Sleep assisting system and method based on endocrine detection

Abstract

The invention discloses a sleep assisting system and method based on endocrine detection, and relates to the technical field of medical health information.The sleep assisting system comprises an acquisition module used for acquiring brain wave signals and electrocardiogram data of a user and obtaining cortisol hormone level data through a wearable sensor; the model building module is used for building a human body circadian rhythm cycle model according to the cortisol hormone level data and the brain wave signals acquired by the acquisition module; the sleep state evaluation module is used for matching the human body circadian rhythm cycle model with the electrocardiogram data acquired by the acquisition module to obtain a sleep state evaluation result; the light adjusting module is used for adjusting indoor light according to the evaluation result of the sleep state evaluation module, guiding melatonin secretion and adjusting the sleep rhythm of the user. Through collaborative analysis of the multi-dimensional physiological signals, the circadian rhythm and sleep state of the user can be evaluated more accurately, and then sleep quality regulation and control are improved.

Description

Technical Field

[0001] The present invention relates to the field of medical health information technology, and in particular to a sleep assistance system and method based on endocrine detection. Background Art

[0002] With the accelerated pace of modern life, insomnia and sleep disorders have become a common health problem worldwide. Studies have shown that insufficient sleep or poor sleep quality can not only lead to inattention and memory loss, but may also increase the risk of cardiovascular disease, depression and metabolic diseases. In response to this problem, a variety of sleep-aiding technologies and devices have been developed on the market, such as sleep-aiding devices that use sound, light, or drug intervention. However, most of these technologies only intervene in superficial sleep problems, ignoring the deep-seated effects of human endocrine and circadian rhythms on sleep. For example, melatonin, as an important hormone for regulating sleep rhythm, is significantly affected by light and circadian rhythms. Therefore, it is difficult to achieve a comprehensive improvement in sleep quality with a single physical or chemical means.

[0003] In recent years, with the rapid development of biosensor technology and artificial intelligence algorithms, sleep aids based on physiological signal analysis have begun to attract attention. By collecting biological signals such as the user's heart rate and brain waves, these devices can make a more accurate assessment of the sleep state. However, current equipment often lacks the ability to comprehensively analyze endocrine signals such as cortisol hormones. As an important marker of the human body's circadian rhythm, fluctuations in cortisol levels directly affect sleep quality and depth. Therefore, the existing technology still has significant deficiencies in multimodal data fusion and circadian rhythm modeling, resulting in limited sleep assessment and intervention capabilities. In addition, the existing sleep aids are not yet perfect in terms of regulating and controlling melatonin secretion and optimizing the user's sleep rhythm, and have failed to fully tap the potential of endocrine signals in sleep intervention. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention proposes a sleep assistance system and method based on endocrine detection to solve the problems mentioned in the background technology.

[0005] The present invention provides the following technical solutions: In a first aspect, the present invention provides a sleep assistance system based on endocrine detection, comprising: The acquisition module is used to collect the user's brain wave signals and electrocardiogram data, and obtain the cortisol hormone level data through wearable sensors; A model building module, used to establish a human circadian rhythm cycle model according to the cortisol hormone level data and the brain wave signal collected by the collection module; A sleep state assessment module, used for matching the human circadian rhythm cycle model with the electrocardiogram data collected by the acquisition module to obtain a sleep state assessment result; A light adjustment module, used to adjust indoor lights according to the evaluation results of the sleep state evaluation module, guide the secretion of melatonin, and adjust the user's sleep rhythm; The brain wave signal is collected by a forehead-attached electrode array; The electrocardiogram data is collected through chest multi-lead electrocardiogram monitoring electrodes, and the electrocardiogram monitoring electrodes are arranged in a standard twelve-lead manner; The cortisol hormone level data is obtained through a wearable bioelectrochemical sensor patch, which non-invasively collects skin interstitial fluid through a microneedle array and uses an electrochemical sensor to detect cortisol concentration in real time.

[0006] As a preferred solution of the sleep assistance system based on endocrine detection of the present invention, the construction of the human circadian rhythm cycle model includes: Performing dynamic analysis on the cortisol hormone level data and drawing a cortisol secretion curve; Decomposing the brain wave signal in the time-frequency domain, calculating the brain wave energy ratios of different frequency bands, and establishing a brain wave activity map; Performing time-series alignment on the cortisol secretion curve and the EEG activity spectrum to obtain a bivariate time series; The human circadian rhythm cycle model is established according to the bivariate time series.

