Sleep data monitoring method suitable for personalized customization of bruxism protection at night

Abstract

This application relates to the technical field of sleep data monitoring, and specifically relates to a sleep data monitoring method suitable for personalized customization of nocturnal bruxism protection. The method includes: constructing a high-frequency electroencephalogram (EEG) feature factor based on amplitude perturbation, sleep-wake propensity degree, and spindle irregularity; extracting all peaks and all valleys in the low-frequency EEG signal, comparing the differences between adjacent peaks and valleys to determine the abnormality of the low-frequency EEG; determining the periodicity of low-frequency fluctuations based on the similarity between different sub-low-frequency EEG signals and the abnormality of each sub-low-frequency EEG signal; comprehensively considering the low-frequency EEG abnormality, the periodicity of low-frequency fluctuations, and the high-frequency EEG feature factor to obtain the sleep impairment coefficient of each light sleep stage, and monitoring the nocturnal bruxism sleep data of the patient to be monitored. The purpose of this application is to improve the accuracy of using EEG signals to monitor patients' nocturnal sleep data.

Description

Technical Field

[0001] This application relates to the technical field of sleep data monitoring, and particularly to a sleep data monitoring method applicable to personalized customization for nocturnal bruxism protection. Background Art

[0002] Nocturnal bruxism is a non-physiological tooth contact condition, specifically referring to the involuntary contraction of the masticatory muscles during sleep, causing the upper and lower teeth to rhythmically and intermittently clench or grind against each other, thereby interrupting the normal physiological rest position of the mandible. It belongs to a sleep disorder. Sleep data monitoring for personalized customization of nocturnal bruxism protection can further provide scientific data support for the complete pathological mechanism of sleep bruxism and help relevant personnel better provide personalized treatment plans for patients.

[0003] Nocturnal bruxism mostly occurs during the light sleep period of the non-rapid eye movement (NREM) phase of patients, causing damage to teeth, periodontal tissues, and the temporomandibular joint, and at the same time affecting the electroencephalogram (EEG) signals during the patients' sleep. When the prior art uses EEG to analyze the sleep status of the monitored object, it usually only analyzes based on the frequency and energy changes of the EEG, and cannot extract and analyze the characteristics of the EEG signal changes caused by the nocturnal bruxism of the monitored object, resulting in the disturbance corresponding to the muscle behavior caused by bruxism in the EEG signal being affected, thus leading to a high analysis error when using EEG signals to monitor the sleep data of nocturnal bruxism objects. Summary of the Invention

[0004] In order to solve the above technical problems, this application provides a sleep data monitoring method applicable to personalized customization for nocturnal bruxism protection to solve the existing problems.

[0005] The sleep data monitoring method applicable to personalized customization for nocturnal bruxism protection of this application adopts the following technical solutions:

[0006] An embodiment of this application provides a sleep data monitoring method applicable to personalized customization for nocturnal bruxism protection, and this method includes the following steps:

[0007] Obtain the high-frequency EEG signal and low-frequency EEG signal of any light sleep stage during the patient's nocturnal sleep, as well as all sleep spindle signals in the high-frequency EEG signal;

[0008] By analyzing the degree of discreteness of the amplitude of the high-frequency EEG signal in the frequency domain at each light sleep stage, and the difference in amplitude between the high-frequency EEG signal and the low-frequency EEG signal in the frequency domain, to determine the degree of sleep arousal tendency at each light sleep stage;

[0009] Judge the temporal chaos degree of all sleep spindle signals in the high-frequency EEG signals, as well as the temporal differences between different sleep spindle signals, so as to determine the sleep spindle irregularities in each light sleep stage;

[0010] For each sleep spindle signal in each light sleep stage, by analyzing the difference between the amplitudes at the maximum frequency and the minimum frequency in the frequency domain, and the difference between each amplitude in the frequency domain and the average distribution of all amplitudes in the frequency domain of the low-frequency EEG signals, determine the amplitude perturbation of each sleep spindle signal in each light sleep stage;

[0011] Integrate the amplitude perturbation, the degree of sleep-wakefulness tendency, and the sleep spindle irregularities to obtain the high-frequency EEG characteristic factors of each light sleep stage;

[0012] Extract all the peaks and all the valleys in the low-frequency EEG signals, and compare the differences between adjacent peaks and valleys to determine the low-frequency EEG abnormality of each light sleep stage;

[0013] By analyzing the abnormalities of the low-frequency EEG signals in each light sleep stage, divide them into multiple sub-low-frequency EEG signals, and based on the similarity between different sub-low-frequency EEG signals and the abnormalities of each sub-low-frequency EEG signal, determine the low-frequency fluctuation periodicity of each light sleep stage;

[0014] Integrate the low-frequency EEG abnormality, the low-frequency fluctuation periodicity, and the high-frequency EEG characteristic factors to obtain the sleep impairment coefficient of each light sleep stage, and monitor the nocturnal bruxism sleep data of the patient to be monitored.

[0015] Preferably, the method for determining the degree of sleep-wakefulness tendency in each light sleep stage is as follows:

[0016] Calculate the variance of all amplitudes of the high-frequency EEG signals in the frequency domain of each light sleep stage;

[0017] Calculate the cumulative sum of the differences between all amplitudes of the high-frequency EEG signals in the frequency domain and all amplitudes of the low-frequency EEG signals in the frequency domain of each light sleep stage;

[0018] Take the product of the variance and the cumulative sum as the degree of sleep-wakefulness tendency in each light sleep stage.

[0019] Preferably, the method for determining the sleep spindle irregularities in each light sleep stage is as follows:

[0020] Obtain the generation time and disappearance time of each sleep spindle signal, and calculate the information entropy of the generation times of all sleep spindle signals in each light sleep stage;

[0021] Record the time interval between the generation time and the disappearance time of each sleep spindle signal in each light sleep stage as the time interval of each sleep spindle signal in each light sleep stage;

[0022] Calculate the cumulative sum of the time interval differences between different sleep spindle signals in each light sleep stage, which is denoted as the sleep difference sum value of each light sleep stage;

[0023] Multiply the sleep difference sum value of all sleep spindle signals in each light sleep stage by the information entropy, and use it as the sleep spindle irregularity condition of each light sleep stage.

[0024] Preferably, the method for determining the amplitude perturbation of each sleep spindle signal in each light sleep stage is as follows:

[0025] Calculate the difference between the amplitude at the maximum frequency and the amplitude at the minimum frequency of each sleep spindle signal in the frequency domain, which is denoted as the amplitude difference of each sleep spindle signal;

[0026] Calculate the mean value of all amplitudes in the frequency domain of the low-frequency EEG signals in each light sleep stage, which is denoted as the low-frequency amplitude mean value of each light sleep stage;

[0027] Calculate the cumulative sum of the differences between all amplitudes of each sleep spindle signal in the frequency domain and the mean value of all amplitudes in the frequency domain of the low-frequency EEG signals in each light sleep stage, which is denoted as the difference sum value of each sleep spindle signal in each light sleep stage;

[0028] Take the reciprocal of the product of the amplitude difference and the difference sum value of each sleep spindle signal in each light sleep stage as the amplitude perturbation of each sleep spindle signal in each light sleep stage.

