A sleep monitoring method and device

Abstract

The present disclosure relates to a sleep monitoring method and device. The method includes obtaining sleep monitoring information of a user in a monitoring period, where the sleep monitoring information includes electroencephalogram data, electromyogram data, and electrooculogram data. The method further includes determining user sleep information based on the electroencephalogram data, electromyogram data, and electrooculogram data in the monitoring period, where the user sleep information includes sleep time information and sleep monitoring information in the wakefulness sleep stage, non-rapid eye movement sleep stage, and rapid eye movement sleep stage. In addition, the method further includes determining sleep time information and sleep monitoring information in three sub-stages of the non-rapid eye movement sleep stage in the user sleep information based on the electrooculogram data in the non-rapid eye movement sleep stage. In this way, it is possible to determine the sleep stage distribution of the user in the current monitoring period based on the multi-dimensional data monitored by the user, and it can more accurately reflect the sleep situation of the user in different monitoring periods.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and more particularly, to a sleep monitoring method and apparatus. Background Art

[0002] Sleep is not a static process, but a dynamic cycle consisting of multiple stages, usually divided into non-rapid eye movement sleep (NREM, abbreviated as N) and rapid eye movement sleep (REM, abbreviated as R). NREM stage 1 is the transition from wakefulness to sleep and is the lightest sleep stage. NREM stage 2 is a stage of light sleep, with a slowed heart rate and a drop in body temperature. NREM stage 3 is deep sleep, during which the body gets the most significant recovery. The REM stage is characterized by rapid eye movements, increased brain activity, and is associated with dreaming.

[0003] With the increasing stress in life and work, the quality of sleep has been significantly reduced, which in turn affects human physical health. Analyzing the sleep structure is very important for evaluating the sleep quality, and thus can improve the user's sleep condition in a targeted manner, and even solve sleep-related diseases. Summary of the Invention

[0004] Embodiments of the present disclosure provide a sleep monitoring method and apparatus.

[0005] In a first aspect of the present disclosure, a sleep monitoring method is provided. The method includes obtaining sleep monitoring information of a user in a monitoring period, where the sleep monitoring information includes electroencephalogram data, electromyogram data, and electrooculogram data. The method further includes determining user sleep information based on the electroencephalogram data, electromyogram data, and electrooculogram data, where the user sleep information includes sleep time information and sleep monitoring information in a wakefulness sleep stage, a non-rapid eye movement sleep stage, and a rapid eye movement sleep stage. In addition, the method further includes determining sleep time information and sleep monitoring information in three sub-stages of the non-rapid eye movement sleep stage in the user sleep information based on the electrooculogram data in the non-rapid eye movement sleep stage.

[0006] In a second aspect of the present disclosure, a sleep monitoring apparatus is provided. The apparatus includes an obtaining module configured to obtain sleep monitoring information of a user in a monitoring period, where the sleep monitoring information includes electroencephalogram data, electromyogram data, and electrooculogram data. The apparatus further includes a first determining module configured to determine user sleep information based on the electroencephalogram data, electromyogram data, and electrooculogram data, where the user sleep information includes sleep time information and sleep monitoring information in a wakefulness sleep stage, a non-rapid eye movement sleep stage, and a rapid eye movement sleep stage. In addition, the apparatus further includes a second determining module configured to determine sleep time information and sleep monitoring information in three sub-stages of the non-rapid eye movement sleep stage in the user sleep information based on the electrooculogram data in the non-rapid eye movement sleep stage.

[0007] In a third aspect of the present disclosure, there is provided a computer program product including a computer program, which is executed by a processor to implement the method according to the first aspect.

[0008] In a fourth aspect of the present disclosure, there is provided a machine-readable storage medium. Machine-executable instructions are stored on the machine-readable storage medium, and the machine-executable instructions are executed by a processor to implement the method provided according to the first aspect of the present disclosure.

[0009] It should be understood that the content described in the summary of the invention section is not intended to limit the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In combination with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. In the drawings, the same or similar reference numerals denote the same or similar elements, where:

[0011] Figure 1 A schematic diagram showing an example environment in which some embodiments of the present disclosure can be implemented;

[0012] Figure 2 A flowchart showing a sleep monitoring method according to some embodiments of the present disclosure;

[0013] Figure 3 A flowchart showing an exemplary process for determining user sleep information according to some embodiments of the present disclosure;

[0014] Figure 4 A schematic diagram showing an example process for determining sleep time information and sleep monitoring information in wake-sleep staging, non-rapid eye movement sleep staging, and rapid eye movement sleep staging according to some embodiments of the present disclosure;

[0015] Figure 5 A schematic diagram showing an example process for determining sleep time information and sleep monitoring information in N1, N2, and N3 sub-stages of non-rapid eye movement sleep staging according to some embodiments of the present disclosure;

[0016] Figure 6 A schematic diagram showing an example process for determining a sleep state according to some embodiments of the present disclosure;

[0017] Figure 7 A schematic diagram showing an exemplary sleep report formed based on user sleep information according to some embodiments of the present disclosure;

[0018] Figure 8A block diagram of a sleep monitoring device according to some embodiments of the present disclosure is shown; and

[0019] Figure 9 A block diagram of an electronic device in which multiple embodiments of the present disclosure can be implemented is shown. Detailed implementation manners

[0020] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0021] In the description of the embodiments of the present disclosure, the term "including" and its like should be understood as an open inclusion, that is, "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "an embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. There may also be other explicit and implicit definitions hereinafter.

[0022] Improving sleep quality is of profound significance for overall health and daily life, and the analysis of sleep structure is particularly important for the evaluation of sleep quality. By analyzing the sleep structure of a user, the sleep situation of the user can be determined, that is, the duration of each sleep stage (referring to each sleep stage mentioned below) of the user from waking up to falling asleep to waking up again in a complete sleep cycle and the relevant physiological parameter data can be known, and then the physiological condition of the user during sleep can be understood. After obtaining the sleep structure of the user, the sleep quality of the user can be evaluated, and even whether the user has health problems affecting health, such as respiratory diseases, cardiovascular diseases, psychological diseases, etc., can be detected.

[0023] In some related technologies, the sleep-wake cycle is promoted by recording body activities through a device worn on the wrist (such as a smart watch). In other related technologies, photoplethysmography is used through a wearable device (such as a smart watch) to monitor heart rate changes, and the sleep structure is analyzed based on the heart rate characteristics of different sleep stages. Although such methods are easy to detect, they mainly rely on one parameter (body movement signal or heart rate) to analyze the sleep structure of the user. In this way, the analyzed sleep structure is not sufficient to accurately reflect the actual sleep situation of the user, the physiological condition of the user in each sleep stage cannot be known, and it is even more impossible to detect whether the user has health problems. Even if an abnormal heart rate problem can be detected, it is only an occasional abnormality and cannot be combined with other physiological parameters to evaluate the diseases related to the abnormal heart rate.

[0024] In some related technologies, polysomnography (PSG) analyzes different stages of sleep by recording multiple physiological parameters. However, such methods are generally carried out in professional sleep centers and use a predefined rule set to identify different sleep stages. For example, a predefined EEG signal rule set is constructed based on the frequency characteristics of electroencephalogram (EEG) signals (such as delta waves, theta waves, etc.). The sleep monitoring and analysis implemented based on such technologies rely on the predefined signal rule set, and the accuracy of the definition of the signal rule set will affect the accuracy of sleep stage identification, and a large number of rules affect the data analysis and processing efficiency. In particular, during the sleep monitoring cycle, each sleep stage will repeatedly switch. For example, the user slowly enters the rapid eye movement (REM) sleep stage from the N1, N2, and N3 stages of non-rapid eye movement (NREM) sleep (i.e., the N1, N2, and N3 sub-stages mentioned later). After the REM sleep stage lasts for a period of time, it may enter the N3 stage of non-REM sleep again, slowly return to the N2 stage, and may enter the N3 stage again. In this complex changing situation, it is necessary to rely on the signal rule set to make judgments for each type one by one, and the analysis and processing efficiency is greatly affected.