[0007] As a preferred embodiment of the sleep assistance system based on endocrine detection of the present invention, the cortisol secretion curve satisfies: ; in, represents the baseline level, and are the Fourier coefficients, is the attenuation coefficient, is the random disturbance term, The main cycle, =1 means 24-hour main cycle, =2 means 12 hours sub-cycle, =3 means 6-hour period, =4 means 3 hours sub-cycle, is the time variable, is the cortisol secretion curve; The calculation of the EEG energy ratio is shown in the following formula: ; in, For a specific frequency and time The EEG energy spectral density under is the brain wave frequency variable, is the frequency band weight function, is the time-varying modulation function, is the EEG energy ratio.

[0008] As a preferred solution of the sleep assistance system based on endocrine detection of the present invention, the bivariate time series is represented by the following formula: ; in, is the time delay variable, For a specific frequency and time Down Delay The EEG energy ratio after 1 unit, is the mutual correlation coefficient; The human circadian rhythm cycle model is expressed by the following formula: ; in, is the coupling coefficient of cortisol-EEG cross-correlation, reflecting the interaction strength between the two. is the external time factor strength, represents the Laplace operator, is the cortisol kinetic coupling coefficient, describing the spatial diffusion characteristics of cortisol concentration, is the EEG activity coupling coefficient, which characterizes the temporal evolution characteristics of EEG features. It is the time derivative of the EEG energy ratio, reflecting the rate of change of EEG activity.

[0009] As a preferred solution of the sleep assistance system based on endocrine detection of the present invention, obtaining the sleep state assessment result includes: Preprocessing the electrocardiogram data to obtain a heart rate variability index; Performing time-series alignment of the heart rate variability index and the human circadian rhythm cycle model to establish an index-model mapping relationship; Based on the indicator-model mapping relationship, calculating the standardized time-varying correlation coefficient; A final sleep state score is constructed based on the time-varying correlation coefficient, and a sleep state evaluation result is obtained according to the sleep state score.

[0010] As a preferred solution of the sleep assistance system based on endocrine detection of the present invention, the indicator-model mapping relationship is as follows: ; in, is the coupling function: ; in, is the heart rate variability feature vector, is the integral variable, representing a time point within the evaluation window, The human circadian rhythm model The predicted value at time, is the baseline coupling strength, is the time attenuation coefficient, is the periodic modulation amplitude.

[0011] As a preferred solution of the sleep assistance system based on endocrine detection of the present invention, when it is detected that the sleep state score is less than or equal to the first preset value and in the early morning, it is determined to strengthen the promotion of wakefulness; the output intensity of the blue light band is gradually increased, and the illumination is gradually increased from the second preset value to the first preset interval, and the duration is 15-20 minutes; if the sleep state score begins to rise, the lighting parameters are maintained; if the sleep state score continues to decrease, the blue light ratio is further increased; When the sleep state score is at a medium level, the color temperature is adjusted to the second preset range, the blue light energy ratio is controlled to the first preset ratio, and the illuminance is maintained within the third preset range; at the same time, the change rate of the sleep state score is continuously monitored, and if a downward trend is shown, the blue light ratio and illuminance are increased; if it remains stable or increases, the existing parameter configuration is maintained; When the sleep state score is greater than or equal to the third preset value and it is during the night time, the color temperature is reduced to a fourth preset range, the proportion of blue light energy is controlled below the second preset ratio, and the illuminance is reduced to below the fourth preset value; if the sleep state score increases abnormally, it indicates that the physiological rhythm is disturbed. At this time, the illuminance is further reduced to below the third preset value and the blue light is completely filtered out.

[0012] In a second aspect, the present invention provides a sleep assistance method based on endocrine detection, comprising: Collect the user's brain wave signals and electrocardiogram data, and obtain cortisol hormone level data through wearable sensors; Establishing a human circadian rhythm cycle model based on the cortisol hormone level data and the brain wave signal; Matching the human circadian rhythm cycle model with the electrocardiogram data to obtain a sleep state assessment result; According to the evaluation result of the sleep state evaluation module, the indoor lighting is adjusted to guide the secretion of melatonin and regulate the user's sleep rhythm.