[0029] Preferably, the expression of the high-frequency EEG characteristic factor of each light sleep stage is: ; where represents the high-frequency EEG characteristic factor of the i-th light sleep stage; represents the degree of sleep-wakefulness tendency of the i-th light sleep stage; represents the sleep spindle irregularity condition of the i-th light sleep stage; represents the amplitude perturbation of the p-th sleep spindle signal in the i-th light sleep stage; represents the total number of sleep spindle signals in the i-th light sleep stage; norm( ) represents the normalization function.

[0030] Preferably, the method for determining the low-frequency EEG abnormality of each light sleep stage is as follows:

[0031] Calculate the difference between each adjacent peak and valley in the low-frequency EEG signals of each light sleep stage, and take the interquartile range of all differences between adjacent peaks and valleys as the peak-valley difference value of each light sleep stage;

[0032] The low-frequency EEG abnormality of the i-th light sleep stage The expression of is: ; where Denote the peak-valley difference value of the i-th light sleep stage; Denote the difference between the y-th peak and the adjacent subsequent valley in the low-frequency EEG signal of the i-th light sleep stage; Denote the number of all peaks in the low-frequency EEG signal of the i-th light sleep stage; exp( ) represents the exponential function with the natural constant as the base.

[0033] Preferably, by analyzing the abnormalities in the low-frequency EEG signals of each light sleep stage, dividing them into multiple sub-low-frequency EEG signals, including:

[0034] Taking the low-frequency EEG signals of each light sleep stage as the input of the anomaly detection algorithm, outputting all anomaly points, and denoting each pair of adjacent anomaly points and the low-frequency EEG signal between them as sub-low-frequency EEG signals.

[0035] Preferably, the expression of the low-frequency fluctuation periodicity of each light sleep stage is: ; In the formula, Denote the low-frequency fluctuation periodicity of the i-th light sleep stage; Denote the similarity between the m-th and n-th sub-low-frequency EEG signals in the i-th light sleep stage; Denote the difference between the anomaly probabilities obtained by the anomaly detection algorithm for two anomaly points in the m sub-low-frequency EEG signals in the i-th light sleep stage; Denote the number of all sub-low-frequency EEG signals in the i-th light sleep stage; Denote a preset constant greater than 0.

[0036] Preferably, the method for determining the sleep impairment coefficient of each light sleep stage is:

[0037] Calculate the ratio of the low-frequency EEG abnormality and the low-frequency fluctuation periodicity of each light sleep stage, and denote it as the low-frequency EEG characteristic factor of each light sleep stage;

[0038] The sleep impairment coefficient of each light sleep stage is the normalized value of the product of the high-frequency EEG characteristic factor and the low-frequency EEG characteristic factor of each light sleep stage.

[0039] Preferably, the monitoring of the nocturnal bruxism sleep data of the patient to be monitored includes:

[0040] Obtain the sleep impairment coefficients of multiple patients in each light sleep stage, and form a sleep characteristic vector with the sleep impairment coefficients of all light sleep stages of each patient. Mark all the sleep characteristic vectors according to the sleep quality standard, take all the marked sleep characteristic vectors as the input of the support vector machine, output the trained support vector machine model, take the sleep characteristic vector of the patient to be monitored as the input of the support vector machine model, and output the sleep quality classification result of the patient to be monitored.

[0041] The present application has at least the following beneficial effects:

[0042] By analyzing the change amplitude of high-frequency electroencephalogram (EEG) signals and the differences between high-frequency EEG signals and low-frequency EEG signals, the present application constructs a sleep-wake tendency degree, which helps to evaluate the stability of brain activities in the light sleep stage, determine whether the patient has significant high-frequency EEG signal behaviors due to bruxism, and reflect the sleep-wake tendency degree of the patient. Secondly, by analyzing the distribution differences of sleep spindle signals in high-frequency EEG signals over time, the present application constructs a sleep spindle irregularity condition, which helps to judge the stability of the duration of the patient's sleep spindle signals and reflect the degree of damage to the sleep spindle signal characteristics. Then, by analyzing the differences between sleep spindle signals and low-frequency EEG signals, the present application constructs an amplitude perturbation property, which helps to accurately judge whether the sleep spindle signals are affected by bruxism, reduces the error in monitoring the sleep data of nocturnal bruxism subjects using EEG signals, and improves the accuracy of monitoring. Further, by comprehensively considering the amplitude perturbation property, the sleep-wake tendency degree, and the sleep spindle irregularity condition, the present application obtains high-frequency EEG characteristic factors for each light sleep stage, which reflect the high-frequency EEG signal change characteristics caused by bruxism in the light sleep period of the patient.

[0043] By analyzing the fluctuation of low-frequency EEG signals, the present application determines the low-frequency EEG abnormality, which helps to judge the magnitude of the low-frequency EEG signal fluctuation in the light sleep stage of the patient and reflect the degree of disturbance to the patient's sleep state. Further, by analyzing the abnormal conditions and periodic changes of low-frequency EEG signals, the present application constructs a low-frequency fluctuation periodicity, which helps to distinguish the effects of nocturnal bruxism and nocturnal snoring on the changes of low-frequency EEG signals in the light sleep stage of the patient, excludes the interference of nocturnal snoring on nocturnal bruxism monitoring, and improves the accuracy of monitoring the patient's nocturnal sleep data using EEG signals. By comprehensively considering the low-frequency EEG abnormality, the low-frequency fluctuation periodicity, and the high-frequency EEG characteristic factors, the present application constructs a sleep impairment coefficient for monitoring the patient's sleep quality, reduces the risk of tooth and sleep quality impairment according to the patient's sleep quality impairment condition, and improves the accuracy of monitoring the patient's nocturnal sleep data using EEG signals. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0045] Figure 1 It is a flowchart of the steps of a sleep data monitoring method applicable to personalized customization for nocturnal bruxism protection provided by an embodiment of the present application;

[0046] Figure 2 Schematic diagram of the sleep impairment coefficient extraction process provided by an embodiment of the present application;

[0047] Figure 3 Schematic diagram of the sleep quality assessment process of the patient to be monitored provided by an embodiment of the present application. Detailed implementation manners

[0048] In order to further elaborate on the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features and effects of the sleep data monitoring method applicable to personalized customization for night grinding protection proposed according to the present application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs.

