and a multi-objective optimization algorithm unit.

[0067] The digital twin construction unit, based on the user's historical EEG, EEG, EMG, heart rate, and body movement signals, constructs a personalized sleep physiological digital twin for the user. The digital twin construction unit is described using a state-space model.

[0068] ;

[0069] Wherein, x(k) is the sleep state vector, including EEG rhythm state, autonomic nervous system state, and sleep depth state; u(k) is the stimulus parameter vector, including somatosensory shaking parameters, somatosensory music parameters, light pulse parameters, and temperature regulation parameters; y(k) is the observation vector, including EEG signal features, EEG signal features, EMG signal features, and heart rate signal features; w(k) is the process noise; v(k) is the observation noise; A is the state transition matrix, describing the evolution rules of the sleep state itself over time: how the sleep state naturally changes from time k to time k+1, obtained by identifying N4SID through subspace from historical sleep data; B is the input matrix, describing how external stimuli (spontaneous shaking, sound and light, temperature, etc.) affect the internal sleep state, used to map stimulus parameters to changes in sleep state; C is the observation matrix, used to map the internal invisible sleep state x(k) to observable physiological features y(k); D is the direct transmission matrix, used to show how the stimulus input u(k) directly affects the observation output.

[0070] The sleep environment digital mapping unit is used to map the body motion parameters, sound and light parameters, and temperature parameters to the environmental input variables of the user's personalized sleep physiological digital twin; among them, the body motion parameters are mapped to the equivalent acceleration input, the sound and light parameters are mapped to the equivalent energy input, and the temperature parameters are mapped to the thermal environment input.

[0071] The real-time status synchronization update unit is used to estimate and correct the status of the user's personalized sleep physiological digital twin in real time using the Kalman filter algorithm.

[0072] The multi-objective optimization algorithm unit is used to find the optimal combination of stimulus parameters by minimizing sleep latency, maximizing sleep efficiency, and minimizing the number of awakenings, with the goal of minimizing sleep latency, maximizing sleep efficiency, and minimizing the number of awakenings. ,in The frequency of slight shaking is perceived by the body. The amplitude of the sway is slightly perceptible to the body. For the somatosensory music envelope frequency, The amplitude of the vibration of the music. , The brightness of the light pulse. Set the ambient temperature. The multi-objective optimization algorithm unit establishes the optimization objective function as follows: ,in To minimize the objective function value, To predict sleep latency, The complement for predicting sleep efficiency To predict the number of awakenings, Q, W, and E are weighting coefficients. The constraints included safety threshold constraints (perceived sway amplitude ≤ 5mm, sound pressure level ≤ 65dB, etc.) and physiological compatibility constraints (stimulation frequency avoids heart rate harmonics). The Particle Swarm Optimization (PSO) algorithm was used with the following configuration: 30 particles, 100 iterations, and inertia weight. Learning factor .

[0073] The predictive parameter adjustment unit, based on the user's personalized sleep physiological digital twin state prediction, pre-adjusts stimulation parameters 5 to 10 minutes in advance. For example, if it is predicted that the user will enter non-rapid eye movement sleep stage 3 in 8 minutes, the system will start reducing the frequency and amplitude of body shaking, turning off light pulses, and lowering the temperature setting 2 minutes in advance to achieve a smooth transition.

[0074] The digital twin optimization module, through the cooperation of the aforementioned digital twin construction unit, sleep environment digital mapping unit, real-time status synchronization update unit, and multi-objective optimization algorithm unit, greatly improves the accuracy of sleep stage prediction, significantly outperforming traditional fixed parameter methods.

[0075] The multimodal collaborative scheduling module is used to coordinate the control parameters of motion-sensing shaking, motion-sensing music, light pulses, and temperature adjustment according to the current sleep stage and phase-locked state and a preset scheduling strategy.

[0076] Awake phase: The frequency of the somatosensory shaking is 1.0 Hz with an amplitude of 3.0 mm; the frequency of the somatosensory music carrier wave is 40 Hz with an envelope frequency of 1.0 Hz; the frequency of the light pulse is 4.0 Hz; and the temperature is 26℃. This phase involves high-intensity stimulation, designed to induce the brain to transition from a wakeful state to a sleep state through the synergistic activation of multiple sensory channels.

[0077] Stage 1 of non-rapid eye movement (NREM) sleep: The somatosensory sway frequency is 0.8 Hz with an amplitude of 2.5 mm; the somatosensory music carrier frequency is 35 Hz with an envelope frequency of 0.8 Hz; the light pulse frequency is 3.0 Hz; and the temperature is 25.5℃. During this stage, the stimulation intensity is moderately reduced, and phase-locked loops are used to synchronize the external rhythm with the alpha waves of the brain.

