WO2020187109A1 - 一种用户睡眠检测方法及*** - Google Patents

一种用户睡眠检测方法及*** Download PDF

Info

Publication number
WO2020187109A1
WO2020187109A1 PCT/CN2020/078822 CN2020078822W WO2020187109A1 WO 2020187109 A1 WO2020187109 A1 WO 2020187109A1 CN 2020078822 W CN2020078822 W CN 2020078822W WO 2020187109 A1 WO2020187109 A1 WO 2020187109A1
Authority
WO
WIPO (PCT)
Prior art keywords
signal
ear
bioelectric
user
impedance
Prior art date
Application number
PCT/CN2020/078822
Other languages
English (en)
French (fr)
Inventor
杨晖
袁鹏
查钧
倪刚
唐卫东
冷爱民
李皓
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2020187109A1 publication Critical patent/WO2020187109A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/369—Electroencephalography [EEG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/389—Electromyography [EMG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/398—Electrooculography [EOG], e.g. detecting nystagmus; Electroretinography [ERG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • A61B5/4812—Detecting sleep stages or cycles
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7253—Details of waveform analysis characterised by using transforms
    • A61B5/726—Details of waveform analysis characterised by using transforms using Wavelet transforms
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device

Definitions

  • This application relates to the field of data processing, in particular to the analysis and processing of the bioelectric signals of the human body, and a method and system for obtaining the user's current sleep classification results through the analysis and processing of the bioelectric signals.
  • the main implementation methods for detecting sleep state are: detecting the characteristic data of sleep through the wristband.
  • the collected data includes the number of times the arm is at rest to swing, the number of times the arm is at rest, the time of continuous arm activity, and the number of arm activities in each stage. Total time; by reading the three-axis data in the register of the acceleration sensor, the criterion for recognizing the arm posture is obtained; by obtaining the heart rate value, the start and end of sleep can be further judged.
  • the algorithm is simple and the device is mature, this method cannot accurately distinguish different stages of sleep; or it can be measured by measuring the heart rate on a sleeping pillow or a sleeping pad.
  • the heart rate will increase or decrease during the transition of a specific sleep stage, when from awakening to light sleep
  • the heart rate slows down during transition, increases slightly during REM, and then becomes slowest during deep sleep.
  • sleep staging is inaccurate, and it is not easy to provide physiological feedback through staging to improve sleep; in addition, there are medical sleep measurements.
  • the equipment is widely used in major medical institutions. However, due to its large size, many human sensor connections, and complicated wiring, it is only suitable for use in hospital beds. The use environment is limited, and the comfort is not good. For daily sleep and fatigue monitoring.
  • the embodiments of the present application provide a sleep detection method and system, which can be applied to the detection of a user's sleep staging.
  • the biometric signal is acquired through the ear side, making the acquisition of the bioelectric signal more convenient and feasible, and the user can perform sleep detection anytime and anywhere. It is no longer limited by the location and the need to wear complex detection equipment, which reduces the measurement cost. At the same time, because multiple signals are considered in the sleep classification process, the accuracy of the sleep classification result judgment is also ensured.
  • an embodiment of the present application provides a user sleep detection method, the method includes: collecting a bioelectric signal by wearing a device on the ear side; the user bioelectric signal includes the user bioelectric signal collected from the ear; The bioelectric signal of the user is subjected to feature decomposition to obtain a biometric signal; the biometric signal includes one or more of brain electrical signals, electrocardiographic signals, eye electrical signals, and electromyographic EMG signals; The characteristic signal is based on the machine learning model to obtain the sleep classification result of the user.
  • the sleep classification result may be the user's sleep staging classification result.
  • obtaining bioelectric signals through the ear side is more convenient and quick.
  • the ear side wearing device is convenient to carry, is set on the ear side, and is not easy to fall off during wearing, making it more convenient and feasible to measure the user's bioelectric signal during sleep detection.
  • biometric signals are considered in the process of sleep detection, which makes the results of sleep detection more accurate and credible.
  • the acquiring the user's bioelectric signal from the user's ear through the ear-side wearing device specifically includes: the ear-side wearing device includes a plurality of ear-side signal measuring units; Whether the impedance between the two ear signal measurement units is lower than the preset threshold; when the impedance between the two ear signal measurement units is lower than the preset threshold; the two ear signal measurement units are collected The potential difference signal of the bioelectric signal is used as the user's bioelectric signal.
  • the multiple ear signal measurement units include a left ear signal measurement unit and a right ear signal measurement unit; determining that the left ear signal measurement unit and Whether the impedance between the right ear side signal measurement units is lower than a preset threshold; when the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than the preset threshold; A potential difference signal between the bioelectric signal collected by the left ear signal measuring unit and the bioelectric signal collected by the right ear signal measuring unit is used as the user's bioelectric signal.
  • the acquiring the user's bioelectric signal from the user's ear through the ear wearing device specifically includes: the ear wearing device is a unilateral ear wearing device, and the plurality of The ear signal measurement unit is a plurality of single ear signal measurement units; it is determined whether the impedance between two of the single ear signal measurement units is lower than a preset threshold; when the two single ear signal measurement units are The impedance between the units is lower than a preset threshold; and the potential difference signal of the bioelectric signals collected by two of the plurality of unilateral ear signal measurement units is used as the user's bioelectric signal.
  • the right ear signal measurement units are multiple; when one of the left ear signal measurement units and The impedance between one of the right ear signal measurement units is higher than the preset threshold; respectively determine whether the impedance between two of the plurality of left ear signal measurement units is lower than the preset threshold, and Whether the impedance between two of the multiple right-ear side signal measurement units is lower than a preset threshold; the bioelectric signal collected by two bioelectric measurement devices in the ear canal whose impedance is lower than the preset threshold The potential difference signal is used as the user's bioelectric signal.
  • the ear-side wearing device By judging the impedance between the measuring units, it is possible to accurately determine whether the ear-side wearing device can perform normal measurement, and it is ruled out that the ear-side wearing device is not worn normally and the ear canal does not fit and cannot be accurately measured. Ensure the accuracy of the user's bioelectric signal.
  • the user bioelectric signal further includes a sensor signal;
  • the sensor signal is one of a motion sensor signal, a heart rate sensor signal, and a sound sensor signal, or Multiple;
  • the analyzing the sleep classification result of the user according to the biological characteristic signal includes: obtaining the sleep classification result of the user according to the biological characteristic signal and the sensor signal.
  • the method includes: obtaining a sleep classification result of the user based on a machine learning model according to the biometric signal, including: according to the biometric signal and an SVM model Obtain the sleep classification result of the user.
  • the method includes: obtaining a sleep classification result of the user according to the biometric signal and the sensor signal, including: according to the biometric signal and The sensor signal and the SVM model obtain the sleep classification result of the user.
  • the method includes: obtaining a sleep classification result of the user based on a machine learning model according to the biometric signal, including: according to the biometric signal and deep neural The network model obtains the sleep classification result of the user.
  • the method includes: obtaining a sleep classification result of the user according to the biometric signal and the sensor signal, including: according to the biometric signal and The sensor signal and the deep neural network model obtain the sleep classification result of the user.
  • Using the machine learning model to determine sleep classification can more accurately analyze the sleep classification corresponding to the user's current biometric signal and/or sensor signal.
