A personalized sleep-aid system and method

Abstract

The application discloses a kind of individualized sleep-aid system and method, it is related to sleep product design field, the system, including: vibration calibration system, for determining first sleep relative energy index according to the vibration excitation eeg of being applied to user, according to first sleep relative energy index adjustment vibration excitation signal frequency and amplitude, until optimal vibration excitation signal is obtained, complete vibration calibration;Sound calibration system, for determining second sleep relative energy index according to the sound excitation eeg of being applied to user, according to second sleep relative energy index adjustment sound type and loudness of sound excitation signal, until optimal sound excitation signal is obtained, complete sound calibration;Sleep-aid module, for when target user needs sleep-aid, with the optimal hypnotic effect key parameter of target user produces corresponding excitation signal, realizes sleep-aid.The application can be aimed at different users, realize the calibration of hypnotic effect key parameter, improve hypnotic effect, improve sleep quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of sleep product design, in particular to a personalized sleep-aiding system and method. BACKGROUND

[0002] Sleep is a very important physiological process for human beings, and is also an important guarantee for maintaining physical health and repairing the body. Due to the accelerated pace of modern social life and high life pressure, sleep quality problems are increasingly prominent. According to statistics, sleep time accounts for about one-third of a person's life, and a decrease in sleep quality can cause great distress to people's lives. In the short term, low-quality sleep often leads to inattention, dizziness, and seriously affects people's learning and work efficiency; in the long term, long-term sleep problems can also cause a series of physiological diseases, such as causing the immune system to decline, growth hormone secretion disorder, causing cardiovascular disease, and even becoming one of the causes of cancer.

[0003] Due to the huge heterogeneity of the human brain, differences in sleep habits, and differences in sleep environment, the sleep instruments or sleep beds and other auxiliary sleep-aiding products currently on the market use fixed amplitude and frequency excitation, lack of personalized design, and their sleep-aiding effects are questionable.

[0004] Currently, there are many types of sleep instruments or sleep beds and other auxiliary sleep-aiding products on the market. These sleep-aiding products are mainly divided into three categories: the first category plays music to relax the user's mood to achieve a sleep-aiding effect; the second category stimulates the user to fall asleep quickly by emitting a specific intensity of current; and the third category mainly relies on external vibration to stimulate the human brain to produce a specific type of brain wave, so that the user quickly enters a sleep state. However, these products still have some problems:

[0005] Single reliance on music stimulation for sleep is easy to greatly reduce the sleep-aiding effect as the use time is prolonged, and does not take into account the individual differences of the user. For example, the patent with application number 202211461180.4 proposes a "system for promoting sleep based on music", which uses the correspondence between music and brain waves to achieve a sleep-regulating function. However, it "plays music with a theta wave frequency after collecting alpha wave information from the human brain waves; plays music with a delta wave frequency after collecting theta wave information from the human brain waves; stops music playing and stops collecting human brain waves after collecting delta wave information from the human brain waves", simply decides to play music with a corresponding frequency after recognizing the corresponding wave brain wave, and although it is assisted by heart rate and respiration rate monitoring, it does not take into account the complexity of various brain wave types at the same time, as well as the difference in dominance caused by the different proportions of different wave brain waves in brain wave signals, so there may be problems of detection conflict and unclear decision-making, and the sleep-aiding effect needs to be improved.

[0006] External current stimulation of a certain intensity to put the human body to sleep is prone to use safety problems after the user enters deep sleep because the electrode patch directly contacts the human body.

[0007] The sleep-aiding method relying on external vibration has a higher current advantage, but there is still room for improvement:

[0008] Patent No. 202310108639.0 proposes a "sleep state and sleep staging monitoring method, device and terminal equipment", which relies on an analysis model trained based on historical brain data and historical blood oxygen data to identify electroencephalogram and blood oxygen data to determine the sleep state. This method increases the analysis model of electroencephalogram and blood sample data, solves the problem of simple reliance on detection data for decision-making, but has a high dependence on the pre-set training sample, and does not consider the difference in human brain structure, and ignores the problem of whether the training sample matches the user, and the monitoring effect needs to be improved.

[0009] Patent No. CN202210790594.5 proposes a "sleep control system and method based on shaking stimulation", which considers the difference in human brain structure and performs near-real-time shaking stimulation control, but the external stimulation is shaking stimulation, and the vibration direction is mainly horizontal. The scientific literature published by De Lucia (1969) entitled "To rock or not to rock that is the question" shows that vertical vibration has a better stimulation effect on sleep than shaking. In addition, the sleep feature value extraction index proposed by this patent has weak correlation with the sleep staging result, and cannot well guide the design of incentive input parameters, and may even be counterproductive, causing the hypnotic bed to become a noise bed, and its sleep-aiding effect needs to be improved.

[0010] In summary, the sleep instruments or sleep beds and other auxiliary hypnotic products currently available on the market not only have a single stimulation factor (music, current or vibration), but also mostly use fixed values for key parameters of hypnotic effect (vibration frequency, vibration amplitude, music type, loudness, etc.), lacking personalized design, and their hypnotic effect needs to be improved. SUMMARY

[0011] Therefore, the embodiments of the present application provide a personalized sleep-aiding system and method, which realize the fusion of hearing and feeling, and can calibrate key parameters of hypnotic effect for different users, improve the hypnotic effect, and improve the sleep quality of users.

