Intelligent awakening system and method based on sleep monitoring

Abstract

According to the intelligent awakening system and method based on sleep monitoring, on the basis of wearable sleep monitoring equipment, by analyzing the sleep stage of a user in real time and combining strategies such as blue light awakening and vibration awakening, the user is awakened at a proper time, so that interference to sleep is reduced, and the sleep monitoring effect is improved. And the comfort of the awakening process and the mental state of the user are improved. Multi-channel physiological signals such as electroencephalogram signals, electro-oculogram signals and mandibular electromyographic signals are used, the advanced signal processing technology is combined, the sleep stage of a user can be accurately analyzed in real time, awakening is carried out at a proper time point, especially sudden awakening is avoided in the deep sleep (N3) stage and the rapid eye movement sleep (REM) stage, and the sleep state of the user is improved. And the sleep inertia is effectively reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of sleep products, and in particular relates to the design of an intelligent wake-up system and method based on sleep monitoring. Background Art

[0002] Sleep inertia (SI) refers to a transition period that the human body experiences when changing from sleep to wakefulness, usually manifested as temporary cognitive impairment, inattention, slow thinking, mood swings, etc. This phenomenon usually occurs in the deep stage of sleep, especially when awakened during deep sleep (N3 stage) or rapid eye movement sleep (REM stage), individuals will experience more severe sleep inertia.

[0003] Studies have shown that sleep inertia is closely related to the sleep stage at the time of awakening. When awakened during deep sleep, the human brain and body are not yet fully ready for activity. At this time, awakening will disrupt the natural rhythm of the biological clock, causing the nervous system to fail to recover to a fully awake state in time, thereby affecting the individual's thinking, memory, judgment, and emotional stability. Sleep inertia generally subsides within 30 minutes after waking up, but in severe cases it may last for 1 to 4 hours, and sleep inertia may also occur during short naps such as lunch breaks. Therefore, how to reduce or eliminate the impact of sleep inertia on individuals is an issue that a sleep product should consider.

[0004] Blue light wake-up technology has received widespread attention in sleep research and smart health devices in recent years. Blue light, especially short-wavelength light in the range of 450-495 nanometers, is believed to have significant physiological effects, especially in regulating the biological clock and affecting sleep quality. Through its stimulation of rhodopsin in the retina, blue light can directly affect the pineal gland in the brain and regulate the secretion of melatonin, thus playing an important role in circadian rhythm. Melatonin is a hormone secreted by the pineal gland that is mainly responsible for regulating the sleep-wake cycle. Usually at night, the secretion of melatonin increases, making people feel sleepy and fall asleep; in the early morning or during the day, blue light can effectively inhibit the secretion of melatonin and help the human body transition from sleep to wakefulness.

[0005] Studies have shown that 20-30 minutes of blue light exposure in the early morning can effectively adjust an individual's sleep stage, making it easier for users to stay awake and comfortable after getting up. Blue light exposure can also be used as a treatment for some patients with sleep disorders. Regular blue light exposure can effectively reset an individual's sleep time and cycle to adjust for jet lag caused by work, etc.

[0006] In many traditional wake-up methods, the alarm time is set without considering the user's specific sleep state, resulting in wake-up in deep sleep or REM sleep. This wrong wake-up time often exacerbates sleep inertia and has a negative impact on users. Especially in the busy modern society, many people ignore the laws of sleep cycles in order to get up on time, resulting in getting up in an inappropriate sleep stage, causing long-term morning fatigue and affecting work efficiency and emotional management throughout the day.

[0007] Although there are some light-based wake-up products on the market that help users wake up by simulating sunrise or providing light of different intensities, most existing light-based wake-up products do not make full use of sleep monitoring technology to accurately determine the user's sleep stage, which leads to certain limitations in achieving personalized and scientific wake-up. Summary of the invention

[0008] The purpose of the present invention is to propose an intelligent wake-up system and method based on sleep monitoring. On the basis of wearable sleep monitoring equipment, the system analyzes the user's sleep stage in real time, combines strategies such as blue light wake-up and vibration wake-up, and wakes up the user at an appropriate time to reduce interference with sleep and improve the comfort of the wake-up process and the user's mental state.