  • an embodiment of the present invention provides a sleep detection system, characterized in that the system includes: an ear wearing device for collecting bioelectric signals; the user bioelectric signals include user bioelectric signals collected from the ear Electrical signal; used to decompose the bioelectric signal of the user to obtain a biometric signal; the biometric signal includes one or more of brain electrical signals, electrocardiographic signals, eye electrical signals, and electromyographic EMG signals Species; sleep detection device for obtaining the user's sleep classification result based on the machine learning model according to the biometric signal.
  • the ear side wearing device includes a plurality of ear side signal measuring units; the ear side wearing device determines whether the impedance between the two ear side signal measuring units is lower than A preset threshold; when the impedance between the two ear signal measuring units is lower than the preset threshold; use the potential difference signal of the bioelectric signal collected by the two ear signal measuring units as the user's bioelectric signal signal.
  • the ear side wearing device includes a left ear ear side signal measuring unit and a right ear side signal measuring unit; the ear side wearing device is also used to determine the left ear Whether the impedance between the ear side signal measurement unit and the right ear side signal measurement unit is lower than the preset threshold; when the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit Lower than a preset threshold; use a potential difference signal between the bioelectric signal collected by the left ear signal measuring unit and the bioelectric signal collected by the right ear signal measuring unit as the user bioelectric signal.
  • the ear-side wearing device includes a plurality of unilateral ear-side signal measurement units; the ear-side wearing device is also used to determine two of the unilateral ears Whether the impedance between the side signal measurement units is lower than a preset threshold, when the impedance between the two unilateral ear signal measurement units is lower than the preset threshold, the multiple unilateral ear signal measurement units are The potential difference signal of the two collected bioelectric signals is used as the user bioelectric signal.
  • the left ear side signal measurement unit is multiple; the right ear side signal measurement unit is multiple; the ear side wearing device is also used for
  • the first judging unit judges that the impedance between one of the left ear signal measuring units and one of the right ear signal measuring units is higher than a preset threshold, and respectively judges which of the plurality of left ear signal measuring units Whether the impedance between the two is lower than a preset threshold, and whether the impedance between two of the plurality of right ear signal measuring units is lower than a preset threshold; and the impedance is lower than the preset threshold
  • the potential difference signal of the bioelectric signal collected by the two bioelectric measuring devices in one ear canal is used as the user's bioelectric signal.
  • the ear-side wearing device is also used to collect sensor signals
  • the sensing signal is one or more of motion sensing signal, heart rate sensing signal, and sound sensing signal;
  • the sleep detection device analyzes the sleep classification result of the user according to the biological characteristic signal, specifically: obtaining the sleep classification result of the user according to the biological characteristic signal and the sensor signal.
  • the sleep detection device is specifically configured to obtain the sleep classification result of the user according to the biometric signal and the SVM model.
  • the sleep detection device is specifically configured to obtain the sleep classification result of the user according to the biometric signal, the sensor signal, and the SVM model.
  • the sleep detection device is specifically configured to obtain the sleep classification result of the user according to the biometric signal and the deep neural network model.
  • the sleep detection device is specifically configured to obtain the sleep classification result of the user according to the biometric signal, the sensor signal, and the deep neural network model.
  • an embodiment of the present invention provides an ear-side wearing device, the device comprising: an ear-side signal measuring unit for collecting bioelectric signals; the user's bioelectric signal includes the user's bioelectric signal collected from the ear
  • the feature decomposition unit is used to perform feature decomposition of the user's bioelectric signal to obtain a biometric signal; the biometric signal includes one of brain electrical signals, electrocardiogram signals, eye electrical signals, and myoelectric EMG signals Or more; a sleep detection unit, configured to obtain a sleep classification result of the user based on a machine learning model according to the biometric signal.
  • the ear-side wearing device includes a plurality of ear-side signal measurement units; the ear-side wearing device further includes a first judging unit for judging two of the ear-side signals Whether the impedance between the measurement units is lower than the preset threshold; when the impedance between the two ear signal measurement units is lower than the preset threshold; the potential of the bioelectric signal collected by the two ear signal measurement units The difference signal is used as the user's bioelectric signal.
  • the multiple ear signal measurement units include a left ear signal measurement unit and a right ear signal measurement unit; the first judgment unit is configured to determine Whether the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold; when the left ear side signal measurement unit and the right ear side signal measurement unit are different The impedance is lower than the preset threshold; the potential difference signal between the bioelectric signal collected by the left ear signal measuring unit and the bioelectric signal collected by the right ear signal measuring unit is used as the user's bioelectric signal signal.
  • the ear-side wearing device is a unilateral ear canal measurement device
  • the multiple ear-side signal measurement units include multiple unilateral ear-side signal measurement units
  • the first judgment unit Used to determine whether the impedance between the two unilateral ear signal measurement units is lower than a preset threshold, and when the impedance between the two unilateral ear signal measurement units is lower than the preset threshold, the The potential difference signal of two collected bioelectric signals in the plurality of unilateral ear side signal measuring units is used as the user's bioelectric signal.
  • the ear wearing device further includes a second judgment Unit; when the first judging unit judges that the impedance between one of the left ear side signal measurement units and one of the right ear side signal measurement units is higher than a preset threshold, the second judgment unit judges the multiple Whether the impedance between two of the left ear side signal measurement units is lower than a preset threshold, and whether the impedance between two of the plurality of right ear side signal measurement units is lower than the preset threshold;
  • the potential difference signal of the bioelectric signal collected by the two bioelectric measuring devices in the ear canal on the side whose impedance is lower than the preset threshold is used as the user's bioelectric signal.
  • the ear-side wearing device further includes a sensing signal measuring unit for collecting sensing signals
  • the sensing signal is one or more of a motion sensing signal, a heart rate sensing signal, and a sound sensing signal; the sleep detection unit analyzes the user's sleep classification result according to the biometric signal, specifically : Obtain the sleep classification result of the user according to the biometric signal and the sensor signal.
  • an embodiment of the present invention provides an ear-side wearing device, the device comprising: an ear-side signal measuring unit for collecting bioelectric signals; the user bioelectric signal includes the user's bioelectric signal collected from the ear
  • the feature decomposition unit is used to perform feature decomposition of the user's bioelectric signal to obtain a biometric signal; the biometric signal includes one of brain electrical signals, electrocardiogram signals, eye electrical signals, and myoelectric EMG signals Or multiple; a sending unit for sending the biometric signal to the signal analysis device.
  • the ear-side wearing device includes a plurality of ear-side signal measuring units; the ear-side wearing device further includes a first judging unit for judging two of the ear-side signals Whether the impedance between the measurement units is lower than the preset threshold; when the impedance between the two ear signal measurement units is lower than the preset threshold; the potential of the bioelectric signal collected by the two ear signal measurement units The difference signal is used as the user's bioelectric signal.
  • the multiple ear side signal measurement units include a left ear side signal measurement unit and a right ear side signal measurement unit; the first disconnection unit is used to determine Whether the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold; when the left ear side signal measurement unit and the right ear side signal measurement unit are different The impedance is lower than the preset threshold; the potential difference signal between the bioelectric signal collected by the left ear signal measuring unit and the bioelectric signal collected by the right ear signal measuring unit is used as the user's bioelectric signal signal.
  • the ear-side wearing device is a unilateral ear canal measurement device
  • the multiple ear-side signal measurement units include multiple unilateral ear-side signal measurement units; the first judgment A unit for determining whether the impedance between the two unilateral ear signal measurement units is lower than a preset threshold, and when the impedance between the two unilateral ear signal measurement units is lower than the preset threshold, The potential difference signal of the two collected bioelectric signals in the plurality of unilateral ear signal measuring units is used as the user's bioelectric signal.