[0050] The following specifically describes the specific solution of the sleep data monitoring method applicable to personalized customization for night grinding protection provided by the present application with reference to the accompanying drawings.

[0051] An embodiment of the present application provides a sleep data monitoring method applicable to personalized customization for night grinding protection. Specifically, the following sleep data monitoring method applicable to personalized customization for night grinding protection is provided. Please refer to Figure 1 , and the method includes the following steps:

[0052] Step S1: Obtain the high-frequency electroencephalogram (EEG) signal and low-frequency EEG signal during any light sleep stage of the patient during night sleep, as well as all sleep spindle signals in the high-frequency EEG signal.

[0053] Obtain the EEG signal of the patient during night sleep through an intelligent wearable device, and amplify and denoise the EEG signal of the patient during night sleep through a signal amplifier and an adaptive filter.

[0054] A large number of electroencephalogram (EEG) signals of patients with bruxism during the non-rapid eye movement (NREM) sleep stage, including the drowsy stage, light sleep stage, deep sleep stage, and rapid eye movement (REM) stage, are obtained through a polysomnography (PSG) system. All these EEG signals are used as the input of a deep convolutional neural network (CNN), and the CNN is trained to obtain a trained neural network model. Further, the EEG signals of the patient to be monitored during the night sleep process are input into the trained neural network model, and the EEG signals of different stages during the night sleep process of the patient to be monitored, that is, the total EEG signals during the night sleep process are divided into EEG signals of different stages. When training the neural network model, the cross-entropy loss is used as the loss function, and Adam is used as the optimization algorithm.

[0055] Among them, the signal amplifier, adaptive filter, and deep convolutional neural network are all well-known technologies, and their specific principles will not be elaborated here.

[0056] Normally, night sleep contains 4 - 5 sleep cycles, and the duration of the NREM light sleep stage in each sleep cycle is 10 - 25 minutes. In this embodiment, the EEG signals of the NREM light sleep stage every 20 minutes during the patient's night sleep process are regarded as a light sleep stage. Since night sleep contains multiple sleep cycles, there are also many light sleep stages. The high-frequency EEG signals (12 - 30 Hz) of β waves and low-frequency EEG signals (4 - 8 Hz) of θ waves in each light sleep stage of the patient to be monitored are obtained through a high-pass filter and a low-pass filter respectively. The high-frequency EEG signals of β waves and low-frequency EEG signals of θ waves in each light sleep stage of the patient to be monitored are used as the input of the fast Fourier transform (FFT) algorithm respectively to obtain the representation of the high-frequency brain waves in the frequency domain in each light sleep stage.

[0057] Among them, the principles of the high-pass filter, low-pass filter, and fast Fourier transform are all well-known technologies, and their respective principle processes will not be elaborated here.

[0058] Step S2: By analyzing the degree of dispersion of the amplitudes of the high-frequency EEG signals in the frequency domain in each light sleep stage, and the difference between the amplitudes of the high-frequency EEG signals and the low-frequency EEG signals in the frequency domain, to determine the degree of sleep-wake tendency in each light sleep stage.

[0059] During the NREM light sleep stage of the patient's nighttime sleep, the patient officially begins to sleep. At this time, the brain waves gradually become irregular, with the frequency and amplitude fluctuating greatly, and occasionally high-frequency large-amplitude brain waves of sleep spindles and low-frequency large-amplitude brain waves of K complexes appear; while the patient's nighttime grinding of teeth will cause the masticatory muscles to carry out tense activities, increasing the patient's alertness and muscle tension, and triggering electroencephalogram (EEG) activities in the motor area of the cerebral cortex. Specifically, in the EEG signals of the patient's light sleep stage, it is manifested as: the difference between the amplitudes of high-frequency EEG signals and low-frequency EEG signals becomes more significant, and the difference between the amplitudes of high-frequency EEG signals at different frequencies is larger. At the same time, the patient is extremely likely to have short-term awakenings during the grinding of teeth, resulting in an increase in local low-frequency fluctuations of the EEG signals.

[0060] Therefore, by analyzing the degree of dispersion of the amplitudes of high-frequency EEG signals in the frequency domain at each light sleep stage, and the difference between the amplitudes of high-frequency EEG signals and low-frequency EEG signals in the frequency domain, to determine the degree of sleep-wakefulness tendency at each light sleep stage, so as to judge whether the patient has grinding teeth. Specifically:

[0061] Calculate the variance of all amplitudes of high-frequency EEG signals in the frequency domain at each light sleep stage;

[0062] Furthermore, calculate the cumulative sum of the differences between all amplitudes of high-frequency EEG signals in the frequency domain and all amplitudes of low-frequency EEG signals in the frequency domain at each light sleep stage.

[0063] Furthermore, take the product of the variance and the cumulative sum as the degree of sleep-wakefulness tendency at each light sleep stage.

[0064] It can be understood from the degree of sleep-wakefulness tendency at each light sleep stage that when the variance of the amplitudes of all frequency components in the high-frequency brain wave signals during the light sleep stage is larger in the frequency domain, it indicates that the instability of the brain activity of the patient during the light sleep stage is stronger, and the awakening and falling asleep behaviors experienced by the brain during the light sleep stage are more frequent; when the cumulative result of the differences between the frequency amplitudes of all high-frequency brain wave signals and the frequency amplitudes of low-frequency brain wave signals during the light sleep stage is larger, it indicates that the behavior of generating high-frequency EEG signals due to grinding teeth in the patient during the light sleep stage is more significant, and the degree of sleep-wakefulness tendency caused by the patient's nighttime grinding teeth behavior during the light sleep stage is greater;

[0065] On the contrary, when the variance of the amplitudes of all frequency components in the high-frequency brain wave signals during the light sleep stage is smaller in the frequency domain, it indicates that the stability of the brain activity of the patient during the light sleep stage is stronger, and the possibility of awakening and falling asleep behaviors experienced by the brain during the light sleep stage is smaller; when the cumulative result of the differences between the frequency amplitudes of all high-frequency brain wave signals and the frequency amplitudes of low-frequency brain wave signals during the light sleep stage is smaller, it indicates that the possibility of the behavior of generating high-frequency EEG signals due to grinding teeth in the patient during the light sleep stage is smaller, and the degree of sleep-wakefulness tendency caused by the patient's nighttime grinding teeth behavior during the light sleep stage is smaller.

[0066] Step S3: Determine the degree of temporal chaos of all sleep spindle signals in the high-frequency EEG signals and the temporal differences between different sleep spindle signals to determine the sleep spindle irregularities in each light sleep stage.