[0025] To this end, embodiments of the present disclosure propose a sleep monitoring method. This method can first determine the sleep time and the corresponding EEG, electromyogram (EMG), and electrooculogram (EOG) data in the wake, non-REM, and REM sleep stages based on the EEG, EMG, and EOG data during the monitoring cycle. Then, based on the EOG data in the non-REM sleep stage, it further subdivides and determines the sleep time and the corresponding EEG, EMG, and EOG data of the three sub-stages in the non-REM sleep stage.

[0026] In this way, based on the data in the three dimensions of EEG, EMG, and EOG, it is possible to accurately identify the sleep structure that reflects the actual sleep situation of the user. Moreover, after analyzing and obtaining the three general sleep stages of wake, non-REM, and REM, based on the EOG data of non-REM, that is, the data of an incomplete monitoring cycle, and based on less data, it is possible to quickly identify the sub-stages in the non-REM sleep stage. In this way, the sleep structure analysis and processing efficiency is high and accurate.

[0027] Figure 1 FIG. shows a schematic diagram of an exemplary environment 100 in which some embodiments of the present disclosure can be implemented. As Figure 1As shown, the environment 100 includes a sleep monitor 104, which has a number of electrodes, including electrodes for detecting electroencephalogram (EEG) data (such as installed on the lateral temporal lobe of the user 102, i.e., in front of the ear), electrodes for detecting electrooculogram (EOG) data (such as installed near the supraorbital ridge of the user 102), and electrodes for detecting electromyogram (EMG) data (such as installed on the chin of the user 102). The sleep monitor 104 collects the physiological data of the user in each sleep stage during the monitoring period through the electrodes attached to various positions of the user 102, including EEG data, EMG data, and EOG data. In addition, the sleep monitor 104 also includes electrodes for detecting electrocardiogram (ECG) data, such as installed on the chest of the user 102. The environment 100 further includes a server 106, which is equipped with a sleep application platform configured with a sleep monitoring algorithm. The server 106 is communicatively connected to the sleep monitor 104, and the sleep monitor 104 sends the data collected by the electrodes to the server 106. The server 106 analyzes and processes the data according to the sleep monitoring algorithm to obtain the user's sleep structure, including the sleep time information and related physiological data (i.e., the sleep monitoring information hereinafter referred to) in the wakefulness sleep stage, non-rapid eye movement (NREM) sleep stage, and rapid eye movement (REM) sleep stage. In some embodiments, based on the physiological data during the monitoring period, such as the EEG, EMG, and EOG data from T1 to T5, the server 106 first determines the W stage (wakefulness sleep stage), N stage (NREM sleep stage), R stage (REM sleep stage) and their corresponding physiological data during the monitoring period. Then, based on the physiological data of the determined N stage (NREM sleep stage), the N1, N2, and N3 stages and their corresponding physiological data are determined.

[0028] As Figure 1 , the environment 100 further includes a terminal device 108, which can be an electronic device such as a mobile phone, a tablet, or a computer, and is installed with client software that can access the sleep application platform. The user can bind the device number of the sleep monitor 104 to their personal account through the client software. The terminal device 108 can display the user's sleep structure analyzed by the server 106 in the form of information on the terminal device. The information presents the order in which the W stage, N1 - N3 stages, and R stage appear during the monitoring period, the time corresponding to each stage, and the data corresponding to each stage ( Figure 1 in which the W, R, N1, and N2 stages are identified by columnar blocks with slashes, stars, horizontal lines, blanks, and cross-lines respectively). In some embodiments, the terminal device 108 displays the above information in the form of a sleep report.

[0029] In this way, based on the multi-dimensional physiological data within the monitoring period, a sleep structure that can reflect the user's actual sleep situation can be determined. Thus, when making a health judgment according to this sleep structure, it is more accurate. This method first determines the approximate sleep stages based on the full amount of data within the monitoring period, and then determines each sub-stage of the non-rapid eye movement (NREM) stage based on local data, that is, the eye movement data within the NREM stage. In this way, there is no need to perform a large amount of data operation and analysis on each stage using a rule set. The stage determination is carried out in two steps, and during the determination of the sub-stages, based on the eye movement data, the time information and physiological data of each sleep stage within the monitoring period can be efficiently processed and analyzed.

[0030] It should be understood that the architectures and functions in the exemplary environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of the present disclosure. Embodiments of the present disclosure can also be applied to other environments with different structures and / or functions.

[0031] Figure 2 The flowchart of a sleep monitoring method 200 according to some embodiments of the present disclosure is shown. The method 200 can be executed, for example, by Figure 1 the server 106 in the environment 100 shown. As Figure 2 shown, at block 202, the method 200 can obtain the sleep monitoring information of the user under the monitoring period. The sleep monitoring information includes electroencephalogram (EEG) data, electromyogram (EMG) data, and electrooculogram (EOG) data. In some embodiments, the sleep monitor is attached to various positions of the user's body through electrodes, and the electrodes are used to monitor physiological data throughout the entire process of the user being awake, falling asleep, sleeping, and waking up, such as physiological data such as EEG, EOG, and EMG (and if necessary, also including electrocardiogram (ECG) and blood oxygen concentration). The sleep monitor can store the collected physiological data therein, which can be stored in the form of chart data, sequence data, or array data. Among them, the monitoring period can be understood as the entire period from when the user turns on the sleep monitor in the awake state to when the user turns off the sleep monitor after waking up again. The sleep monitor sends the collected data of one monitoring period to the server.

[0032] At block 204, method 200 may determine user sleep information based on EEG data, EMG data, and EOG data during a monitoring period. The user sleep information includes sleep time information and sleep monitoring information for wakefulness, non-rapid eye movement (NREM) sleep stages, and rapid eye movement (REM) sleep stages. In some embodiments, the server can perform W, N, and R stage identification based on the physiological data (including EEG data, EMG data, and EOG data) obtained during the monitoring period, that is, it can determine the sleep time information for each stage, including start and end times, and can also determine the relevant physiological data for the corresponding stage, that is, it can determine the relevant sleep monitoring information for each stage. According to the start and end times of each stage, the order of each sleep stage can be determined. In addition, the server stores the determined time information and sleep monitoring information of the sleep stages in the form of user sleep information.

[0033] At block 206, method 200 may determine the sleep time information and sleep monitoring information for the three sub-stages of the non-rapid eye movement sleep stage in the user sleep information based on the EOG data during the non-rapid eye movement sleep stage. In some embodiments, the server can determine the sleep time information for the three sub-stages N1, N2, and N3 of the N stage, including start and end times, and the relevant physiological data for the corresponding stage, including EEG data, EMG data, and EOG data, based on the EOG data in the relevant physiological data of the N stage determined at block 204.

[0034] In this way, it is possible to first determine the general distribution of sleep stages during the monitoring period based on the full amount of data in the monitoring period, mainly clarifying the arrangement of wakefulness, non-rapid eye movement sleep stages, and rapid eye movement sleep stages during the monitoring period. It is possible to determine how many wakefulness, non-rapid eye movement sleep stages, and rapid eye movement sleep stages there are in a monitoring period, as well as their respective start and end times and their respective corresponding sleep monitoring information. Then, based on the EOG data in the non-rapid eye movement sleep stage during the monitoring period, a detailed identification of the non-rapid eye movement sleep stage is performed to identify the sub-stages within this stage based on less data. In this way, it is possible to more accurately identify the sleep structure that reflects the actual sleep situation of the user based on multi-dimensional data, and the processing efficiency is relatively high.

