CN109044280A

CN109044280A - A kind of sleep stage method and relevant device

Info

Publication number: CN109044280A
Application number: CN201810950257.1A
Authority: CN
Inventors: 梁杰; 王伟; 冯澍婷; 刘洪涛; 张启
Original assignee: Shenzhen Het Data Resources and Cloud Technology Co Ltd
Current assignee: Shenzhen Hetai Intelligent Home Appliance Controller Co ltd
Priority date: 2018-08-20
Filing date: 2018-08-20
Publication date: 2018-12-21
Anticipated expiration: 2038-08-20
Also published as: CN109044280B

Abstract

This application discloses a kind of sleep stage method and relevant devices, comprising: the first electricity physiological signal of prefrontal area first in acquisition user's sleep procedure；Then sleep physiology signal is extracted from first electricity physiological signal, the sleep physiology signal includes at least one in the first EEG signals, electro-ocular signal and electromyography signal；Then according to the sleep physiology signal, the sleep stage of the user is determined as a result, the sleep stage result is used to assess the health status of the user.Using the embodiment of the present application, the accuracy of sleep stage can be improved.

Description

Sleep staging method and related equipment

Technical Field

The present application relates to the field of electronic technologies, and in particular, to a sleep staging method and related devices.

Background

Sleep, as a complex physiological process, is an important link for restoration, integration and consolidation of the body. According to the physiological characteristics of a human body during sleep, the sleep can be divided into a wake period, a non-rapid eye movement sleep period and a rapid eye movement sleep period, wherein the non-rapid eye movement sleep period can be divided into I, II, III and IV periods. The research on sleep stages has important application significance in health condition assessment such as sleep state, sleep disease diagnosis and sleep quality. Currently, in clinical sleep analysis, sleep staging mainly depends on experts' experience to stage the sleep process according to the overnight continuous sleep data of testers, resulting in low accuracy of sleep staging results. Or a dynamic sensor such as an accelerometer is used for judging different sleep periods by identifying the motion time and the motion amplitude according to the motion signal, however, the method has a high probability of misjudgment in the two states of waking and sleeping.

Disclosure of Invention

The embodiment of the application provides a sleep staging method and related equipment. The accuracy of sleep staging can be improved.

A first aspect of the present application provides a sleep staging method, including:

collecting a first electrophysiological signal of a forehead area in a sleeping process of a user;

extracting a sleep physiological signal from the first electrophysiological signal, the sleep physiological signal including at least one of a first electroencephalogram signal, an electrooculogram signal, and an electromyogram signal;

and determining a sleep staging result of the user according to the sleep physiological signal.

Wherein the determining the sleep staging result of the user according to the sleep physiological signal comprises:

extracting physiological characteristic information of the user from the sleep physiological signal, wherein the physiological characteristic information comprises at least one of the following: the energy change rate corresponding to the first electroencephalogram signal, the eye movement position and the eye movement frequency corresponding to the electrooculogram signal, and the myoelectric position, the myoelectric energy and the myoelectric duration corresponding to the myoelectric signal;

and determining a sleep staging result of the user according to the physiological characteristic information.

Wherein, before the collection user sleep in-process forehead area's first electrophysiological signal, still include:

collecting a second electrophysiological signal of the forehead area when the user is in a non-sleep state as a reference signal;

the acquiring physiological characteristic information of the user from the sleep physiological signal comprises:

extracting a second electroencephalogram signal from the reference signal;

determining a first electrical wave energy of the first brain electrical signal and a second electrical wave energy of the second brain electrical signal;

determining the energy change rate according to the first radio wave energy and the second radio wave energy.

Wherein the acquiring physiological characteristic information of the user from the sleep physiological signal comprises:

determining at least one of the eye movement position and the eye movement frequency from the eye electrical signal.

Wherein before extracting the sleep physiological signal from the first electrophysiological signal, the method further comprises:

acquiring the signal amplitude of the first electrophysiological signal and counting the signal energy of the first electrophysiological signal;

determining that the first electrophysiological signal contains the ocular signal if the signal amplitude is above a first threshold and the signal energy is concentrated in a first frequency interval.

and determining at least one of the myoelectric position, the myoelectric energy and the myoelectric duration according to the myoelectric signal.

and if the signal amplitude is higher than a second threshold value and the signal energy is concentrated in a second frequency interval, determining that the first electrophysiological signal contains the electromyographic signal.