[0009] The technical solution of the present invention is as follows: In the first aspect, the present invention provides an intelligent awakening system based on sleep monitoring, including a monitoring module, a awakening module, a Bluetooth module and a processor. The processor is respectively communicated with the monitoring module and the awakening module through the Bluetooth module. The monitoring module is used to collect physiological signals of the user during sleep. The Bluetooth module is used to transmit the collected physiological signals to the processor, and transmit the instructions of the processor to the awakening module. The processor performs sleep staging in real time according to the collected physiological signals, and determines whether and how to wake up the user. The awakening module wakes up the user by combining vibration and blue light stimulation.

[0010] Furthermore, the monitoring module includes a ground signal acquisition unit, an EEG signal acquisition unit, an EOG signal acquisition unit, an EMG signal acquisition unit and a reference signal acquisition unit. The EEG signal acquisition unit is adhered to the user's forehead through conductive soft glue, the EOG signal acquisition unit is adhered to the user's eye through conductive soft glue, the EMG signal acquisition unit is adhered to the user's jaw through conductive soft glue, and the reference signal acquisition unit is adhered to the mastoid behind the user's ear through conductive soft glue.

[0011] Furthermore, the wake-up module includes a vibration unit and a blue LED light worn on the forehead of the user.

[0012] In a second aspect, the present invention provides an intelligent awakening method based on sleep monitoring, comprising the following steps:

[0013] S1. Set the user's alarm time.

[0014] S2. Collecting physiological signals of the user during sleep.

[0015] S3. According to the physiological signals of the user during sleep, a real-time sleep staging algorithm is used to obtain the sleep staging result of the user.

[0016] S4. According to the sleep staging result of the user, determine whether the user is in the deep sleep stage or the rapid eye movement sleep stage at the alarm time. If so, proceed to step S5; otherwise, proceed to step S6.

[0017] S5. Expose the user to blue light and monitor changes in the user's sleep stages in real time. In response to the user transitioning to a light sleep stage, vibrate to wake up the user, thereby ending the wake-up process.

[0018] S6. Vibrate to wake up the user, ending the wake-up process.

[0019] Furthermore, the physiological signals collected during the user's sleep in step S2 include electroencephalogram signals, electrooculogram signals and electromyography signals.

[0020] Further, step S3 includes the following sub-steps:

[0021] S31, intercepting the EEG signal, EOG signal and EMG signal of the user during sleep for 30 seconds, and extracting their time-frequency features through short-time Fourier transform.

[0022] S32. Input the time-frequency features into the filter bank layer to learn and enhance the sub-frequency bands that contribute to the sleep staging task.

[0023] S33, inputting the enhanced time-frequency features into the first RNN layer to obtain the temporal dynamic information of the EEG signal, the EOG signal and the EMG signal.

[0024] S34, input the temporal dynamic information into the attention layer, weight the timing signals therein, and obtain the periodized numerical results corresponding to the original 30s EEG signals, EOG signals and EMG signals.

[0025] S35. Input the stage numerical results into the second RNN layer to obtain long-term sleep stage timing information.

[0026] S36: Input the long-term sleep staging timing information into the output layer to obtain the user's sleep staging result.

[0027] Furthermore, in step S5, the maximum time for the user to be exposed to blue light is set to 30 minutes. If the user does not transition to the light sleep stage within 30 minutes, the user is forced to be awakened by vibration.

[0028] The beneficial effects of the present invention are:

[0029] (1) The present invention effectively reduces sleep inertia by accurately determining the user's sleep stage and waking up the user at an appropriate time, especially avoiding sudden awakening during the deep sleep (N3) and rapid eye movement (REM) sleep stages.

[0030] (2) The present invention uses multi-channel physiological signals such as EEG signals, EOG signals and mandibular EMG signals, combined with advanced signal processing technology, to accurately analyze the user's sleep stage in real time. This high-precision sleep monitoring technology provides a solid foundation for accurate personalized wake-up, ensuring wake-up at the appropriate time rather than disturbing the user in the deep stage of the sleep cycle.

[0031] (3) The present invention can not only be applied to sleep management in the daily lives of ordinary consumers, but can also be extended to sleep management for special groups (such as night shift workers, jet lag adjustment, flight adjustment, etc.). In the future, this technology can be combined with other health management equipment to form a more comprehensive personalized health solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 The figure shows a block diagram of an intelligent wake-up system based on sleep monitoring provided in the first embodiment of the present invention.

[0033] Figure 2 The figure is a schematic diagram of the structure of an intelligent wake-up system based on sleep monitoring provided in the first embodiment of the present invention.