  • the ear wearing device further includes a second judgment Unit; when the first judging unit judges that the impedance between one of the left ear side signal measurement units and one of the right ear side signal measurement units is higher than a preset threshold, the second judgment unit judges the multiple Whether the impedance between two of the left ear side signal measurement units is lower than a preset threshold, and whether the impedance between two of the plurality of right ear side signal measurement units is lower than the preset threshold;
  • the potential difference signal of the bioelectric signal collected by the two bioelectric measuring devices in the ear canal on the side whose impedance is lower than the preset threshold is used as the user's bioelectric signal.
  • the ear-side wearing device further includes a sensing signal measuring unit for collecting sensing signals
  • the sensing signal is one or more of motion sensing signal, heart rate sensing signal, and sound sensing signal.
  • an embodiment of the present invention provides a sleep detection device.
  • the device includes: a receiving unit configured to receive a biometric signal from an ear-worn device; the biometric signal includes an electrocardiographic signal, an eye electrical signal, One or more of myoelectric EMG signals, and brain electrical signals; a sleep detection unit, configured to obtain a sleep classification result of the user based on a machine learning model according to the biometric signal.
  • the receiving unit is further configured to receive sensing signals from the ear-side wearing device; the sensing signals are motion sensing signals, heart rate sensing signals, and sound sensing One or more of the signals; the sleep detection unit analyzes the user’s sleep classification result according to the biometric signal, specifically: obtaining the user’s sleep according to the biometric signal and the sensor signal Classification results.
  • an embodiment of the present invention provides an ear-side wearing device, the device comprising: an ear-side signal measuring unit for collecting bioelectric signals; the user's bioelectric signal includes the user's bioelectric signal collected from the ear
  • the feature decomposition unit is used to perform feature decomposition of the user's bioelectric signal to obtain a biometric signal; the biometric signal includes one of brain electrical signals, electrocardiogram signals, eye electrical signals, and myoelectric EMG signals Or more; a processor configured to obtain the sleep classification result of the user based on a machine learning model according to the biometric signal.
  • the ear-side wearing device includes a plurality of ear-side signal measurement units; the processor is used to determine whether the impedance between the two ear-side signal measurement units is lower than a predetermined Set a threshold; when the impedance between the two ear signal measuring units is lower than a preset threshold; use the potential difference signal of the bioelectric signal collected by the two ear signal measuring units as the user bioelectric signal .
  • the multiple ear signal measurement units include a left ear signal measurement unit and a right ear signal measurement unit; the processor is used to determine the left ear Whether the impedance between the side signal measurement unit and the right ear signal measurement unit is lower than the preset threshold; when the impedance between the left ear signal measurement unit and the right ear signal measurement unit is low At a preset threshold; the potential difference signal between the bioelectric signal collected by the left ear signal measuring unit and the bioelectric signal collected by the right ear signal measuring unit is used as the user's bioelectric signal.
  • the ear-side wearing device is a unilateral ear canal measurement device
  • the ear-side signal measurement unit includes a plurality of unilateral ear-side signal measurement units
  • the processor is further configured to Determine whether the impedance between the two unilateral ear signal measurement units is lower than a preset threshold, and when the impedance between the two unilateral ear signal measurement units is lower than the preset threshold, the multiple The potential difference signal of the two collected bioelectric signals in one single ear side signal measuring unit is used as the user's bioelectric signal.
  • the processor is further configured to: The first judging unit judges that the impedance between one of the left ear signal measuring units and one of the right ear signal measuring units is higher than a preset threshold, and judges two of the plurality of left ear signal measuring units respectively Whether the impedance between the two is lower than a preset threshold, and whether the impedance between two of the plurality of right ear signal measuring units is lower than a preset threshold; and whether the impedance is lower than the preset threshold
  • the potential difference signal of the bioelectric signal collected by two bioelectric measuring devices in one ear canal is used as the user's bioelectric signal.
  • the ear-side wearing device further includes a sensing signal measurement unit for collecting sensing signals
  • the sensing signal is one or more of a motion sensing signal, a heart rate sensing signal, and a sound sensing signal; the sleep detection unit analyzes the user's sleep classification result according to the biometric signal, specifically : Obtain the sleep classification result of the user according to the biometric signal and the sensor signal.
  • an embodiment of the present invention provides an ear-side wearing device, the device comprising: an ear-side signal measuring unit for collecting bioelectric signals; the user's bioelectric signal includes the user's bioelectric signal collected from the ear
  • the feature decomposition unit is used to perform feature decomposition of the user's bioelectric signal to obtain a biometric signal; the biometric signal includes one of brain electrical signals, electrocardiogram signals, eye electrical signals, and myoelectric EMG signals Or multiple; a sending unit for sending the biometric signal to the user's bioelectric signal analysis device.
  • the ear-side wearing device includes a plurality of ear-side signal measurement units; the processor is used to determine whether the impedance between the two ear-side signal measurement units is lower than a predetermined Set a threshold; when the impedance between the two ear signal measuring units is lower than a preset threshold; use the potential difference signal of the bioelectric signal collected by the two ear signal measuring units as the user bioelectric signal .
  • the multiple ear side signal measurement units include a left ear side signal measurement unit and a right ear side signal measurement unit; the ear side wearing device further includes a processor, Used to determine whether the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold; when the left ear side signal measurement unit and the right ear side signal measurement unit The impedance between the signal measuring units is lower than the preset threshold; the potential difference signal of the bioelectric signal collected by the left ear side signal measuring unit and the bioelectric signal collected by the right ear side signal measuring unit is used as the Describe the user's bioelectric signal.
  • the ear side wearing device is a unilateral ear canal measurement device
  • the ear side signal measurement unit includes a plurality of unilateral ear side signal measurement units
  • the ear side wearing device is also
  • a processor is included for determining whether the impedance between the two unilateral ear signal measurement units is lower than a preset threshold, and when the impedance between the two unilateral ear signal measurement units is lower than the preset threshold Threshold, using a potential difference signal of the bioelectric signal collected by two of the plurality of single ear side signal measurement units as the user's bioelectric signal.
  • the ear-side wearing device further includes a processor;
  • the processor separately judges the multiple left ears Whether the impedance between two of the side signal measurement units is lower than a preset threshold, and whether the impedance between two of the plurality of right ear signal measurement units is lower than the preset threshold;
  • the potential difference signal of the bioelectric signal collected by the two bioelectric measuring devices in the ear canal on one side of the preset threshold is used as the user's bioelectric signal.
  • the ear-side wearing device further includes a sensing signal measuring unit, which is also used to collect sensing signals;
  • the sensing signal is one or more of motion sensing signal, heart rate sensing signal, and sound sensing signal.
  • an embodiment of the present invention provides a sleep detection device.
  • the device includes: a receiving unit configured to receive a biometric signal from an ear-worn device; the biometric signal includes brain electrical signals, electrocardiographic signals, An electrooculogram signal, one or more of electromyographic EMG signals; a processor, configured to obtain a sleep classification result of the user based on a machine learning model according to the biometric signal.
  • the receiving unit is further configured to receive sensing signals from the ear-side wearing device; the sensing signals are motion sensing signals, heart rate sensing signals, and sound sensing signals.
  • the processor analyzes the sleep classification result of the user according to the biometric signal, specifically: obtaining the sleep classification of the user according to the biometric signal and the sensor signal result.