[0035] Figure 3FIG. 0 shows a flowchart of an exemplary process 300 for determining user sleep information according to some embodiments of the present disclosure. At block 302, the process 300 may obtain electroencephalogram (EEG) data during a monitoring period T, which includes brain waves and is recorded by an electroencephalogram (EEG). At block 304, it is determined whether the average frequency of the brain waves in consecutive frames of the EEG data is greater than or equal to a frequency threshold. If so, the process proceeds to block 306 to determine that the sleep time period corresponding to the EEG data of the consecutive frames is the sleep time information of the wake sleep stage W. Accordingly, the EEG data, electromyogram data, and electrooculogram data of the sleep time period are determined as the sleep monitoring information of the wake sleep stage W. Here, a frame refers to a data segment of a fixed time length, generally referred to as an epoch, which is usually set to 30 seconds. Consecutive frames may be set as multiple consecutive data segments of a fixed time length, such as 4 or 5, or even more. For the convenience of accurate identification, generally, the number should not be too large, not exceeding 6. Taking consecutive frames as a time window, a frequency judgment is made once. The frequency threshold is configured based on the characteristics of the brain waves in the wake sleep stage, generally set to 13 Hz. In some embodiments, assuming there are 20 frames in 10 minutes, taking 4 consecutive frames as a time window, the average frequency of the brain waves of 4 consecutive frames (such as frames 0 to 3) is obtained based on the spectrum analysis technique. If it is greater than or equal to the frequency threshold, it is determined that the brain waves of the 4 consecutive frames belong to the wake sleep stage W. Then, for the next 4 consecutive frames (such as frames 1 to 4), the average frequency of the brain waves is obtained based on the frequency analysis technique. If it is greater than or equal to the frequency threshold, it is determined that the brain waves of frame 4 also belong to the wake sleep stage W. In this way, consecutive frames are obtained by sliding the window for judgment until the end. In addition, the above process may also obtain multiple time windows by sliding the window and perform judgments synchronously. In some embodiments, assuming there are 20 frames in 10 minutes, taking 4 consecutive frames as a time window, the average frequency of the brain waves of 4 consecutive frames (such as frames 0 to 3) is obtained based on the spectrum analysis technique. If it is greater than or equal to the frequency threshold, it is determined that the brain waves of the 4 consecutive frames belong to the wake sleep stage W. Then, for the next 4 consecutive frames (such as frames 4 to 7), the average frequency of the brain waves is obtained based on the frequency analysis technique. If it is greater than or equal to the frequency threshold, it is determined that the brain waves of frames 4 to 7 also belong to the wake sleep stage W. In this way, consecutive frames are obtained by sliding the window for judgment until the end. In addition, the above process may also obtain multiple time windows by sliding the window and perform judgments synchronously. At block 304, if it is determined that the average frequency of the brain waves in consecutive frames is less than the frequency threshold, the next consecutive frame may be obtained for continued judgment.

[0036] At block 308, the process 300 may obtain electromyogram (EMG) data and electrooculogram (EOG) data for the remaining sleep time periods in the monitoring period T other than the wake-sleep stage W determined at block 306. The remaining sleep time periods in the monitoring period T are identified for sleep staging using the EOG data and the EMG data. The EOG data includes electrooculogram waves, which are recorded by electrooculography (EOG). The EMG data includes electromyogram waves, which are recorded by electromyography (EMG). At block 310, it is determined whether the change in the EMG voltage corresponding to consecutive frames in the EMG data containing the minimum EMG voltage amplitude is stable. At block 312, it is determined whether the eye movement speed in the EOG data for the sleep time period corresponding to the determination at block 310 is greater than or equal to an eye movement threshold. The eye movement threshold is set based on the eye movement speed in the rapid eye movement (REM) sleep stage, generally 100 deg / s. The process for obtaining the eye movement speed in the EOG data includes integrating the EOG signal, calculating the displacement of the integration result, then converting the horizontal and vertical displacements into angles, calculating the angular change between adjacent time points and dividing by the time interval, and determining the obtained angular velocity as the eye movement speed. If the determinations at blocks 310 and 312 are both yes, then the sleep time information and sleep monitoring information for the REM sleep stage R can be determined from the remaining sleep time periods. When a human body is in the REM sleep stage R, compared with other sleep stages, the muscles are relaxed, the amplitude of EMG activity is low, and the eye movement speed rotates rapidly due to dreams or active neuronal activities. When the above two characteristics are satisfied, the relevant information for the REM sleep stage R can be determined. In this way, after the REM sleep stage in the remaining sleep time periods is determined, at block 316, the other sleep time periods in the remaining sleep time periods except for the REM sleep stage can be determined as non-REM sleep stages. Accordingly, based on the time information of the other sleep time periods, the corresponding sleep monitoring information is determined.

[0037] As Figure 3 , the process 300 may, based on the EOG data of the non-REM sleep stage N determined at block 316, determine the sleep time information and sleep monitoring information for the first and third sub-stages N1 and N3 of the non-REM sleep stage at block 318. Then, based on the sleep time information of the first and third sub-stages N1 and N3 determined at block 318, the sleep time information and sleep monitoring information for the second sub-stage N2 of the non-REM sleep stage are determined.

[0038] In this way, identification can be performed according to the significant characteristics of the human body in different sleep stages. Based on the significant characteristics in the wake-sleep stage and the non-rapid eye movement (NREM) sleep stage, the former has significant changes in brain wave frequency, and the latter has significant changes in eye movement and electromyogram. Thus, the wake-sleep stage and the rapid eye movement (REM) sleep stage are identified from the monitoring period in sequence based on their respective characteristics. Based on the exclusion method, the part of the monitoring period that is not identified can be determined as the NREM sleep stage. The above method does not need to rely on a large number of rule sets, and can roughly analyze the sleep structure of the monitoring period by using relatively simple algorithms for identification and judgment. Then, based on the electrooculogram data of the determined NREM sleep stage, the sub-stages of the NREM sleep stage located between the wake-sleep stage and the REM sleep stage can be determined.

[0039] Figure 4 FIG. shows a schematic diagram of an exemplary process 400 for determining sleep time information and sleep monitoring information in the wake-sleep stage, the non-rapid eye movement (NREM) sleep stage, and the rapid eye movement (REM) sleep stage according to some embodiments of the present disclosure. The process 400 may include a first acquisition unit 404 acquiring electroencephalogram data 402 of a monitoring period T1 to T N , acquiring consecutive frames in the electroencephalogram wave 406 and sending them to a first response unit 408 for processing. When it is determined that the average frequency of the electroencephalogram waves in the sleep time period corresponding to the consecutive frames from T1 to T 1+i and the sleep time period from T N-j to T N is greater than or equal to the frequency threshold, then it is determined that the sleep time period from T1 to T 1+i and the sleep time period from T N-j to T N are both in the wake-sleep stage, where i, j, and N are natural numbers, and both i and j are less than N, and 1 + i < N - j. Then, a second acquisition unit 416 acquires electrooculogram waves 418-1 of the remaining sleep time period from T 1+i to T N-j from the electrooculogram data 412, and acquires electromyogram waves 418-2 of the remaining sleep time period from T 1+i to T N-j from the electromyogram data 414, and sends them to a second response unit 420. The second response unit 420 determines that the relevant sleep time period is the rapid eye movement (REM) sleep stage when the electromyogram data has the minimum electromyogram voltage amplitude and the electromyogram voltage change corresponding to the consecutive frames including the minimum electromyogram voltage amplitude is stable, and the eye movement speed of the electrooculogram data corresponding to the sleep time period of the electromyogram data is not less than the eye movement threshold, and the other sleep time periods are the non-rapid eye movement (NREM) sleep stage of the sleep time information. In the example shown in the figure, the sleep time period from T 1+m to T 1+n is determined as the rapid eye movement (REM) sleep stage, and the other sleep time periods from T 1+i to T 1+m and T1+n ~T N-j It is determined as non-rapid eye movement sleep staging. Among them, n and m are natural numbers and less than N, and 1 + i < 1 + m < 1 + n < N - j. Then, the determination unit 424 determines the user sleep information 426 based on the time information of each stage of the brain wave 410 for which the wake-sleep staging is determined, and the eye waves 422-1 and 422-2 for which the non-rapid eye movement sleep analysis and rapid eye movement sleep staging are determined. The user sleep information 426 includes electroencephalogram data, electrooculogram data, and electromyogram data, and different sleep stages correspond to different electro-wave data.

