Self-adaptive neuro-regulation sleep optimization system and method, wearable device and medium

Abstract

The invention provides an adaptive neuro-regulation sleep optimization system and method, a wearable device and a medium, the adaptive neuro-regulation sleep optimization system comprises: an acquisition module configured to acquire an electroencephalogram signal of a user; the processing module is configured to determine a first nerve stimulation parameter based on the sleep stage where the electroencephalogram signal is located, and determine a second nerve stimulation parameter based on the phase characteristic of the electroencephalogram signal, and based on the first nerve stimulation parameter, the second nerve stimulation parameter and a preset stimulation signal parameter, correspondingly generating and outputting self-adaptive nerve stimulation signals of one or more stimulation types so as to adjust the nerve of the user and optimize sleep. According to the method, the nerve stimulation signal is generated in real time based on the electroencephalogram signal of the user, so that self-adaptive nerve regulation is performed on the user, and targeted sleep optimization can be performed on the user through the nerve stimulation signal.

Description

Technical Field

[0001] The present application belongs to the field of sleep health technology, and in particular, relates to an adaptive neural regulation sleep optimization system, method, wearable device and medium. Background Art

[0002] Sleep is an important requirement of human life and is essential for physical health, psychological balance and energy recovery. Good sleep not only makes people energetic, but also effectively supports the immune system, heart health and brain function. However, fast-paced life, high-pressure work, the popularity of electronic products and irregular work and rest have caused many people to face sleep problems.

[0003] At present, the intervention of sleep disorders mainly relies on drugs, but drugs may cause side effects and drug resistance, making it difficult to continuously improve sleep. There are mostly two types of health products on the market: sleep monitoring equipment and sleep intervention equipment, but there is a lack of closed-loop feedback between these two types of products, which makes it difficult to form a comprehensive and effective sleep optimization effect. Traditional sleep monitoring equipment is mostly suitable for hospitals. It is large in size and complicated to operate, and is not suitable for daily use; and wearable devices such as smart bracelets are also difficult to comprehensively improve sleep status due to insufficient monitoring accuracy and lack of effective intervention mechanisms. In addition, sleep intervention products usually use open-loop neural stimulation, but due to the lack of real-time feedback regulation, the sleep optimization effect is limited. Therefore, there is a need for a sleep optimization system based on adaptive neural regulation to help users improve sleep quality more effectively in daily life. Summary of the invention

[0004] The purpose of the present application is to provide an adaptive neural regulation sleep optimization system, method, wearable device and medium to solve the technical problem of how to perform adaptive neural regulation based on the user's EEG signals to optimize sleep.

[0005] In a first aspect, the present application provides an adaptive neuromodulation sleep optimization system, comprising: a collection module configured to collect EEG signals of a user;

[0006] The processing module is configured to determine a first neural stimulation parameter based on the sleep stage of the EEG signal, determine a second neural stimulation parameter based on the phase characteristics of the EEG signal, and generate and output adaptive neural stimulation signals of one or more stimulation categories based on the first neural stimulation parameter, the second neural stimulation parameter and preset stimulation signal parameters to adjust the user's neural optimization sleep.

[0007] In an implementation of the first aspect, the processing module determines the current sleep stage of the user based on the EEG signal, and determines a preset frequency and a preset amplitude adapted to the current sleep stage as the first neural stimulation parameter;

[0008] The processing module determines whether the current sleep stage has changed based on the EEG signal, and in response to the change of the current sleep stage, determines a preset frequency and a preset amplitude of the sleep stage after adaptation to the change as the first neural stimulation parameters; wherein different sleep stages correspond to their own adaptively matched first neural stimulation parameters; the first neural stimulation parameters include a neural stimulation frequency difference and a neural stimulation amplitude.

[0009] In an implementation of the first aspect, the processing module performs segmented processing on the EEG signal within a preset time window to obtain a plurality of segmented EEG signals;

[0010] The processing module determines the sleep stage of each of the EEG segmented signals to obtain a sleep stage determination result; if the count of the sleep stage determination results of the same type is greater than a preset threshold, and the sleep stage determination result of this type is different from the current sleep stage, it is determined that the current sleep stage has changed.

[0011] In an implementation of the first aspect, the processing module determines the user's current sleep stage based on the EEG signal, obtains a target frequency band adapted to the current sleep stage, obtains a phase characteristic of the EEG signal based on the target frequency band, and determines an induced phase as the second neural stimulation parameter based on the phase characteristic of the EEG signal and the evoked response potential delay of the neural stimulation signal.

[0012] In an implementation of the first aspect, the processing module obtains a first filtering phase offset generated after the EEG signal of the target frequency band is processed by the first filter, and obtains a second filtering phase offset generated after the frequency domain signal of the EEG signal of the target frequency band is processed by the second filter;

[0013] The processing module obtains the phase feature of the electroencephalogram signal based on the first filtering phase offset and the second filtering phase offset.

[0014] In an implementation of the first aspect, the processing module determines a first neural stimulation frequency and a second neural stimulation frequency based on the neural stimulation frequency difference, generates a first neural stimulation signal based on the first neural stimulation frequency and the neural stimulation amplitude, generates a second neural stimulation signal based on the second neural stimulation frequency and the neural stimulation amplitude, and generates the neural stimulation signal based on the first neural stimulation signal and the second neural stimulation signal;

[0015] The processing module outputs the neural stimulation signal based on the second neural stimulation parameter and the preset stimulation signal parameter; the preset stimulation signal parameter includes the output duration of the neural stimulation signal.

[0016] In an implementation of the first aspect, the neural stimulation signal includes one or more of an acoustic neural stimulation signal, a tactile neural stimulation signal, an electrical neural stimulation signal, and an optical neural stimulation signal.

[0017] In a second aspect, the present application provides a wearable device comprising: one or more sensors configured to collect biological signals of a user in real time; one or more processors; and one or more memories, wherein the memories store computer-readable codes, and when the computer-readable codes are executed by the one or more processors, the functions of the adaptive neural regulation sleep optimization system as described are implemented.