[0013] The beneficial effects of the present invention are: collecting brain wave signals, electrocardiogram data and cortisol hormone levels, comprehensively reflecting changes in neural activity, cardiac function and endocrine rhythm, and realizing collaborative analysis of multi-dimensional physiological signals. Compared with the single signal monitoring method, the system can more accurately evaluate the user's circadian rhythm and sleep state, provide a scientific basis for subsequent lighting adjustment and rhythm optimization, and effectively improve the accuracy and personalization of sleep quality control. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 The system block diagram of a sleep assistance system based on endocrine detection. DETAILED DESCRIPTION

[0015] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0016] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0017] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0018] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0019] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0020] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0021] Example 1: Reference Figure 1 , which is the first embodiment of the present invention, and provides a sleep assistance system based on endocrine detection, including a collection module, a model building module, a sleep state assessment module and a light adjustment module; Specifically, the acquisition module acquires the user's physiological signals, including three main dimensions: first, brain wave signals are acquired through a forehead-attached electrode array, the electrode array includes at least 8 signal acquisition points, and the sampling frequency is 250Hz; second, electrocardiogram data are acquired through chest multi-lead ECG monitoring electrodes, the ECG monitoring electrodes are arranged in a standard twelve-lead manner, and the sampling frequency is 1000Hz; finally, cortisol hormone level data is acquired using a wearable bioelectrochemical sensor patch, the sensor patch non-invasively collects skin interstitial fluid through a microneedle array, and uses an electrochemical sensor to detect cortisol concentration in real time, with a sampling interval of 5 minutes.

[0022] The above three types of data are transmitted in real time through a low-power Bluetooth module, where the EEG signal focuses on monitoring the spectrum distribution of delta waves, theta waves, alpha waves and beta waves, the electrocardiogram data focuses on the RR interval variability index, and the cortisol hormone level data tracks the 24-hour concentration change curve. This step provides a comprehensive data basis for subsequent sleep status assessment through the coordinated collection of multi-dimensional physiological signals.

[0023] Furthermore, the model building module establishes a human circadian rhythm cycle model based on the collected physiological data, specifically including: first, performing a 24-hour dynamic analysis on the cortisol hormone level data, extracting the peak concentration time point, the trough concentration time point and the concentration change slope, and drawing a cortisol secretion curve, wherein the cortisol secretion curve satisfy: ; in, represents the baseline level, and are the Fourier coefficients, is the attenuation coefficient, is the random disturbance term, The main cycle, =1 means 24-hour main cycle, =2 means 12 hours sub-cycle, =3 means 6-hour period, =4 means 3 hours sub-cycle, is the time variable.

[0024] Secondly, the EEG signal is decomposed in the time-frequency domain to calculate the energy ratio of the four frequency bands of δ wave, θ wave, α wave and β wave, and a 24-hour EEG activity map is established. The calculation formula is: ; in, For a specific frequency and time The EEG energy spectral density under is the brain wave frequency variable, is the frequency band weight function, is a time-varying modulation function.

[0025] Among them, the frequency band weight function The following definition: ; in, is the center frequency of each frequency band, is the frequency band bandwidth parameter, is the Gaussian smoothing kernel function.

[0026] Construction of time-varying modulation function H(t): ; middle, For circadian rhythm modulation depth, is the reference time point, is the time scale parameter.

[0027] It should be noted that the EEG energy ratio is expanded in the time domain, and a time-varying characteristic sequence of the energy ratio is established through 24-hour continuous monitoring. Then, the time axis of the time-varying characteristic sequence is calibrated to divide the 24-hour cycle into three characteristic periods: the morning-to-dusk transition period, the daytime activity period, and the nighttime sleep period. During the characteristic period, the sleep-wake transition point and the change pattern of sleep depth are identified through the dynamic change characteristics of the energy ratio.

[0028] Finally, the time-varying characteristic sequence of the EEG energy ratio is converted into a two-dimensional time-frequency distribution map. In the two-dimensional time-frequency distribution map, the horizontal axis represents the 24-hour time span, the vertical axis represents the four characteristic frequency bands, and the map intensity is determined by the energy ratio at the corresponding moment. Through the spatiotemporal distribution characteristics of the EEG energy ratio, a complete EEG activity map is formed.

[0029] Furthermore, the cortisol secretion curve is aligned with the EEG activity spectrum, and the common periodic features of the two sets of data are extracted by wavelet transform to construct a bivariate time series, and its cross-correlation function for: ; in, is the time delay variable.