  • an embodiment of the present invention provides a bioelectric signal detection method, including: the ear-side wearing device includes a plurality of ear-side signal measurement units for collecting user bioelectric signals from the ear; The signal is characterized by decomposition to obtain a biometric signal; the biometric signal includes one or more of brain electrical signals, electrocardiographic signals, ocular electrical signals, and myoelectric EMG signals; sending the biological feature signals to the signal Analysis device.
  • the user's bioelectric signal collected from the ear side specifically includes: determining whether the impedance between the two ear side signal measurement units is lower than a preset threshold; when the impedance between the two ear side signal measurement units is low At a preset threshold; the potential difference signal of the bioelectric signal collected by the bioelectric signal measured by the two ear signal measuring units is used as the user's bioelectric signal.
  • the plurality of ear side signal measurement units include a left ear side signal measurement unit and a right ear side signal measurement unit; the judgment of two of the ear side signal measurement units Whether the impedance between the two ear side signal measuring units is lower than the preset threshold value, when the impedance between the two ear side signal measuring units is lower than the preset threshold value, the bioelectric signals collected by the two ear side signal measuring units are collected
  • the potential difference signal of the signal as the user's bioelectric signal is specifically: judging whether the impedance between the left ear side signal measuring unit and the right ear side signal measuring unit is lower than a preset threshold; The impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold; the bioelectric signal collected by the left ear side signal measurement unit and the right ear side
  • the potential difference signal of the bioelectric signal collected by the signal measuring unit is used as the user's bioelectric signal.
  • the ear side wearing device is a unilateral ear side wearing device;
  • the multiple ear side signal measurement units include multiple unilateral ear side signal measurement units;
  • the two The potential difference signal of the bioelectric signal collected by a single ear side signal measuring unit is used as the user's bioelectric signal.
  • the potential difference signal of the signal is used as the user's bioelectric signal.
  • the ear-side wearing device also collects a sensing signal; the sensing signal is one of a motion sensing signal, a heart rate sensing signal, and a sound sensing signal Or multiple; sending the sensing signal to a signal analysis device.
  • an embodiment of the present invention provides a sleep detection method, including:
  • biometric signals from the ear-worn device include one or more of brain electrical signals, electrocardiographic signals, eye electrical signals, and myoelectric EMG signals; based on machine learning according to the biological feature signals
  • the model obtains the sleep classification result of the user.
  • the method further includes receiving a sensing signal from the ear side wearing device; the sensing signal is one of a motion sensing signal, a heart rate sensing signal, and a sound sensing signal One or more types; analyzing the user's sleep classification result according to the biometric signal, specifically: obtaining the user's sleep classification result according to the biometric signal and the sensor signal.
  • the method includes obtaining a sleep classification result of the user according to the biometric signal and an SVM model.
  • the method includes obtaining a sleep classification result of the user according to the biometric signal, the sensor signal, and an SVM model.
  • the method includes obtaining a sleep classification result of the user according to the biometric signal and a deep neural network model.
  • the method includes obtaining a sleep classification result of the user according to the biometric signal, the sensor signal, and a deep neural network model.
  • the user's sleep classification result may specifically be the user's sleep staging result, or the judgment result of whether the user is currently in a sleep state.
  • the biometric signal may be one or more of electrocardiographic signals, ocular signals, electromyographic EMG signals, and multiple biometric signals of brain electrical signals.
  • the determining whether the impedance between the two ear side signal measurement units is lower than a preset threshold may be selected from multiple ear side signal measurement units based on a preset setting Two, it can also be based on the priority setting order to select two ear side signal measurement units for comparison. In the case that the impedance is always lower than the preset threshold, you can compare the preset times to terminate the comparison, or terminate after traversing all conditions Compare.
  • the determining whether the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold may be the left ear side signal
  • the measurement unit and the right ear side signal measurement unit are both one, and they are directly compared; it is also possible that both the left ear side signal measurement unit and the right ear side signal measurement unit are multiple.
  • Two ear signal measurement units and two right ear signal measurement units are selected respectively, or two ear signal measurement units are selected for comparison based on the priority setting sequence, and the impedance is always lower than the preset
  • the comparison can be terminated by a preset number of comparisons, or the comparison can be terminated after traversing all situations.
  • the judging whether the impedance between the multiple unilateral ear signal measurement units is lower than a preset threshold may be two unilateral ear signal measurement units and directly compare them; It can also be based on a preset setting to select two from multiple single-sided ear signal measurement units, or it can be based on the priority setting sequence to select two ear side signal measurement units for comparison, and the impedance is always lower than the preset
  • the threshold is set, the comparison can be terminated by the preset number of comparisons, or the comparison can be terminated after traversing all situations.
  • the multiple left ears are determined separately Whether the impedance between two of the side signal measurement units is lower than a preset threshold, and whether the impedance between two of the plurality of right ear signal measurement units is lower than the preset threshold, it may be left, There are two ear-side signal measurement units for the right ear, which are directly compared; it can also be based on preset settings to select two from multiple left and right ear-side signal measurement units; it can also be for the left ear.
  • the side signal measurement unit selects two left ear ear side signal measurement units based on the priority setting order for comparison.
  • the impedance is always lower than the preset threshold, it can compare the preset times to terminate the comparison, or after traversing all situations Termination of comparison; for the right ear side signal measurement unit, two right ear side signal measurement units are selected for comparison based on the priority setting sequence.
  • the impedance is always lower than the preset threshold value, the preset number of comparisons can be terminated. Compare, or terminate the comparison after traversing all cases.
  • the implementation of the technical solutions of the embodiments of the present application can solve the problem that the current technical products are complex and not portable, the user's bioelectric signal is single, and cannot be detected in time if they are not worn correctly, or the new measurement solution can be instantly adapted
  • the collection of multiple types of biometric signals through the ear makes the collection of the user’s bioelectrical signals more convenient and feasible.
  • the wearing state of the ear-side wearing device is judged by measuring the impedance value between the units, and through the method of machine learning, the sleep Judgment in stages can determine the user's current sleep state relatively accurately, which facilitates more accurate and convenient evaluation of the user's sleep quality.
  • FIG. 1 shows a schematic diagram of an application scenario in an embodiment of the present application
  • Figure 2 shows the structure of sleep staging in the R&K sleep staging standard
  • Figure 3 shows the brain waves of a person in different stages of wakefulness, light sleep, rapid eye movement and slow wave sleep
  • Figure 4 shows the sleep cycle distribution of ordinary people during sleep according to the R&K sleep staging standard
  • Figure 5a shows a typical application scenario of an embodiment of the present invention
  • Figure 5b shows a wearing manner of an embodiment of the present invention
  • FIG. 6 shows a flowchart of a method for detecting user sleep according to an embodiment of the present invention
  • FIG. 7 shows a flow chart of a collection method for collecting bioelectric signals from the ear side according to an embodiment of the present application
  • FIG. 8 shows a flow chart of a method for collecting bioelectric signals from the ear side according to an embodiment of the present application
  • FIG. 9 corresponds to a sleep detection system according to an embodiment of the present application.
  • FIG. 9a corresponds to another sleep detection system according to an embodiment of the present application.
  • FIG. 9b corresponds to another sleep detection system according to an embodiment of the present application.
  • FIG. 10a shows a structural diagram of an ear-side wearing device according to an embodiment of the present application for unilateral measurement
  • FIG. 10b shows a structural diagram of an ear-side wearing device according to an embodiment of the present application when measuring on both sides;
  • Fig. 10c shows a structural diagram of an ear wearing device according to an embodiment of the present application.