[0034] Figure 3 The figure is a flow chart of an intelligent awakening method based on sleep monitoring provided in the second embodiment of the present invention.

[0035] Figure 4 FIG. 1 is a schematic diagram of a real-time sleep staging algorithm provided in Embodiment 2 of the present invention.

[0036] Figure 5 The figure shows a schematic diagram of the wake-up process provided in the second embodiment of the present invention.

[0037] Explanation of the accompanying drawings: 1-ground signal acquisition unit, 2-electroencephalogram signal acquisition unit, 3-electrooculogram signal acquisition unit, 4-electromyography signal acquisition unit, 5-reference signal acquisition unit, 6-vibration unit, 7-blue light LED lamp. DETAILED DESCRIPTION

[0038] Now, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be understood that the embodiments shown and described in the accompanying drawings are only exemplary and are intended to explain the principles and spirit of the present invention, rather than to limit the scope of the present invention.

[0039] Embodiment 1:

[0040] The embodiment of the present invention provides an intelligent wake-up system based on sleep monitoring, such as Figure 1 As shown, it includes a monitoring module, a wake-up module, a Bluetooth module and a processor. The processor is connected to the monitoring module and the wake-up module through the Bluetooth module. The monitoring module is used to collect physiological signals of the user during sleep. The Bluetooth module is used to transmit the collected physiological signals to the processor, and transmit the instructions of the processor to the wake-up module. The processor performs sleep staging in real time according to the collected physiological signals, and determines whether and how to wake up the user. The wake-up module wakes up the user by combining vibration and blue light stimulation.

[0041] like Figure 2 As shown, in the embodiment of the present invention, the monitoring module includes a ground signal acquisition unit 1, an EEG signal acquisition unit 2, an EO signal acquisition unit 3, an EMG signal acquisition unit 4 and a reference signal acquisition unit 5. The EEG signal acquisition unit 2 is adhered to the user's forehead through a conductive soft adhesive, the EO signal acquisition unit 3 is adhered to the user's eye through a conductive soft adhesive, the EMG signal acquisition unit 4 is adhered to the user's jaw through a conductive soft adhesive, and the reference signal acquisition unit 5 is adhered to the mastoid behind the user's ear through a conductive soft adhesive. The physiological signals collected by the monitoring module during the user's sleep are transmitted to the processor via Bluetooth, and the processor includes but is not limited to client applications, cloud, etc.

[0042] like Figure 2 As shown, in the embodiment of the present invention, the wake-up module includes a vibration unit 6 and a blue LED lamp 7 worn on the forehead of the user.

[0043] Embodiment 2:

[0044] The embodiment of the present invention provides an intelligent awakening method based on sleep monitoring, such as Figure 3 As shown, the following steps S1 to S6 are included:

[0045] S1. Set the user's alarm time, that is, the time when the user expects to be woken up.

[0046] S2. Collecting physiological signals of the user during sleep.

[0047] In the embodiment of the present invention, the monitoring module provided in the first embodiment collects physiological signals of the user during sleep, including electroencephalogram signals, electrooculogram signals and electromyography signals.

[0048] S3. According to the physiological signals of the user during sleep, a real-time sleep staging algorithm is used to obtain the sleep staging result of the user.

[0049] like Figure 4 As shown, step S3 includes the following sub-steps S31 to S36:

[0050] S31, intercepting the EEG signal, EOG signal and EMG signal of the user during sleep for 30 seconds, and extracting their time-frequency features through short-time Fourier transform.

[0051] S32. Input the time-frequency features into the filter bank layer to learn and enhance the sub-frequency bands that contribute to the sleep staging task.

[0052] S33. Input the enhanced time-frequency features into the first RNN (recurrent neural network) layer to obtain the temporal dynamic information of the EEG signal, the EOG signal and the EMG signal.

[0053] S34, input the temporal dynamic information into the attention layer, weight the timing signals therein, and obtain the periodized numerical results corresponding to the original 30s EEG signals, EOG signals and EMG signals.

[0054] S35. Input the stage numerical results into the second RNN layer to obtain long-term sleep stage timing information.

[0055] S36: Input the long-term sleep staging timing information into the output layer to obtain the user's sleep staging result.

[0056] S4. According to the sleep staging result of the user, determine whether the user is in the deep sleep stage or the rapid eye movement sleep stage at the alarm time. If so, proceed to step S5; otherwise, proceed to step S6.