[0067] Sleep spindles are a characteristic EEG activity that appears during NREM light sleep. They are spindle-shaped brain waves with a relatively high frequency (12 - 16 Hz) and large amplitude, and are a sign that sleep enters the light sleep stage. The condition of teeth grinding at night in patients is usually accompanied by strong muscle tension and is closely related to mental stress; teeth grinding at night can cause the masticatory muscles of the patient to contract frequently, reducing sleep stability, and may cause a reduction or destruction of the sleep spindle characteristics in the EEG signals, specifically manifested as an increase in the instability of sleep spindle signals in the light sleep stage, a decrease in the amplitude of sleep spindle signals, and a smaller difference from low-frequency EEG signals.

[0068] Therefore, by analyzing the degree of temporal chaos of sleep spindle signals and the temporal differences between different sleep spindle signals, determine the sleep spindle irregularities in each light sleep stage, so as to more accurately monitor whether the patient has teeth grinding during the light sleep period. Specifically:

[0069] Use the high-frequency EEG signals of each light sleep stage of the patient as the input of the deep convolutional neural network, and output the sleep spindle signals in the high-frequency EEG signals. Among them, the cross-entropy is used as the loss function, and adam is used as the optimization algorithm.

[0070] Further, obtain the generation time and disappearance time of each sleep spindle signal in each light sleep stage, and calculate the information entropy of the generation times of all sleep spindle signals in each light sleep stage;

[0071] Among them, the calculation process of information entropy is a well-known technology, and its specific calculation principle and steps will not be elaborated.

[0072] Further, record the time interval between the generation time and disappearance time of each sleep spindle signal in each light sleep stage as the time interval of each sleep spindle signal in each light sleep stage;

[0073] Further, calculate the cumulative sum of the time interval differences between different sleep spindle signals in each light sleep stage, and record it as the sleep difference sum value of each light sleep stage;

[0074] It should be noted that there are many methods to measure the differences between data. In this embodiment, the absolute value of the difference in the time intervals between different sleep spindle signals in each light sleep stage is calculated to measure the difference in the time intervals between different sleep spindle signals. Implementers can also use other methods to measure the differences between data, such as the square or ratio of the differences. Regarding the selection of methods to measure the differences between data, this embodiment does not make special restrictions.

[0075] Further, the product of the sleep difference sum value of all sleep spindle signals in each light sleep stage and the information entropy is used as the sleep spindle irregularity condition of each light sleep stage.

[0076] It can be understood from the sleep spindle irregularity conditions of each light sleep stage that when the information entropy of the generation time of the sleep spindle signal in the light sleep stage is larger, it indicates that the process of the patient entering the light sleep period during light sleep is more irregular, and the stronger the instability of the generation of the sleep spindle signal during the NREM light sleep process due to nocturnal bruxism; when the cumulative result of the differences between all sleep spindle signals and the generation time intervals of the remaining all sleep spindle signals in the light sleep stage is larger, it indicates that the duration of the sleep spindle signals generated during the process of the patient entering the light sleep period is more unstable, and the more obvious the damage condition of the characteristics of the sleep spindle signals generated during the light sleep period due to nocturnal bruxism, and the larger the sleep spindle irregularity condition.

[0077] On the contrary, when the information entropy of the generation time of the sleep spindle signal in the light sleep stage is smaller, it indicates that the process of the patient entering the light sleep period during light sleep is more regular, and the less likely the patient is to have nocturnal bruxism; when the cumulative result of the differences between all sleep spindle signals and the generation time intervals of the remaining all sleep spindle signals in the light sleep stage is smaller, the less likely the patient is to have nocturnal bruxism, and the smaller the finally obtained sleep spindle irregularity condition.

[0078] Step S4: For each sleep spindle signal in each light sleep stage, by analyzing the difference between the amplitudes at the maximum frequency and the minimum frequency in its frequency domain, and the difference between each amplitude in its frequency domain and the average distribution of all amplitudes in the frequency domain of the low-frequency electroencephalogram signal, determine the amplitude disturbance of each sleep spindle signal in each light sleep stage.

[0079] Bruxism behavior is greatly affected by emotional factors such as stress and anxiety. During the process of a patient with nocturnal bruxism entering the light sleep period, bruxism will not only exacerbate the irregularity of the generation of sleep spindle signals during the light sleep period and the degree of damage to the duration, but also the influence of the patient's emotional factors will cause the amplitudes of the sleep spindle signals in the light sleep period to be lower, that is, the amplitudes of the sleep spindle signals are smaller and more difficult to identify.

[0080] Therefore, by analyzing the difference between the amplitudes at the maximum frequency and the minimum frequency in the frequency domain of the sleep spindle signal, and the difference between each amplitude in its frequency domain and the average distribution of all amplitudes in the frequency domain of the low-frequency electroencephalogram signal, determine the amplitude disturbance of each sleep spindle signal in each light sleep stage, so as to further judge the bruxism situation during the patient's sleep process. Specifically:

[0081] Calculate the difference between the amplitude at the maximum frequency and the amplitude at the minimum frequency in the frequency domain of each sleep spindle signal, and record it as the amplitude difference of each sleep spindle signal.

[0082] Further, calculate the mean value of all amplitudes in the frequency domain of the low-frequency EEG signals in each light sleep stage, which is denoted as the low-frequency amplitude mean value of each light sleep stage;

[0083] Further, calculate the cumulative sum of the differences between all amplitudes of each sleep spindle signal in the frequency domain and the mean value of all amplitudes in the frequency domain of the low-frequency EEG signals in each light sleep stage, which is denoted as the difference sum value of each sleep spindle signal in each light sleep stage;

[0084] Further, take the reciprocal of the product of the amplitude difference and the difference sum value of each sleep spindle signal in each light sleep stage as the amplitude perturbation of each sleep spindle signal in each light sleep stage.

[0085] It should be noted that there are many methods to measure the differences between data. In this embodiment, the absolute value of the difference between the amplitude at the maximum frequency and the amplitude at the minimum frequency of each sleep spindle signal in the frequency domain is calculated to measure the difference between the corresponding amplitudes at the maximum and minimum frequencies; the absolute value of the difference between all amplitudes of each sleep spindle signal in the frequency domain and the mean value of all amplitudes in the frequency domain of the low-frequency EEG signals in each light sleep stage is calculated to measure the difference between the amplitude of the sleep spindle signal in the frequency domain and the low-frequency signal. Implementers can also combine specific situations and adopt other methods to measure the differences between data, such as the square or ratio of the difference. Regarding the selection of the method to measure the differences between data, this embodiment has no special restrictions.