[0012] To achieve the above object, the embodiments of the present application provide the following solutions:

[0013] The personalized sleep-aiding system comprises a vibration calibration system, a sound calibration system and a sleep-aiding module; the vibration calibration system and the sound calibration system are connected with the sleep-aiding module.

[0014] The vibration calibration system is configured to:

[0015] When the current vibration stimulation signal is applied to the user, a current vibration stimulation electroencephalogram of the user is collected, and a current first sleep relative energy index is determined according to the current vibration stimulation electroencephalogram; the first sleep relative energy index represents energy proportions of theta waves and delta waves in the vibration stimulation electroencephalogram.

[0016] If the current first sleep relative energy index is greater than a set first maximum energy proportion, the current vibration stimulation signal is taken as an optimal vibration stimulation signal, otherwise, the frequency and amplitude of the current vibration stimulation signal are adjusted until the optimal vibration stimulation signal is obtained.

[0017] The sound calibration system is configured to:

[0018] When the current sound stimulation signal is applied to the user, a current sound stimulation electroencephalogram of the user is collected, and a current second sleep relative energy index is determined according to the current sound stimulation electroencephalogram; the second sleep relative energy index represents energy proportions of theta waves and delta waves in the sound stimulation electroencephalogram.

[0019] If the current second sleep relative energy index is greater than a set second maximum energy proportion, the current sound stimulation signal is taken as an optimal sound stimulation signal, otherwise, the sound type and loudness of the current sound stimulation signal are adjusted until the optimal sound stimulation signal is obtained.

[0020] The sleep-aiding module is configured to:

[0021] Optimal hypnosis effect key parameters of each user are obtained; the optimal hypnosis effect key parameters comprise optimal vibration parameters and / or optimal sound parameters; the optimal vibration parameters comprise the frequency and amplitude of the optimal vibration stimulation signal; the optimal sound parameters comprise the sound type and loudness of the optimal sound stimulation signal.

[0022] When a target user needs sleep aid, the optimal hypnosis effect key parameters of the target user are determined from the optimal hypnosis effect key parameters of each user, and a corresponding stimulation signal is generated according to the optimal hypnosis effect key parameters of the target user to realize sleep aid for the target user.

[0023] Optionally, the vibration calibration system comprises:

[0024] The first electroencephalogram collection module is configured to:

[0025] collecting a current vibration-induced electroencephalogram signal of a user;

[0026] a first electroencephalogram signal denoising module, configured to:

[0027] performing multi-layer wavelet decomposition on the current vibration-induced electroencephalogram signal, performing soft threshold function processing on the decomposed vibration-induced electroencephalogram signal, and performing multi-layer wavelet reconstruction on the processed vibration-induced electroencephalogram signal to obtain a denoised vibration-induced electroencephalogram signal;

[0028] extracting a rhythm wave in the denoised vibration-induced electroencephalogram signal by using a wavelet packet decomposition method to obtain a first rhythm wave;

[0029] a first personalized hypnosis feature design module, configured to:

[0030] calculating a proportion of energy of a theta wave and a delta wave in the first rhythm wave in total energy to obtain a current first sleep relative energy index; the total energy is a sum of energy of an alpha wave, a beta wave, the theta wave and the delta wave;

[0031] a first feedback adjustment module, configured to:

[0032] determining whether the current first sleep relative energy index is greater than a set first maximum energy proportion, if yes, outputting the current vibration-induced signal as an optimal vibration-induced signal, otherwise, adjusting a frequency and an amplitude of the current vibration-induced signal, and returning the vibration-induced signal with the adjusted frequency and amplitude to the first electroencephalogram signal collecting module.

[0033] Optionally, the sound calibration system comprises:

[0034] a second electroencephalogram signal collecting module, configured to:

[0035] collecting a current sound-induced electroencephalogram signal of a user;

[0036] a second electroencephalogram signal denoising module, configured to:

[0037] performing multi-layer wavelet decomposition on the current sound-induced electroencephalogram signal, performing soft threshold function processing on the decomposed sound-induced electroencephalogram signal, and performing multi-layer wavelet reconstruction on the processed sound-induced electroencephalogram signal to obtain a denoised sound-induced electroencephalogram signal;

[0038] extracting a rhythm wave in the denoised sound-induced electroencephalogram signal by using a wavelet packet decomposition method to obtain a second rhythm wave;

[0039] a second personalized hypnosis feature design module, configured to:

[0040] The proportion of energy of the theta wave and the delta wave in the second rhythm wave in total energy is calculated to obtain a current second sleep relative energy index; the total energy is a sum of energy of the alpha wave, the beta wave, the theta wave and the delta wave;

[0041] The second feedback adjustment module is configured to:

[0042] If the current second sleep relative energy index is greater than the second maximum energy proportion, the current sound excitation signal is output as an optimal sound excitation signal; otherwise, the sound type and the loudness of the current sound excitation signal are adjusted, and the sound excitation signal after the sound type and the loudness adjustment is returned to the second electroencephalogram signal collection module.

[0043] Optionally, the vibration calibration system further comprises:

[0044] The vibration parameter adjustment range setting module is configured to set a frequency range and an amplitude range of the vibration excitation signal.

[0045] In terms of adjusting the frequency and the amplitude of the current vibration excitation signal, the first feedback adjustment module is specifically configured to:

[0046] The frequency and the amplitude of the current vibration excitation signal are adjusted in the frequency range and the amplitude range with a set frequency step and a set amplitude step.