[0030] Based on the bivariate time series, a nonlinear dynamics method is used to establish a human circadian rhythm cycle model : ; in, is the coupling coefficient of cortisol-EEG cross-correlation, reflecting the interaction strength between the two. is the external time factor strength, represents the Laplace operator, is the cortisol kinetic coupling coefficient, describing the spatial diffusion characteristics of cortisol concentration, is the EEG activity coupling coefficient, which characterizes the temporal evolution characteristics of EEG features. is the time derivative of the EEG energy ratio, reflecting the rate of change of EEG activity; the stability index S of the model is calculated as follows: ; in, for The Lyapunov exponent of is the number of sampling points.

[0031] Furthermore, the sleep state assessment module first performs noise reduction and baseline drift correction on the electrocardiogram data, and uses a wavelet threshold denoising method to eliminate power frequency interference and myoelectric noise; secondly, it performs R wave detection and RR interval sequence extraction, and the RR interval sequence reflects the dynamic change characteristics of the heartbeat interval; then, the RR interval sequence is screened for outliers and interpolated to ensure the continuity and reliability of the data; finally, the RR interval sequence is segmented according to a 24-hour cycle and aligned with the time axis of the circadian rhythm cycle model.

[0032] Perform time domain analysis on the preprocessed RR interval sequence, construct a heart rate variability index, align the heart rate variability index with the human circadian rhythm cycle model, and establish an index-model mapping relationship. Specifically, the heart rate variability index The eigenvector of is shown below: ; in, is the time-varying weight matrix: ; in, ~ is the weight coefficient, is the time constant, is the standard deviation of the RR intervals between adjacent normal heart beats, is the root mean square of the difference between adjacent RR intervals, It is the ratio of low frequency to high frequency power.

[0033] Establishing the characteristic vector and circadian rhythm model of heart rate variability index The mapping relationship : ; in, is the coupling function: ; in, is the heart rate variability feature vector, is the integral variable, representing a time point within the evaluation window, The human circadian rhythm model The predicted value at time, is the baseline coupling strength, ranging from [0.8-1.2], is the time attenuation coefficient, with a value range of [0.01-0.05], is the periodic modulation amplitude, and its value range is [0.1-0.3].

[0034] Based on the above mapping relationship, the standardized time-varying correlation coefficient is calculated : ; in, is the output value of the mapping relationship, For the mapping relationship The local mean of A model of the human circadian rhythm cycle. Model of the human circadian rhythm cycle The local mean of For the mapping relationship The local standard deviation of Model of the human circadian rhythm cycle The local standard deviation of .

[0035] Finally, the final sleep state score is constructed based on the correlation coefficient : ; middle, Reflecting changing trends, Indicates the accumulated historical information. , and Reasonable configuration can realize the comprehensive evaluation of static features, dynamic features and cumulative features.

[0036] The lighting adjustment module will The value range is standardized to 0-100, where 0 means that the sleep state deviates seriously from the circadian rhythm, and 100 means that it is completely in line with the ideal circadian rhythm. Based on this score, a segmented dimming strategy is established: When detected At a low level (less than 40) and in the early morning (6:00-9:00), the system determines that it needs to be strengthened to promote wakefulness. At this time, the light adjustment strategy is: gradually increase the output intensity of the blue light band (460-480nm), and the illumination gradually increases from 50lux to 250-300lux, for 15-20 minutes. If it starts to rise, the lighting parameters are maintained; If it continues to decrease, the proportion of blue light will increase further, and the maximum illumination can reach 400-450lux.

[0037] when At a medium level (40-70), a balanced spectrum configuration is used. The color temperature is adjusted to the range of 5500-6500K, the proportion of blue light energy is controlled at 25-30%, and the illumination is maintained at 350-500lux. At the same time, the system continuously monitors the change rate of Score(t): if there is a downward trend, the proportion of blue light (no more than 35%) and illumination (up to 600lux) are appropriately increased; if it remains stable or increases, the existing parameter configuration is maintained.

[0038] according to The system predicts the user’s physiological rhythm status based on the changing trend of the user’s circadian rhythm. When it is greater than 70 and fluctuates steadily, the lighting transition plan begins: gradually reduce the blue light output, slowly adjust the color temperature from 6500K to 3000-4000K, and simultaneously reduce the illumination to 200-300lux. The transition duration is adjusted according to the specific value of Score(t), and is generally controlled at 60-90 minutes. when Keep it at a high level (greater than 70) and use warm lighting solutions during night time: the color temperature is reduced to 2700-3000K, the proportion of blue light energy is controlled below 5%, and the illumination is reduced to below 100lux. An abnormal increase indicates that the physiological rhythm is disturbed. At this time, the illumination should be further reduced to below 50 lux and the blue light should be completely filtered out.