[0086] It can be understood from the amplitude perturbation of each sleep spindle signal in each light sleep stage that when the difference between the amplitude at the maximum frequency and the amplitude at the minimum frequency within the sleep spindle signal in the light sleep stage is smaller, it indicates that the interference of the grinding teeth condition on the generation of the sleep spindle signal during the light sleep period of the patient is more serious, and the amplitude differences at all frequencies of the sleep spindle signal are smaller, making it more difficult to identify; when the cumulative result of the differences between the frequency amplitudes of all signal components within the sleep spindle signal and the mean value of the amplitudes at all frequencies of the low-frequency EEG signals in the light sleep stage is smaller, it indicates that the high-frequency sleep spindle signals generated by the patient during the light sleep period are weaker, and the interference of the sleep spindle signals generated during the light sleep period by grinding teeth is stronger, and the amplitude perturbation of the sleep spindle signal is stronger;

[0087] On the contrary, when the difference between the amplitude at the maximum frequency and the amplitude at the minimum frequency within the sleep spindle signal in the light sleep stage is larger, it indicates that the interference of the grinding teeth condition on the generation of the sleep spindle signal during the light sleep period of the patient is less serious, that is, the probability of grinding teeth is smaller; when the cumulative result of the differences between the frequency amplitudes of all signal components within the sleep spindle signal and the mean value of the amplitudes at all frequencies of the low-frequency EEG signals in the light sleep stage is larger, it indicates that the high-frequency sleep spindle signals generated by the patient during the light sleep period are more serious, and the amplitude perturbation of the sleep spindle signal is weaker.

[0088] Step S5: Obtain the high-frequency EEG characteristic factors for each light sleep stage by comprehensively considering the amplitude perturbation, sleep-wake tendency degree, and spindle irregularity.

[0089] As a sleep disorder, the EEG signals of patients with bruxism during light sleep not only show unstable brain activities and an increased sleep-wake tendency degree but also disrupt and damage the characteristic sleep spindle signals during light sleep. To characterize the changes in high-frequency EEG signals caused by bruxism in patients during light sleep, in this embodiment, the high-frequency EEG characteristic factors for each light sleep stage are determined by analyzing the amplitude perturbation of all sleep spindle signals in each light sleep stage, as well as the sleep-wake tendency degree and the spindle irregularity. The specific process is as follows:

[0090] The high-frequency EEG characteristic factor of the i-th light sleep stage is expressed as:

[0091] ; where represents the sleep-wake tendency degree of the i-th light sleep stage; represents the spindle irregularity of the i-th light sleep stage; represents the amplitude perturbation of the p-th sleep spindle signal in the i-th light sleep stage; represents the total number of sleep spindle signals in the i-th light sleep stage; norm( ) represents the normalization function.

[0092] From the high-frequency EEG characteristic factors of each light sleep stage, it can be understood that when the sleep-wake tendency degree of the light sleep stage is greater, it indicates that the high-frequency EEG signal behavior caused by bruxism during the light sleep stage of the patient is more significant, and the patient experiences more frequent awakening and falling asleep behaviors during the light sleep stage; when the spindle irregularity of the light sleep stage is greater and the amplitude interference of all sleep spindle signals in the light sleep stage is stronger, it indicates that the interference phenomenon of sleep spindle signal generation caused by bruxism during the light sleep stage of the patient is more obvious, the phenomenon of the decrease in the amplitude of sleep spindle signals is more serious, and it is more difficult to identify, and the higher the high-frequency EEG characteristic factor;

[0093] Conversely, when the sleep-wake tendency degree of the light sleep stage is smaller, it indicates that the high-frequency EEG signal behavior caused by bruxism during the light sleep stage of the patient is less significant; when the spindle irregularity of the light sleep stage is smaller and the amplitude interference of all sleep spindle signals in the light sleep stage is weaker, it indicates that the interference phenomenon of sleep spindle signal generation caused by bruxism during the light sleep stage of the patient is less obvious, the phenomenon of the decrease in the amplitude of sleep spindle signals is less severe, and the high-frequency EEG characteristic factor is smaller.

[0094] Step S6: Extract all the peaks and all the valleys in the low-frequency EEG signals, and compare the differences between adjacent peaks and valleys to determine the low-frequency EEG abnormality of each light sleep stage.

[0095] As a sleep disorder, during the NREM light sleep stage of the patient's nocturnal sleep, the chewing muscle tension caused by bruxism not only changes the patient's high-frequency EEG signals, but also disrupts the patient's sleep state during the light sleep stage, making it difficult for the brain to maintain deep and stable slow-wave sleep, increasing the fluctuations of theta wave low-frequency EEG signals (4-8 Hz) and decreasing their amplitudes.

[0096] Based on the above analysis, the peaks and valleys in the low-frequency EEG signals of each light sleep stage are extracted. There are many commonly used peak extraction algorithms. In this embodiment, the AMPD (Automatic multiscale-based peak detection) peak detection algorithm is used to obtain all the peaks and valleys of the low-frequency EEG signals. Implementers can also use other peak extraction algorithms such as the derivative method. Regarding the selection of the peak extraction algorithm, no special restrictions are made in this embodiment. The AMPD (Automatic multiscale-based peak detection) peak detection algorithm is a well-known technology, and its specific principle and process of extracting peaks will not be elaborated here.

[0097] Furthermore, the low-frequency EEG abnormality is calculated for any light sleep stage to characterize the change in the low-frequency EEG signals due to bruxism. Specifically:

[0098] Calculate the difference between each adjacent peak and valley in the low-frequency EEG signals of each light sleep stage, and take the interquartile range of all the differences between adjacent peaks and valleys as the peak-valley difference value of each light sleep stage;

[0099] The low-frequency EEG abnormality of the i-th light sleep stage is expressed as: ; where, represents the peak-valley difference value of the i-th light sleep stage; represents the difference between the y-th peak and its adjacent subsequent valley in the low-frequency EEG signals of the i-th light sleep stage; represents the number of all peaks in the low-frequency EEG signals of the i-th light sleep stage; exp( ) represents the exponential function with the natural constant as the base.

[0100] Among them, the calculation process of the interquartile range is a well-known technology, and its specific calculation principle and steps will not be elaborated here.

[0101] It can be understood from the abnormality of low-frequency EEG in each light sleep stage that when the interquartile range of the corresponding amplitude difference between adjacent peaks and valleys of the low-frequency EEG signal in the frequency domain during the light sleep stage is larger, it indicates that the amplitude change of the low-frequency EEG signal of the patient during the light sleep stage is more unstable, and the greater the volatility of the low-frequency EEG signal of the patient during the light sleep period due to nocturnal bruxism; when the cumulative result of the difference between the amplitudes of adjacent peaks and valleys of each low-frequency EEG signal during the light sleep stage is larger, it indicates that the phenomenon of amplitude reduction of the low-frequency EEG signal due to nocturnal bruxism during the light sleep period of the patient is more significant, and the abnormality of the low-frequency EEG in the light sleep stage is greater;

[0102] On the contrary, when the interquartile range of the corresponding amplitude difference between adjacent peaks and valleys of the low-frequency EEG signal in the frequency domain during the light sleep stage is smaller, it indicates that the amplitude change of the low-frequency EEG signal of the patient during the light sleep stage is more stable, and the smaller the volatility of the low-frequency EEG signal of the patient during the light sleep period due to nocturnal bruxism; when the cumulative result of the difference between the amplitudes of adjacent peaks and valleys of each low-frequency EEG signal during the light sleep stage is smaller, it indicates that the phenomenon of amplitude reduction of the low-frequency EEG signal due to nocturnal bruxism during the light sleep period of the patient is less obvious, and the abnormality of the low-frequency EEG in the light sleep stage is smaller.