[0047] Optionally, the sound calibration system further comprises:

[0048] The sound parameter adjustment range setting module is configured to set a sound type range and a loudness range of the sound excitation signal.

[0049] In terms of adjusting the sound type and the loudness of the current sound excitation signal, the second feedback adjustment module is specifically configured to:

[0050] The sound type and the loudness of the current sound excitation signal are adjusted in the sound type range and the loudness range with a set loudness step.

[0051] Optionally, the initial frequency of the vibration excitation signal is 8 Hz; the initial amplitude of the vibration excitation signal is 1 cm; the frequency range is 0-30 Hz; the amplitude range is 0-3 cm; the frequency step is 1 Hz; and the amplitude step is 0.01 cm.

[0052] Optionally, the sound type range is baroque instrumental music, human vocal music and sounds in nature; the loudness range is 1-5 sone; and the loudness step is 0.1 sone.

[0053] Optionally, the first maximum energy proportion is 0.9; and the second maximum energy proportion is 0.85.

[0054] Optionally, the personalized sleep-aiding system further comprises a cloud APP; the cloud APP is configured to store the optimal hypnosis effect key parameters of each user.

[0055] The application further provides a personalized sleep-aiding method, which is implemented by using the above-mentioned personalized sleep-aiding system; the method comprises the following steps of:

[0056] obtaining the optimal hypnosis effect key parameters of each user; the optimal hypnosis effect key parameters comprise optimal vibration parameters and / or optimal sound parameters; the optimal vibration parameters comprise the frequency and amplitude of the optimal vibration excitation signal; the optimal sound parameters comprise the sound type and loudness of the optimal sound excitation signal;

[0057] when a target user needs sleep aid, determining the optimal hypnosis effect key parameters of the target user from the optimal hypnosis effect key parameters of each user, generating corresponding excitation signals according to the optimal hypnosis effect key parameters of the target user, and achieving sleep aid for the target user;

[0058] wherein the determination method of the optimal vibration excitation signal is as follows:

[0059] when the current vibration excitation signal is applied to the user, the current vibration excitation brain electrical signal of the user is collected, and the current first sleep relative energy index is determined according to the current vibration excitation brain electrical signal; the first sleep relative energy index represents the energy proportion of theta waves and delta waves in the vibration excitation brain electrical signal;

[0060] if the current first sleep relative energy index is greater than the set first maximum energy proportion, the current vibration excitation signal is taken as the optimal vibration excitation signal, otherwise, the frequency and amplitude of the current vibration excitation signal are adjusted until the optimal vibration excitation signal is obtained;

[0061] wherein the determination method of the optimal sound excitation signal is as follows:

[0062] when the current sound excitation signal is applied to the user, the current sound excitation brain electrical signal of the user is collected, and the current second sleep relative energy index is determined according to the current sound excitation brain electrical signal; the second sleep relative energy index represents the energy proportion of theta waves and delta waves in the sound excitation brain electrical signal;

[0063] if the current second sleep relative energy index is greater than the set second maximum energy proportion, the current sound excitation signal is taken as the optimal sound excitation signal, otherwise, the sound type and loudness of the current sound excitation signal are adjusted until the optimal sound excitation signal is obtained.

[0064] According to the specific embodiments of the application, the following technical effects are achieved:

[0065] The vibration calibration system of the embodiment extracts a sleep relative energy index of a vibration excitation electroencephalogram signal, adjusts the frequency and amplitude of the vibration excitation signal according to the sleep relative energy index, finds an optimal vibration excitation signal, and completes vibration calibration; the sound calibration system extracts a sleep relative energy index of a sound excitation electroencephalogram signal, adjusts the sound type and loudness of the sound excitation signal according to the sleep relative energy index, finds a sound vibration excitation signal, and completes sound calibration; after the vibration calibration and the sound calibration are completed, the sleep-aiding module can generate a corresponding excitation signal according to the optimal hypnotic effect key parameter of a user, and realize sleep aiding. The embodiment realizes a hearing-sensing fusion compound, and can realize calibration of a hypnotic effect key parameter, improve the hypnotic effect, and improve the sleep quality of the user. BRIEF DESCRIPTION OF DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described in the following are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0067] Figure 1 The structure diagram of the personalized sleep-aiding system provided by the embodiment of the present application is shown in the figure.

[0068] Figure 2 The multi-layer wavelet decomposition block diagram of the original electroencephalogram signal provided by the embodiment of the present application is shown in the figure.

[0069] Figure 3 The flowchart of the design of the personalized hypnotic feature design module provided by the embodiment of the present application is shown in the figure.

[0070] Figure 4 The processing flowchart of the vibration calibration system provided by the embodiment of the present application is shown in the figure.

[0071] Figure 5 The processing flowchart of the sound calibration system provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0072] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0073] In order to make the above objectives, characteristics and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0074] Embodiment one

[0075] The sleep instrument or sleep bed and other auxiliary sleep products existing in the market currently use fixed amplitude and frequency excitation, lack personalized design, and the sleep effect thereof needs to be discussed. The present application realizes personalized sleep aid based on a sleep feature recognition and closed-loop control method, and through design of a vibration calibration system and a sound calibration system, calibration of key parameters (frequency, amplitude, sound type, loudness, etc.) of an optimal sleep aid effect of a user is completed, aiming to escort the sleep of a unique individual.

[0076] Referring to Figure 1 The personalized sleep aid system of the embodiment comprises a vibration calibration system, a sound calibration system and a sleep aid module; the vibration calibration system and the sound calibration system are connected with the sleep aid module.