The first electroencephalogram signal comprises at least one of a first frequency band electric wave, a second frequency band electric wave, a third frequency band electric wave and a fourth frequency band electric wave;

the determining the sleep stage result of the user according to the physiological characteristic information comprises:

determining the sleep staging result as a deep sleep stage when the first electrophysiological signal does not include the electromyographic signal, the energy change rate of the first frequency band electric wave is greater than a third threshold, the energy change rate of the second frequency band electric wave is not greater than a fourth threshold, the energy change rate of the third frequency band electric wave is less than a fifth threshold, and the eye movement frequency and the eye movement position are zero; or

Determining the sleep staging result as a waking period when the myoelectric energy is greater than a sixth threshold, the myoelectric duration exceeds a seventh threshold, the energy change rate of the second frequency band electric wave is not greater than the fourth threshold, the energy change rate of the third frequency band electric wave is not less than the fifth threshold, the energy change rate of the fourth frequency band electric wave is not less than an eighth threshold, and the eye movement frequency is not greater than a ninth threshold; or

And determining that the sleep staging result is a light sleep stage when the myoelectric energy is greater than the sixth threshold, the myoelectric duration exceeds the seventh threshold, the energy change rate of the second frequency band electric wave is greater than the fourth threshold, and the energy change rate of the third frequency band electric wave is less than the fifth threshold.

A second aspect of the embodiments of the present application discloses a sleep staging apparatus, including:

an acquisition module for acquiring a first electrophysiological signal of the forehead region during sleep

An extraction module, configured to extract a sleep physiological signal from the first electrophysiological signal, where the sleep physiological signal includes at least one of a first electroencephalogram signal, an electrooculogram signal, and an electromyogram signal;

and the determining module is used for determining the sleep staging result of the user according to the sleep physiological signal.

Wherein the determining module is further configured to:

Wherein the acquisition module is further configured to:

the extraction module is further configured to:

extracting a second electroencephalogram signal from the reference signal;

the determination module is further to:

Wherein the determining module is further configured to:

Wherein the extraction module is further configured to:

Wherein the determining module is further configured to: and determining at least one of the myoelectric position, the myoelectric energy and the myoelectric duration according to the myoelectric signal.

Wherein the extraction module is further configured to:

the determination module is further to:

Accordingly, the present application provides a storage medium, wherein the storage medium is used for storing an application program, and the application program is used for executing a sleep staging method disclosed in the first aspect of the embodiments of the present application when the application program runs.

Accordingly, a third aspect of embodiments of the present application provides an electronic device, including a processor, a memory, a communication interface, and a bus;

the processor, the memory and the communication interface are connected through the bus and complete mutual communication;

the memory stores executable program code;

the processor executes a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute a sleep staging method disclosed in the first aspect of the embodiment of the present application.

Accordingly, the present application provides an application program, wherein the application program is configured to execute, at runtime, a sleep staging method disclosed in the first aspect of the embodiments of the present application.

According to the embodiment of the application, first, a first electrophysiological signal of a forehead area in the sleeping process of a user is collected; then extracting a sleep physiological signal from the first electrophysiological signal, wherein the sleep physiological signal comprises at least one of a first electroencephalogram signal, an electrooculogram signal and an electromyogram signal; and then determining a sleep staging result of the user according to the sleep physiological signal, wherein the sleep staging result is used for evaluating the health state of the user, so that the accuracy of sleep staging can be improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flowchart of a sleep staging method according to an embodiment of the present application;

fig. 2 is a schematic flowchart of a method for determining an energy normalization rate according to an embodiment of the present disclosure;

fig. 3 is a schematic flowchart of a method for extracting electrooculogram information according to an embodiment of the present application;

fig. 4 is a schematic flowchart of a method for extracting electromyographic information according to an embodiment of the present application;

FIG. 5 is a schematic structural diagram of a decision tree according to an embodiment of the present disclosure;

FIG. 6 is a schematic flow chart diagram of another sleep staging method provided by an embodiment of the present application;

FIG. 7 is a schematic diagram of a power spectrum provided by an embodiment of the present application;

FIG. 8 is an overall block diagram of a sleep staging method provided by an embodiment of the present application;

FIG. 9 is a schematic diagram of another sleep staging apparatus according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Referring to fig. 1, fig. 1 is a schematic flowchart illustrating a sleep staging method according to an embodiment of the present disclosure. As shown in the figure, the method in the embodiment of the present application includes:

s101, collecting a first electrophysiological signal of a forehead area in a sleeping process of a user.

During the sleep process of the user, the electrophysiological signal of the forehead area of the user can be collected through a wearable head device such as an eye mask or a mask during the whole sleep process, wherein the electrophysiological signal is an analog signal. The acquired electrophysiological signals are then segmented into signal segments of one block every 30 seconds(s), and the determination of the sleep stage result is made with the signal segment as the smallest signal unit. For example, by collecting electrophysiological signals from the forehead region of the user between 22:00-02:00, (60 × 4)/30 ═ 480 signal segments can be obtained. The first electrophysiological signal is therefore also a signal segment of duration 30 s.