[0103] Step S7: By analyzing the abnormality of the low-frequency EEG signals in each light sleep stage, divide them into multiple sub-low-frequency EEG signals, and determine the low-frequency fluctuation periodicity of each light sleep stage based on the similarity between different sub-low-frequency EEG signals and the abnormality of each sub-low-frequency EEG signal.

[0104] Evaluating the increase in the low-frequency EEG signal fluctuation and the decrease in amplitude due to nocturnal bruxism during the light sleep period of the patient only through the abnormality of the low-frequency EEG has the following disadvantages. That is, the patient's snoring at night will cause airway obstruction and trigger awakening reactions during sleep, which will also lead to an increase in the low-frequency EEG signal fluctuation and a decrease in amplitude during the light sleep period of the patient. However, snoring at night is often accompanied by periodic fluctuations, while bruxism is usually an irregular behavior, that is, the periodicity of the low-frequency EEG signal change of the patient during the light sleep period caused by nocturnal bruxism is lower than that caused by snoring at night.

[0105] Therefore, based on the above analysis, take the low-frequency EEG signals of each light sleep stage as the input of the anomaly detection algorithm, output all anomaly points and their respective anomaly probabilities, and record every two adjacent anomaly points and the low-frequency EEG signals between them as sub-low-frequency EEG signals.

[0106] It should be noted that there are many common anomaly detection algorithms. In this embodiment, the Bayesian change point detection algorithm is used to obtain each anomaly point and the anomaly probability of the anomaly point in the low-frequency EEG signal. Implementers can also use other anomaly detection methods such as the LOF anomaly detection algorithm. Regarding the selection of the anomaly detection algorithm, no special restrictions are made in this embodiment.

[0107] Among them, the Bayesian power grid detection algorithm is a well-known technology, and its specific principle will not be elaborated here.

[0108] Specifically, the low-frequency EEG signals before the first anomaly point and after the last anomaly point are not analyzed.

[0109] Furthermore, based on the similarity between different sub-low-frequency EEG signals and the anomaly conditions of each sub-low-frequency EEG signal, the low-frequency fluctuation periodicity of each light sleep stage is determined, specifically as follows:

[0110] The low-frequency fluctuation periodicity of the i-th light sleep stage has the following expression: ; in the formula, represents the similarity between the m-th sub-low-frequency EEG signal and the n-th sub-low-frequency EEG signal in the i-th light sleep stage; represents the difference between the anomaly probabilities obtained by the anomaly detection algorithm for two anomaly points in the m sub-low-frequency EEG signals in the i-th light sleep stage; represents the number of all sub-low-frequency EEG signals in the i-th light sleep stage; represents a preset constant greater than 0, which is used to prevent the denominator from being 0. In this embodiment, takes the value of 0.01. On the premise of ensuring that the denominator is not 0 and does not overly affect the calculation result, the implementer can also set it according to the specific situation. This embodiment does not make special restrictions.

[0111] It should be noted that there are many methods to measure the similarity between two signals. In this embodiment, the Jaccard similarity coefficient between two sub-low-frequency EEG signals is calculated to measure the similarity between two sub-low-frequency EEG signals. The implementer can also use other methods such as cosine similarity that can measure the similarity between signals. Regarding the selection of methods for measuring the similarity between signals, this embodiment does not make special restrictions.

[0112] Among them, the calculation process of the Jaccard similarity coefficient is a well-known technology, and its specific calculation steps will not be elaborated here.

[0113] Based on the periodicity of low-frequency fluctuations in each light sleep stage, it can be understood that when the difference in abnormal probabilities between two abnormal points corresponding to the sub-low-frequency EEG signals in the light sleep stage is smaller, it indicates that the abnormal condition of the low-frequency EEG signals generated during the patient's light sleep period is more prominent, and the change in the low-frequency EEG signals during the patient's light sleep period is more likely to be caused by nocturnal periodic snoring rather than irregular nocturnal bruxism behavior; when the cumulative result of the similarity between each sub-low-frequency EEG signal and the remaining sub-low-frequency EEG signals in the light sleep stage is larger, it indicates that the difference between each sub-low-frequency EEG signal during the patient's light sleep period is smaller, the synchronization of the low-frequency EEG signal changes caused by nocturnal snoring during the patient's sleep process is more significant, the periodicity of low-frequency fluctuations in the patient's light sleep stage is larger, that is, the periodicity of the low-frequency EEG signal changes during the patient's light sleep period is stronger, and the change in the low-frequency EEG signals during the patient's light sleep period is more likely to be caused by nocturnal periodic snoring rather than irregular nocturnal bruxism behavior;

[0114] Conversely, if the difference in abnormal probabilities between two abnormal points corresponding to the sub-low-frequency EEG signals in the light sleep stage is smaller, and the cumulative result of the similarity between each sub-low-frequency EEG signal and the remaining sub-low-frequency EEG signals in the light sleep stage is larger, the periodicity of low-frequency fluctuations is smaller, the periodicity of the low-frequency EEG signal changes during the patient's light sleep period is weaker, and the patient is more likely to have irregular nocturnal bruxism behavior during nocturnal sleep.

[0115] Preferably, the schematic diagram of the sleep impairment coefficient extraction process provided in this embodiment is as Figure 2 shown.

[0116] Step S8: Integrate the low-frequency EEG abnormality, the periodicity of low-frequency fluctuations, and the high-frequency EEG characteristic factors to obtain the sleep impairment coefficient for each light sleep stage.

[0117] Through the low-frequency EEG abnormality and the periodicity of low-frequency fluctuations in the patient's light sleep stage EEG signals, the increase in low-frequency EEG signal fluctuations and the decrease in amplitude caused by nocturnal bruxism can be accurately evaluated, and then the change characteristics of the patient's low-frequency EEG signals affected by bruxism during the light sleep period can be reflected.

[0118] Based on the above analysis, for the low-frequency EEG characteristic factor of any light sleep stage, it can be calculated in the following way:

[0119] Calculate the ratio of the low-frequency EEG abnormality to the periodicity of low-frequency fluctuations in each light sleep stage, and record it as the low-frequency EEG characteristic factor of each light sleep stage.