[0077] The vibration calibration system is used for:

[0078] When the current vibration excitation signal is applied to the user, the current vibration excitation electroencephalogram of the user is collected, and a current first sleep relative energy index is determined according to the current vibration excitation electroencephalogram; the first sleep relative energy index represents the energy proportion of theta waves and delta waves in the vibration excitation electroencephalogram.

[0079] If the current first sleep relative energy index is greater than a set first maximum energy proportion, the current vibration excitation signal is taken as an optimal vibration excitation signal, otherwise, the frequency and amplitude of the current vibration excitation signal are adjusted until the optimal vibration excitation signal is obtained.

[0080] The sound calibration system is used for:

[0081] When the current sound excitation signal is applied to the user, the current sound excitation electroencephalogram of the user is collected, and a current second sleep relative energy index is determined according to the current sound excitation electroencephalogram; the second sleep relative energy index represents the energy proportion of theta waves and delta waves in the sound excitation electroencephalogram.

[0082] If the current second sleep relative energy index is greater than a set second maximum energy proportion, the current sound excitation signal is taken as an optimal sound excitation signal, otherwise, the sound type and loudness of the current sound excitation signal are adjusted until the optimal sound excitation signal is obtained.

[0083] The sleep aid module is used for:

[0084] Obtaining optimal hypnosis effect key parameters of each user; the optimal hypnosis effect key parameters include optimal vibration parameters and / or optimal sound parameters; the optimal vibration parameters include the frequency and amplitude of the optimal vibration excitation signal; the optimal sound parameters include the sound type and loudness of the optimal sound excitation signal.

[0085] When the target user needs sleep aid, the optimal hypnosis effect key parameters of the target user are determined from the optimal hypnosis effect key parameters of each user, and the corresponding excitation signal is generated based on the optimal hypnosis effect key parameters of the target user to achieve sleep aid for the target user.

[0086] In one example, the vibration calibration system comprises:

[0087] The first brain electrical signal acquisition module is configured to acquire the current vibration excitation brain electrical signal of the user.

[0088] The first brain electrical signal denoising module is configured to perform multi-layer wavelet decomposition on the current vibration excitation brain electrical signal, process the decomposed vibration excitation brain electrical signal using a soft threshold function, and perform multi-layer wavelet reconstruction on the processed vibration excitation brain electrical signal to obtain a denoised vibration excitation brain electrical signal. The rhythm wave in the denoised vibration excitation brain electrical signal is extracted using a wavelet packet decomposition method to obtain a first rhythm wave.

[0089] The first personalized hypnosis feature design module is configured to calculate the proportion of the energy of the theta wave and the delta wave in the first rhythm wave in the total energy to obtain a current first sleep relative energy index; the total energy is the sum of the energy of the alpha wave, the beta wave, the theta wave, and the delta wave.

[0090] The first feedback adjustment module is configured to determine whether the current first sleep relative energy index is greater than a set first maximum energy proportion, and if so, output the current vibration excitation signal as an optimal vibration excitation signal, otherwise, adjust the frequency and amplitude of the current vibration excitation signal, and return the vibration excitation signal with the adjusted frequency and amplitude to the first brain electrical signal acquisition module. In an example, the first maximum energy proportion can be set to 0.9.

[0091] In one example, the sound calibration system comprises:

[0092] The second brain electrical signal acquisition module is configured to acquire the current sound excitation brain electrical signal of the user.

[0093] The second brain electrical signal denoising module is configured to:

[0094] The current sound-stimulated electroencephalogram signal is subjected to multi-layer wavelet decomposition, the sound-stimulated electroencephalogram signal after decomposition is processed by using a soft threshold function, and the sound-stimulated electroencephalogram signal after processing is subjected to multi-layer wavelet reconstruction to obtain a sound-stimulated electroencephalogram signal after denoising. The rhythm wave in the sound-stimulated electroencephalogram signal after denoising is extracted by using the wavelet packet decomposition method to obtain a second rhythm wave.

[0095] The second personalized hypnosis feature design module is configured to: calculate the proportion of the energy of the theta wave and the delta wave in the second rhythm wave in the total energy to obtain a current second sleep relative energy index.

[0096] The second feedback adjustment module is configured to: determine whether the current second sleep relative energy index is greater than a set second maximum energy proportion, if yes, output the current sound-stimulated signal as an optimal sound-stimulated signal, otherwise, adjust the sound type and loudness of the current sound-stimulated signal, and return the sound-stimulated signal after adjusting the sound type and loudness to the second electroencephalogram signal acquisition module. Illustratively, the second maximum energy proportion can be set to 0.85.

[0097] In one example, the vibration calibration system further comprises a vibration parameter adjustment range setting module configured to set a frequency range and an amplitude range of the vibration-stimulated signal.

[0098] In adjusting the frequency and amplitude of the current vibration-stimulated signal, the first feedback adjustment module is specifically configured to: adjust the frequency and amplitude of the current vibration-stimulated signal by a set frequency step and a set amplitude step within the frequency range and the amplitude range.

[0099] The values of specific parameters of the vibration calibration system can be selected according to actual needs. For example, the initial frequency of the vibration-stimulated signal can be 8 Hz; the initial amplitude of the vibration-stimulated signal can be 1 cm; the frequency range can be 0-30 Hz; the amplitude range can be 0-3 cm; the frequency step can be 1 Hz; and the amplitude step can be 0.01 cm.