[0040] In some embodiments, the determination process of the stable change of the electromyogram voltage corresponding to the continuous frame with the minimum electromyogram voltage amplitude in the electromyogram data includes determining the minimum electromyogram voltage amplitude from the remaining sleep time period, and two mutation points before and after the minimum electromyogram voltage amplitude. The mutation point refers to the ratio of its voltage amplitude to the minimum electromyogram voltage amplitude being greater than the amplitude ratio threshold, and the amplitude ratio threshold is greater than or equal to 1.5. In one example, the electromyogram wave is shown by the electromyogram voltage. By identifying the voltage amplitudes at all wave troughs in the waveform and determining the minimum electromyogram voltage amplitude therefrom, it can be determined that a period of time near this minimum electromyogram voltage amplitude may be the rapid eye movement sleep stage. By identifying the mutation points before and after the minimum electromyogram voltage amplitude, if the voltage amplitude of the previous mutation point and the minimum electromyogram voltage amplitude are greater than or equal to 1.5, the time period before the previous mutation point is not in the rapid eye movement sleep stage. If the voltage amplitude of the latter mutation point and the minimum electromyogram voltage amplitude are greater than or equal to 1.5, the time period after the latter mutation point is not in the rapid eye movement sleep stage. The determination process further includes determining that the change of the electromyogram voltage corresponding to the continuous frame within the sleep time period between the two mutation points is stable in response to the average voltage amplitude within the sleep time period between the two mutation points not being greater than the amplitude threshold. In one example, the average voltage amplitude of the data within the sleep time period between the two mutation points is calculated and then compared with the amplitude threshold. If it does not exceed the amplitude threshold, it is stable. The amplitude threshold is determined based on the general change of the electromyogram in the rapid eye movement sleep stage, and the amplitude threshold is the electromyogram voltage value, generally 5 μV.

[0041] In some embodiments, due to poor electrode contact or special body positions, it may result in the occurrence of the minimum electromyogram (EMG) voltage during sleep stages other than the rapid eye movement (REM) sleep stage. Determine the minimum EMG voltage amplitude from the remaining sleep time period, and two mutation points before and after the minimum EMG voltage amplitude, which includes first determining the minimum EMG voltage amplitude from the remaining sleep time period. When no mutation point is identified before or after the minimum EMG voltage amplitude, that is, as long as one mutation point is not identified, then the minimum EMG voltage amplitude needs to be re-determined. Then, determine the second smallest EMG voltage amplitude from the remaining sleep time period. Identify mutation points before and after the second smallest EMG voltage amplitude. If there are any, determine the second smallest EMG voltage amplitude as the target minimum EMG voltage amplitude. Otherwise, repeat the above process until the target minimum EMG voltage amplitude is determined. After that, based on the foregoing embodiments, determine the stability of the EMG voltage change between the two mutation points.

[0042] Figure 5 FIG. shows a schematic diagram of an exemplary process 500 for determining sleep time information and sleep monitoring information for N1, N2, and N3 sub-stages during non-REM sleep stages according to some embodiments of the present disclosure. The process 500 includes a time extraction unit 504 extracting the sleep time information for the wake and REM sleep stages respectively from any sleep monitoring information (such as electroencephalogram (EEG), electromyogram (EMG), electrooculogram (EOG) data) in the user sleep information 502, and determining the start time (or end time) of the first sub-stage of non-REM sleep and the end time (or start time) of the third sub-stage of non-REM sleep located between adjacent wake and REM sleep stages in block 506-1 and block 506-2 respectively. In some embodiments, the sleep structure generally shows such a situation of "W-N1-N2-N3-R-N3-N2-N1-W". In this case, there are two sub-situations: "W-N1-N2-N3-R" and "R-N3-N2-N1-W". By judging the occurrence order of adjacent W and R, it is possible to determine whether it is the former or the latter sub-situation. Then, for the former, the end time of the wake sleep stage can be determined as the start time of the first sub-stage of non-REM sleep (such as Figure 5 T shown in 1+i ), and the start time of the REM sleep stage can be determined as the end time of the third sub-stage of non-REM sleep (such as Figure 5 T shown in 1+m ). For the latter, the start time of the wake sleep stage can be determined as the end time of the first sub-stage of non-REM sleep (such as Figure 5 T shown in N-j ), and the end time of the REM sleep stage can be determined as the start time of the third sub-stage of non-REM sleep (such as Figure 5 T shown in1+n ).

[0043] For example Figure 5 , the process 500 includes the response unit 510 determining, in block 512, the sleep time information of the first sub-stage and the third sub-stage of the non-rapid eye movement (NREM) sleep stage based on the change in the electrooculogram (EOG) voltage of consecutive frames in the EOG data during the NREM sleep stage that is located before the adjacent wake-sleep stage and rapid eye movement (REM) sleep stage (which can be the N stage corresponding to T 1+i ~T 1+m , or the N stage corresponding to T 1+n ~T N-j ), and one of two sub-cases (the former sub-case corresponds to T 1+i ~T 1+m , and the latter sub-case corresponds to T 1+n ~T N-j ). In some embodiments, the sleep time information of the N1 and N3 sub-stages can be determined in parallel. In other embodiments, the sleep time information of the N1 sub-stage can be determined first and then the sleep time information of the N3 sub-stage, or, the sleep time information of the N3 sub-stage can be determined first and then the sleep time information of the N1 sub-stage.

[0044] In some embodiments, for the N stage corresponding to T 1+i ~T 1+m , in response to the EOG voltage of consecutive frames in the EOG data during the NREM sleep stage remaining unchanged (such as 508-1 in Figure 5 ), taking the end time of the third sub-stage of the NREM sleep stage (i.e., T 1+m ) as a reference, determining the sleep time period corresponding to the EOG data corresponding to the consecutive frames (assuming the start time of the consecutive frames is T x , then the sleep time period is T x ~T 1+mThe sleep time information for the third sub-stage of non-rapid eye movement sleep staging. In one example, taking the end time of the third sub-stage as a reference, consecutive frames are intercepted forward. If the average electrooculogram (EOG) voltage of the consecutive frames does not exceed a stable voltage threshold, which is a value close to 0, such as 0.5 microvolts, it is considered that the EOG voltage of the consecutive frames remains unchanged. During this process, first, the interception judgment is made according to the preset length of the consecutive frames, and then the length of the consecutive frames is gradually increased for the interception judgment until the average EOG voltage of the consecutive frames exceeds the stable voltage threshold. Then, it is considered that the sleep time period corresponding to the EOG data corresponding to the length of the previously intercepted consecutive frames is the sleep time information for the third sub-stage. In another example, taking the end time of the third sub-stage as a reference, the waveform of the consecutive frames is intercepted forward. If the waveform line segment is a straight line segment or the coincidence rate with the straight line segment reaches more than 95%, it is considered that the EOG voltage of the consecutive frames remains unchanged. The sleep time period corresponding to the EOG data corresponding to the intercepted consecutive frame length is the sleep time information for the third sub-stage.