[0039] By changing the intensity of the blue light output, the secretion of melatonin is guided to regulate the user's sleep rhythm.

[0040] Furthermore, this embodiment also provides a sleep assistance method based on endocrine detection, comprising: Collect the user's brain wave signals and electrocardiogram data, and obtain cortisol hormone level data through wearable sensors; Establishing a human circadian rhythm cycle model based on the cortisol hormone level data and the brain wave signal; Matching the human circadian rhythm cycle model with the electrocardiogram data to obtain a sleep state assessment result; According to the evaluation result of the sleep state evaluation module, the indoor lighting is adjusted to guide the secretion of melatonin and regulate the user's sleep rhythm.

[0041] This embodiment also provides a computer device, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the sleep assistance method based on endocrine detection as proposed in the above embodiment.

[0042] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0043] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, the sleep assistance method based on endocrine detection as proposed in the above embodiment is implemented.

[0044] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0045] Embodiment 2: This is the second embodiment of the present invention. This embodiment provides a sleep assistance system based on endocrine detection. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0046] This experiment selected 30 healthy volunteers aged between 25 and 35 (15 males and 15 females), and the experiment lasted for 14 consecutive days. All volunteers maintained a normal schedule one week before the experiment and avoided drinking alcohol, caffeine and other substances that affect sleep. The experimental site was selected in a professional sleep laboratory, equipped with an intelligent lighting system that can achieve precise spectral control in the 460-480nm band, with an illumination range of 0-1000lux and an adjustable color temperature range of 2700K-6500K.

[0047] The experiment used the newly developed multimodal physiological signal acquisition system MSC-2000, which integrates three core modules: (1) an 8-channel EEG acquisition module using dry electrode technology, with electrodes made of Ag / AgCl material, contact impedance <5kΩ, and common mode rejection ratio >100dB; (2) a 12-lead ECG acquisition module using flexible printed circuit technology, with a signal-to-noise ratio >60dB and a sampling accuracy of 24bit; (3) a graphene-based microneedle array bioelectrochemical sensor with an 8×8 array layout, a puncture depth of 200μm, and a detection limit of 0.1ng / mL.

[0048] The data collection process strictly follows standard operating procedures: first, the electrode positions of the volunteers are marked, and after disinfection with medical alcohol, the EEG electrodes are arranged at Fp1, Fp2, F3, F4, C3, C4, O1, and O2 positions according to the international 10-20 system; second, the ECG electrodes are placed according to the standard twelve-lead positions, and conductive glue is used to ensure stable contact; finally, the microneedle array sensor patch is attached to the inside of the volunteer's non-dominant wrist and fixed with medical tape.

[0049] All sensors are connected to the central processor via the low-power Bluetooth 5.0 protocol, using 256-bit AES encryption for transmission, with data latency less than 10ms. The central processor uses a dual-core architecture, a main frequency of 2.4GHz, and is equipped with 4GB RAM, which can achieve real-time signal processing and storage. The system uses an adaptive filtering algorithm for noise suppression, and the Signal-to-Noise Ratio (SNR) improvement rate reaches 15dB.

[0050] To ensure the accuracy and reliability of the experimental data, a 24-hour equipment stability test was conducted before formal data collection. The test results showed that the EEG signal drift was <0.1μV / h, the ECG baseline drift was <0.05mV / h, and the intra-batch coefficient of variation (CV) of cortisol detection was <5%.