[0100] In one example, the sound calibration system further comprises a sound parameter adjustment range setting module configured to set a sound type range and a loudness range of the sound-stimulated signal.

[0101] In adjusting the sound type and loudness of the current sound-stimulated signal, the second feedback adjustment module is specifically configured to: adjust the sound type and loudness of the current sound-stimulated signal by a set loudness step within the sound type range and the loudness range.

[0102] The values of the specific parameters of the sound calibration system can be selected according to actual needs. For example, the sound type range can be baroque instrumental music, human vocal music and natural sounds; the loudness range can be 1-5 sone; and the loudness step can be 0.1 sone.

[0103] In one example, the personalized sleep-aiding system further comprises a cloud APP, and the cloud APP is configured to store the optimal hypnosis effect key parameters of each user.

[0104] A more specific embodiment is given below to further introduce the above-mentioned personalized sleep-aiding system in detail.

[0105] First, each module in the vibration calibration system and the sound calibration system is described. The first and second electroencephalogram signal acquisition modules are collectively referred to as the electroencephalogram signal acquisition module; the first and second electroencephalogram signal denoising modules are collectively referred to as the electroencephalogram signal denoising module; the first and second personalized hypnosis feature design modules are collectively referred to as the personalized hypnosis feature design module; and the first and second feedback adjustment modules are collectively referred to as the feedback adjustment module.

[0106] The electroencephalogram signal acquisition module is based on an electroencephalogram acquisition system, with a sampling frequency of 256-1000 Hz, a resolution of 24 Bits, and an input impedance higher than 50 GΩ. The electroencephalogram signal acquisition module includes an electroencephalogram acquisition sensor, which does not require gel and is designed to be worn on the human body, greatly improving the comfort of the individual testing process. The user wears the electrode cap and lies on the sleep bed; under the initial vibration (frequency 8 Hz, amplitude 1 cm) and sound (sound type selected as natural flowing water sound, loudness 1 sone) compound excitation, the individual's electroencephalogram signal is collected.

[0107] The original electroencephalogram signal has the characteristics of strong nonlinearity, non-stationarity and complex composition. The electroencephalogram signal denoising module preprocesses the original electroencephalogram signal to extract the rhythm wave that can reflect the sleep staging of the human body.

[0108] Wavelet transform is widely used in electroencephalogram signal processing field due to its multi-resolution, diversity of basis functions and other advantages. In this specific example, the original electroencephalogram signal is denoised by wavelet soft threshold method, and the low frequency rhythm wave closely related to sleep staging research is extracted by wavelet packet decomposition. The specific implementation process of the electroencephalogram signal denoising module is as follows:

[0109] Step 1: Denoising the original electroencephalogram signal by wavelet decomposition. In this specific example, Morlet wavelet basis function and 3 layers of wavelet decomposition are selected, and the original electroencephalogram signal is decomposed into three layers in Matlab. The expression of Morlet wavelet basis function is as follows:

[0110]

[0111] wherein ψ represents the Morlet wavelet function expression, f represents the frequency, ξ represents the damping ratio, τ represents the time parameter, and t represents any time in the time series.

[0112] The original brain electrical signal multilayer wavelet decomposition block diagram is shown in Figure 2 Figure 2 The (1, 0), (2, 0), (3, 0) represent the low frequency signals of the first layer, the second layer, and the third layer respectively; (1, 1), (2, 1), (3, 1) represent the high frequency signals of the first layer, the second layer, and the third layer respectively. The original brain electrical signal can be represented as (0, 0) = (3, 0) + (3, 1) + (2, 1) + (1, 1).

[0113] Step 2: Select a soft threshold function to threshold the coefficients of the low frequency and high frequency signals of each layer after decomposition. The soft threshold function expression is as follows:

[0114]

[0115] wherein x represents the coefficient before denoising, x den represents the coefficient after denoising, and λ represents the threshold. The soft threshold function is to retain the decomposition coefficients with smaller absolute values.

[0116] Step 3: Use the Mallat decomposition method in the discrete wavelet transform to reconstruct the non-zero decomposition coefficients after processing, to obtain the denoised brain electrical signal. The Mallat decomposition reconstruction formula is as follows:

[0117]

[0118] wherein n represents the total number of sampling points, j represents the number of decomposition layers, k is the scale coefficient, A j (n) represents the brain electrical signal obtained after reconstruction (i.e. the denoised brain electrical signal), A j+1 (n) represents the brain electrical low frequency signal before reconstruction, i.e. the brain electrical low frequency signal of the upper layer, D j+1 (n) represents the brain electrical high frequency signal before reconstruction, i.e. the brain electrical high frequency signal of the upper layer, * represents convolution, h(n), h(n-2k) represent the wavelet reconstruction low pass filter coefficients under two adjacent scale coefficients, and g(n), g(n-2k) represent the wavelet reconstruction high pass filter coefficients under two adjacent scale coefficients.

[0119] ​Step 4: The denoised electroencephalogram signal is processed by wavelet packet decomposition to extract rhythm waves strongly related to sleep staging, which are used as input signals of the individualized hypnosis feature design module. The wavelet transform theory has been relatively mature, and the wavelet base function selected in this embodiment is Morlet wavelet, and the wavelet packet decomposition layer is 6.