In a specific implementation, after the first electrophysiological signal is acquired, the first electrophysiological signal can be sampled, but not limited to, at a sampling rate of 500 hertz (Hz) to be converted into a digital signal for processing.

Optionally, before acquiring the first electrophysiological signal of the forehead region during the sleep of the user, the second electrophysiological signal of the forehead region when the user is in the non-sleep state may be acquired first as the reference signal, wherein the user is determined to be in the awake state within the first 1 minute before the acquisition of the electrophysiological signal of the forehead region is started, and therefore the signal acquired within the 1 minute may be used as the reference signal.

S102, extracting a sleep physiological signal from the first electrophysiological signal, wherein the sleep physiological signal comprises at least one of a first electroencephalogram signal, an electrooculogram signal and an electromyogram signal.

In a specific implementation, a first Electroencephalogram (EGG) signal may be extracted from the first electrophysiological signal, and a second electroencephalogram signal may be extracted from the reference signal, where as shown in fig. 2, the first electrophysiological signal and the reference signal may be respectively input to a 0.5 Hz-35 Hz band-pass filter, so as to obtain pure first and second electroencephalograms.

It should be noted that the band pass filter is an Infinite impulse feedback (IIR) zero phase filter. A general IIR filter is a nonlinear phase filter that changes the phase of an original signal when filtering the signal and is a nonlinear change. The EEG signal has unstable characteristics, and useful EEG information in the sleep stage is represented in a low frequency range of 0.5 Hz-30 Hz. Therefore, small phase distortion can cause great change of low-frequency signals, and a zero-phase IIR filter is selected in the embodiment of the application.

Alternatively, an Electro-ocular signal (EOG) may be extracted from the first electrophysiological signal, wherein, as shown in fig. 3, the analog first electrophysiological signal may be first down-sampled at a sampling rate of 25Hz to remove the partial EEG signal and the partial electromyogram signal from the first electrophysiological signal. And then carrying out median filtering on the sampled first electrophysiological signal so as to obtain a pure EOG signal. Here, since the signal of EOG is mainly around 10Hz, the template size of median filtering is taken to be 5.

Optionally, an Electromyography (EMG) signal may be extracted from the first electrophysiological signal, wherein, as shown in fig. 4, a pure, high frequency EMG signal may be obtained by inputting the first electrophysiological signal into a high pass filter with a cut-off frequency of 45 Hz. S103, determining a sleep staging result of the user according to the sleep physiological signal. Wherein the sleep staging results may be used to assess the health status of the user.

In a specific implementation, the physiological characteristic information of the user may be first acquired from sleep physiology, and then the sleep staging result may be determined according to the physiological characteristic information.

Wherein the physiological characteristic information may include an energy change rate of the EEG, and the energy change rate may represent a change in energy of the electric wave in the first electrophysiological signal relative to the electric wave in the reference signal. In order to determine the energy change rate of the EEG, a first wave energy of the first brain electrical signal and a second wave energy of the second brain electrical signal are then determined, wherein, as shown in fig. 2, a power spectrum of the first brain electrical signal and the second brain electrical signal can be obtained by periodogram power spectrum estimation, and then the first wave energy and the second wave energy are obtained according to the power spectrum. Finally, the energy change rate is determined from the first and second radio wave energies.

it should be noted that the first electroencephalogram signal and the second electroencephalogram signal may include a first frequency band electric wave, a second frequency band electric wave, a third frequency band electric wave, and a fourth frequency band electric wave, wherein the first frequency band electric wave may be a delta wave of 0.5Hz to 4Hz, the second frequency band electric wave may be a theta wave of 4Hz to 7Hz, the third frequency band electric wave may be α waves of 8Hz to 12Hz, and the fourth frequency band electric wave may be an β wave of 13Hz to 30Hz, so that energy change rates of the 4 electroencephalogram waves may be respectively obtained

here, i is a frequency interval in which the δ wave, the θ wave, the β wave, and the α wave are located, for example, 4Hz to 7Hz, and when the intervals 4Hz to 7Hz are serialized into 4, 5, 6, and 7, range (i) is 4. P is the power corresponding to the frequency point in i, for example, for the θ wave, coordinate points (4,9), (5, 10), (6, 7), (7, 12) whose abscissa is in the range of 4Hz to 7Hz are found on the power spectrum, and the average power of the θ wave is obtained as P (9+10+7+12)/4 is 9.5 dB/Hz.