[0045] In some embodiments, for the N stage corresponding to T 1+n ~T N-j When the EOG voltage of the consecutive frames in the EOG data under non-rapid eye movement sleep staging (such as Figure 5 508-2) remains unchanged, taking the start time of the third sub-stage of non-rapid eye movement sleep staging (i.e., T 1+n ) as a reference, the sleep time period corresponding to the EOG data corresponding to the consecutive frames is determined (assuming the end time of the consecutive frames is T y , then the sleep time period is T 1+n ~T y ) as the sleep time information for the third sub-stage of non-rapid eye movement sleep staging. In one example, taking the start time of the third sub-stage as a reference, consecutive frames are intercepted backward. If the average EOG voltage of the consecutive frames does not exceed a stable voltage threshold, which is a value close to 0, such as 0.5 microvolts, it is considered that the EOG voltage of the consecutive frames remains unchanged. During this process, first, the interception judgment is made according to the preset length of the consecutive frames, and then the length of the consecutive frames is gradually increased for the interception judgment until the average EOG voltage of the consecutive frames exceeds the stable voltage threshold. Then, it is considered that the sleep time period corresponding to the EOG data corresponding to the length of the previously intercepted consecutive frames is the sleep time information for the third sub-stage. In another example, taking the start time of the third sub-stage as a reference, the waveform of the consecutive frames is intercepted backward. If the waveform line segment is a straight line segment or the coincidence rate with the straight line segment reaches more than 95%, it is considered that the EOG voltage of the consecutive frames remains unchanged. The sleep time period corresponding to the EOG data corresponding to the intercepted consecutive frame length is the sleep time information for the third sub-stage.

[0046] During the third sub-stage of non-rapid eye movement (NREM) sleep in the average human body, eye movements almost completely stop but still exhibit fluctuations, approaching zero. At this stage, the user is in a deep sleep stage. In this way, based on the significant difference in eye movements between the N3 sub-stage and other stages, the sleep time information of the third sub-stage can be effectively identified from the NREM sleep stages.

[0047] In some embodiments, for T 1+i ~T 1+m corresponding N stage, in response to the average interval time between the positive and negative amplitudes of adjacent electrooculogram (EOG) voltages in consecutive frames of EOG data during NREM sleep stages being not less than the interval threshold, using the start time of the first sub-stage of NREM sleep stages (i.e., T 1+i ) as a reference, determine the sleep time period corresponding to the EOG data of this consecutive frame (assuming the end time of the consecutive frame is T x’ , then the sleep time period is T 1+i ~ T x’ ) as the sleep time information of the first sub-stage of NREM sleep stages. In an example, when there are multiple positive and negative amplitudes in a consecutive frame, calculate the interval time between the positive and negative amplitudes of adjacent EOG voltages to obtain multiple interval times, and calculate the average interval time of multiple interval times within the consecutive frame. The interval threshold is generally set to 0.5 seconds. When the average interval time is greater than or equal to the interval threshold, then determine that the sleep time period corresponding to the consecutive frame is the sleep time information of the first sub-stage of NREM sleep stages. In this process, first, according to the preset length of the consecutive frame, start from the start time of the N1 stage and intercept and judge backward, and then gradually increase the length of the consecutive frame for interception and judgment until the average interval time between the positive and negative amplitudes of adjacent EOG voltages in the consecutive frame is less than the interval threshold, then consider that the sleep time period corresponding to the EOG data of the length of the previously intercepted consecutive frame is the sleep time information of the first sub-stage.

[0048] In some embodiments, for T 1+n ~T N-j corresponding N stage, in response to the average interval time between the positive and negative amplitudes of adjacent EOG voltages in consecutive frames of EOG data during NREM sleep stages being not less than the interval threshold, using the end time of the first sub-stage of NREM sleep stages (i.e., T N-j ) as a reference, determine the sleep time period corresponding to the EOG data of this consecutive frame (assuming the start time of the consecutive frame is T y’ , then the sleep time period is T y’ ~T N-j)The sleep time information is for the first sub-stage of non-rapid eye movement (NREM) sleep staging. In one example, when there are multiple positive and negative amplitudes in consecutive frames, the time intervals between the positive and negative amplitudes of adjacent electrooculogram (EOG) voltages are calculated to obtain multiple time intervals, and the average time interval within the consecutive frames is calculated. The interval threshold is generally set to 0.5 seconds. When the average time interval is greater than or equal to the interval threshold, it is determined that the sleep time period corresponding to the consecutive frames is the sleep time information for the first sub-stage of NREM sleep staging. In this process, first, based on the length of the preset consecutive frames, intercept and judge backward from the end time of the N1 stage, and then gradually increase the length of the consecutive frames for intercept and judgment until the average time interval between the positive and negative amplitudes of the adjacent EOG voltages in the consecutive frames is less than the interval threshold. Then, it is considered that the sleep time period corresponding to the EOG data corresponding to the length of the previously intercepted consecutive frames is the sleep time information for the first sub-stage.

[0049] Generally, during the first sub-stage of NREM sleep in the human body, slow eye movements occur, and the time for the amplitude change of the eye voltage is longer than that in other sleep stages. In this way, based on the significant difference in eye movements between the N1 sub-stage and other stages, the sleep time information for the first sub-stage can be effectively identified from the NREM sleep staging.

[0050] As Figure 5 shown, the process 500 includes a time determination unit 514. Based on the sleep time information of N1 and N3 determined in block 512, the sleep time information for the second sub-stage of NREM sleep staging can be determined in block 516. In some embodiments, based on the end time of the first sub-stage and the start time of the third sub-stage of NREM sleep staging located between the adjacent wake-sleep stage and rapid eye movement (REM) sleep stage, the sleep time information for the second sub-stage of NREM sleep staging is determined. Taking Figure 5 as an example, the start time T x of the third sub-stage is the end time of the second sub-stage, and the end time T x’ of the first sub-stage is the start time of the second sub-stage. Then, the sleep time information for the second sub-stage corresponding to the first sub-case is T x’ ~T x . In some embodiments, based on the start time of the first sub-stage and the end time of the third sub-stage of NREM sleep staging located between the adjacent wake-sleep stage and REM sleep stage, the sleep time information for the second sub-stage of NREM sleep staging is determined. Taking Figure 5 as an example, the start time T y’ of the first sub-stage is the end time of the second sub-stage, and the end time T yIf it is the start time of the second sub-stage, the sleep time information of the second sub-stage corresponding to the second sub-case is T y ~ T y’ 。By identifying the first sub-stage and the second sub-stage, without relying on the physiological characteristics of the user during the second sub-stage, the sleep time information of the second sub-stage of non-rapid eye movement sleep stage can be quickly determined. Then, based on the sleep time information determined for each sub-stage, the sleep monitoring information related to the sleep time information is determined as the sleep monitoring information for the sub-stage corresponding to the non-rapid eye movement sleep stage.

[0051] In some embodiments, such situations as "R-N2-N3-R", "R-N3-N2-N3-R", "R-N3-N2-N1-N2-N3-R", and "R-N2-N1-N2-N3-R" may also occur in the sleep structure. Based on the electrooculogram data during non-rapid eye movement sleep stage, determining the sleep time information and sleep monitoring information for the three sub-stages of non-rapid eye movement sleep stage also includes another set of process subdivisions for non-rapid eye movement sleep stage by judging the situation where there are adjacent Rs and no W during this period. The process includes determining the end time or start time of the third sub-stage of non-rapid eye movement sleep stage located between the adjacent rapid eye movement sleep stages based on the respective sleep time information of the adjacent rapid eye movement sleep stages in the monitoring cycle. The process also includes determining the sleep time information of the third sub-stage of non-rapid eye movement sleep stage located between the adjacent rapid eye movement sleep stages based on the electrooculogram voltage change of consecutive frames in the electrooculogram data during non-rapid eye movement sleep stage between the adjacent rapid eye movement sleep stages, and the end time or start time of the third sub-stage of non-rapid eye movement sleep stage. This process includes identifying the first sub-stage of non-rapid eye movement sleep stage for the sleep time period between the adjacent rapid eye movement sleep stages excluding the third sub-stage. If not identified, the sleep time information of the second sub-stage of non-rapid eye movement sleep stage is determined based on the time information of rapid eye movement sleep stage and the sleep time information of the third sub-stage of non-rapid eye movement sleep stage. If identified, first determine the sleep time information of the first sub-stage of non-rapid eye movement sleep stage, and then determine the sleep time information of the second sub-stage of non-rapid eye movement sleep stage based on the time information of rapid eye movement sleep stage, the sleep time information of the third sub-stage of non-rapid eye movement sleep stage, and the sleep time information of the first sub-stage of non-rapid eye movement sleep stage. Finally, based on the sleep time information of each sub-stage of non-rapid eye movement sleep stage between adjacent Rs, the corresponding sleep monitoring information is determined.