  • FIG. 11 shows a structural diagram of an ear wearing device integrated with a sleep detection function according to an embodiment of the present application
  • FIG. 12 shows a structural diagram of another ear wearing device according to an embodiment of the present application.
  • FIG. 13 shows a schematic structural diagram of a sleep detection device according to an embodiment of the present application.
  • FIG. 14 shows a structural diagram of another ear wearing device according to an embodiment of the present application.
  • FIG. 15 shows a structural diagram of another ear wearing device according to an embodiment of the present application.
  • FIG. 16 shows a flowchart of a method for measuring user-related signals provided by an embodiment of the present application
  • Fig. 17 shows a flowchart of a sleep detection method provided by an embodiment of the present application.
  • the one or more structural composition of the functions, modules, features, units, etc. mentioned in the specific embodiments of the present application can be understood as consisting of any physical or tangible components (for example, software and hardware running on a computer device). (For example, logic functions implemented by a processor or a chip), etc., and/or any other combination) are implemented in any manner.
  • the illustrated division of various devices into different modules or units in the drawings may reflect the use of corresponding different physical and tangible components in actual implementation.
  • a single module in the drawings of the embodiments of the present application may also be implemented by multiple actual physical components.
  • any two or more modules depicted in the drawings may also reflect different functions performed by a single actual physical component.
  • the embodiments of the present application are mainly used for the monitoring of the user's sleep staging, and the user's sleep classification result is determined by analyzing the user's bioelectric signal characteristics, so that the user's current sleep situation and the user's overall sleep quality can be determined according to the user's current sleep status.
  • Bioelectric signals can be obtained from the surface of the human skin. Common bioelectric signals include EEG signals, ECG, EOG and EMG signals. In addition, there are motion signals, heart rate signals, sound signals, etc., which are characteristic signals that are highly correlated with the user's current state. In the prior art, sleep classification usually considers more EEG signals and motion signals. In this application, the above-mentioned multiple types of user characteristic signals will be combined to analyze the user's sleep state, so as to integrate multiple types of information and comprehensively consider the user's sleep state. The relationship between the EEG signal and the user's sleep will be specifically illustrated below.
  • EEG signals are the external manifestation of brain activity, and different brain activities are manifested as brain electrical signals with different characteristics. Studies have shown that the temporal and spatial frequency domain analysis of these EEG patterns can help reverse the analysis of human intention activities, which provides a theoretical basis for the application of EEG signals.
  • the scalp EEG signal is a kind of biological electrical signal.
  • the electric field formed by the potential changes of 86 billion neurons in the brain is conducted through the volume conductor composed of the cortex, skull, meninges and scalp, and then generates a potential distribution on the scalp.
  • the EEG signal can be obtained by recording the potential distribution of these changes with a specific device.
  • EEG signals can be divided into spontaneous EEG and Evoked Potential (EP).
  • Spontaneous brain electricity is a potential change spontaneously produced by nerve cells in the brain when there is no specific external stimulus.
  • the evoked EEG is the change of brain potential caused by different types of stimuli such as sound, light, and electricity by nerve cells in the brain.
  • the detection of sleep state involved in the strength of the present invention can be realized by detecting and analyzing the spontaneous brain electrical signal of a person.
  • Figure 1 shows that spontaneous EEG signals are classified into different types according to different frequency ranges, and the corresponding generation states.
  • Sleep staging based on EEG signals separates several different stages of sleep, determines the length of time occupied by each stage, and analyzes the changes in sleep quality.
  • NREM sleep phase I (N1): In the N1 phase, a person's physical activity begins to decrease, the mind begins to be at a loss, and the consciousness gradually becomes blurred. After a few minutes of pre-sleep, the brain state gradually stabilizes, and the entire period is about 1-10 minutes. People who wake up during this period are easily awakened, and people who wake up usually deny sleep. From the perspective of physiological indicators, the level of myoelectricity is significantly reduced, the heart rate is significantly slower, blood pressure and body temperature are slightly lower than those in the awake state, and breathing is gradually regular.
  • the EEG signal is a low-voltage mixed wave, the main frequency is 4-8Hz, the amplitude is between 50-100 ⁇ V, spikes may also appear, but the spindle wave and K complex wave will not appear.
  • N2 NREM sleep phase II
  • N1 and N2 are both light sleep periods, and they may be awakened or awakened by themselves.
  • the brain has a spindle wave and K complex wave, the main frequency is 4-15Hz, the amplitude is 50-150 ⁇ V, which is slightly larger than the sleep stage I.
  • the period of the spindle wave or K complex wave is generally less than 3 minutes, otherwise it is considered that the sleep phase II has not been entered.
  • N3 NREM sleep stage III
  • N4 sleep is deep, awakening is very difficult, brain signal characteristics are similar to sleep stage III, but the components below 2 Hz are significantly increased, mainly 0.5-2 Hz, with an amplitude of 100-200 ⁇ V between.
  • REM sleep period During this period, rapid eye movements can be found, and the body does not move. Most dreams also occur during this period. REM sleep is generally 90-120 minutes, and NREM sleep is generally 4-7 hours. REM sleep lasts for a short time, but it plays an important role in human memory function. From the perspective of brain signals, this stage is mainly a mixed-frequency low-voltage fast wave, the frequency is 15-30Hz, and the amplitude is usually less than 50 ⁇ V.
  • EEG signals In addition to EEG signals, other user characteristic signals can also be used to determine the user's sleep state, such as whether or not to sleep, or to further determine the user's sleep staging result.
  • FIG. 5a is a typical application scenario of an embodiment of the present invention.
  • the ear-side wearing device 101 is close to the user's ear, collects bioelectric signals from the ear, and sends the user's bioelectric signals to the user's sleep monitoring device 102, where the ear
  • the specific operation of the wearing device 101 may optionally include a left ear side signal measurement unit 101a and a right ear side signal measurement unit 101b, or only a single ear side signal measurement unit.
  • the ear wearing device 101 collects the user's bioelectric signal, it sends the user's bioelectric signal to the sleep detection device 102 for judging the user's sleep classification result.
  • the measurement signal needs to be processed accordingly.
  • the related processing can include potential difference processing to eliminate external noise signal interference and enhance the signal; conventional de-noise processing, and
  • the collected bioelectric signals of the user are subjected to feature extraction, and various bioelectric signals are obtained from the measured signals, such as one or more of brain electric signals, eye electric signals, electrocardiographic signals, and electromyographic signals. Since EEG signals are more important in the process of sleep staging analysis, usually one of the preferred extraction methods is ocular electrical signals, electrocardiographic signals, one or more of electromyographic signals, and EEG signals.
  • the specific form of the ear wearing device 101 may be earphones or earplugs.
  • User sleep monitoring device 102 (specifically, it can be a handheld terminal, such as a mobile phone, PDA, pad, etc., or it can be a part of the ear wearing device 101, integrated in the ear wearing device, or integrating the sleep classification function in the cloud server) Analyze the user's EEG signals.
  • the user’s sleep status obtained by analysis can also be used for subsequent sleep improvement processing. For example, when the user’s sleep quality is judged to be poor, the user is reminded to take a rest, increase the amount of exercise, or play aids in the ear-worn device. Sleep music to help improve users’ sleep.
  • the module for sleep adjustment or reminder can be set in any position of the system, such as the ear-worn device 101 or the sleep detection device 102.