In addition, the power spectrum estimation based on the Welch method is adopted in the periodogram method in the embodiment of the applicationThe power spectrum estimation method of (1). The reason is that the Welch method-based power spectrum estimation method combines windowing processing and averaging processing, and effectively reduces frequency false peaks. In the power spectrum estimation method of Welch method, if the signal to be processed is a signal x with length m_m(n) then, first, for x_m(n) performing segmentation, wherein each segment of signals are allowed to overlap, if the length of each segment of signals is M, the signals are divided into L segments, and L is (M-M/2)/(M/2), then the modified power spectrum of each segment of signals is

Wherein,ω (n) is a window function. In the embodiment of the application, the window function is a Hamming window function, the window length is 250 sampling points, and the overlapping rate of two adjacent sections of signals is 50%, so that enough data in an analysis window can be divided into about 10 sections.

Optionally, the physiological characteristic information may further include an eye movement position and an eye movement frequency. The eye movement position and the eye movement frequency may be determined from the electrical eye signals, wherein the eye movement position and the eye movement frequency may be obtained using a threshold-based peak detection technique, as shown in fig. 3. For example, the EOG sequence is x [ j ]]When x [ j ] is reached_p]When the formula (1) is satisfied, j is_pDetermining the position of peak point of eye movement, namely the eye movement position, and the eye movement frequency is xj]The quotient of the sequence length and the duration of the EOG.

Where j ∈ [ j ]_p-25,j_p+25]，Δ＝(max{x[j]}-min{x[j]})*0.25。

Optionally, the physiological characteristic information may further include an electromyographic position, an electromyographic energy, and an electromyographic duration, where the electromyographic energy represents an energy of an electromyographic signal in the first electrophysiological signal, the electromyographic duration represents a duration of the electromyographic signal, and the electromyographic position is a position of a peak point of the electromyographic signal. The electromyographic position, the electromyographic energy and the electromyographic duration can be determined according to the electromyographic signal, wherein, as shown in fig. 4, the high-pass filtered EMG signal can be subjected to Hilbert (Hilbert) transformation so as to obtain an analytic signal of a real signal, and then envelope information of the real signal is obtained through the analytic signal; and finally, detecting the envelope through a peak value detection technology based on a threshold value method to obtain the electromyographic position, the electromyographic energy and the duration of the EMG signal.

For example, if x (t) is a real signal, then the Hilbert transform of x (t) is

Corresponding analytic signal is

The envelope of the signal is

After obtaining the physiological characteristic information, the physiological characteristic information may be input into a decision tree as shown in fig. 5 to determine the sleep staging results. Among them, there are four cases:

for convenience of description, the delta wave, the α wave, the alpha wave and the β wave in the first electroencephalogram signal are defined as delta waves₁Wave, theta₁wave, alpha₁wave and beta₁the delta wave, theta wave, α wave and β wave in the second brain electrical signal are recorded as delta₂Wave, theta₂wave, alpha₂wave and beta₂the energy change rates of the delta wave, the α wave, the alpha wave, and the β wave may be further described as delta₁/δ₂、θ₁/θ₂、α₁/α₂、β₁/β₂。

In the first case: when the first electrophysiological signal does not include an EMG signal and is delta₁/δ₂Greater than a third threshold (denoted as x)₃) And theta₁/θ₂Is not greater than the fourth threshold (the fourth threshold is marked as x)₄) and alpha is₁/α₂Is less than a fifth threshold (the fifth threshold is marked as x)₅) And when the eye movement frequency and the eye movement position are zero, determining that the sleep staging result is a deep sleep stage. Wherein x is₃May be but is not limited to 1.2, x₄May be but is not limited to 1.2, x₅May be, but is not limited to, 0.5, with zero eye movement frequency and eye movement position indicating a no eye movement event.

In the second case: when the electromyographic energy is larger than a sixth threshold (the sixth threshold is marked as x)₆) And the myoelectricity duration exceeds a seventh threshold (the seventh threshold is marked as x)₇) And theta₁/θ₂Not more than x₄and alpha is₁/α₂Not less than x₅and beta₁/β₂Not less than the eighth threshold (the eighth threshold is denoted as x)₈) And the eye movement frequency is not more than a ninth threshold (the ninth threshold is marked as x)₉) And then determining that the sleep staging result is a waking period. Wherein x is₆May be, but is not limited to, 0.8 times the energy of the EMG signal in the reference signal, x₇Can be but is not limited to 15s, x₉And may be, but is not limited to, 2 Hz.

In the third case: when the myoelectric energy is more than x₆And the duration of myoelectricity exceeds x₇And theta₁/θ₂Greater than x₄and alpha is₁/α₂Less than x₅And then determining that the sleep staging result is a light sleep period.