[0052] In some embodiments, for the cases of "R-N2-N3-R" or "R-N3-N2-N3-R", first determine whether N3 exists. After that, when N1 is not recognized, determine N2. The process of determining N3 can be achieved by judging whether the electrooculogram voltage of consecutive frames remains unchanged, and based on the time of the previous R or the next R and the consecutive frames involved in the steadily changing electrooculogram voltage, determine the sleep time information of N3. If N3 does not exist and N1 is not recognized either, then determine the non-rapid eye movement sleep stage between adjacent Rs as N2. Taking "R-N2-N3-R" as an example, in one example, use the start time of the next R as the end time of N3, and use the start point of the consecutive frames with stable voltage change as the start time of N3, so that the sleep time information of N3 can be determined. After that, based on the sleep time information of N3 and the sleep time information of R, the sleep time information of N2 can be determined. Taking "R-N2-N3-R" as an example, in another example, use the end time of the previous R as the start time of N2, and use the start time of N3 as the end time of N2, so that the sleep time information of N2 can be determined. Finally, based on their respective sleep time information, the corresponding sleep monitoring information can be determined.

[0053] In some embodiments, for the cases of "R-N3-N2-N1-N2-N3-R" or "R-N2-N1-N2-N3-R", first determine whether N3 exists, and then identify N1 and N2. The process of determining N3 can be achieved by judging whether the electrooculogram voltage of consecutive frames remains unchanged, and based on the time of the previous R or the next R and the consecutive frames involved in the steadily changing electrooculogram voltage, determine the sleep time information of N3. Then, from the electrooculogram data corresponding to the remaining sleep time period, identify the part where the electrooculogram waveform is a square wave. When the duration of the square wave is greater than 1 minute, determine the duration of the square wave as the sleep time information of N1. Then determine the unrecognized sleep time period as the sleep time information of N2. Based on the fact that during N1, eye movement activity is slower and generally more regular, and generally shows a square wave change. Determine the sleep time period where N1 is located by identifying the waveform. After that, after determining the sleep time information of N3 and N1, the sleep time information of N2 can be quickly determined. When the duration of the square wave is not greater than 1 minute, then determine the sleep time period between adjacent Rs except for N3 as the sleep time information of N2. In this case, if the user briefly enters the N1 stage and quickly enters N2, then approximately default their sleep state to be in N2. If N3 is not recognized but there are N1 and N2, then after recognizing N1 based on the foregoing method, determine the remaining sleep time period as N2. Finally, based on their respective sleep time information, the corresponding sleep monitoring information can be determined.

[0054] In some embodiments, during the period between adjacent W and R, N3 may not be present before N2 enters R, or during the period between adjacent R and W, N3 may not be present before R leaves and enters N2. Based on the electrooculogram data during the non-rapid eye movement (NREM) sleep stage between adjacent wake-sleep stages and rapid eye movement (REM) sleep stages in a monitoring period, determining the sleep time information and sleep monitoring information for the three sub-stages of the NREM sleep stage further includes, in response to the NREM sleep stage not having a third sub-stage, based on the electrooculogram voltage change of consecutive frames in the electrooculogram data during the NREM sleep stage between the adjacent wake-sleep stage and REM sleep stage, and the start time or end time of the first sub-stage of the NREM sleep stage, determining the sleep time information of the first sub-stage of the NREM sleep stage. Then, based on the sleep time information of the first sub-stage of the NREM sleep stage and the sleep time information of the NREM sleep stage, determining the sleep time information of the second sub-stage of the NREM sleep stage. That is, the sleep time period within the NREM sleep stage excluding the first sub-stage is determined as the sleep time information of the second sub-stage. In one example, if it is determined using some embodiments that there is no situation where the electrooculogram voltage of consecutive frames remains unchanged in the electrooculogram data during the NREM sleep stage, then it is determined that the NREM sleep stage does not have a third sub-stage. Then, using some embodiments, it is determined that the average interval time between the positive and negative amplitudes of adjacent electrooculogram voltages of consecutive frames in the electrooculogram data during the NREM sleep stage is not less than the interval threshold, and based on the start time or end time of the first sub-stage of the NREM sleep stage determined using some embodiments as a reference, the sleep time period corresponding to the electrooculogram data of this consecutive frame is determined as the sleep time information of the first sub-stage of the NREM sleep stage. Finally, the remaining sleep time period in the NREM sleep stage is determined as the sleep time information of the second sub-stage of the NREM sleep stage. Taking the sleep structure of W first and then R as an example, the end time of N1 is taken as the start time of N2, and the start time of R is taken as the end time of N2. Taking the sleep structure of R first and then W as an example, the end time of R is taken as the start time of N2, and the start time of N1 is taken as the end time of N2.

[0055] Figure 6A schematic diagram of an example process 600 for determining a sleep state according to some embodiments of the present disclosure is shown. The process 600 may include, based on user sleep information 602 and electrocardiogram data 604 and blood oxygen saturation data 606 during a monitoring period, a data extraction unit 608 extracting sleep time information for non-rapid eye movement (NREM) sleep stages and rapid eye movement (REM) sleep stages, and determining, at block 610, the corresponding electrocardiogram data and blood oxygen saturation data for the NREM sleep stages and REM sleep stages. The process 600 includes, based on the corresponding electrocardiogram data and blood oxygen saturation data for the NREM sleep stages and REM sleep stages, a state determination unit 612 performing state determination to determine whether the user is in a normal sleep state as shown in block 614 or in a hypopnea sleep state as shown in block 616. In some embodiments, in response to the blood oxygen saturation data at multiple moments during the NREM sleep stages and REM sleep stages being not greater than a blood oxygen threshold, the electrocardiogram data corresponding to the multiple moments is obtained. Thereafter, in response to the change rate of the heart rate of the electrocardiogram data at the multiple moments compared to the heart rate of the electrocardiogram data at a previous moment exceeding an electrocardiogram change rate threshold, it is determined that the user is in a hypopnea sleep state; otherwise, the user is in a normal sleep state. In one example, a heart rate value may be obtained by processing an electrocardiogram wave, the heart rate values H1 of the electrocardiogram data at multiple consecutive moments are obtained, and at the same time, the heart rate values H0 of the electrocardiogram data at multiple consecutive moments before that are obtained. By calculating (H1 - H0) / H0, the change rate is obtained. Generally, under normal circumstances, the electrocardiogram change rate is about 1%, or even close to 0. When the set heart rate change threshold is 1% (the appropriate threshold can also be adjusted according to the heart rate status of each user, especially for users with arrhythmia, the threshold can be increased), when the heart rate suddenly becomes very slow or very fast, and when the blood oxygen saturation data is poor, the user is in a hypopnea sleep state. Among them, the electrocardiogram data is collected by electrode patches attached to the chest and uploaded to the server. The electrocardiogram data includes electrocardiogram waves, which are recorded by an electrocardiogram (ECG or EKG), and the electrocardiogram change rate threshold is determined based on the electrocardiogram data of a large number of users in a normal sleep state. The blood oxygen saturation data is collected by a pulse oximeter and uploaded to the server, and the blood oxygen threshold is generally 94%.

[0056] In this way, by first detecting the situation of blood oxygen saturation data at consecutive moments and then combining the electrocardiogram data at consecutive moments, the sleep state of the user can be identified more reliably and accurately. When a hypopnea sleep state occurs, the user may have serious sleep health problems such as apnea in the later stage. By identifying the hypopnea sleep state, the user's physical state can be prompted, so that the user can improve the poor physical state in time.