[0018] In a third aspect, the present application provides an adaptive neural regulation sleep optimization method, comprising: collecting EEG signals of a user; determining a first neural stimulation parameter based on the sleep stage of the EEG signal; determining a second neural stimulation parameter based on the phase characteristics of the EEG signal; and generating and outputting adaptive neural stimulation signals of one or more stimulation categories based on the first neural stimulation parameter, the second neural stimulation parameter and preset stimulation signal parameters to regulate the user's neural optimization sleep.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium having instructions stored thereon, which, when executed by a processor, causes the processor to execute the adaptive neural regulation sleep optimization system as described above.

[0020] As described above, the adaptive neural regulation sleep optimization system, method, wearable device and medium described in this application have the following beneficial effects:

[0021] On the one hand, the present application uses an adaptive neural regulation method to determine the first neural stimulation parameter based on the changing characteristics of the user's EEG signal in real time, thereby generating a neural stimulation signal, thereby realizing real-time generation of a neural stimulation signal based on the user's EEG signal, thereby performing adaptive neural regulation on the user, and further enabling targeted sleep optimization for the user through the neural stimulation signal.

[0022] On the other hand, the present application accurately extracts the phase characteristics of EEG to determine the second neural stimulation parameter, and then outputs a neural stimulation signal based on this, so that the evoked response potential of the neural stimulation signal can reach a peak value at a specified time, thereby improving the synchronization and stability between the neural stimulation signal and the user's intrinsic brain activity, and then being able to efficiently optimize the user's sleep through the neural stimulation signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 Shown is a schematic diagram of an implementation structure of the adaptive neural regulation sleep optimization system described in this application.

[0024] Figure 2 A schematic diagram of the principle of the adaptive neural regulation sleep optimization system described in an embodiment of the present application is shown.

[0025] Figure 3 Another principle schematic diagram of the adaptive neural regulation sleep optimization system described in an embodiment of the present application is shown.

[0026] Figure 4 Shown is a flow chart of the adaptive neural regulation sleep optimization method described in an embodiment of the present application.

[0027] Figure 5A Shown is a schematic diagram of an application scenario of the adaptive neural regulation sleep optimization method described in this application.

[0028] Figure 5B Shown is a schematic diagram of another application scenario of the adaptive neural regulation sleep optimization method described in this application.

[0029] Figure 6 Shown is a schematic diagram of the internal structure of the wearable device described in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0031] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0032] In addition, in this application, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0033] In today's society, the fast pace of life, heavy work pressure, the popularity of digital devices and irregular work and rest patterns have caused many people to encounter various sleep problems. Long-term sleep problems may seriously affect the physical and mental health of individuals. In order to solve these sleep problems, a variety of sleep intervention products have emerged on the market. For example, smart monitoring devices can monitor users' physical activities and heart rates in real time, and smart air purifiers improve the sleeping environment to promote better breathing and sleep quality. However, these products usually lack personalized control solutions, fail to provide real-time feedback, and cannot optimize sleep according to the user's actual status.

[0034] In order to at least solve the above technical problems, the embodiment of the present application provides an adaptive neural regulation sleep optimization system, which can generate neural stimulation signals in real time based on the user's EEG signals through adaptive neural regulation, so as to perform adaptive neural regulation on the user, and then can optimize the user's sleep in a targeted manner through neural stimulation signals. In addition, the present application accurately extracts the phase characteristics of the EEG to determine the time to output the neural stimulation signal, improves the synchronization and stability between the neural stimulation signal and the user's internal brain activity, and then can efficiently optimize the user's sleep through the neural stimulation signal.

[0035] Figure 1 The structure diagram of the adaptive neural regulation sleep optimization system provided by the embodiment of the present application is shown. Figure 1 As shown, the adaptive neural regulation sleep optimization system 1 includes a collection module 11 and a processing module 12 .

[0036] The acquisition module 11 is configured to acquire the user's EEG signals and send the acquired EEG signals to the processing module 12. The acquisition module 11 can be a wearable EEG signal acquisition device or a sensor device, and the wearable bio-signal acquisition device can be in any form such as a headband, a head cap, a head ring, an eye mask, etc., and this application does not impose any restrictions on this.

[0037] In some embodiments, the acquisition module 11 can collect the user's electroencephalogram (EEG) signals in real time through a brain-computer device. The acquisition area may include frontal electrodes Fp1, Fp2, F7, F8, Fpz, temporal lobe electrodes Tp9, Tp10, central electrodes C3, C4, Cz and occipital electrodes O1, O2, Oz.

[0038] In some embodiments, frontal electrodes Fp1, Fp2, F7, and F8 are selected to collect the user's EEG signals. The EEG signals include α wave, β wave, θ wave, and δ wave signals. Different EEG signals represent different activity states of the user's brain, for example, β wave corresponds to the excited state of the user's brain, α wave corresponds to the awake state of the user's brain, θ wave corresponds to the user's light sleep state, and δ wave corresponds to the user's deep sleep state.

[0039] The processing module 12 is configured to determine a first neural stimulation parameter based on the sleep stage of the EEG signal, determine a second neural stimulation parameter based on the phase characteristics of the EEG signal, and generate and output adaptive neural stimulation signals of one or more stimulation categories based on the first neural stimulation parameter, the second neural stimulation parameter and the preset stimulation signal parameter, so as to adaptively adjust the user's neural optimization sleep. In some embodiments, the processing module 12 can be an embedded hardware system or any type of chip with a processor, and the processing module 12 can be integrated with the acquisition module 11 into a wearable control device. In other embodiments, the processing module 12 can also be a separate hardware system that interacts with the acquisition module 11 to receive the biological signals collected by the acquisition module 11, and the present application does not impose any restrictions on this.