[0078] Stage 2 of non-rapid eye movement (NREM) sleep: The somatosensory swaying frequency is 0.6 Hz with an amplitude of 2.0 mm; the somatosensory music carrier frequency is 30 Hz with an envelope frequency of 0.6 Hz; the light pulse frequency is 2.0 Hz; and the temperature is 25°C. During this stage, the phase-locked target frequency band transitions from alpha waves to theta waves (4-8 Hz), promoting deeper sleep.

[0079] Stage 3 of non-rapid eye movement (NREM) sleep: The frequency of somatosensory swaying is 0.3 Hz with an amplitude of 1.0 mm; the frequency of somatosensory music carrier wave is 20 Hz with an envelope frequency of 0.3 Hz; light pulses are off; and the temperature is 24.5℃. This stage is deep sleep, with stimulation intensity reduced to a minimum to avoid arousal interference.

[0080] REM sleep: The frequency of somatosensory shaking is 0.5 Hz and the amplitude is 1.5 mm; the frequency of somatosensory music carrier wave is 25 Hz and the envelope frequency is 0.5 Hz; the frequency of light pulses is 1.0 Hz; and the temperature is 24 ℃. During this stage, the stimulation parameters rise moderately to maintain the physiological stability of REM sleep.

[0081] The timing coordination of each modal stimulus follows these principles: the envelope phase of the tactile swaying and the tactile music should be synchronized (phase difference <15°), the start time of the light pulse should be aligned with the trough time of the tactile swaying, and the rate of change of temperature regulation should not exceed 0.5℃ / min.

[0082] The multimodal stimulus synchronization output module is used to convert optimized stimulus parameters into physical output and apply them to the user.

[0083] Specifically, the multimodal stimulation synchronous output module includes a motion-sensing motion drive unit, a motion-sensing music vibration unit, a light pulse stimulation unit, a temperature control unit, and a user interaction feedback unit. The motion-sensing motion drive unit uses a voice coil motor with a stroke of ±5mm and a frequency response range of 0.1 to 5Hz; the motion-sensing music vibration unit uses a motion-sensing music transducer with a frequency range of 20 to 200Hz and a power of 50W; the light pulse stimulation unit uses a light-emitting diode array with a wavelength of 480nm blue light and an adjustable brightness range of 0 to 50 cd / m²; the temperature control unit uses a PTC ceramic heating element with a power of 200W and a temperature control accuracy of ±0.5℃; and the user interaction feedback unit uses a touchscreen to display the current sleep state, stimulation parameters, and system operation log.

[0084] The effect evaluation and closed-loop feedback module is used to monitor the user's physiological response in real time, evaluate the effect of stimulation, and make dynamic corrections when parameters deviate from the optimal or adverse response is detected. The updated data is then fed back to the digital twin optimization module for model iteration.

[0085] Specifically, the effect evaluation and closed-loop feedback module is equipped with the following security protection mechanisms:

[0086] The maximum amplitude of the perceived sway is 5.0mm, and the minimum frequency is 0.2Hz and the maximum frequency is 2.0Hz.

[0087] The upper limit of sound pressure level for motion-sensing music is 65dB;

[0088] The upper limit for light pulse brightness is 50 cd / m², and the upper limit for frequency is 5.0 Hz;

[0089] The temperature adjustment range is 20 to 30℃;

[0090] When any parameter exceeds the safety threshold, the system automatically reduces the output intensity of that mode or pauses the output and issues an alarm.

[0091] To verify the technical effectiveness of the system of the present invention, a rigorous randomized controlled trial was designed:

[0092] I. Test Subjects

[0093] Sixty patients with primary insomnia were recruited, including 28 males and 32 females, aged 25 to 55 years, with a disease duration of ≥3 months. Inclusion criteria: meeting the diagnostic criteria for insomnia in the International Classification of Sleep Disorders, Third Edition; a Pittsburgh Sleep Quality Index score greater than 7; and not taking sleep aids in the past month. Exclusion criteria: severe physical illness; mental disorders; pregnancy or lactation; and allergies to stimuli. Patients were randomly divided into 5 groups of 12 each: a blank control group, a traditional white noise group, a single shaking group, a single music group, and the system of this invention group.