[0120] It can be understood from the low-frequency EEG characteristic factors that when the abnormality of the low-frequency EEG in the light sleep stage is higher and the low-frequency fluctuation periodicity is smaller at the same time, it indicates that the increase in the low-frequency EEG signal fluctuation and the decrease in the amplitude caused by nocturnal bruxism during the patient's light sleep period are more obvious, the sleep quality of the patient during the light sleep period is more severely disturbed by nocturnal bruxism, and the low-frequency EEG characteristic factor is larger; on the contrary, when the abnormality of the low-frequency EEG in the light sleep stage is lower and the low-frequency fluctuation periodicity is larger at the same time, it indicates that the increase in the low-frequency EEG signal fluctuation and the decrease in the amplitude caused by nocturnal bruxism during the patient's light sleep period are less obvious, and the low-frequency EEG characteristic factor is smaller.

[0121] Furthermore, based on the interference condition of the high-frequency EEG signal and the change characteristics of the low-frequency EEG signal during the patient's light sleep period, the sleep quality impairment condition caused by nocturnal bruxism during the patient's light sleep period can be evaluated, which is used to assist relevant personnel in customizing the treatment plan for the patient's nocturnal bruxism and the improvement of subsequent treatment according to the patient's sleep quality impairment condition.

[0122] Based on the above analysis, for the sleep impairment coefficient of any light sleep stage, it can be determined by the high-frequency EEG characteristic factor and the low-frequency EEG characteristic factor of the light sleep stage. Specifically:

[0123] The sleep impairment coefficient of each light sleep stage is the normalized value of the product of the high-frequency EEG characteristic factor and the low-frequency EEG characteristic factor of each light sleep stage.

[0124] It can be understood from the sleep impairment coefficient of each light sleep stage that when the sleep quality of the patient during the light sleep period is more affected by nocturnal bruxism, the awakening tendency of the patient during the light sleep period is higher, the behavior of generating high-frequency EEG signals during the light sleep period is more significant, the increase in the low-frequency EEG signal fluctuation and the decrease in the amplitude caused by nocturnal bruxism are more significant, and the patient's sleep impairment coefficient is larger; on the contrary, when the sleep quality of the patient during the light sleep period is less affected by nocturnal bruxism, the awakening tendency of the patient during the light sleep period is lower, the behavior of generating high-frequency EEG signals during the light sleep period is less significant, and the patient's sleep impairment coefficient is smaller.

[0125] Step S9: Monitor the nocturnal bruxism sleep data of the patient based on the sleep impairment coefficient of each light sleep stage.

[0126] The higher the sleep impairment coefficient, the worse the patient's sleep quality is affected by nocturnal bruxism, the greater the awakening tendency of the patient during the light sleep period, and the less sufficient and effective sleep the patient can get. Relevant personnel can evaluate the patient's sleep condition according to the size or change characteristics of the sleep impairment coefficient of each stage during the patient's light sleep period. Specifically:

[0127] Obtain the electroencephalogram (EEG) signal data of patients under different standard sleep qualities, and obtain the sleep impairment coefficients of each light sleep stage during the light sleep period of the patients through the above method. Denote the vector composed of the sleep impairment coefficients corresponding to all light sleep stages of the patients as the sleep feature vector. Mark the sleep feature vector according to the standard sleep quality, and the marked content is excellent sleep quality, good sleep quality, and poor sleep quality. Use all the marked sleep feature vectors as the input of the SVM support vector machine to train the SVM classification model. Use the trained SVM model as the classification model for monitoring patients' nocturnal bruxism during sleep. Since the training of the SVM support vector machine is a well-known technology, the specific acquisition process will not be elaborated too much.

[0128] Further, use the sleep feature vector composed of the sleep impairment coefficients corresponding to all light sleep stages during the light sleep period of the patient to be monitored as the input of the trained SVM classification model to obtain the classification result of the patient's sleep quality.

[0129] Among them, both the SVM support vector machine and the process of training the SVM model are well-known technologies, and their specific principle processes will not be elaborated.

[0130] Preferably, the schematic diagram of the sleep quality assessment process of the patient to be monitored provided in this embodiment is as Figure 3 shown.

[0131] It should be noted that the methods for obtaining the sleep impairment coefficients and sleep feature vectors of multiple patients and the patient to be monitored in each light sleep stage are the same, and all follow the methods for obtaining the sleep impairment coefficients and sleep feature vectors in steps S1 - S9.

[0132] So far, this embodiment comprehensively analyzes the degree of generation of high-frequency EEG signals caused by bruxism behavior during the light sleep stage of the patient and the interference condition of the sleep spindle characteristic signals, and accurately evaluates the change condition of the high-frequency EEG signals of the patient during the light sleep period caused by nocturnal bruxism; obtains the low-frequency EEG signal feature factors according to the change characteristics of the low-frequency EEG signals caused by nocturnal bruxism during the light sleep period of the patient. On the basis of distinguishing the changes in the low-frequency EEG signals of the patient during the light sleep period caused by nocturnal snoring and nocturnal bruxism, further consider the increase in the low-frequency EEG signal fluctuations and the decrease in the amplitude during the light sleep period of the patient; obtain the sleep impairment coefficient through the high-frequency EEG feature factor and the low-frequency EEG feature factor to evaluate the patient's sleep quality. At the same time, it can help relevant personnel accurately master the patient's nocturnal bruxism condition according to the EEG signal characteristics during the light sleep period, and provide scientific data support for subsequent personalized customization of nocturnal bruxism protection measures, improve the accuracy of using EEG signals to monitor nocturnal sleep quality, and reduce the risk of damage to the patient's teeth and sleep quality.

[0133] It should be noted that: the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. Also, the specific embodiments of this specification have been described above. Additionally, the processes depicted in the drawings do not necessarily require the specific order or consecutive order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0134] Each embodiment in this specification is described in a progressive manner. For the same or similar parts between the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

[0135] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; modifying the technical solutions recorded in the foregoing embodiments, or equivalently replacing some of the technical features, does not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included within the protection scope of the present application.