[0040] In some embodiments, the processing module 12 is also configured to pre-process the EEG signals collected by the acquisition module 11 to improve the signal-to-noise ratio of the EEG signals, thereby improving the signal quality. For example, the processing module 12 can perform re-reference, filtering, detrending, etc. on the collected EEG signals. Among them, the processing module 12 can use a 0.1-45Hz bandpass filter (such as a second-order Butterworth filter) to filter the collected EEG signals, and use a notch filter to filter out interference from the 50Hz power frequency and its harmonics. For the specific preprocessing method, this application is not limited to this. In addition, after the EEG signal is filtered, the processing module 12 will also perform 30-second segment processing on the filtered EEG signal to meet the format requirements of the data set.

[0041] Further, the processing module 12 determines the current sleep stage of the user based on the EEG signal, and determines the preset frequency and preset amplitude adapted to the current sleep stage as the first neural stimulation parameter. When the user begins to fall asleep, the user will usually experience 5 sleep stages in one sleep cycle, including Wake stage, N1 stage, N2 stage, N3 stage and REM stage. Among them, the user is awake during the Wake stage, and the EEG signal is α wave at this time. When the user enters the N1 stage, the user is in a light sleep state, and the EEG signal is related to theta wave, and α wave occasionally appears and the user is easy to wake up. When the user enters the N2 stage, short-term bursts of sleep spindles and K complex waves appear in the EEG signal. When the user enters the N3 stage, δ waves begin to be generated exclusively in the user's EEG signal, and at this time, the user enters a deep sleep state. When the user switches to the REM stage, it is often accompanied by eye movement, and the EEG signal is a fast, low-amplitude β wave. Therefore, the current sleep stage of the user can be judged based on the characteristics of the user's EEG signal. For example, when the user's electroencephalogram signal is a theta wave, it can be determined that the user's current sleep stage is stage N1.

[0042] In some embodiments, the processing module 12 can infer the filtered EEG signal through a machine learning algorithm to determine the current sleep stage of the user, that is, determine which sleep stage the user is currently in among the Wake stage, N1 stage, N2 stage, N3 stage and REM stage. This application does not impose any restrictions on the machine learning algorithm. For example, algorithms such as neural networks, attention mechanisms, decision trees, and support vector machines can be used to determine the current sleep stage of the user.

[0043] After determining the current sleep stage of the user, the processing module 12 determines the first neural stimulation parameter based on the preset frequency and preset amplitude adapted to the current sleep stage. That is, the first neural stimulation parameter actually corresponds to the preset frequency and preset amplitude of the current sleep stage of the user, and different sleep stages correspond to their own adaptively matched first neural stimulation parameters. In some embodiments, the first neural stimulation parameter includes a neural stimulation frequency difference and a neural stimulation amplitude.

[0044] Among them, for the neural stimulation frequency difference, it corresponds to the preset frequency of the current sleep stage. In some embodiments, a target frequency band can actually be specified for each sleep stage, and a preset frequency can be specified within the range of the target frequency band. That is, for each sleep stage, a target frequency band and a preset frequency with adaptive matching correspond to each stage. For example, for the Wake stage, the target frequency band can be specified as α wave, and the preset frequency can be set to any value within the band range of α wave, that is, any frequency value can be selected within 7.5-12.5Hz as the preset frequency corresponding to the Wake stage. For another example, for the N1 stage, the target frequency band can be specified as θ wave, and the preset frequency can be set to any value within the band range of θ wave, that is, any frequency value can be selected within 4.5-7.5Hz as the preset frequency corresponding to the N1 stage. For another example, for the N2 stage, the target frequency band can be specified as δ wave, and the preset frequency can be set to any value within the band range of δ wave, that is, any frequency value can be selected within 0.5-4.5Hz as the preset frequency corresponding to the N2 stage. When the sleep stage is N3 or REM, the user has actually entered a deep sleep state. At this time, sleep optimization for the user is no longer necessary, and there is no need to determine the target frequency.

[0045] In other embodiments, a target frequency band may be specified for each sleep stage to extract a personal center frequency, thereby using the personal center frequency as a preset frequency. That is, after the processing module 12 performs filtering processing on the EEG signal, it performs N-point sliding window processing, and uses fast Fourier transform to calculate the spectrum characteristics of the EEG signal in the target frequency band. Based on this, the frequency value with the highest frequency energy is extracted as the personal center frequency ICF, and the personal center frequency is the preset frequency corresponding to the current sleep stage. For example, if the target frequency band of the Wake period is specified as α wave, the spectrum characteristics of the α wave are obtained through the above process, and the frequency value with the highest frequency energy is extracted as the personal center frequency ICF, and the personal center frequency is the preset frequency of the Wake period.

[0046] Among them, for the neural stimulation amplitude, it corresponds to the preset amplitude of the current sleep stage. In some embodiments, different preset amplitudes can be set in advance for different sleep stages, and as the sleep cycle deepens, the corresponding preset amplitudes gradually decrease. For example, for the Wake stage, the preset amplitude can be set to 68dB, for the N1 stage, the preset amplitude can be set to 64dB, for the N2 stage, the preset amplitude can be set to 60dB, and when the sleep stage is the N3 stage or the REM stage, the user has actually entered a deep sleep state, and the user's sleep optimization can no longer be performed at this time. In other embodiments, only the preset amplitude of the Wake stage can be set, and as the sleep cycle deepens, the preset amplitude adapted to the sleep stage can be adjusted according to the set adjustment value. That is, when the user enters the next successive sleep stage, the preset amplitude will be adaptively adjusted downward by a percentage until the sleep optimization stops when entering the N3 stage or the REM stage. For another example, when the user returns from stage N3 or REM to stage N1 or N2, the preset amplitude will also be adaptively adjusted upward by one or two percentage points to help the user deepen their sleep. In other words, the preset amplitude is adaptively adjusted upward or downward according to the changes in the user's sleep stages.