[0094] II. Test Conditions

[0095] The trial lasted for seven consecutive nights, from 10 PM to 6 AM the following day. The monitoring equipment was a polysomnography (PSG, Compumedics Grael). Environmental control measures included: temperature 22±1℃, humidity 50±5%, and ambient noise <30dB. The system of this invention was configured with all functions enabled (neural oscillation phase-locked loop + digital twin optimization + multimodal collaboration).

[0096] III. Evaluation Indicators

[0097] Sleep latency: the time from lights out to the onset of the first non-rapid eye movement (NREM) stage 2 sleep; Sleep efficiency: total sleep time / time spent in bed × 100%; Number of nighttime awakenings: the number of awakenings during NREM stage 1 and beyond; Pittsburgh Sleep Quality Index (PSQI): a subjective score, with a total score of 0 to 21, and ≤5 indicating good sleep quality.

[0098] IV. Test Results

[0099] As shown in Table 1:

[0100] Table 1. Comparison of test results with existing technologies

[0101] V. Statistical Analysis

[0102] Statistical software was used, and one-way ANOVA was employed for inter-group comparisons. The differences between the system group and the blank control group were highly significant; the differences between the system group and the single-swing group were significant; and the differences between the system group and the single-music group were significant. This confirms that the synergistic effect of multimodal stimulation is significantly superior to that of a single stimulus mode.

[0103] VI. Verification of the neural oscillation phase-locking effect

[0104] As shown in Table 2:

[0105] Table 2 Verification of the neural oscillation phase-locking effect

[0106] VII. Performance Verification of the Digital Twin Optimization Module

[0107] As shown in Table 3:

[0108] Table 3 Performance Comparison of Digital Twin Optimization Modules

[0109] VIII. Conclusion

[0110] The experimental data demonstrate that the system of this invention achieves precise synchronization between external stimuli and brain electrical rhythms through neural oscillation phase-locking. Combined with personalized parameter prediction and multimodal collaborative scheduling of the digital twin optimization module, it significantly outperforms existing single technologies in core indicators such as sleep latency, sleep efficiency, number of nighttime awakenings, and subjective sleep quality, demonstrating outstanding technical effects and clinical application value.

[0111] like Figure 2 As shown, the present invention also provides a sleep aid method based on neural oscillation phase-locking and digital twin optimization, comprising:

[0112] S1. Simultaneously collect user's electroencephalogram (EEG), electrooculogram (EOG), electromyogram (EMG), heart rate, body movement, and ambient light signals;

[0113] S2. Filter, denoise, extract features, and determine sleep stages for the collected signals;

[0114] S3. Based on the phase-locked loop principle, the instantaneous phase of the user's EEG signal is extracted in real time, and a stimulation signal with the same frequency and phase as the target nerve oscillation is generated. Through phase error feedback adjustment, the external stimulation phase and the nerve oscillation phase are converged to the phase-locked state.

[0115] S4. Based on the user's personalized sleep physiological digital twin, predict future sleep state changes and generate the optimal combination of stimulation parameters;

[0116] S5. Based on the current sleep stage and phase-locked state, coordinate the control parameters of motion-sensing shaking, motion-sensing music, light pulses, and temperature adjustment according to the preset scheduling strategy.

[0117] S6. Convert the optimized stimulation parameters into physical output and apply them to the user;

[0118] S7. Monitor the user's physiological response in real time, evaluate the effect of stimulation, and make dynamic corrections when parameters deviate from the optimal or adverse response is detected. Feed the updated data back to the digital twin optimization module for model iteration.

[0119] The sleep aid method based on neural oscillation phase-locked loop and digital twin optimization provided in this application embodiment can be applied to the above system embodiment. Its implementation principle and technical effect are similar, and will not be described again here.

[0120] Figure 3 This is a schematic diagram of the electronic device that implements the sleep aid method based on neural oscillation phase-locked loop and digital twin optimization according to the present invention.

[0121] Electronic devices may include processors, memory, communication buses, and communication interfaces, and may also include computer programs stored in memory and capable of running on the processor, such as sleep aid programs optimized based on neural oscillation phase-locking and digital twins.

[0122] In some embodiments, the processor can be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor is the control unit of the electronic device, connecting various components of the device through various interfaces and lines. It executes programs or modules stored in memory (e.g., executing a sleep aid program optimized based on neural oscillation phase-locked loops and digital twins) and calls data stored in memory to perform various functions and process data within the electronic device.