[0120] The electroencephalogram signal denoising module extracts four kinds of rhythm waves, namely δ wave, θ wave, α wave and β wave. When the brain is in a drowsy state or enters deep sleep, δ wave and θ wave appear in large quantities in the electroencephalogram signal. Based on this rule, a hypnosis relative energy index is proposed. The flow chart of the individualized hypnosis feature design module is shown in Figure 3 .

[0121] In combination with Figure 3 , the individualized sleep feature design module is described as follows: 1) Calculate the energy of the denoised electroencephalogram signal, i.e. total energy E. 2) Calculate the total energy of active δ wave and θ wave in deep sleep, i.e. E(θ) + E(δ). 3) Calculate the sleep relative energy index E opt in this embodiment. The calculation formula is as follows:

[0122]

[0123]

[0124]

[0125] wherein n represents the total number of sampling points, x i represents the amplitude of the denoised electroencephalogram signal at sampling point i, x θi and x δi represent the amplitude of the extracted θ wave and the amplitude of the extracted δ wave at each sampling point, respectively; and E(θ) and E(δ) represent the energy of the δ wave and the energy of the θ wave, respectively.

[0126] The vibration calibration system mainly obtains the vibration frequency and amplitude required for the optimal hypnosis effect of different individuals. The specific measure is that the test personnel wear an electrode cap on the sleep bed, and are subjected to vibrations of different frequencies and amplitudes, and the optimal frequency and amplitude are determined according to the hypnosis relative energy index of the electroencephalogram signal. The processing flow of the vibration calibration system is shown in Figure 4 .

[0127] The sound calibration system mainly completes the sound type and loudness of the optimal hypnosis effect of different individuals. The processing flow of the sound calibration system is shown in Figure 5The vibration calibration system and the sound calibration system fuse physiological perception and hearing to form a sleep bed personalized recognition system with hearing-sensation combination, and determine physiological perception parameters (frequency, amplitude) and hearing parameters (sound type including baroque instrumental music, human music and natural sounds such as flowing water and rain, and loudness) based on the proposed relative energy index feedback of hypnosis.

[0128] The vibration calibration system of the embodiment realizes the best hypnosis effect for different users, and completes the calibration of the frequency and amplitude key parameters of the excitation input. The sound calibration system realizes the best hypnosis effect for different users, and completes the calibration of the sound type (instrumental sound, human voice, natural sound, etc.) and sound loudness. Specifically, the vibration calibration system and the sound calibration system each consist of three modules, namely, an electroencephalogram signal acquisition module, an electroencephalogram signal denoising module, and a personalized hypnosis feature index design module. First, the electroencephalogram signal of the user is acquired. Then, the original electroencephalogram signal is subjected to wavelet denoising processing, and the rhythm wave strongly related to human sleep staging research is extracted through wavelet packet decomposition. Based on the extracted rhythm wave, the relative energy index of hypnosis is calculated. The present application is a hearing-sensation fusion personalized composite recognition, which considers the internal and external composite bidirectional input of vibration (frequency, amplitude) and sound (sound type, loudness), and multi-directional and stereoscopic stimulation of the resonance of delta wave and theta wave in the rhythm wave, so as to realize the best hypnosis effect of the user. For different users, the relative energy index of hypnosis is used to guide the recognition and calibration of important sleep feature parameters (frequency, amplitude, sound type, and loudness) of the vibration calibration system and the sound calibration system in a closed loop. After the calibration is completed, the results are uploaded to the personal cloud account, and the user can call the results at any time through the APP of the mobile phone.

[0129] In actual application, the above-mentioned personalized sleep aid system realizes the sleep aid process based on the relative energy index of hypnosis as follows:

[0130] 1) Vibration calibration system: the individual wears the electrode cap, lies flat on the sleep bed, and sets the initial vibration excitation frequency to 8 Hz and the amplitude to 1 cm. After the processing of the electroencephalogram signal acquisition module, the electroencephalogram signal denoising module, and the personalized hypnosis feature index design module, the output relative energy index of hypnosis is compared with the preset maximum energy proportion of hypnosis 0.9. If the output relative energy index of hypnosis is greater than 0.9, the set frequency and amplitude parameters are output. If the output relative energy index of hypnosis is less than 0.9, the input frequency and amplitude are adjusted. The vibration calibration system parameter setting frequency range is 0-30 Hz with a step of 1 Hz, and the amplitude range is 0-3 cm with a step of 0.01 cm. The grid search is performed within the set frequency and amplitude range, and the step is increased successively until the output relative energy index of hypnosis is greater than 0.9, that is, the optimal vibration parameters (frequency, amplitude) are output.

[0131] 2) Sound calibration system: the individual wears the electrode cap, lies on the sleep bed, sets the sound type natural flowing water sound, loudness 1 sone, and after the processing of the electroencephalogram signal acquisition module, the electroencephalogram signal denoising module, and the personalized hypnosis characteristic index design module, the output hypnosis relative energy index is compared with the pre-set hypnosis maximum energy proportion value 0.85, if the output hypnosis relative energy index is greater than 0.85, the set sound type and loudness parameters are output; if the output hypnosis relative energy index is less than 0.85, the input sound type and loudness are adjusted and fed back. The sound calibration system sets the sound type to include baroque instrumental music, human voice music and natural sounds such as flowing water and rain, and 20 kinds of sound types; the loudness range is 1-5 sone, and the step size is 0.1 sone. Grid search is performed within the sound type and loudness setting range, and the step size is increased one by one until the output hypnosis relative energy index is greater than 0.85, that is, the optimal sound parameters (sound type, loudness) are output.