[0051] The experiment obtained the experimental data shown in Table 1 below, as shown in the following table: Table 1 Experimental data table Test No. EEG alpha wave energy ratio (%) Heart rate variability index (ms) Cortisol concentration (ng / mL) Light intensity (lux) Sleep status score Blue light ratio (%) Average sleep latency (min) Control-01 23.5 45.6 12.3 350 65 25 35.2 Test-01 28.7 52.3 10.8 300 78 20 28.6 Control-02 21.8 43.2 13.5 400 62 30 38.4 Test-02 29.4 54.8 11.2 275 82 18 25.8 Control-03 22.6 44.8 12.8 375 64 28 36.7 Test-03 30.1 55.6 10.5 250 85 15 24.3 Control-04 24.2 46.5 13.1 425 63 32 37.9 Test-04 31.2 56.2 10.1 225 87 12 23.1 Control-05 22.9 45.1 12.9 390 66 27 35.8 Test-05 30.8 55.9 10.3 240 86 14 23.8 Through the systematic analysis of the experimental data, it can be clearly observed that the present invention has a significant effect in improving sleep quality. First, from the perspective of the EEG alpha wave energy ratio, the average value of the test group (Test group) is 30.04%, which is significantly higher than the 23.0% of the control group (Control group), an increase of 30.6%. Alpha waves are closely related to the state of relaxation, and a higher alpha wave energy ratio indicates that the test group subjects have achieved a better state of relaxation.

[0052] In terms of heart rate variability (HRV), the average value of the test group was 54.96ms, which was 22.0% higher than the 45.04ms of the control group. Higher HRV indicates that the autonomic nervous system has enhanced regulatory ability and parasympathetic nerve activity, which is highly consistent with the physiological characteristics of high-quality sleep.

[0053] The concentration of cortisol is an important indicator of stress hormones. The average value of the test group was 10.58 ng / mL, which was 18.1% lower than that of the control group (12.92 ng / mL). This result shows that the intelligent light regulation system of the present invention can effectively reduce the level of cortisol at night, which is conducive to the initiation and maintenance of sleep.

[0054] In terms of lighting parameters, the test group used a softer lighting scheme, with an average illumination of 258 lux and an average blue light ratio of 15.8%, while the control group had these two indicators of 388 lux and 28.4% respectively. A softer lighting environment and lower blue light exposure effectively protect the secretion rhythm of melatonin.

[0055] The most convincing is the comparison between the sleep state score and the average sleep latency. The average sleep state score of the test group reached 83.6 points, an increase of 30.6% from the 64.0 points of the control group. At the same time, the average sleep latency of the test group was only 25.12 minutes, which was significantly shortened by 31.7% from the 36.8 minutes of the control group. The improvement of these two core indicators directly confirms the outstanding effectiveness of the present invention in optimizing sleep efficiency.

[0056] Through Pearson correlation analysis, it was found that the sleep state score was significantly positively correlated with the EEG alpha wave energy ratio (r=0.892, p<0.001) and the heart rate variability index (r=0.865, p<0.001), and was significantly negatively correlated with the cortisol concentration (r=-0.831, p<0.001). This synergistic change of multiple indicators verifies the systemic mechanism of the present invention in regulating the human circadian rhythm.

[0057] The experimental results fully prove that the present invention can significantly improve sleep quality, shorten sleep time, and optimize sleep structure through the coordinated collection and analysis of multi-dimensional physiological signals combined with intelligent light adjustment strategies. Compared with the traditional single parameter monitoring method, the present invention achieves a more comprehensive and accurate sleep state assessment and adjustment, which has important innovation and practical value.

[0058] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A sleep assistance system based on endocrine detection, characterized in that: include: The acquisition module is used to collect the user's brain wave signals and electrocardiogram data, and obtain the cortisol hormone level data through wearable sensors; A model building module, used to establish a human circadian rhythm cycle model according to the cortisol hormone level data and the brain wave signal collected by the collection module; A sleep state assessment module, used for matching the human circadian rhythm cycle model with the electrocardiogram data collected by the acquisition module to obtain a sleep state assessment result; A light adjustment module, used to adjust the indoor light according to the evaluation result of the sleep state evaluation module, guide the secretion of melatonin, and adjust the sleep rhythm of the user; The brain wave signal is collected by a forehead-attached electrode array; The electrocardiogram data is collected through chest multi-lead electrocardiogram monitoring electrodes, and the electrocardiogram monitoring electrodes are arranged in a standard twelve-lead manner; The cortisol hormone level data is obtained through a wearable bioelectrochemical sensor patch, which non-invasively collects skin interstitial fluid through a microneedle array and uses an electrochemical sensor to detect cortisol concentration in real time.

2. The sleep assistance system based on endocrine detection as claimed in claim 1, characterized in that: The construction of the human circadian rhythm cycle model includes: Performing dynamic analysis on the cortisol hormone level data and drawing a cortisol secretion curve; Decomposing the brain wave signal in the time-frequency domain, calculating the brain wave energy ratios of different frequency bands, and establishing a brain wave activity map; Performing time-series alignment on the cortisol secretion curve and the EEG activity spectrum to obtain a bivariate time series; The human circadian rhythm cycle model is established according to the bivariate time series.