In a fourth case: and (6) pending determination. In this case, in conjunction with the description given at step S101 in the embodiment of the present application, each 30S signal segment is further taken as a frame signal, so that the sleep staging result of the first electrophysiological signal can be determined from the sleep staging results of the previous frame signal and the next frame signal adjacent to the first electrophysiological signal. And if the previous frame signal and the next frame signal are not in a pending state and belong to the same sleep period (such as a light sleep period), determining that the first electrophysiological signal is in the same sleep period as the previous frame signal and the next frame signal. When the previous frame signal and the next frame signal are not in the undetermined state and are not in the same sleep period, determining that the first electrophysiological signal is in the same sleep period as the previous frame signal, for example, when the previous frame signal belongs to a light sleep period and the next frame signal is in a deep sleep period, determining that the first physiological electrical signal belongs to a light sleep period. And if only one frame of the previous frame and the next frame is not in a pending state, determining that the first physiological electric signal belongs to the sleep period to which the signal which is not in the pending state belongs. For example, if the previous frame of signal belongs to the awake period and the next frame of signal is in a pending state, it is determined that the first electrophysiological signal belongs to the awake period.

After the sleep staging result of each signal segment in the continuous electrophysiological signals in the whole sleep period (such as 22: 00-07: 00) is determined, the time periods of the waking period, the light sleep period and the deep sleep period can be respectively determined, so as to determine the time length and the conversion condition of each sleep period, and accordingly, the sleep quality of the user can be evaluated, diseases related to sleep can be diagnosed, and the like.

In the embodiment of the application, first, a first electrophysiological signal of a forehead area in the sleeping process of a user is collected; then extracting a sleep physiological signal from the first electrophysiological signal, wherein the sleep physiological signal comprises at least one of a first electroencephalogram signal, an electrooculogram signal and an electromyogram signal; and then determining a sleep staging result of the user according to the sleep physiological signal, wherein the sleep staging result is used for evaluating the health state of the user, so that the accuracy of sleep staging can be improved.

Referring to fig. 6, fig. 6 is a flowchart illustrating another sleep staging method according to an embodiment of the present disclosure. As shown in the figure, the method in the embodiment of the present application includes:

s601, collecting a first electrophysiological signal of a forehead area in a sleeping process of a user. This step is the same as step S101 in the previous embodiment, and is not described again.

S602, extracting a first electroencephalogram signal from the first electrophysiological signal.

In a specific implementation, as shown in fig. 2, the first electrophysiological signal may be input to a 0.5 Hz-35 Hz band-pass filter, so as to obtain a pure first electroencephalogram signal.

S603, the energy change rates of the first frequency band electric wave, the second frequency band electric wave, the third frequency band electric wave and the fourth frequency band electric wave in the first electroencephalogram signal are determined.

in the specific implementation, the first frequency range electric wave can be a delta wave of 0.5Hz to 4Hz, the second frequency range electric wave can be a theta wave of 4Hz to 7Hz, the third frequency range electric wave can be β waves of 8Hz to 12Hz, and the fourth frequency range electric wave can be a beta wave of 13Hz to 30 Hz.

S604, determining whether the first electroencephalogram signal contains an electro-oculogram signal. If yes, go to step S605, and if no, go to step S606.

In a specific implementation, the signal amplitude of the first electrophysiological signal may be obtained first, and the signal energy of the first electrophysiological signal may be counted; the first electrophysiological signal is then determined to contain the ocular signal when the signal amplitude is above a first threshold, such as 100 millivolts (mv), and the signal energy is concentrated in a first frequency interval, such as 0Hz to 10 Hz. Wherein the signal amplitude may be an average signal amplitude of the first electrophysiological signal. Secondly, the frequency interval in which the signal energy is concentrated can be firstly determined according to the distribution state of the power spectrum statistical signal energy of the first electrophysiological signal, for example, the power spectrum of the first electrophysiological signal is as shown in fig. 7, and then the signal energy can be determined to be concentrated at about 95Hz to 105Hz, 195Hz to 205Hz and 398Hz to 402 Hz. The concentration of the signal energy in a certain frequency interval indicates that the first physiological electrical signal includes a signal with a higher intensity and in the frequency band. Meanwhile, because the electro-ocular signals are mainly distributed in the first frequency interval, when the energy of the first electrophysiological signal is gathered in the first frequency interval, the electro-ocular signals contained in the first brain electrical signal can be determined. For example, when the first electrophysiological signal has a signal amplitude of 120mv, it is determined that 120mv is higher than 100mv, and the energy is concentrated in the range of 0 Hz-10 Hz, it is determined that the first electrophysiological signal comprises an EOG signal.