[0047] When the adaptive neural regulation sleep optimization system provided in the embodiment of the present application starts to run, the acquisition module 11 starts to collect the user's EEG signals in real time, and the processing module 12 will determine the user's current sleep stage based on the EEG signals and determine the corresponding first neural stimulation parameters. In addition, during the operation of the entire system, the processing module 12 will also determine whether the user's sleep stage has changed in real time based on the EEG signals, and in response to the change of the current sleep stage, determine the preset frequency and preset amplitude of the sleep stage after the change as the first neural stimulation parameter. That is, the processing module 12 actually monitors the user's current sleep stage in real time, and when it is determined that the user's sleep stage has changed, it will immediately determine the first neural stimulation parameter corresponding to the changed sleep stage. In other words, in the adaptive neural regulation sleep optimization system provided in the embodiment of the present application, the processing module 12 repeatedly determines the user's current sleep stage based on the EEG signals collected by the acquisition module 11, and repeatedly determines the first neural stimulation parameters based on this, thereby realizing adaptive neural regulation based on the user's brain and improving the effectiveness of sleep optimization.

[0048] In order to determine whether the user's current sleep stage has changed, the processing module 12 performs segmented processing on the EEG signal within the preset time window, obtains multiple EEG segmented signals, and determines the sleep stage of each of the EEG segmented signals to obtain a sleep stage determination result. At this time, if the count of the sleep stage determination results of the same type is greater than the preset threshold, and the sleep stage determination result of this type is different from the current sleep stage, it is determined that the current sleep stage has changed.

[0049] In some embodiments, when the system starts running, the acquisition module 11 acquires the user's EEG signal, and the processing module 12 determines the user's current sleep stage. Afterwards, a 10-minute time window is preset. Since the data set format of the EEG signal is fixed to 30 seconds, there are 20 EEG segmented signals within the 10-minute time window. The sleep stages of these 20 EEG segmented signals are judged, and the judgment results of the sleep stages are obtained, including the Wake stage, REM stage, N1 stage, N2 stage or N3 stage. Afterwards, the judgment results of these 20 sleep stages are classified and counted. For example, within the 10-minute time window, there are 8 N1 stages, 10 Wake stages, and 2 N2 stages, and the classification and statistical results are 8, 10, and 2, respectively. In other embodiments, there may also be 20 Wake stages, and the count of the Wake stages is 20.

[0050] At this time, if the count of the same type of sleep stage judgment result is greater than the preset threshold, and the sleep stage judgment result of this type is different from the current sleep stage, it is determined that the current sleep stage has changed. For example, when the system is running, the user's current sleep stage is stage N1. If the count of one of the stages in the Wake stage, N2 stage, N3 stage or REM stage is greater than the preset threshold, it is considered that the user has entered the corresponding sleep stage. For another example, when the system starts running, the processing module 12 determines that the user is in the Wake stage. If the count result of the Wake stage is greater than the threshold within the 10-minute time window, since the Wake stage is the current sleep stage, the user's current sleep stage should not be considered to have changed at this time.

[0051] It should be noted that the specific length of the preset time window can be set as needed, and the present application is not limited to this.

[0052] At the same time, after the system starts running, the processing module 12 will also determine the second nerve stimulation parameter in real time.

[0053] As described above, after determining the current sleep stage of the user, the processing module 12 can obtain the target frequency band adapted to the current sleep stage. The processing module 12 obtains the phase characteristics of the EEG signal based on the target frequency band. Specifically, the processing module 12 obtains the first filtering phase offset θ1 generated after the EEG signal of the target frequency band is processed by the first filter, obtains the second filtering phase offset θ2 generated after the frequency domain signal of the EEG signal of the target frequency band is processed by the second filter, and obtains the phase characteristics of the EEG signal based on the first filtering phase offset θ1 and the second filtering phase offset θ2.

[0054] In some embodiments, for the first filtering phase offset θ1, a 0.1-45Hz bandpass filter (such as a second-order Butterworth filter) can be used as the first filter to filter the EEG signal in the target frequency band. At this time, the first filtering phase offset θ1 of the preset frequency can be calculated according to the parameters of the 0.1-45Hz bandpass filter.

[0055] In some embodiments, for the second filtering phase offset θ2, a filter of the target frequency band can be used as a second filter to filter the frequency domain signal of the EEG signal of the target frequency band. In some embodiments, after filtering the EEG signal, the processing module 12 performs N-point sliding window processing, and uses fast Fourier transform to calculate the frequency spectrum characteristics of the EEG signal of the target frequency band, that is, X[f]. Then, Hilbert transform is performed on X[f], the negative frequency component value is set to zero, and the positive frequency component is multiplied by 2 to obtain Y[f]. The second filter of the target frequency band is applied to Y[f] to obtain the filtered frequency domain signal, and the amplitude and phase response of the pulse frequency are obtained according to the parameters of the filter, so that the second filtering phase offset θ2 can be obtained. Then, the processing module 12 inversely transforms the filtered frequency domain signal back to the time domain to obtain a complex valued signal Z[n], and obtains the real-time phase angle through the complex valued signal Z[n] analysis, and based on this, the phase characteristics of the EEG signal can be extracted by subtracting θ1 and θ2.

[0056] To further illustrate the above process, the α band will be used as the target band for the Wake period. When the user determines that the user's current sleep stage is the Wake period and obtains the corresponding target frequency band as the α band, the collected EEG signal is filtered using a 0.1-45Hz bandpass filter, and the filtered EEG signal is processed by an N-point sliding window, and the frequency spectrum characteristics of the α band EEG signal, i.e., X[f], are calculated using a fast Fourier transform. At this time, the first filtering phase offset θ1 can be obtained according to the parameters of the 0.1-45Hz bandpass filter. After that, a Hilbert transform is performed on X[f], the negative frequency component value is set to zero, and the positive frequency component is multiplied by 2 to obtain Y[f]. Y[f] is filtered using an α band (7.5-12.5Hz) filter to obtain the filtered frequency domain signal, and the second filtering phase offset θ2 is obtained. Finally, the filtered frequency domain signal is inversely transformed back to the time domain to obtain a complex-valued signal Z[n]. The real-time phase angle is obtained by analyzing the complex-valued signal Z[n], and the phase characteristics of the EEG signal can be extracted by subtracting θ1 and θ2 from the real-time phase angle.