[0057] Figure 7A schematic diagram of an exemplary sleep report 700 formed based on user sleep information according to some embodiments of the present disclosure is shown. After analyzing the sleep structure based on the foregoing embodiments, the mobile terminal presents the user sleep information in the sleep report 700 based on the processing result of the server, such as the wake-sleep stages, non-rapid eye movement sleep stages (including N1, N2, N3 sub-stages), and rapid eye movement sleep stages, including the time, duration, and chronological arrangement of multiple sleep stages. The sleep situation during the time periods T1 to T5 is presented in the form of a bar chart in the sleep report 700, and the bars with slashes, stars, horizontal lines, blanks, and cross lines are used to identify W, R, N1, N2, and N3 respectively. Moreover, a total analysis of the entire sleep structure is performed in the sleep report 700 to determine the user's actual sleep onset time, sleep onset duration, sleep duration, and average sleep cycle.

[0058] Figure 8 A block diagram of a sleep monitoring device 800 according to some embodiments of the present disclosure is shown. As Figure 8 shown, the device 800 includes an acquisition module 802 configured to acquire the sleep monitoring information of the user under a monitoring period, and the sleep monitoring information includes electroencephalogram data, electromyogram data, and electrooculogram data. The device 800 further includes a first determination module 804 configured to determine the user sleep information based on the electroencephalogram data, electromyogram data, and electrooculogram data under the monitoring period, and the user sleep information includes the sleep time information and sleep monitoring information in the wake-sleep stage, non-rapid eye movement sleep stage, and rapid eye movement sleep stage. In addition, the device 800 further includes a second determination module 806 configured to determine the sleep time information and sleep monitoring information in the three sub-stages of the non-rapid eye movement sleep stage in the user sleep information based on the electrooculogram data in the non-rapid eye movement sleep stage.

[0059] In some embodiments, the first determination module 804 includes a first response unit configured to determine that the sleep time period corresponding to the electroencephalogram data of the continuous frames is the sleep time information of the wake-sleep stage when the average frequency of the brain waves in the electroencephalogram data of the continuous frames is not less than the frequency threshold. The first determination module 804 includes a second response unit configured to determine that the relevant sleep time period is the rapid eye movement sleep stage and the other sleep time periods are the sleep time information of the non-rapid eye movement sleep stage from the remaining sleep time periods except the wake-sleep stage in the monitoring period in response to that the electromyogram data has the minimum electromyogram voltage amplitude and the electromyogram voltage change corresponding to the continuous frames including the minimum electromyogram voltage amplitude is stable, and the eye movement speed of the electrooculogram data corresponding to the sleep time period of the electromyogram data is not less than the eye movement threshold. In addition, the first determination module 804 further includes a determination unit configured to determine the sleep monitoring information related to the sleep time period as the sleep monitoring information of the sleep stage corresponding to the sleep time period based on the determined sleep time period.

[0060] In some embodiments, the second determination module 806 includes a time extraction unit configured to determine the start time of the first sub-stage and the end time of the third sub-stage of the non-rapid eye movement (NREM) sleep stage located between the adjacent wake-sleep stage and rapid eye movement (REM) sleep stage in the monitoring period, or determine the end time of the first sub-stage and the start time of the third sub-stage of the NREM sleep stage located between the adjacent wake-sleep stage and REM sleep stage, based on the sleep time information of the adjacent wake-sleep stage and REM sleep stage in the monitoring period respectively. The second determination module 806 includes a response unit configured to determine the sleep time information of the third sub-stage and the sleep time information of the first sub-stage of the NREM sleep stage located between the adjacent wake-sleep stage and REM sleep stage, based on the change of the electrooculogram (EOG) voltage in consecutive frames in the EOG data under the NREM sleep stage between the adjacent wake-sleep stage and REM sleep stage in the monitoring period, and the start time of the first sub-stage and the end time of the third sub-stage or the end time of the first sub-stage and the start time of the third sub-stage of the NREM sleep stage. The second determination module 806 includes a time determination unit configured to determine the sleep time information of the second sub-stage of the NREM sleep stage, based on the sleep time information of the third sub-stage and the sleep time information of the first sub-stage of the NREM sleep stage located between the adjacent wake-sleep stage and REM sleep stage. In addition, the second determination module 806 includes a determination unit configured to determine the sleep monitoring information related to the sleep time information as the sleep monitoring information under the sub-stage of the NREM sleep stage, based on the sleep time information determined for each sub-stage.

[0061] Figure 9 FIG. shows a schematic block diagram of an exemplary device 900 that may be used to implement the embodiments of the present disclosure. As Figure 9 shown, the device 900 includes a processor 901 that can execute various appropriate actions and processes according to the computer program instructions stored in the read-only memory (ROM) 902 and loaded into the random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The processor 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904. The input / output (I / O) interface 905 is also connected to the bus 904.

[0062] The various processes and treatments described above, such as method 200, may be executed by processor 901. For example, in some embodiments, method 200 may be implemented as a software program tangibly embodied in a machine-readable medium. In some embodiments, part or all of the software program may be loaded and / or installed onto device 900 via ROM 902. When the software program is loaded into RAM 903 and executed by processor 901, one or more actions of method 200 described above may be performed.

[0063] The functions described above herein may be performed at least in part by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip of systems (SOCs), complex programmable logic devices (CPLDs), and the like.

[0064] The program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, a special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0065] The present disclosure may be a method, an apparatus, a system, and / or a program product. The program product may include a machine-readable storage medium having thereon machine-readable program instructions for performing various aspects of the present disclosure. The machine-readable program instructions described herein may be downloaded from the machine-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the machine-readable program instructions from the network and forwards the machine-readable program instructions for storage in the machine-readable storage medium in each computing / processing device.

[0066] The machine program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The machine-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the machine-readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit may execute the machine-readable program instructions to implement various aspects of the present disclosure.

[0067] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. Additionally, although the operations are depicted in a particular order, this should be understood to require that the operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed to achieve the desired result. In certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented separately or in any suitable sub-combination in multiple implementations.

[0068] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. On the contrary, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A sleep monitoring method, characterized in that, Including: Obtaining the sleep monitoring information of a user in a monitoring period, where the sleep monitoring information includes electroencephalogram (EEG) data, electromyogram (EMG) data, and electrooculogram (EOG) data; Based on the EEG data, EMG data, and EOG data in the monitoring period, determining the user's sleep information, where the user's sleep information includes the sleep time information and sleep monitoring information in the wake-sleep stage, non-rapid eye movement (NREM) sleep stage, and rapid eye movement (REM) sleep stage; including: When the average frequency of the brain waves in consecutive frames of the EEG data is not less than the frequency threshold, determining that the sleep time period corresponding to the EEG data of the consecutive frames is the sleep time information in the wake-sleep stage; When the EMG data has the minimum EMG voltage amplitude and the change in the EMG voltage corresponding to the consecutive frames including the minimum EMG voltage amplitude is stable, and the eye movement speed of the EOG data corresponding to the sleep time period of the EMG data is not less than the eye movement threshold, determining, from the remaining sleep time periods in the monitoring period except for the wake-sleep stage, that the relevant sleep time period is the REM sleep stage, and the other sleep time periods are the sleep time information in the NREM sleep stage; Based on the determined sleep time periods, determining the sleep monitoring information related to the sleep time periods as the sleep monitoring information in the sleep stage corresponding to the sleep time periods; and Based on the EOG data in the NREM sleep stage, determining the sleep time information and sleep monitoring information in the three sub-stages of the NREM sleep stage in the user's sleep information.