Claims

1. A sleep data monitoring method suitable for personalized nighttime bruxism protection, characterized in that: The method comprises the following steps: Obtain high-frequency EEG signals and low-frequency EEG signals of any light sleep stage during the nighttime sleep of the patient to be monitored, as well as all sleep spindle signals in the high-frequency EEG signals; By analyzing the discrete degree of the amplitude of high-frequency EEG signals in the frequency domain in each light sleep stage, as well as the difference between the amplitude of high-frequency EEG signals and low-frequency EEG signals in the frequency domain, the degree of sleep arousal tendency in each light sleep stage can be determined; Obtain the generation time and disappearance time of each sleep spindle signal, calculate the information entropy of the generation time of all sleep spindle signals in each light sleep stage; record the time interval between the generation time and disappearance time of the sleep spindle signal in each light sleep stage as the time interval of the sleep spindle signal; take the product of the cumulative sum of the time interval differences between different sleep spindle signals in each light sleep stage and the information entropy as the sleep spindle irregularity of each light sleep stage; For each sleep spindle signal in each light sleep stage, the amplitude disturbance of each sleep spindle signal in each light sleep stage is determined by analyzing the difference between its amplitude at the maximum frequency and the minimum frequency in the frequency domain, and the difference between its individual amplitudes in the frequency domain and the average distribution of all amplitudes in the frequency domain of the low-frequency EEG signal; The high-frequency EEG characteristic factors of each light sleep stage are obtained by integrating the amplitude disturbance, the degree of sleep-wake tendency and the irregularity of sleep. Extract all peaks and valleys in low-frequency EEG signals, and compare the differences between adjacent peaks and valleys to determine the abnormalities of low-frequency EEG in each light sleep stage; By analyzing the abnormalities of low-frequency EEG signals in each light sleep stage, the signals are divided into multiple sub-low-frequency EEG signals. Based on the similarities between different sub-low-frequency EEG signals and the abnormalities of each sub-low-frequency EEG signal, the periodicity of low-frequency fluctuations in each light sleep stage is determined. The sleep impairment coefficient of each light sleep stage is obtained by integrating the low-frequency EEG abnormality, low-frequency fluctuation periodicity and high-frequency EEG characteristic factors, and the nighttime bruxism sleep data of the monitored patients are monitored; The monitoring of the nighttime teeth grinding sleep data of the patient to be monitored includes: The sleep impairment coefficients of multiple patients in each light sleep stage are obtained, and the sleep impairment coefficients of all light sleep stages of each patient are combined into a sleep feature vector, the sleep feature vectors of all patients are marked according to the sleep quality standard, all the marked sleep feature vectors are used as the input of the support vector machine, and the trained support vector machine model is output, the sleep feature vectors of the patient to be monitored are used as the input of the support vector machine model, and the sleep quality classification result of the patient to be monitored is output.

2. The sleep data monitoring method suitable for personalized customization of nighttime bruxism protection according to claim 1, characterized in that: The method for determining the degree of sleep awakening tendency in each light sleep stage is as follows: Calculate the variance of all amplitudes of high-frequency EEG signals in the frequency domain at each light sleep stage; Calculate the cumulative sum of the differences between all amplitudes of the high-frequency EEG signals in the frequency domain and all amplitudes of the low-frequency EEG signals in the frequency domain in each light sleep stage; The product of the variance and the cumulative sum is used as the degree of sleep awakening tendency in each light sleep stage.

3. The sleep data monitoring method suitable for personalized customization of nighttime bruxism protection according to claim 1, characterized in that: The method for determining the amplitude disturbance of each sleep signal in each light sleep stage is as follows: Calculate the difference between the amplitude of each sleep spindle signal at the maximum frequency and the amplitude at the minimum frequency in the frequency domain, and record it as the amplitude difference of each sleep spindle signal; Calculate the mean of all amplitudes in the frequency domain of low-frequency EEG signals in each light sleep stage, and record it as the mean low-frequency amplitude of each light sleep stage; Calculate the cumulative sum of the differences between all amplitudes of each sleep spindle signal in the frequency domain and the mean of all amplitudes of the low-frequency EEG signal in the frequency domain in each light sleep stage, and record it as the difference sum value of each sleep spindle signal in each light sleep stage; The inverse of the product of the amplitude difference of each sleep spindle signal in each light sleep stage and the difference sum value is taken as the amplitude disturbance susceptibility of each sleep spindle signal in each light sleep stage.

4. The sleep data monitoring method suitable for personalized customization of nighttime bruxism protection according to claim 1, characterized in that: The expression of the high-frequency EEG characteristic factor of each light sleep stage is: ; In the formula, Represents the high-frequency EEG characteristic factor of the i-th light sleep stage; Indicates the degree of sleep awakening tendency in the i-th light sleep stage; Indicates the irregularity of sleep in the i-th light sleep stage; represents the amplitude disturbance of the p-th sleep spindle signal in the ith light sleep stage; represents the total number of sleep spindle signals in the i-th light sleep stage; norm() represents the normalization function.

5. The sleep data monitoring method suitable for personalized customization of nighttime bruxism protection according to claim 1, characterized in that: The method for determining the abnormality of low-frequency EEG in each light sleep stage is as follows: Calculate the difference between each adjacent peak and valley value in the low-frequency EEG signal of each light sleep stage, and use the interquartile range of the difference between all adjacent peaks and valley values ​​as the peak-valley difference value of each light sleep stage; Abnormality of low-frequency EEG in the i-th light sleep stage The expression is: ; In the formula, represents the peak-to-valley difference value of the i-th light sleep stage; Represents the difference between the yth peak and its adjacent valley in the low-frequency EEG signal of the i-th light sleep stage; represents the number of all peaks in the low-frequency EEG signal of the i-th light sleep stage; exp( ) represents an exponential function with a natural constant as the base.

6. The sleep data monitoring method suitable for personalized customization of nighttime bruxism protection according to claim 1, characterized in that: By analyzing the abnormal conditions of low-frequency EEG signals in each light sleep stage, the signals are divided into multiple sub-low-frequency EEG signals, including: The low-frequency EEG signals in each light sleep stage are used as the input of the anomaly detection algorithm, all abnormal points are output, and the low-frequency EEG signals between every two adjacent abnormal points and the two between them are recorded as sub-low-frequency EEG signals.

7. The sleep data monitoring method suitable for personalized customization of nighttime bruxism protection according to claim 6, characterized in that: The expression of the periodicity of low-frequency fluctuations in each light sleep stage is: ; In the formula, represents the periodicity of low-frequency fluctuations in the i-th light sleep stage; represents the similarity between the mth sub-low-frequency EEG signal and the nth sub-low-frequency EEG signal in the i-th light sleep stage; It represents the difference between the abnormal probabilities of two abnormal points in the m sub-low-frequency EEG signals in the i-th light sleep stage obtained by the abnormality detection algorithm; represents the number of all sub-low-frequency EEG signals in the i-th light sleep stage; Indicates a preset constant greater than 0.

8. The sleep data monitoring method suitable for personalized customization of nighttime bruxism protection according to claim 1, characterized in that: The method for determining the sleep impairment coefficient of each light sleep stage is: Calculate the ratio of low-frequency EEG abnormality to low-frequency fluctuation periodicity in each light sleep stage, and record it as the low-frequency EEG characteristic factor in each light sleep stage; The sleep impairment coefficient of each light sleep stage is the normalized value of the product of the high-frequency EEG characteristic factor and the low-frequency EEG characteristic factor of each light sleep stage.

Images