[0057] S5, such as Figure 5 As shown in (a), if the user is in the deep sleep (N3) stage or the rapid eye movement (REM) sleep stage at the alarm time, the user is irradiated with blue light and the changes in the user's sleep stage are monitored in real time. In response to the user's transition to the light sleep (N1 or N2) stage, the user is awakened by vibration, thereby ending the awakening process.

[0058] In the embodiment of the present invention, considering the effectiveness of blue light exposure, the maximum time for blue light exposure to the user is set to 30 minutes. If the user does not transition to the light sleep stage within 30 minutes, the user is forced to be awakened by vibration.

[0059] S6, such as Figure 5 As shown in (b), if the user is in a light sleep (N1 or N2) stage at the alarm time, the user is directly awakened by vibration, ending the awakening process.

[0060] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. An intelligent wake-up system based on sleep monitoring, characterized in that: It includes a monitoring module, a wake-up module, a Bluetooth module and a processor. The processor is connected to the monitoring module and the wake-up module through the Bluetooth module. The monitoring module is used to collect physiological signals of the user during sleep. The Bluetooth module is used to transmit the collected physiological signals to the processor and transmit the processor's instructions to the wake-up module. The processor performs sleep staging in real time according to the collected physiological signals and determines whether and how to wake up the user. The wake-up module wakes up the user by combining vibration and blue light stimulation.

2. The intelligent wake-up system based on sleep monitoring according to claim 1, characterized in that: The monitoring module comprises a ground signal acquisition unit (1), an electroencephalogram signal acquisition unit (2), an electrooculogram signal acquisition unit (3), an electromyogram signal acquisition unit (4) and a reference signal acquisition unit (5); the electroencephalogram signal acquisition unit (2) is adhered to the forehead of a user via a conductive soft adhesive, the electrooculogram signal acquisition unit (3) is adhered to the side of the eye of the user via a conductive soft adhesive, the electromyogram signal acquisition unit (4) is adhered to the jaw of the user via a conductive soft adhesive, and the reference signal acquisition unit (5) is adhered to the mastoid behind the ear of the user via a conductive soft adhesive.

3. The intelligent wake-up system based on sleep monitoring according to claim 1, characterized in that: The wake-up module comprises a vibration unit (6) worn on the forehead of a user and a blue LED lamp (7).

4. An intelligent awakening method based on sleep monitoring, characterized in that: The following steps are involved: S1. Set the user's alarm time; S2, collecting physiological signals of the user during sleep; S3, obtaining the sleep staging result of the user using a real-time sleep staging algorithm according to the physiological signals of the user during sleep; S4, judging whether the user is in the deep sleep stage or the rapid eye movement sleep stage at the alarm time according to the sleep staging result of the user, if so, proceeding to step S5, otherwise proceeding to step S6; S5, irradiating the user with blue light and monitoring the changes in the user's sleep stage in real time, and in response to the user's transition to a light sleep stage, vibrating to wake up the user, thereby ending the wake-up process; S6. Vibrate to wake up the user, ending the wake-up process.

5. The intelligent awakening method based on sleep monitoring according to claim 4, characterized in that: The physiological signals collected during the user's sleep in step S2 include electroencephalogram signals, electrooculogram signals and electromyography signals.

6. The intelligent awakening method based on sleep monitoring according to claim 5, characterized in that: The step S3 comprises the following sub-steps: S31, intercepting the EEG signal, EOG signal and EMG signal of the user during sleep for 30 seconds, and extracting their time-frequency features through short-time Fourier transform; S32, inputting the time-frequency features into the filter bank layer to learn and enhance the sub-frequency bands that contribute to the sleep staging task; S33, inputting the enhanced time-frequency features into the first RNN layer to obtain the temporal dynamic information of the EEG signal, the EOG signal and the EMG signal; S34, input the temporal dynamic information into the attention layer, weight the time series signal therein, and obtain the stage numerical results corresponding to the original 30s EEG signal, EOG signal and EMG signal; S35, inputting the stage numerical results into the second RNN layer to obtain long-term sleep stage timing information; S36: Input the long-term sleep stage timing information into the output layer to obtain the user's sleep stage result.

7. The intelligent awakening method based on sleep monitoring according to claim 4, characterized in that: In step S5, the maximum time for the user to be exposed to blue light is set to 30 minutes. If the user does not transition to the light sleep stage within 30 minutes, the user is forced to be awakened by vibration.

Images