3. The sleep assistance system based on endocrine detection as claimed in claim 2, characterized in that: The cortisol secretion curve satisfies: ； in, represents the baseline level, and are the Fourier coefficients, is the attenuation coefficient, is the random disturbance term, The main cycle, =1 means 24-hour main cycle, =2 means 12 hours sub-cycle, =3 means 6-hour period, =4 means 3 hours sub-cycle, is the time variable, is the cortisol secretion curve; The calculation of the EEG energy ratio is shown in the following formula: ； in, For a specific frequency and time The EEG energy spectral density under is the brain wave frequency variable, is the frequency band weight function, is the time-varying modulation function, is the EEG energy ratio.

4. The sleep assistance system based on endocrine detection as claimed in claim 3, characterized in that: The bivariate time series is expressed as follows: ； in, is the time delay variable, For a specific frequency and time Down Delay The EEG energy ratio after 1 unit, is the mutual correlation coefficient; The human circadian cycle model It is expressed by the following formula: ； in, is the coupling coefficient of cortisol-EEG cross-correlation, reflecting the interaction strength between the two. is the external time factor strength, represents the Laplace operator, is the cortisol kinetic coupling coefficient, describing the spatial diffusion characteristics of cortisol concentration, is the EEG activity coupling coefficient, which characterizes the temporal evolution characteristics of EEG features. It is the time derivative of the EEG energy ratio, reflecting the rate of change of EEG activity.

5. The sleep assistance system based on endocrine detection as claimed in claim 4, characterized in that: Obtaining the sleep state assessment result includes: Preprocessing the electrocardiogram data to obtain a heart rate variability index; Performing time-series alignment of the heart rate variability index and the human circadian rhythm cycle model to establish an index-model mapping relationship; Based on the indicator-model mapping relationship, calculating the standardized time-varying correlation coefficient; A final sleep state score is constructed based on the time-varying correlation coefficient, and a sleep state evaluation result is obtained according to the sleep state score.

6. The sleep assistance system based on endocrine detection as claimed in claim 5, characterized in that: The indicator-model mapping relationship is shown in the following formula: ； in, is the coupling function: ； in, is the heart rate variability feature vector, is the integral variable, representing a time point within the evaluation window, The human circadian rhythm model The predicted value at time, is the baseline coupling strength, is the time attenuation coefficient, is the periodic modulation amplitude.

7. The sleep assistance system based on endocrine detection as claimed in claim 6, characterized in that: The adjusting of indoor lighting comprises: When it is detected that the sleep state score is less than or equal to the first preset value and it is in the early morning, it is determined to strengthen the promotion of wakefulness; the output intensity of the blue light band is gradually increased, and the illumination is gradually increased from the second preset value to the first preset interval, and the duration is 15-20 minutes; if the sleep state score begins to rise, the lighting parameters are maintained; if the sleep state score continues to decrease, the blue light ratio is further increased; When the sleep state score is at a medium level, the color temperature is adjusted to the second preset range, the blue light energy ratio is controlled to the first preset ratio, and the illuminance is maintained within the third preset range; at the same time, the change rate of the sleep state score is continuously monitored, and if a downward trend is shown, the blue light ratio and illuminance are increased; if it remains stable or increases, the existing parameter configuration is maintained; When the sleep state score is greater than or equal to the third preset value and it is during the night time, the color temperature is reduced to a fourth preset range, the proportion of blue light energy is controlled below the second preset ratio, and the illuminance is reduced to below the fourth preset value; if the sleep state score increases abnormally, it indicates that the physiological rhythm is disturbed. At this time, the illuminance is further reduced to below the third preset value and the blue light is completely filtered out.

8. A sleep assistance method based on endocrine detection, based on the sleep assistance system based on endocrine detection according to any one of claims 1 to 7, characterized in that: include: Collect the user's brain wave signals and electrocardiogram data, and obtain cortisol hormone level data through wearable sensors; Establishing a human circadian rhythm cycle model based on the cortisol hormone level data and the brain wave signal; Matching the human circadian rhythm cycle model with the electrocardiogram data to obtain a sleep state assessment result; According to the evaluation result of the sleep state evaluation module, the indoor lighting is adjusted to guide the secretion of melatonin and regulate the user's sleep rhythm.

Images