[0057] After acquiring the phase feature of the EEG signal, the processing module 12 determines the induced phase based on the phase feature of the EEG signal and the evoked response potential delay of the neural stimulation signal to determine the second neural stimulation parameter.

[0058] In fact, when the system starts running and outputs an adaptive neural stimulation signal to act on the brain, an evoked response potential delay will occur. This means that there is a certain delay time in the electrophysiological response of the brain to the stimulation signal. That is, the adaptive neural regulation sleep optimization system provided in the embodiment of the present application needs to determine the second neural stimulation parameter to determine the specific time of outputting the neural stimulation signal to achieve the sleep optimization effect.

[0059] For example, for the acoustic wave neural stimulation signal, the delay of its evoked response potential is 62.5ms. Assuming that the user is currently in the N2 stage, the specified target frequency band is the δ band, the target frequency is 2.5Hz, and the period is 400ms, the phase offset when the acoustic wave neural stimulation signal occurs should be (62.5 / 400)*360=15.625°. In order to trigger the evoked response potential of the acoustic wave stimulation signal at the peak of the EEG signal, it can be determined that the induced phase is 360°-15.625°=344.375°. Based on this, 344.375° is used as the second neural stimulation parameter.

[0060] After determining the first neural stimulation parameter and the second neural stimulation parameter, the processing module 12 generates and outputs an adaptive neural stimulation signal based on the first neural stimulation parameter, the second neural stimulation parameter and the preset stimulation signal parameter to adjust the user's nerves to optimize sleep. In fact, since the first neural stimulation parameter and the second neural stimulation parameter change in real time with the user's EEG signal, the neural stimulation signal generated based on this can adaptively adjust the user's nerves to achieve a maximized sleep optimization effect.

[0061] The neural stimulation signal includes one or more of an acoustic neural stimulation signal, a tactile neural stimulation signal, an electrical neural stimulation signal and an optical neural stimulation signal.

[0062] Among them, for the generation process, the processing module 12 determines the first neural stimulation frequency and the second neural stimulation frequency based on the neural stimulation frequency difference, generates a first neural stimulation signal based on the first neural stimulation frequency and the neural stimulation amplitude, generates a second neural stimulation signal based on the second neural stimulation frequency and the neural stimulation amplitude, and generates the neural stimulation signal based on the first neural stimulation signal and the second neural stimulation signal.

[0063] Taking the acoustic wave neural stimulation signal as an example, when the processing module 12 determines the current sleep stage of the user, it can obtain the preset frequency adapted to the current sleep stage, and use the preset frequency as the neural stimulation frequency difference. In fact, the neural stimulation frequency difference is the frequency "perceived" by the user's brain under the action of the neural stimulation signal. For the acoustic wave neural stimulation signal, the processing module 12 determines the first neural stimulation frequency and the second neural stimulation frequency of the sound wave based on the neural stimulation frequency difference, and then generates a first neural stimulation signal for being perceived by the left ear based on the first neural stimulation frequency and the neural stimulation amplitude, and generates a second neural stimulation signal for being perceived by the right ear based on the second neural stimulation frequency and the neural stimulation amplitude, and the first neural stimulation signal and the second neural stimulation signal actually together constitute a binaural acoustic wave stimulation, which is applied to the user's brain. That is, in fact, the processing module 12 generates a binaural acoustic wave neural stimulation signal presenting two frequencies. For example, when the processing module 12 determines that the neural stimulation frequency difference is 6 Hz and the neural stimulation amplitude is 68 dB, the processing module 12 can determine that the first neural stimulation frequency and the second neural stimulation frequency are 100 Hz and 94 Hz, respectively. Then the processing module 12 generates a first neural stimulation signal based on 100 Hz and 68 dB, that is, the sound wave stimulation perceived by the left ear (left channel), and generates a second neural stimulation signal based on 94 Hz and 68 dB, that is, the sound wave stimulation perceived by the right ear (right channel). At this time, the sound waves of the left channel and the sound waves of the right channel can be combined in the processing module 12 and output as a whole by the processing module 12, that is, the processing module 12 outputs an overall sound wave neural stimulation signal. The sound wave neural stimulation signal is perceived by the user through the left and right ears of the user respectively, that is, when the sound wave neural stimulation signal acts on the user's brain, the user's left ear presents a frequency of 100 Hz and the right ear presents a frequency of 94 Hz, and the user's brain can "perceive" a frequency of 6 Hz. At this time, the preset frequency of the current sleep stage can be consistent with each other, so as to achieve resonance to affect the user's brain and achieve sleep optimization. The amplitude of the acoustic nerve stimulation signal is consistent with the preset amplitude of the current sleep stage, which further improves the sleep optimization effect.