And S605, acquiring the electro-oculogram information according to the electro-oculogram signal. Wherein the electro-ocular information comprises eye movement position and eye movement frequency.

In a specific implementation, as shown in fig. 3, the analog first electrophysiological signal may be sampled at a sampling rate of 25Hz first, so as to remove a portion of the electroencephalogram signal and a portion of the electromyogram signal in the first electrophysiological signal. And then carrying out median filtering on the sampled first electrophysiological signal so as to obtain a pure EOG signal. Wherein, because the signal of EOG is mainly about 10Hz, the size of the template of the median filtering is taken as 5; at least one of the eye movement position and the eye movement frequency is then determined from the electrical eye signals, wherein the eye movement position and the eye movement frequency may be obtained using a threshold based peak detection technique. For example, the EOG sequence is x [ j ]]When x [ j ] is reached_p]When the formula (1) is satisfied, j is_pDetermining the position of peak point of eye movement, namely the eye movement position, and the eye movement frequency is xj]The quotient of the sequence length and the duration of the EOG.

S606, determining whether the first electrophysiological signal comprises an electromyographic signal. If yes, S607 is executed, and if not, S608 is executed.

In a specific implementation, the signal amplitude of the first electrophysiological signal may be obtained first, and the signal energy of the first electrophysiological signal may be counted; then, when the signal amplitude is higher than a second threshold value (such as 100mv) and the signal energy is concentrated in a second frequency interval (such as 45 Hz-80 Hz), determining that the first electrophysiological signal contains the electromyographic signal. Wherein the signal amplitude may be an average signal amplitude of the first electrophysiological signal. Secondly, the distribution state of the signal energy can be firstly counted according to the power spectrum of the first electrophysiological signal, and the frequency interval in which the signal energy is gathered can be determined. Meanwhile, because the myoelectric signal is mainly distributed in the second frequency interval, when the energy of the first electrophysiological signal is gathered in the second frequency interval, it can be determined that the first electroencephalogram signal contains the myoelectric signal.

And S607, acquiring the electromyographic information according to the electromyographic signal. The myoelectric information comprises a myoelectric position, myoelectric energy and myoelectric duration.

In a specific implementation, the EMG signal may be extracted from the first electrophysiological signal, wherein, as shown in fig. 4, a pure, high-frequency EMG signal may be obtained by inputting the first electrophysiological signal into a high-pass filter with a cutoff frequency of 45 Hz; then, the electromyographic position, the electromyographic energy and the electromyographic duration are determined according to the electromyographic signal, wherein, as shown in fig. 4, hilbert transformation can be performed on the high-pass filtered EMG signal so as to obtain an analytic signal of a real signal, envelope information of the real signal is obtained through the analytic signal, and finally, the envelope is detected through a peak value detection technology based on a threshold value method so as to obtain the electromyographic position, the electromyographic energy and the electromyographic duration.

S608, determining a sleep stage result of the user according to at least one of the energy change rate, the electro-oculogram information and the electromyogram information. This step is the same as S103 in the previous embodiment, and is not described again.

In summary, the flow and method of the sleep staging method in the embodiment of the present application can be represented by the block diagram shown in fig. 8. Firstly, acquiring a first electrophysiological signal, and then acquiring physiological characteristic information of a user in a sleeping process according to an EEG signal, an EMG signal and an EOG signal in the first electrophysiological signal; and then inputting the physiological characteristic information into a decision tree to obtain a sleep staging result.

Referring to fig. 9, fig. 9 is a schematic structural diagram of a sleep staging device according to an embodiment of the present application. As shown in the figures, the apparatus in the embodiment of the present application includes:

the collecting module 901 is configured to collect a first electrophysiological signal of a forehead area of a user during a sleep process.

In a specific implementation, after the first electrophysiological signal is acquired, the first electrophysiological signal may be sampled, but not limited to, at a sampling rate of 500 hertz (Hz) to be converted into a digital signal for processing.

Optionally, the acquiring module 901 is further configured to, before acquiring the first electrophysiological signal of the forehead area during the sleep process of the user, first acquire, as a reference signal, the second electrophysiological signal of the forehead area when the user is in the non-sleep state, where the user is determined to be in the awake state within the first 1 minute before the acquisition of the electrophysiological signal of the forehead area is started, and therefore, the signal acquired within the 1 minute may be used as the reference signal.

An extracting module 902, configured to extract a sleep physiological signal from the first electrophysiological signal, where the sleep physiological signal includes at least one of a first electroencephalogram signal, an electrooculogram signal, and an electromyogram signal.