[0132] The individualized sleep characteristic recognition of the sound- sensation fusion system is completed for different individuals, that is, the optimal vibration parameters (frequency, amplitude) and (frequency, amplitude) are determined. The above-mentioned individualized parameters are uploaded to the cloud APP, and the individual can call at any time.

[0133] Embodiment two

[0134] In order to realize the system corresponding to the above-mentioned embodiment one, the following provides an individualized sleep aid method to obtain the corresponding functions and technical effects.

[0135] The method comprises:

[0136] (1) obtaining the optimal hypnosis effect key parameters of each user; the optimal hypnosis effect key parameters include optimal vibration parameters and / or optimal sound parameters; the optimal vibration parameters include the frequency and amplitude of the optimal vibration excitation signal; the optimal sound parameters include the sound type and loudness of the optimal sound excitation signal.

[0137] (2) when the target user needs sleep aid, determining the optimal hypnosis effect key parameters of the target user from the optimal hypnosis effect key parameters of each user, generating corresponding excitation signals with the optimal hypnosis effect key parameters of the target user, and realizing sleep aid for the target user.

[0138] The determination method of the optimal vibration excitation signal is:

[0139] When the current vibration excitation signal is applied to the user, the current vibration excitation electroencephalogram signal of the user is collected, and the current first sleep relative energy index is determined according to the current vibration excitation electroencephalogram signal; the first sleep relative energy index represents the energy proportion of theta waves and delta waves in the vibration excitation electroencephalogram signal.

[0140] If the current first sleep relative energy index is greater than the set first maximum energy ratio, the current vibration excitation signal is taken as the optimal vibration excitation signal, otherwise, the frequency and amplitude of the current vibration excitation signal are adjusted until the optimal vibration excitation signal is obtained.

[0141] The method for determining the optimal sound excitation signal comprises the following steps:

[0142] When the current sound excitation signal is applied to the user, the current sound excitation EEG signal of the user is collected, and the current second sleep relative energy index is determined according to the current sound excitation EEG signal; the second sleep relative energy index represents the energy ratio of theta waves and delta waves in the sound excitation EEG signal.

[0143] If the current second sleep relative energy index is greater than the set second maximum energy ratio, the current sound excitation signal is taken as the optimal sound excitation signal, otherwise, the sound type and loudness of the current sound excitation signal are adjusted until the optimal sound excitation signal is obtained.

[0144] The embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts of each embodiment can be referred to each other. For the method disclosed by the embodiments, since it corresponds to the system disclosed by the embodiments, the description is relatively simple, and the relevant part can be referred to the system part.

[0145] The principles and implementation manners of the present application are described by using specific examples. The above description of the embodiments is only used to help understand the method of the present application and its core idea. For those skilled in the art, according to the idea of the present application, the specific implementation manner and application range can be changed. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A personalized sleep aid system, characterized in that, include: The system includes a vibration calibration system, a sound calibration system, and a sleep aid module; both the vibration calibration system and the sound calibration system are connected to the sleep aid module. The vibration calibration system is used for: When the current vibration stimulation signal is applied to the user, the user's current vibration stimulation EEG signal is collected, and the current first sleep relative energy index is determined based on the current vibration stimulation EEG signal; the first sleep relative energy index characterizes the energy ratio of theta waves and delta waves in the vibration stimulation EEG signal; If the current first sleep relative energy index is greater than the set first maximum energy ratio, then the current vibration excitation signal is taken as the optimal vibration excitation signal; otherwise, the frequency and amplitude of the current vibration excitation signal are adjusted until the optimal vibration excitation signal is obtained. The sound calibration system is used for: When the current sound stimulus signal is applied to the user, the user's current sound stimulus EEG signal is collected, and the current second sleep relative energy index is determined based on the current sound stimulus EEG signal; the second sleep relative energy index characterizes the energy ratio of theta waves and delta waves in the sound stimulus EEG signal; If the current second sleep relative energy index is greater than the set second maximum energy ratio, then the current sound excitation signal is taken as the optimal sound excitation signal; otherwise, the sound type and loudness of the current sound excitation signal are adjusted until the optimal sound excitation signal is obtained. The sleep aid module is used for: Obtain the key parameters for optimal hypnotic effect for each user; The key parameters for the optimal hypnotic effect include: optimal vibration parameters and / or optimal sound parameters; the optimal vibration parameters include: the frequency and amplitude of the optimal vibration excitation signal; the optimal sound parameters include: the sound type and loudness of the optimal sound excitation signal. When a target user needs sleep aid, the optimal hypnotic effect key parameters for the target user are determined from the optimal hypnotic effect key parameters of each user. The corresponding stimulus signals are generated based on the optimal hypnotic effect key parameters for the target user to achieve sleep aid for the target user.

2. The personalized sleep aid system according to claim 1, characterized in that, The vibration calibration system includes: The first EEG signal acquisition module is used for: Collect the user's current vibration-induced EEG signals; The first EEG signal denoising module is used for: The current vibration-excited EEG signal is subjected to multi-level wavelet decomposition. The decomposed vibration-excited EEG signal is processed using a soft threshold function. The processed vibration-excited EEG signal is then reconstructed using multi-level wavelet decomposition to obtain the denoised vibration-excited EEG signal. The first rhythmic wave was obtained by extracting the rhythmic wave from the denoised vibration-excited EEG signal using wavelet packet decomposition. The first personalized hypnotic feature design module is used for: The proportion of the energy of theta waves and delta waves in the first rhythm wave is calculated to obtain the current first sleep relative energy index; the total energy is the sum of the energies of alpha waves, beta waves, theta waves, and delta waves; The first feedback adjustment module is used for: Determine whether the current first sleep relative energy index is greater than the set first maximum energy ratio. If so, output the current vibration excitation signal as the optimal vibration excitation signal. Otherwise, adjust the frequency and amplitude of the current vibration excitation signal and return the frequency and amplitude adjusted vibration excitation signal to the first EEG signal acquisition module.