  • the ear side in the embodiment of the present invention refers to the area on the human ear and near the ear where bioelectric signals can be measured, such as the inner ear canal, the auricle, the ear groove, the back of the ear, and the area around the ear.
  • the bioelectric signal is collected by deploying the ear-side signal measuring unit on the human ear area and near the human ear.
  • Fig. 5b is an exemplary signal collection manner of wearing the ear-side wearing device according to an embodiment of the present invention, and exemplarily shows a signal collection manner of obtaining bioelectric signals from the inside of the ear canal.
  • 401 is the human ear canal
  • 403 is the ear side signal measurement unit
  • 402 is the main body of the ear side wearing device
  • 404 is the user's auricle.
  • Fig. 6 is a user sleep detection method according to an embodiment of the present invention, which specifically includes the following steps:
  • S601 Collect bioelectric signals from the ear side through the ear side wearing device
  • the ear-side wearing device may include an ear-side signal measuring unit for wearing on the ear side, and fitting the ear-side skin during wearing, so as to collect bioelectric signals.
  • the ear wearing device can be unilateral or bilateral according to the collection needs.
  • the unilateral ear signal measurement unit is used to obtain the user's bioelectric signal from the left or right ear canal, and the two sides can be specifically divided into the left ear
  • the ear side signal measurement unit and the right ear side signal measurement unit are used to obtain user bioelectric signals from the left and right ear canals respectively.
  • the user's bioelectric signal that needs to be measured from the ear side may be the user's bioelectric signal.
  • the usual acquisition method is to measure and acquire the flexible electrode close to the skin of the ear.
  • the measured signal is usually a mixed signal, which requires subsequent decomposition processing to obtain one or a biological characteristic signal.
  • the ear-side wearing device can be controlled by a switch to control whether it starts signal collection.
  • the specific operation method can include pressing the physical button of the headset, or touching the virtual button to start working on the corresponding APP, or not through
  • the switch control power supply is always in working condition when there is electricity.
  • the embodiment of the present application will judge the wearing condition of the ear wearing device, and decide whether to collect data or whether to collect data according to the judgment result.
  • the data is used to analyze the user's sleep classification.
  • the ear-side wearing device includes a plurality of ear-side signal measurement units; it is determined whether the impedance between the two ear-side signal measurement units is lower than the preset threshold; The impedance is lower than a preset threshold; and the potential difference signal of the bioelectric signal measured by the two ear side signal measuring units is used as the user's bioelectric signal.
  • the ear side wearing device for bilateral ear canal measurement, that is, the ear side wearing device includes a left ear ear side signal measurement unit and a right ear side signal measurement unit.
  • the collection method of collecting bioelectric signals from the ear side can be further shown in the figure 7 shows, including:
  • S60101 Determine whether the ear side wearing device can perform measurement normally by determining whether the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold.
  • the left ear side signal measurement unit and the right ear side signal measurement unit may be one or more than one.
  • the shape of the left/right ear side signal measurement unit may be an electrode during the realization process.
  • a preset threshold can be set to determine the wearing condition of the ear-side wearing device.
  • the preset judgment threshold of impedance may be the impedance value of the surface of the ear.
  • the impedance value between the two measurement units is directly obtained for judgment.
  • left ear signal measurement units and right ear signal measurement units there may be multiple measurement strategies. If arbitrarily select a left ear side signal measurement unit and a right ear side signal measurement unit to obtain the impedance value, it can also be the left ear side signal measurement unit at the preset position and the right ear side at the preset position.
  • the impedance value between the side signal measuring units is acquired only once, and it is judged whether the left and right ears are worn normally according to the acquired impedance value. Or you can set the priority order to perform matching measurements one by one, and terminate the measurement and judgment after a preset number of measurements if the preset threshold is not met, or perform measurements one by one until the impedance below the preset value is measured. It means that the ear-worn device can measure normally, otherwise it means it cannot work normally.
  • the specific measurement method in the case of multiple measurement units is not limited here.
  • the bioelectric signal collected by the left ear side signal measurement unit and the right ear side signal measurement unit acquires the user's bioelectric signal.
  • the wearing device can perform measurements normally; the user's bioelectric signal is acquired according to the potential difference signal between the bioelectric signal collected by the left ear signal measuring unit and the bioelectric signal collected by the right ear signal measuring unit.
  • the specific method for obtaining the user's bioelectric signal may include: The potential difference signal between the bioelectric signal collected by the left ear side signal measuring unit and the bioelectric signal collected by the right ear side signal measuring unit obtains the user's bioelectric signal; the ear side wearing device may also be set The reference electrode separately obtains the bioelectric signal collected by the left ear side signal measurement unit and the first potential difference signal of the reference electrode, and the bioelectric signal collected by the right ear side signal measurement unit and the second potential difference signal of the reference electrode. Potential difference signal, and then obtain the difference signal between the first potential difference signal and the second potential difference signal.
  • the impedance between the left ear signal measurement unit and the right ear signal measurement unit is lower than the preset threshold It is determined that the ear canals corresponding to the two measurement units measured can be measured normally.
  • the potential difference signal between the bioelectric signal collected by the left ear side signal measuring unit and the bioelectric signal collected by the right ear side signal measuring unit that can be measured normally after the measurement is determined as the user bioelectric signal signal.
  • the measured The ear canals corresponding to the two measurement units can be measured normally.
  • the potential difference signal between the bioelectric signal collected by the left ear side signal measuring unit and the bioelectric signal collected by the right ear side signal measuring unit that can be measured normally after the measurement is determined as the user bioelectric signal Signal, or based on the measurement result that the ear-worn device can be measured normally, select any left-ear signal measurement unit and right-ear signal measurement unit, or a pre-designated left-ear signal measurement unit And the right ear side signal measuring unit to obtain the potential difference signal of the collected bioelectric signal as the user's bioelectric signal.
  • step S50103 may be included.
  • the left ear side signal measurement unit and the right ear side signal measurement unit need to be multiple.
  • the threshold determines that at least one of the ear canals corresponding to the two measurement units cannot be measured normally.
  • the impedance between the left ear signal measurement unit and the right ear signal measurement unit is higher than the preset threshold, the measured At least one of the ear canals corresponding to the two measurement units cannot be measured normally. That is, when the impedance between one of the left ear side signal measurement units and one of the right ear side signal measurement units is higher than the preset threshold, it is determined that at least one of the ear canals corresponding to the two measurement units cannot be performed normally measuring.
  • the impedance between two of the plurality of left ear signal measurement units is lower than a preset threshold, And whether the impedance between two of the plurality of right ear signal measuring units is lower than a preset threshold.
  • this application can also set the priority order to perform the measurement between the two left/right ear side signal measurement units, and terminate the measurement and judgment after a preset number of measurements if the preset threshold is not met, or perform pair by pair After measuring until the impedance lower than the preset value is measured, it means that the ear-worn device can be measured normally. Otherwise, when all the conditions are traversed, no impedance lower than the preset value is measured, indicating that the normal measurement cannot be performed.
  • this application does not limit the specific measurement method in the case of single-side multiple measurement units.
  • the potential difference signal of the bioelectric signal collected by the left ear ear signal measuring unit and the bioelectric signal collected by the right ear ear signal measuring unit that can be measured normally after the measurement is determined as the user Bioelectric signal.