2. The method according to claim 1, wherein the judgment process for the change in the EMG voltage corresponding to the consecutive frames having the minimum EMG voltage amplitude and including the minimum EMG voltage amplitude in the EMG data being stable includes: Determining the minimum EMG voltage amplitude and two mutation points before and after the minimum EMG voltage amplitude from the remaining sleep time periods, where the mutation point means that the ratio of its voltage amplitude to the minimum EMG voltage amplitude is greater than the amplitude ratio threshold, and the amplitude ratio threshold is greater than or equal to 1.5; And When the average voltage amplitude in the sleep time period between the two mutation points is not greater than the amplitude threshold, determining that the change in the EMG voltage corresponding to the consecutive frames in the sleep time period between the two mutation points is stable.

3. The method according to claim 2, wherein determining the minimum EMG voltage amplitude and two mutation points before and after the minimum EMG voltage amplitude from the remaining sleep time periods includes: Determining the minimum EMG voltage amplitude from the remaining sleep time periods; When no mutation point is identified before or after the minimum EMG voltage amplitude, determining the second smallest EMG voltage amplitude from the remaining sleep time periods; And When two mutation points are identified before and after the second smallest EMG voltage amplitude, determining the second smallest EMG voltage amplitude as the target minimum EMG voltage amplitude, otherwise, repeating the above process to re-determine the Nth smallest EMG voltage amplitude and two mutation points before and after the Nth smallest EMG voltage amplitude.

4. The method according to claim 1, wherein determining the sleep time information and sleep monitoring information for the three sub-stages of the non-rapid eye movement (NREM) sleep stage in the user's sleep information based on the electrooculogram (EOG) data under the NREM sleep stage includes: Based on the sleep time information of the adjacent wake-sleep stage and rapid eye movement (REM) sleep stage in the monitoring period, determining the start time of the first sub-stage and the end time of the third sub-stage of the NREM sleep stage located between the adjacent wake-sleep stage and REM sleep stage, or determining the end time of the first sub-stage and the start time of the third sub-stage of the NREM sleep stage located between the adjacent wake-sleep stage and REM sleep stage; Based on the change in EOG voltage of consecutive frames in the EOG data under the NREM sleep stage located between the adjacent wake-sleep stage and REM sleep stage, and the start time of the first sub-stage and the end time of the third sub-stage of the NREM sleep stage or the end time of the first sub-stage and the start time of the third sub-stage of the NREM sleep stage, determining the sleep time information of the third sub-stage and the sleep time information of the first sub-stage of the NREM sleep stage located between the adjacent wake-sleep stage and REM sleep stage; Based on the sleep time information of the third sub-stage and the sleep time information of the first sub-stage of the NREM sleep stage located between the adjacent wake-sleep stage and REM sleep stage, determining the sleep time information of the second sub-stage of the NREM sleep stage; And Based on the sleep time information determined for each sub-stage, determining the sleep monitoring information related to the sleep time information as the sleep monitoring information for the sub-stage of the NREM sleep stage.

5. The method according to claim 4, wherein determining the sleep time information of the third sub-stage and the sleep time information of the first sub-stage of the NREM sleep stage based on the change in EOG voltage of consecutive frames in the EOG data under the NREM sleep stage located between the adjacent wake-sleep stage and REM sleep stage, and the start time of the first sub-stage and the end time of the third sub-stage of the NREM sleep stage or the end time of the first sub-stage and the start time of the third sub-stage of the NREM sleep stage includes: In response to the EOG voltage of consecutive frames remaining unchanged in the EOG data under the NREM sleep stage, taking the end time or start time of the third sub-stage of the NREM sleep stage as a reference, determining the sleep time period corresponding to the EOG data of this consecutive frame as the sleep time information of the third sub-stage of the NREM sleep stage; And In response to the average interval time between the positive and negative amplitudes of adjacent electrooculogram voltages of consecutive frames in the electrooculogram data under the non-rapid eye movement sleep stage being not less than an interval threshold, with the start time or end time of the first sub-stage of the non-rapid eye movement sleep stage as a reference, determine that the sleep time period corresponding to the electrooculogram data of this consecutive frame is the sleep time information of the first sub-stage of the non-rapid eye movement sleep stage.

6. The method according to claim 4, wherein determining the sleep time information and sleep monitoring information under the three sub-stages of the non-rapid eye movement sleep stage based on the electrooculogram data under the non-rapid eye movement sleep stage further includes: In response to the non-rapid eye movement sleep stage located between adjacent wake-sleep stages and rapid eye movement sleep stages not having a third sub-stage, based on the electrooculogram voltage change situation of consecutive frames in the electrooculogram data under the non-rapid eye movement sleep stage located between the adjacent wake-sleep stage and rapid eye movement sleep stage, and the start time or end time of the first sub-stage of the non-rapid eye movement sleep stage, determine that the sleep time period corresponding to the electrooculogram data is the sleep time information of the first sub-stage of the non-rapid eye movement sleep stage; and Based on the sleep time information of the first sub-stage of the non-rapid eye movement sleep stage and the sleep time information of the non-rapid eye movement sleep stage, determine the sleep time information of the second sub-stage.

7. The method according to claim 1, wherein the sleep monitoring information further includes electrocardiogram data and blood oxygen saturation data, and the method further includes: Based on the sleep time information of the non-rapid eye movement sleep stage and rapid eye movement sleep stage in the user sleep information, determine the electrocardiogram data and blood oxygen saturation data under the non-rapid eye movement sleep stage and rapid eye movement sleep stage from the sleep monitoring information; Based on the electrocardiogram data and the blood oxygen saturation data under the non-rapid eye movement sleep stage and rapid eye movement sleep stage, determine the sleep state of the user, and the sleep state includes a normal sleep state and a hypopnea sleep state.

8. The method according to claim 7, wherein determining the sleep state of the user based on the electrocardiogram data and the blood oxygen saturation data under the non-rapid eye movement sleep stage and rapid eye movement sleep stage includes: In response to the blood oxygen saturation data at multiple moments being not greater than a blood oxygen threshold, obtain the electrocardiogram data corresponding to the multiple moments; and In response to the change rate of the heart rate of the electrocardiogram data at the multiple moments compared to the heart rate of the electrocardiogram data at previous multiple moments exceeding an electrocardiogram change threshold, determine that the user is in a hypopnea sleep state, otherwise, the user is in a normal sleep state.

9. A sleep monitoring device, characterized in that, including: An acquisition module, configured to acquire sleep monitoring information of a user in a monitoring period, and the sleep monitoring information includes electroencephalogram data, electromyogram data, and electrooculogram data; A first determination module, configured to determine user sleep information based on the electroencephalogram data, electromyogram data, and electrooculogram data in the monitoring period, where the user sleep information includes sleep time information and sleep monitoring information in the wakefulness sleep stage, non-rapid eye movement sleep stage, and rapid eye movement sleep stage; the first determination module includes: A first response unit, configured to determine that the sleep time period corresponding to the electroencephalogram data of consecutive frames is the sleep time information of the wakefulness sleep stage when the average frequency of the brain waves in the consecutive frames of the electroencephalogram data is not less than the frequency threshold; A second response unit, configured to determine that the relevant sleep time period is the rapid eye movement sleep stage and the other sleep time periods are the sleep time information of the non-rapid eye movement sleep stage from the remaining sleep time periods other than the wakefulness sleep stage in the monitoring period when the electromyogram data has the minimum electromyogram voltage amplitude and the change of the electromyogram voltage corresponding to the consecutive frames including the minimum electromyogram voltage amplitude is stable, and the eye movement speed of the electrooculogram data corresponding to the sleep time period of the electromyogram data is not less than the eye movement threshold; A determination unit, configured to determine the sleep monitoring information related to the sleep time period as the sleep monitoring information corresponding to the sleep stage of the sleep time period based on the determined sleep time period; and A second determination module, configured to determine the sleep time information and sleep monitoring information of three sub-stages of the non-rapid eye movement sleep stage in the user sleep information based on the electrooculogram data in the non-rapid eye movement sleep stage.

Images