[0123] The memory includes at least one type of readable storage medium, including flash memory, portable hard drives, multimedia cards, card-type memory (e.g., SD or DX memory), magnetic storage, magnetic disks, optical disks, etc. In some embodiments, the memory can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory can be an external storage device of the electronic device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory can include both internal and external storage units of the electronic device. The memory can be used not only to store application software and various types of data installed on the electronic device, such as code for a sleep aid program optimized based on neural oscillation phase-locked loops and digital twins, but also to temporarily store data that has been output or will be output.

[0124] The communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. The bus is configured to enable communication between memory and at least one processor.

[0125] The communication interface is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0126] Figure 3 Only electronic devices with relevant components are shown; it will be understood by those skilled in the art that... Figure 3The structure shown does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0127] For example, a power supply, although not shown, may also include a power source (such as a battery) to power various components. Preferably, the power supply can be logically connected to at least one processor via a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power sources, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be elaborated further here.

[0128] It should be understood that the embodiments are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0129] The sleep aid program stored in the memory of the electronic device, based on neural oscillation phase-locked loop and digital twin optimization, is a combination of multiple computer programs. For the specific implementation method of the processor for these computer programs, please refer to [reference needed]. Figure 2 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0130] Furthermore, if the modules / units integrated into an electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, a computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).

[0131] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following functions: Figure 2 The flowchart shown is for a sleep aid method based on neural oscillation phase-locking and digital twin optimization.

[0132] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0133] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0134] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0135] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0136] Furthermore, although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0137] It should be understood that those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

[0138] The present invention has been described above with reference to the accompanying drawings. Obviously, the implementation of the present invention is not limited to the above-described manner. Any improvements made using the inventive concept and technical solution of the present invention, or the direct application of the inventive concept and technical solution of the present invention to other situations without modification, are all within the protection scope of the present invention.

Claims

1. A sleep aid system based on neural oscillation phase-locked loop and digital twin optimization, characterized in that, include: The signal acquisition module is used to simultaneously acquire the user's electroencephalogram (EEG) signals, electrooculogram (EOG) signals, electromyogram (EMG) signals, heart rate signals, body movement signals, and ambient light signals. The signal processing and determination module is used to filter, denoise, extract features, and determine sleep stages of the acquired signals. The neural oscillation phase-locked control module is used to extract the instantaneous phase of the user's EEG signal in real time based on the phase-locked loop principle, generate a stimulation signal that is in phase and frequency with the target neural oscillation, and adjust the external stimulation phase and the neural oscillation phase to converge to the phase-locked state through phase error feedback. The digital twin optimization module is used to predict future sleep state changes based on a user's personalized sleep physiological digital twin and generate the optimal combination of stimulation parameters. The multimodal collaborative scheduling module is used to coordinate the control parameters of motion-sensing shaking, motion-sensing music, light pulses and temperature adjustment according to the current sleep stage and phase-locked state and a preset scheduling strategy. The multimodal stimulus synchronous output module is used to convert the optimized stimulus parameters into physical output and apply them to the user; The effect evaluation and closed-loop feedback module is used to monitor the user's physiological response in real time, evaluate the effect of stimulation, and make dynamic corrections when parameters deviate from the optimal or adverse response is detected. The updated data is then fed back to the digital twin optimization module for model iteration.

2. The sleep aid system based on neural oscillation phase-locked loop and digital twin optimization according to claim 1, characterized in that, The signal processing and determination module includes: The EEG signal preprocessing unit is used to perform bandpass filtering and notch filtering preprocessing on the acquired user EEG signals. The electrooculometry and electromyography noise filtering unit is used to combine the acquired user electrooculometry and electromyography signals to perform independent component analysis and noise reduction on the preprocessed user electroencephalogram signal. The heart rate variability analysis unit is used to calculate the time-domain and frequency-domain indices of heart rate variability based on the collected user heart rate signals. The sleep stage identification unit is used to determine sleep stages based on the user's denoised EEG signal, heart rate variability time-domain and frequency-domain indicators, collected user electrooculogram signal, user electromyogram signal, user body movement signal and ambient light signal, using an XGBoost classifier.

3. The sleep aid system based on neural oscillation phase-locked loop and digital twin optimization according to claim 2, characterized in that, The input features of the XGBoost classifier include the multi-band power spectrum of the user's EEG signal, the slow wave index of the EEG signal, the activity of the EMG signal, the time-domain and frequency-domain indices of heart rate variability, body movement counts, and ambient light intensity. The output is a five-category system: wakefulness, non-rapid eye movement (NREM) sleep stage 1, NREM sleep stage 2, NREM sleep stage 3, and rapid eye movement (REM) sleep.