  • the potential difference signal of the bioelectric signal collected by the left ear side signal measuring unit and the bioelectric signal collected by the right ear side signal measuring unit that can be measured normally after the measurement is determined as the user's biological
  • the specific method of the electrical signal may include directly acquiring the user's bioelectric signal by the potential difference signal of the bioelectric signal collected by the two ear side signal measurement units that can normally measure one side; the ear side wearing device may also be provided with a reference electrode , Respectively acquiring the bioelectric signal collected by the one ear side signal measuring unit and the third potential difference signal of the reference electrode, and the bioelectric signal collected by the other ear side signal measuring unit and the fourth potential difference signal of the reference electrode, and then Obtain a difference signal between the third potential difference signal and the fourth potential difference signal.
  • the selection of the ear signal measurement unit can have multiple transmissions, such as directly selecting two measurement units for impedance value judgment to obtain the potential difference signal, or selecting the measurement unit according to a preset setting, or selecting arbitrarily.
  • the method of obtaining the potential difference signal in the present application may be implemented through software instructions, or may be implemented through hardware circuits.
  • the ear side wearing device for unilateral measurement, that is, the ear side wearing device only includes the left ear side signal measurement unit or the right ear side signal measurement unit.
  • the left ear side signal measurement unit or the right ear side signal measurement unit There are multiple ear signal measurement units, that is, there are multiple single ear signal measurement units.
  • the collection method of collecting bioelectric signals from the ear side can also be shown in Figure 8, and further includes:
  • S60111 Determine whether the ear side wearing device can perform measurement normally by determining whether the impedance between the two signal measurement units in the unilateral ear side signal measurement unit is lower than a preset threshold.
  • the application can also set the priority order to perform the measurement between two unilateral ear signal measurement units, and terminate the measurement and judgment after the preset number of measurements if the preset threshold is not met, or perform the measurement pair by pair until the measurement
  • the impedance is lower than the preset value, it means that the ear-worn device can be measured normally. Otherwise, when all the conditions are traversed, no impedance lower than the preset value is measured, which means that the normal measurement cannot be performed.
  • the application also does not limit the specific measurement method in the case of multiple measurement units on one side.
  • S60112 When it is determined that the ear side wearing device can perform measurement normally, use the potential difference signal of the bioelectric signal collected by two of the plurality of unilateral ear side signal measurement units as the user bioelectric signal.
  • the ear side wearing device can work normally measuring. After the measurement, the potential difference signal of the bioelectric signal collected by the two unilateral ear signal measuring units that are determined to be able to be measured is used as the user's bioelectric signal.
  • the specific method of using the potential difference signal of the bioelectric signal collected by the two unilateral ear signal measuring units that can be measured normally after the measurement as the user's bioelectric signal may include directly connecting the two ears that can be measured normally
  • the potential difference signal of the bioelectric signal collected by the signal measuring unit obtains the user's bioelectric signal;
  • the ear-side wearing device may also be provided with a reference electrode to separately obtain the bioelectric signal and the reference electrode collected by the one ear-side signal measuring unit And the bioelectric signal collected by the other ear signal measuring unit and the sixth potential difference signal of the reference electrode, and then the difference signal of the fifth potential difference signal and the sixth potential difference signal is obtained.
  • the potential difference signal of the bioelectric signal collected by the two unilateral ear signal measuring units that can be measured normally is used as the user's bioelectric signal, or the ear wearing device can be considered normal based on the measurement result
  • any two single-sided ear canal measurement units or two pre-designated single-sided ear canal measurement units are selected to obtain the collected potential difference signal of the bioelectric signal as the user's bioelectric signal.
  • the ear-side wearing device may also include a sensor unit, such as a heart rate sensor (specifically, a PPG sensor, or other sensing devices for measuring heart rate) for measuring and acquiring heart rate signals, and a motion sensor ( Specifically, it can be an IMU motion sensor, or other sensing devices for measuring motion. It can be used to measure and perceive user activities, and a sound sensor (which can be a microphone or other sensing devices for measuring sound). ) Is used to detect the user's voice.
  • a sensor unit such as a heart rate sensor (specifically, a PPG sensor, or other sensing devices for measuring heart rate) for measuring and acquiring heart rate signals
  • a motion sensor Specifically, it can be an IMU motion sensor, or other sensing devices for measuring motion. It can be used to measure and perceive user activities, and a sound sensor (which can be a microphone or other sensing devices for measuring sound). ) Is used to detect the user's voice.
  • the bioelectric signal may be a mixed signal of the user's biometric signal, which is used for the later extraction of the biometric signal.
  • the sensor signal may be a motion sensor signal, a heart rate sensor signal, or a sound signal according to the deployment of sensors in the specific implementation process. One or more of the sensing signals.
  • S602 Perform feature decomposition on the bioelectric signal of the user to obtain a biometric signal
  • the biometric signal includes one or more of ECG signals, EOG signals, EMG signals, and EEG signals.
  • ECG signals EOG signals
  • EMG signals EEG signals
  • feature decomposition to extract different types of biological characteristic signals, which can be extracted according to the different spectrums of different types of signals.
  • the more common one is to use blind source separation algorithm independent component analysis (ICA) to decompose to obtain multiple biological signals.
  • Feature signal components These components may correspond to EEG signals, ECG, EOG, and EMG signals, etc., and extract signal features.
  • S603 Obtain a sleep classification result of the user according to the biometric signal.
  • the analysis of sleep classification results in the embodiment of the present invention may be implemented in a machine learning manner.
  • machine learning models such as SVM model for analysis, or deep neural network model for analysis.
  • the analysis is carried out according to the deep neural network model.
  • This embodiment is specifically a CNN convolutional neural network model.
  • the analysis method is to obtain the probabilities of the corresponding sleep period of the sleep stage according to the sampling of biometric signals and the CNN model to determine Sleep classification of the corresponding sleep period.
  • obtaining the sleep classification result of the user according to the biometric signal includes specifically obtaining the user's sleep classification result according to the biometric signal and sensor signal.
  • the sleep situation can be specifically obtained by obtaining the user's current sleep stage classification result, or obtaining the sleep stage composition of the user's entire sleep stage, which can be a full-stage analysis, or an interval sampling of different sleep periods for analysis.
  • Analyze according to the SVM model According to the sampling of the biological characteristic signal and the sensor signal and the SVM model, the probability of the sleep stage of the corresponding sleep period is obtained, so as to determine the sleep stage of the corresponding sleep period.
  • the analysis is performed according to the deep neural network model.
  • This embodiment is specifically a CNN convolutional neural network model.
  • the analysis method is to obtain the probability of the sleep classification of the sleep period corresponding to the signal according to the sampling of biometric signals and sensor signals and the CNN model , To determine the sleep classification of the corresponding sleep period.
  • step S502 when the machine learning model is used to analyze the sleep classification results, step S502 may not be performed, that is, the biometric signal is not extracted, and the user's bioelectric signal is directly used for model training, and then in the analysis process , Directly use the sample of the detected user's bioelectric signal as input to obtain the corresponding sleep classification probability.
  • the sleep classification result in the embodiment of the present invention may output the probability of the sleep stage corresponding to the analyzed signal, or the probability of whether the user is in a sleep state, or a direct probability-based judgment result.
  • the threshold is greater than or equal to the preset threshold. According to the needs of specific implementation, it can be greater than or equal to the preset threshold, and also less than the preset threshold. According to the needs of specific implementation, it can also be less than or equal to the preset threshold. Set the threshold.