[0064] For another example, for tactile nerve stimulation signals, human smooth skin mainly contains four types of mechanical receptors: Pacinian corpuscles, tactile corpuscles, Merkel tactile discs and Ruffini corpuscles. In addition, there are also mechanical receptors in the skin where hair grows, especially the hair cells in the cochlea are the most sensitive. Mechanical receptors are actually mainly composed of specific types of neurons, which will stimulate action potentials when they sense mechanical stimulation. The peripheral conduction of signals is mainly carried out in the terminal organs. During the somatosensory conduction process, the afferent nerve transmits the signal to the dorsal column nucleus through the synapse, where a second signal is generated and transmitted to the thalamus. The thalamus then generates a third signal, which is eventually transmitted to the ventral basal nucleus and finally reaches the somatosensory cortex. Therefore, when the processing module 12 determines that the neural stimulation frequency difference is 6Hz and the neural stimulation amplitude is 68B, the processing module 12 can determine that the first neural stimulation frequency and the second neural stimulation frequency are 100Hz and 94Hz respectively. The processing module 12 generates a first neural stimulation signal based on 100Hz and 68dB, that is, the tactile stimulation perceived by the left hand, and generates a second neural stimulation signal based on 94Hz and 68dB, that is, the tactile stimulation perceived by the right hand. At this time, the tactile stimulation at the left hand and the tactile stimulation at the right hand can be combined in the processing module 12 and output as a whole by the processing module 12, that is, the processing module 12 outputs an overall tactile neural stimulation signal. The tactile neural stimulation signal is perceived by the user through the left and right hands of the user respectively, that is, when the tactile neural stimulation signal acts on the user, the user's left hand is applied with a tactile stimulation of 100Hz, and the right ear is applied with a tactile stimulation of 94Hz. At this time, the user's brain can finally "perceive" a frequency of 6Hz. Then, it is possible to achieve resonance by being consistent with the preset frequency of the current sleep stage to affect the user's brain and achieve sleep optimization. And the amplitude of the neural stimulation signal issued is consistent with the preset amplitude of the current sleep stage, further improving the sleep optimization effect.

[0065] For electrical neural stimulation and optical neural stimulation signals, they are actually output to the user as a whole neural stimulation signal. The user perceives the two frequencies of neural stimulation respectively so that the difference between the two frequencies can resonate with the brain and improve the sleep optimization effect.

[0066] In addition, in order to ensure that the neural stimulation signal can be output at a specific time point of brain activity, thereby improving the synchronization and effect of neural regulation, the processing module 12 will also output the neural stimulation signal based on the second neural stimulation parameters and the preset stimulation signal parameters; the preset stimulation signal parameters include the output duration of the neural stimulation signal.

[0067] As mentioned above, the second neural stimulation parameter is actually an induced phase, and outputting a neural stimulation signal at this induced phase can trigger the induced potential of the neural stimulation signal at the peak of the EEG signal. Therefore, the processing module 12 will output the neural stimulation signal based on the second neural stimulation parameter.

[0068] For example, for the acoustic wave neural stimulation signal, the delay of its evoked response potential is 62.5ms. Assuming that the user is currently in the N2 stage, the specified target frequency band is the δ band, the target frequency is 2.5Hz, and the period is 400ms, the phase offset when the acoustic wave neural stimulation signal occurs should be (62.5 / 400)*360=15.625°. In order to trigger the evoked response potential of the acoustic wave stimulation signal at the peak of the EEG signal, it can be determined that the induced phase is 360°-15.625°=344.375°. Based on this, 344.375° is used as the second neural stimulation parameter. At this time, the processing module 12 should output the acoustic wave neural stimulation signal at 344.375°.

[0069] It should be noted that for different types of stimulation, the delay of the stimulus evoked response potential is different. The above embodiment of the present application only takes the delay of the evoked response potential of the sound wave stimulation as 62.5ms as an example to illustrate the specific process of determining the second nerve stimulation parameter.

[0070] Furthermore, the preset stimulation signal parameters include the output duration of the neural stimulation signal. That is, after the processing module 12 determines the output time point based on the second neural stimulation parameter, it will also continue to output the neural stimulation signal based on the preset output duration. It should be noted that the output duration can be personalized according to user needs, and this application does not impose any restrictions on this.

[0071] In addition, for optical neural stimulation signals, the preset stimulation signal parameters should also include the color or wavelength of light. In fact, light of a specific wavelength can effectively regulate biological rhythms and affect sleep, mood, and cognitive functions. Therefore, if you want to generate and output an optical neural stimulation signal, you should determine the wavelength of the light in advance. For example, the preset stimulation signal parameters can be preset to blue light, and the system will eventually generate a blue light neural stimulation signal based on the first neural stimulation parameter, and output a blue light neural stimulation signal based on the second neural stimulation parameter and the preset output duration.

[0072] Furthermore, after obtaining the first neural stimulation parameter, the second neural stimulation parameter and the preset stimulation signal parameter, the processing module 12 can correspondingly generate and output one or more of the acoustic neural stimulation signal, the tactile neural stimulation signal, the electrical neural stimulation signal and the optical neural stimulation signal, thereby achieving more comprehensive neural regulation by combining neural stimulation of various senses, and promoting better sleep quality and overall health.

[0073] It should be noted that Figure 1 The structure of the adaptive neural regulation sleep optimization system shown in is only provided as an embodiment. The division of the acquisition module 11 and the processing module 12 is only a logical function division, and there may be other division methods in actual implementation. The implementation device of the adaptive neural regulation sleep optimization system described in this application includes but is not limited to the structure of the adaptive neural regulation sleep optimization system listed in this embodiment. All structural deformations and replacements of the prior art made according to the principles of this application are included in the protection scope of this application.

[0074] Figure 2 The schematic diagram of the principle of an adaptive neural regulation sleep optimization system provided by the embodiment of the present application is shown. Figure 2 As shown, when the adaptive neural regulation sleep optimization system starts running, it starts to collect the user's EEG signals and performs pre-processing such as filtering on the signals. Afterwards, the system determines the user's current sleep stage based on the EEG signals, obtains the preset amplitude adapted to the current sleep stage and the preset frequency of the target frequency band as the first neural stimulation parameter, and determines in real time whether the current sleep stage has changed, so as to obtain the first neural stimulation parameter adapted to the current sleep stage in real time. At the same time, the system obtains the phase characteristics of the EEG signal based on the target frequency band, and determines the induced phase as the second neural stimulation parameter. Finally, the system generates and outputs a neural stimulation signal based on the first neural stimulation parameter, the second neural stimulation parameter and the preset signal parameter.