4. The sleep aid system based on neural oscillation phase-locked loop and digital twin optimization according to claim 1, characterized in that, The neural oscillation phase-locked control module includes: The phase extraction unit uses Hilbert transform to extract the instantaneous phase of the user's EEG signal; The phase-locked loop unit is used to compare the phase of the external stimulus reference signal with the instantaneous phase of the user's EEG signal, converge to the phase-locked state, and output the phase error. The stimulation signal generation unit is used to generate a stimulation signal that is in phase and frequency with the target nerve oscillation based on the phase error of the output.

5. The sleep aid system based on neural oscillation phase-locked loop and digital twin optimization according to claim 4, characterized in that, The phase-locked loop unit's phase-locking determination condition is: the absolute value of the phase error is less than a preset degree and the duration is greater than a preset duration.

6. The sleep aid system based on neural oscillation phase-locked loop and digital twin optimization according to claim 1, characterized in that, The digital twin optimization module includes: The digital twin construction unit constructs a personalized sleep physiology digital twin based on the user's historical EEG signals, historical EEG signals, historical EMG signals, historical heart rate signals, and historical body movement signals. The sleep environment digital mapping unit is used to map the body shaking parameters, sound and light parameters, and temperature parameters into the environmental input variables of the user's personalized sleep physiological digital twin. The real-time status synchronization update unit is used to perform real-time estimation and parameter correction of the status of the user's personalized sleep physiological digital twin using the Kalman filter algorithm. The multi-objective optimization algorithm unit is used to solve for the optimal combination of stimulus parameters by minimizing sleep latency, maximizing sleep efficiency, and minimizing the number of awakenings, with the particle swarm optimization algorithm as the optimization objectives. The predictive parameter adjustment unit pre-adjusts the stimulation parameters based on the state prediction of the user's personalized sleep physiological digital twin.

7. The sleep aid system based on neural oscillation phase-locked loop and digital twin optimization according to claim 6, characterized in that, The objective function of the multi-objective optimization algorithm unit is: minimizing the objective function value equals the first weight coefficient multiplied by the predicted sleep latency, plus the second weight coefficient multiplied by the complement of the predicted sleep efficiency, plus the third weight coefficient multiplied by the predicted number of awakenings, where the sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient equals 1.

8. The sleep aid system based on neural oscillation phase-locked loop and digital twin optimization according to claim 6, characterized in that, The digital twin building blocks are described using a state-space model: ； Where x(k) is the sleep state vector, including EEG rhythm state, autonomic nervous system state, and sleep depth state; u(k) is the stimulus parameter vector, including somatosensory shaking parameters, somatosensory music parameters, light pulse parameters, and temperature regulation parameters; y(k) is the observation vector, including EEG signal features, electrooculography signal features, electromyography signal features, and heart rate signal features; w(k) is the process noise; v(k) is the observation noise; A is the state transition matrix; B is the input matrix; C is the observation matrix; and D is the direct transmission matrix.

9. The sleep aid system based on neural oscillation phase-locked loop and digital twin optimization according to claim 1, characterized in that, The multimodal stimulation synchronous output module includes a body-sensing shaking drive unit, a body-sensing music vibration unit, a light pulse stimulation unit, and a temperature regulation unit.

10. A sleep aid method based on neural oscillation phase-locked loop and digital twin optimization, used to execute the sleep aid system based on neural oscillation phase-locked loop and digital twin optimization as described in any one of claims 1 to 9, characterized in that, include: Simultaneously collect user's electroencephalogram (EEG), electrooculogram (EOG), electromyogram (EMG), heart rate, body movement, and ambient light signals; The collected signals are filtered, denoised, feature extracted, and sleep stage determined. Based on the phase-locked loop principle, the instantaneous phase of the user's EEG signal is extracted in real time to generate a stimulation signal that is in phase and frequency with the target neural oscillation. Through phase error feedback adjustment, the external stimulation phase and the neural oscillation phase converge to a phase-locked state. Based on a user's personalized sleep physiological digital twin, predict future sleep state changes and generate the optimal combination of stimulation parameters; Based on the current sleep stage and phase-locked state, and in accordance with the preset scheduling strategy, coordinate the control parameters of somatosensory shaking, somatosensory music, light pulses and temperature regulation. The optimized stimulus parameters are converted into physical outputs and applied to the user; The system monitors users' physiological responses in real time, assesses the effects of stimulation, and dynamically corrects parameters when they deviate from the optimal range or cause adverse reactions. The updated data is then fed back to the digital twin optimization module for model iteration.

Images