3. The personalized sleep aid system according to claim 1, characterized in that, The sound calibration system includes: The second EEG signal acquisition module is used for: Collect the user's current voice-stimulated EEG signals; The second EEG signal denoising module is used for: The current sound-stimulated EEG signal is subjected to multi-level wavelet decomposition, the decomposed sound-stimulated EEG signal is processed using a soft threshold function, and the processed sound-stimulated EEG signal is reconstructed using multi-level wavelet to obtain the denoised sound-stimulated EEG signal. The second rhythmic wave was obtained by extracting the rhythmic wave from the denoised sound-excited EEG signal using wavelet packet decomposition. The second personalized hypnotic feature design module is used for: The proportion of the energy of theta waves and delta waves in the second rhythm wave is calculated to obtain the current second sleep relative energy index; the total energy is the sum of the energies of alpha waves, beta waves, theta waves, and delta waves. The second feedback adjustment module is used for: Determine whether the current second sleep relative energy index is greater than the set second maximum energy ratio. If so, output the current sound stimulus signal as the optimal sound stimulus signal. Otherwise, adjust the sound type and loudness of the current sound stimulus signal and return the sound stimulus signal with adjusted sound type and loudness to the second EEG signal acquisition module.

4. The personalized sleep aid system according to claim 2, characterized in that, The vibration calibration system also includes: The vibration parameter adjustment range setting module is used to set the frequency range and amplitude range of the vibration excitation signal; In adjusting the frequency and amplitude of the current vibration excitation signal, the first feedback adjustment module is specifically used for: The frequency and amplitude of the current vibration excitation signal are adjusted within the frequency range and amplitude range by a set frequency step size and a set amplitude step size.

5. The personalized sleep aid system according to claim 3, characterized in that, The sound calibration system further includes: The sound parameter adjustment range setting module is used to set the sound type range and loudness range of the sound excitation signal; In adjusting the sound type and loudness of the current sound excitation signal, the second feedback adjustment module is specifically used for: The sound type and loudness of the current sound excitation signal are adjusted within the range of sound type and the range of loudness by a set loudness step.

6. The personalized sleep aid system according to claim 4, characterized in that, The initial frequency of the vibration excitation signal is 8 Hz; the initial amplitude of the vibration excitation signal is 1 cm; the frequency range is 0–30 Hz; the amplitude range is 0–3 cm; the frequency step size is 1 Hz; and the amplitude step size is 0.01 cm.

7. The personalized sleep aid system according to claim 5, characterized in that, The sound type range is Baroque instrumental music, vocal music and natural sounds; the loudness range is 1 to 5 sone; the loudness step is 0.1 sone.

8. The personalized sleep aid system according to claim 1, characterized in that, The first maximum energy percentage is 0.9; the second maximum energy percentage is 0.

85.

9. The personalized sleep aid system according to claim 1, characterized in that, Also includes: The cloud-based app is used to store key parameters for optimal hypnotic effects for each user.

10. A personalized sleep aid method, characterized in that, The method is implemented using the personalized sleep aid system described in any one of claims 1-9; the method includes: Obtain the key parameters for optimal hypnotic effect for each user; the key parameters for optimal hypnotic effect include: optimal vibration parameters and / or optimal sound parameters; the optimal vibration parameters include: the frequency and amplitude of the optimal vibration excitation signal; the optimal sound parameters include: the sound type and loudness of the optimal sound excitation signal; When a target user needs sleep aid, the optimal hypnotic effect key parameters for the target user are determined from the optimal hypnotic effect key parameters of each user. The corresponding stimulus signals are generated based on the optimal hypnotic effect key parameters for the target user to achieve sleep aid for the target user. The method for determining the optimal vibration excitation signal is as follows: When the current vibration stimulation signal is applied to the user, the user's current vibration stimulation EEG signal is collected, and the current first sleep relative energy index is determined based on the current vibration stimulation EEG signal; the first sleep relative energy index characterizes the energy ratio of theta waves and delta waves in the vibration stimulation EEG signal; If the current first sleep relative energy index is greater than the set first maximum energy ratio, then the current vibration excitation signal is taken as the optimal vibration excitation signal; otherwise, the frequency and amplitude of the current vibration excitation signal are adjusted until the optimal vibration excitation signal is obtained. The method for determining the optimal sound excitation signal is as follows: When the current sound stimulus signal is applied to the user, the user's current sound stimulus EEG signal is collected, and the current second sleep relative energy index is determined based on the current sound stimulus EEG signal; the second sleep relative energy index characterizes the energy ratio of theta waves and delta waves in the sound stimulus EEG signal; If the current second sleep relative energy index is greater than the set second maximum energy ratio, then the current sound excitation signal is taken as the optimal sound excitation signal; otherwise, the sound type and loudness of the current sound excitation signal are adjusted until the optimal sound excitation signal is obtained.

Images