[0075] Figure 3 The schematic diagram of the principle of an adaptive neural regulation sleep optimization method provided in an embodiment of the present application is shown. Figure 3As shown, when the adaptive neural regulation sleep optimization system starts running, the system collects the user's EEG signals in real time, and monitors the user's current sleep stage in real time. When the user's sleep stage changes, the first neural stimulation parameter (neural stimulation frequency difference and neural stimulation amplitude) will also change adaptively to generate an adaptive neural stimulation signal. Among them, the adaptively matched neural stimulation frequency difference of the Wake period corresponds to the preset frequency within the α wave band, the adaptively matched neural stimulation frequency difference of the N1 period corresponds to the preset frequency within the θ wave band, and the adaptively matched neural stimulation frequency difference of the N2 period corresponds to the preset frequency within the δ wave band. And the Wake period, N1 period and N2 period all have adaptively matched neural stimulation amplitudes. When it is determined that the user's current sleep stage is N3 or REM period, the system suspends operation. After determining the first neural stimulation parameter, the system obtains the phase characteristics of the EEG signal to determine the induced phase as the second neural stimulation parameter, and outputs the neural stimulation signal based on the preset stimulation signal parameters.

[0076] It should be noted that the length of time the system is running can be controlled. When the system determines that the user has entered the N3 or REM stage, the system will suspend operation. However, if the system is still within the running time, the system will monitor the user's sleep stage in real time. Once it is determined that the user has returned to the Wake stage, N1 stage or N2 stage, the system will restart. That is, during the entire operation of the system, the user's current sleep stage is actually being determined in real time, and the first neural stimulation parameters adapted to the current sleep stage are obtained.

[0077] Figure 4 The flowchart of the adaptive neural regulation sleep optimization method provided in the embodiment of the present application is shown. Figure 4 As shown, the adaptive neural regulation sleep optimization method includes steps S1 to S4.

[0078] S1. Collect the user's EEG signal.

[0079] S2. Determine a first neural stimulation parameter based on the sleep stage of the EEG signal.

[0080] S3. Determine a second neural stimulation parameter based on the phase characteristics of the EEG signal.

[0081] S4. Generate and output adaptive neural stimulation signals of one or more stimulation categories based on the first neural stimulation parameters, the second neural stimulation parameters and preset stimulation signal parameters to adjust the user's neural optimization sleep.

[0082] The description of steps S1 to S4 may refer to the above contents and will not be repeated here.

[0083] The protection scope of the sleep regulation method described in the embodiment of the present application is not limited to the execution order of the steps listed in the present embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present application are included in the protection scope of the present application.

[0084] The adaptive neural regulation sleep optimization method provided in the embodiment of the present application can be implemented by the adaptive neural regulation sleep optimization system, but the implementation device of the adaptive neural regulation sleep optimization method includes but is not limited to the structure of the adaptive neural regulation sleep optimization system described in this embodiment.

[0085] For example, in some embodiments, the adaptive neural regulation sleep optimization method described in the present application can be applied to end-cloud interaction scenarios. Figure 5A The following is a schematic diagram of the structure of the client-cloud interaction scenario in these implementations. Figure 5A As shown, the end-cloud interaction system 2 includes a wearable control device 20 and a cloud server 21. The wearable control device 20 and the cloud server 21 can communicate with each other, and the communication method is not limited to wired or wireless.

[0086] When the user is ready to enter a certain physiological state, he can wear the wearable control device 20. At this time, the wearable control device 20 will collect the user's EEG signals in real time and send the EEG signals to the cloud server 21. The cloud server 21 will process the EEG signals and control the wearable control device 20 to output adaptive neural stimulation signals to the user. In addition, the cloud server 21 will also store the sleep data of the user during the sleep cycle.

[0087] In some other embodiments, the physiological state regulation method described in the present application can be applied to another terminal-cloud interaction scenario. Figure 5B The following is a schematic diagram of the structure of the client-cloud interaction scenario in these implementations. Figure 5B As shown, the end-cloud interaction system 2 includes a wearable control device 20, a cloud server 21 and a host computer 22. The wearable control device 20, the cloud server 21 and the host computer 22 can communicate with each other, and the communication method is not limited to wired or wireless.

[0088] At this time, when the user puts on the wearable control device 20, the wearable control device 20 can be controlled by the host computer 22 to collect the user's EEG signals in real time, and execute the adaptive neural regulation sleep optimization method provided in the embodiment of the present application to generate a neural stimulation signal. At the same time, the sleep data of the user during the sleep cycle can be uploaded to the host computer 22 via Bluetooth or other communication methods, and then transmitted to the cloud server 21 through the host computer for storage.

[0089] It should be noted that the cloud server 21 may include one or more servers, or one or more processing nodes, or one or more virtual machines running on the server. The cloud server 21 may also be called a server cluster, a management platform, a physiological state control center, etc. This application does not impose any restrictions on this.

[0090] In the several embodiments provided in the present application, it should be understood that the disclosed system, device or method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules or units, which can be electrical, mechanical or other forms.

[0091] The modules / units described as separate components may or may not be physically separated, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, the functional modules / units in the various embodiments of the present application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0092] Those of ordinary skill in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0093] An embodiment of the present application also provides a wearable device, comprising: one or more sensors configured to collect biological signals of a user in real time; one or more processors; and one or more memories, wherein the memories store computer-readable codes, and when the computer-readable codes are executed by the one or more processors, the functions of the bio-health system as described above are implemented.

[0094] The wearable device can be used with the help of Figure 6 The exemplary computing device architecture shown in FIG. Figure 6 As shown, the exemplary computing device may include a bus 910, one or more CPUs 920, a read-only memory (ROM) 930, a random access memory (RAM) 940, a communication port 950 connected to a network, an input / output component 960, a hard disk 970, etc. The storage device in the computing device 900, such as the ROM 930 or the hard disk 970, may store various data or files used for computer processing and / or communication and program instructions executed by the CPU. The computing device 900 may also include a sensor 980. Of course, Figure 6 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 6 One or more components of a computing device are shown.