In specific implementation, a first electroencephalogram signal can be extracted from the first electrophysiological signal, and a second electroencephalogram signal can be extracted from the reference signal, wherein, as shown in fig. 2, the first electrophysiological signal and the reference signal can be respectively input into a 0.5 Hz-35 Hz band-pass filter, so as to obtain a first electroencephalogram signal and a second electroencephalogram signal which are pure.

The band pass filter is an IIR zero-phase filter. A general IIR filter is a nonlinear phase filter that changes the phase of an original signal when filtering the signal and is a nonlinear change. The EEG signal has unstable characteristics, and useful EEG information in the sleep stage is represented in a low frequency range of 0.5 Hz-30 Hz. Therefore, small phase distortion can cause great change of low-frequency signals, and a zero-phase IIR filter is selected in the embodiment of the application.

Optionally, the extraction module 902 is further configured to extract the EOG signal from the first electrophysiological signal, wherein, as shown in fig. 3, the analog first electrophysiological signal may be first down-sampled at a sampling rate of 25Hz to remove the partial EEG signal and the partial electromyogram signal from the first electrophysiological signal. And then carrying out median filtering on the sampled first electrophysiological signal so as to obtain a pure EOG signal. Here, since the signal of EOG is mainly around 10Hz, the template size of median filtering is taken to be 5.

Optionally, the extracting module 902 is further configured to determine whether the first electrophysiological signal includes the EOG signal before extracting the EOG signal from the first electrophysiological signal, wherein a signal amplitude of the first electrophysiological signal may be obtained first, and a signal energy of the first electrophysiological signal may be counted; the method then determines that the first electrophysiological signal contains the ocular signal when the signal amplitude is above a first threshold and the signal energy is concentrated in a first frequency interval (e.g., 0Hz to 10 Hz). Wherein the signal amplitude may be an average signal amplitude of the first electrophysiological signal. Secondly, the distribution state of the signal energy can be firstly counted according to the power spectrum of the first electrophysiological signal, and the frequency interval in which the signal energy is gathered can be determined. Meanwhile, because the electro-ocular signals are mainly distributed in the first frequency interval, when the energy of the first electrophysiological signal is gathered in the first frequency interval, the electro-ocular signals contained in the first brain electrical signal can be determined. For example, when the first electrophysiological signal has a signal amplitude of 120mv, it is determined that 120mv is higher than 100mv, and the energy is concentrated in the range of 0 Hz-10 Hz, it is determined that the first electrophysiological signal comprises an EOG signal.

Optionally, the extraction module 902 may be further configured to extract the EMG signal from the first electrophysiological signal, wherein, as shown in fig. 4, the first electrophysiological signal may be input to a high-pass filter with a cut-off frequency of 45Hz to obtain a pure, high-frequency EMG signal.

Optionally, the extracting module 902 is further configured to determine whether the EMG signal is included in the first electrophysiological signal before extracting the EMG signal from the first electrophysiological signal, wherein the signal amplitude of the first electrophysiological signal may be obtained first and the signal energy of the first electrophysiological signal may be counted; then, when the signal amplitude is higher than a second threshold value and the signal energy is concentrated in a second frequency interval (e.g. 45 Hz-80 Hz), it is determined that the first electrophysiological signal comprises an EMG signal.

A determining module 903, configured to determine a sleep staging result of the user according to the sleep physiological signal. In a specific implementation, the physiological characteristic information of the user may be first acquired from sleep physiology, and then the sleep staging result may be determined according to the physiological characteristic information.

where i is a frequency interval in which the δ wave, the θ wave, the β wave, and the α wave are located, for example, 4Hz to 7Hz, and when the intervals 4Hz to 7Hz are serialized into 4, 5, 6, and 7, range (i) 4. P is the power corresponding to the frequency point in i, for example, for the θ wave, coordinate points (4,9), (5, 10), (6, 7), (7, 12) whose abscissa is in the range of 4Hz to 7Hz are found on the power spectrum, and the average power of the θ wave P (9+10+7+12)/4 (9.5 dB/H) can be obtained as 9.5dB/H_z。

In addition, the power spectrum estimation method based on the Welch method is adopted in the periodogram power spectrum estimation in the embodiment of the application. The reason is that the Welch method-based power spectrum estimation method combines windowing processing and averaging processing, and effectively reduces frequency false peaks. In the power spectrum estimation method of Welch method, if the signal to be processed is a signal x with length m_m(n) then, first, for x_m(n) performing segmentation, wherein each segment of signals are allowed to overlap, if the length of each segment of signals is M, the signals are divided into L segments, and L is (M-M/2)/(M/2), then the modified power spectrum of each segment of signals is

Optionally, the physiological characteristic information may further include an eye movement position and an eye movement frequency. The eye movement position and the eye movement frequency may be determined from the electrical eye signals, wherein the eye movement position and the eye movement frequency may be obtained using a threshold-based peak detection technique, as shown in fig. 3.

In the second case: when the electromyographic energy is larger than a sixth threshold (the sixth threshold is marked as x)₆) And the myoelectricity duration exceeds a seventh threshold (the seventh threshold is marked as x)₇) And theta₁/θ₂Not more than x₄and alpha is₁/α₂Not less than x₅and beta₁/β₂Not less than an eighth threshold value (eighthThe threshold is denoted x₈) And the eye movement frequency is not more than a ninth threshold (the ninth threshold is marked as x)₉) And then determining that the sleep staging result is a waking period. Wherein x is₆May be, but is not limited to, 0.8 times the energy of the EMG signal in the reference signal, x₇Can be but is not limited to 15s, x₉And may be, but is not limited to, 2 Hz.

Referring to fig. 10, fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown, the electronic device may include: at least one processor 1001, such as a CPU, at least one communication interface 1002, at least one memory 1003, at least one bus 1004. Bus 1004 is used to enable, among other things, connectivity communications between these components. For example, the electronic device may be a wearable head-mounted device, an eye mask, a mask, or the like. In this embodiment, the communication interface 1002 of the electronic device in this application is a wired sending port, and may also be a wireless device, for example, including an antenna apparatus, for performing signaling or data communication with other node devices. The memory 1003 may be a high-speed RAM memory or a non-volatile memory (e.g., at least one disk memory). The memory 1003 may optionally be at least one storage device located remotely from the processor 1001. A set of program codes is stored in the memory 1003 and the processor 1001 is used to call the program codes stored in the memory for performing the following operations:

The processor 1001 is further configured to perform the following operation steps:

and determining the sleep staging result according to the physiological characteristic information.

wherein the physiological characteristic information comprises an energy change rate of the electroencephalogram signal;

extracting a second electroencephalogram signal from the reference signal;

and determining the eye movement position and the eye movement frequency according to the eye electric signals.

and determining the myoelectric position, the myoelectric energy and the myoelectric duration according to the myoelectric signal.

It should be noted that, the present application also provides a storage medium for storing an application program, where the application program is used to execute, when running, the operation performed by the electronic device in the sleep staging method shown in fig. 1 and fig. 6.

It should be noted that, the embodiment of the present application also provides an application program, where the application program is configured to execute, when running, operations performed by the electronic device in the sleep staging method shown in fig. 1 and fig. 6.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others. The above-mentioned embodiments further explain the objects, technical solutions and advantages of the present application in detail. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A sleep staging method, the method comprising:

2. The method of claim 1, wherein determining the sleep staging result for the user based on the sleep physiological signal comprises:

acquiring physiological characteristic information of the user from the sleep physiological signal, wherein the physiological characteristic information comprises at least one of the following: the energy change rate corresponding to the first electroencephalogram signal, the eye movement position and the eye movement frequency corresponding to the electrooculogram signal, and the myoelectric position, the myoelectric energy and the myoelectric duration corresponding to the myoelectric signal;

3. The method of claim 2, wherein prior to collecting the first electrophysiological signal of the forehead region during sleep of the user, further comprising:

extracting a second electroencephalogram signal from the reference signal;

4. The method of claim 2, wherein prior to extracting the sleep physiological signal from the first electrophysiological signal, further comprising:

5. The method of claim 2, wherein prior to extracting the sleep physiological signal from the first electrophysiological signal, further comprising:

6. The method according to any one of claims 2-5, wherein the first brain electrical signal comprises at least one of a first frequency band electric wave, a second frequency band electric wave, a third frequency band electric wave and a fourth frequency band electric wave;

the determining the sleep staging result according to the physiological characteristic information comprises:

7. A sleep staging apparatus, the apparatus comprising:

8. The apparatus of claim 7, wherein the determination module is further to:

9. The apparatus of claim 8, wherein the acquisition module is further to:

the extraction module is further configured to:

extracting a second electroencephalogram signal from the reference signal;

the determination module is further to:

10. The apparatus of claim 8, wherein the extraction module is further to:

11. The apparatus of claim 8, wherein the extraction module is further to:

12. The apparatus according to any one of claims 8-11, wherein the first electroencephalogram signal includes at least one of a first-band electric wave, a second-band electric wave, a third-band electric wave, and a fourth-band electric wave;

the determination module is further to:

13. An electronic device, comprising: a processor, a memory, a communication interface, and a bus;

the memory stores executable program code;

the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory for performing the sleep staging method according to any one of claims 1 to 6.

14. A computer-readable storage medium having stored thereon a plurality of instructions adapted to be loaded by a processor and to perform the sleep staging method according to any one of claims 1 to 6.