[0095] The embodiment of the present application also provides a computer-readable storage medium, on which instructions are stored, and when the instructions are executed by the processor, the processor executes the physiological state regulation method as described in the present application. A person of ordinary skill in the art can understand that all or part of the steps in the method for implementing the above embodiment can be executed by computer-readable instructions stored on a computer-readable storage medium. Computer-readable storage media include, but are not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0096] The present application also provides a computer program product or a computer program, which includes computer-readable instructions stored in a computer-readable storage medium. The processor of the computer device can read the computer-readable instructions from the computer-readable storage medium, and the processor executes the computer-readable instructions, so that the computer device performs the physiological state regulation method described in each of the above embodiments.

[0097] The adaptive neural regulation sleep optimization system, method, wearable device and medium provided by the present application, on the one hand, determines the first neural stimulation parameter based on the changing characteristics of the user's EEG signal in real time, thereby generating a neural stimulation signal, and realizes the real-time generation of a neural stimulation signal based on the user's EEG signal, thereby performing adaptive neural regulation on the user, and then being able to perform targeted sleep optimization for the user through the neural stimulation signal. On the other hand, the present application accurately extracts the phase characteristics of the EEG to determine the second neural stimulation parameter, and then outputs the neural stimulation signal based on this, so that the evoked response potential of the neural stimulation signal can reach a peak value at a specified time, and then can efficiently optimize the user's sleep through the neural stimulation signal.

[0098] The descriptions of the processes or structures corresponding to the above-mentioned figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0099] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. An adaptive neural regulation sleep optimization system, characterized in that: include: A collection module, configured to collect the user's EEG signal; The processing module is configured to determine a first neural stimulation parameter based on the sleep stage of the EEG signal, determine a second neural stimulation parameter based on the phase characteristics of the EEG signal, and generate and output adaptive neural stimulation signals of one or more stimulation categories based on the first neural stimulation parameter, the second neural stimulation parameter and preset stimulation signal parameters to adjust the user's neural optimization sleep.

2. The adaptive neural regulation sleep optimization system according to claim 1, characterized in that: Also includes: The processing module determines the current sleep stage of the user based on the EEG signal, and determines a preset frequency and a preset amplitude adapted to the current sleep stage as the first neural stimulation parameter; The processing module determines whether the current sleep stage changes based on the EEG signal, and in response to the change of the current sleep stage, determines a preset frequency and a preset amplitude adapted to the changed sleep stage as the first neural stimulation parameter; Different sleep stages correspond to their own adaptively matched first neural stimulation parameters; the first neural stimulation parameters include neural stimulation frequency difference and neural stimulation amplitude.

3. The adaptive neural regulation sleep optimization system according to claim 2, characterized in that: Also includes: The processing module processes the EEG signal within the preset time window in segments to obtain a plurality of EEG segment signals; The processing module determines the sleep stage of each of the EEG segmented signals to obtain a sleep stage determination result; if the count of the sleep stage determination results of the same type is greater than a preset threshold, and the sleep stage determination result of this type is different from the current sleep stage, it is determined that the current sleep stage has changed.

4. The adaptive neural regulation sleep optimization system according to claim 1, characterized in that: Also includes: The processing module determines the user's current sleep stage based on the EEG signal, obtains a target frequency band adapted to the current sleep stage, obtains the phase characteristics of the EEG signal based on the target frequency band, and determines the induced phase as the second neural stimulation parameter based on the phase characteristics of the EEG signal and the evoked response potential delay of the neural stimulation signal.

5. The adaptive neural regulation sleep optimization system according to claim 4, characterized in that: Also includes: The processing module obtains a first filtering phase offset generated after the EEG signal of the target frequency band is processed by the first filter, and obtains a second filtering phase offset generated after the frequency domain signal of the EEG signal of the target frequency band is processed by the second filter; The processing module obtains the phase feature of the electroencephalogram signal based on the first filtering phase offset and the second filtering phase offset.

6. The adaptive neural regulation sleep optimization system according to claim 2, characterized in that: Also includes: The processing module determines a first neural stimulation frequency and a second neural stimulation frequency based on the neural stimulation frequency difference, generates a first neural stimulation signal based on the first neural stimulation frequency and the neural stimulation amplitude, generates a second neural stimulation signal based on the second neural stimulation frequency and the neural stimulation amplitude, and generates the neural stimulation signal based on the first neural stimulation signal and the second neural stimulation signal; The processing module outputs the neural stimulation signal based on the second neural stimulation parameter and the preset stimulation signal parameter; the preset stimulation signal parameter includes the output duration of the neural stimulation signal.

7. The adaptive neural regulation sleep optimization system according to claim 1, characterized in that: The neural stimulation signal includes one or more of an acoustic neural stimulation signal, a tactile neural stimulation signal, an electrical neural stimulation signal and an optical neural stimulation signal.

8. A wearable device, characterized in that: include: At least one sensor configured to collect the user's brain electrical signals in real time; At least 1 processor; and At least one memory, wherein the memory stores computer-readable code, and when the computer-readable code is executed by the one or more processors, the function of the adaptive neural regulation sleep optimization system according to any one of claims 1 to 7 is realized.

9. An adaptive neural regulation sleep optimization method, characterized in that: include: Collecting the user's EEG signals; Determining a first neural stimulation parameter based on the sleep stage of the EEG signal; determining a second neural stimulation parameter based on a phase characteristic of the EEG signal; Based on the first neural stimulation parameter, the second neural stimulation parameter and the preset stimulation signal parameter, an adaptive neural stimulation signal of one or more stimulation categories is correspondingly generated and output to adjust the user's neural optimization sleep.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed by the processor, the functions of the adaptive neural regulation sleep optimization system according to any one of claims 1 to 7 are realized.

Images