  • the bioelectric signal used for feature decomposition in the embodiments of the present application may also be a bioelectric signal after secondary processing, such as a biological signal after conventional processing such as buffer amplification, filtering, secondary amplification, A/D conversion, etc. electric signal. Or other signals after denoising, amplification, and digital-to-analog conversion processing.
  • a bioelectric signal after secondary processing such as a biological signal after conventional processing such as buffer amplification, filtering, secondary amplification, A/D conversion, etc. electric signal.
  • other signals after denoising, amplification, and digital-to-analog conversion processing may also be the signal after the feature information is further extracted, for example, the heart rate signal can be extracted directly based on the ECG signal for subsequent sleep classification analysis.
  • SVM Small Vector Machine
  • CNN Convolutional Neural Network
  • the sleep detection method of the present application relates to an artificial intelligence method related to machine learning, and a general artificial intelligence method usually involves model training and real-time algorithm recognition.
  • Part 1 Model training
  • the present invention relates to two parts of bioelectric signal and sensor signal. Therefore, in the model training stage, these two types of signals also need to be acquired for feature extraction and model training.
  • the purpose is to use known target data samples to train the model to obtain the minimum loss. Model parameters under.
  • SVM model training consists of the following parts: signal acquisition, signal preprocessing, feature extraction and selection, pattern classification and result output. Among them, feature extraction and selection and pattern classification are the two most critical steps.
  • the probability corresponding to each stage can be output for the judgment of sleep stage. It is necessary to perform denoising preprocessing on the multi-band and multi-brain bioelectric signals generated by the person in each stage of sleep staging (which may be the sleep staging label has been marked by a doctor), for example, power frequency notching is performed first. Then use the blind source separation algorithm independent component analysis (ICA) to decompose multiple characteristic signal components: these components may correspond to one or more of the EEG signal, ECG, EOG and EMG signal, and Extract signal features.
  • ICA blind source separation algorithm independent component analysis
  • the decomposed characteristic signal (such as one or more of EEG, ECG, EOG, EMG)
  • each type of signal into segments, and each segment has a data length of 7500 points (sampling frequency 250Hz, acquisition 30s), select one
  • the 25-minute data of the sleep stage is divided into multiple 30s for feature extraction, and the ratio of the energy sum of each feature of the sleep stage is calculated.
  • the db4 wavelet basis can be used to perform wavelet decomposition, and calculate the energy and energy of alpha wave (8-13Hz), beta wave (13-30Hz), theta wave (4-7Hz), delta (1-4Hz) on 1-30Hz, respectively Ratio of
  • the ECG, EMG, and EOG signals are decomposed by wavelet based on the wavelet, and the ratio of the sum of the energy at that frequency is calculated.
  • the energy ratio calculation formula is as follows:
  • [mu] i is the i-th layer band decomposition (e.g. energy, a ratio calculation EGG signal, different bands corresponding to different types of EGG signal) and the ratio of the total energy
  • D i (k) is the i-layer band decomposition
  • n is the number of data of the i-th layer wavelet coefficient
  • E s is the total energy sum of each frequency band signal
  • N is the total number of divided frequency bands.
  • the ratio of the energy sum of the alpha, beta, theta, delta wave and other characteristic signals in the EEG signal of the current sleep stage will be obtained. If there are 7 types of signals, it corresponds to the 7-dimensional signal characteristics. , Import into SVM (support vector machine), one of the 30s segment data can get sleep staging classification probability results, training to get the SVM model parameters with the highest recognition accuracy, for example, here SVM can use the radial basis kernel function as the activation function, and According to experience, we can choose to recognize when gamma is 8.0 and penalty factor C is 10.0.
  • the other biometric signals and sensor signal characteristics (such as energy and ratio) of each sleep stage, the ratio of the alpha energy sum of the EEG signal and the energy of other characteristic signals are extracted in the same way Together with the ratio, it is imported into the SVM as a signal feature for model parameter training.
  • the trained SVM model can output the probability value corresponding to the sleep classification according to the characteristic signal, or the energy and ratio of the characteristic signal and the sensor signal during sleep classification analysis, which is used to determine the corresponding signal of the current analysis Sleep staging results.
  • a typical convolutional neural network architecture usually includes input ->[[convolutional layer]*N->[pooling layer]*M->[fully connected layer]*K->recognition operation, where N1, M1 and K are integers and can be set as required.
  • the offline training process of a convolutional neural network based on bioelectrical signals is to first perform multi-band and multi-brain bioelectrical signals generated by people in sleep and non-sleep phases (which can be marked by a doctor for sleep staging).
  • De-noise preprocessing decompose the bioelectric signal of multiple frequency bands and multiple regions according to the subspace decomposition algorithm ICA and obtain one or more of EEG signal, ECG, EOG and EMG signal.
  • the preprocessed decomposed signal is formed into a multi-dimensional signal and its corresponding label (such as the corresponding sleep staging category) is input into the convolutional neural network, specifically, for the decomposed bioelectric signal (such as EEG, ECG, EOG) , One or more of EMG), each type of signal is segmented, and the data length of each segment can be 7500 points (sampling frequency 250Hz, acquisition 30s), if all four types of biometric signals are included, EEG, ECG, EOG, EMG four-dimensional signal matrix, the signal matrix is combined with its corresponding label, and input into the convolutional neural network. Iterative optimization solution is performed according to the stochastic gradient descent algorithm.
  • the corresponding convolution kernel parameters and the parameters in the fully connected layer are obtained when the objective function converges.
  • the final recognition layer can adopt the softmax layer, and when it is only necessary to distinguish between sleep and non-sleep, the probabilities corresponding to the two categories can be output. When more sleep states need to be distinguished, the number of output ports can be increased accordingly. Therefore, in the training phase of the convolutional neural network, various parameters in the convolutional layer, pooling layer, fully connected layer and classification model need to be determined to ensure high accuracy of subsequent target recognition. One of the 30s segment data can get the sleep stage classification probability result.
  • the offline training process of the convolutional neural network based on the characteristic signal and sensor signal First, the EGG characteristic signal, PPG heart rate signal, IMU movement generated by the person in the sleep and non-sleep stage (the sleep staging label has been marked by the doctor) Signal, microphone audio signal, etc. (Select the type of signal required in the training phase according to the type of signal that needs to be analyzed in the application phase. For example, the application phase collects EEG signals, eye signals and motion signals for sleep analysis, then the training phase requires Obtain EEG signals, eye signals and motion signals at different labeling stages.) Perform denoising preprocessing.
  • bioelectric signal it may be necessary to decompose the multi-band and multi-zone bioelectric signal according to the subspace decomposition algorithm ICA.
  • ICA subspace decomposition algorithm
  • the preprocessed decomposed signal and multi-sensing signal (one or more of PPG heart rate signal, IMU motion signal, microphone audio signal) are formed into a multi-dimensional signal and input into the convolutional neural network.
  • each type of signal is segmented, and each segment of data is 7500 points (sampling frequency) 250Hz, acquisition 30s), and form EEG, ECG, EOG, EMG, PPG heart rate, IMU, audio and other multi-dimensional signal matrix.
  • the dimension is different according to the specific application requirements.
  • the signal matrix is combined with its corresponding label and input Convolutional neural network. According to the gradient descent algorithm, iteratively find the corresponding convolution kernel and each parameter in the fully connected layer when the neural network error is minimized.
  • the softmax regression classification model is usually used in the final recognition operation stage.
  • the softmax model needs to be trained in advance to obtain a loss function. Through stochastic gradient descent, the known training data probability is input into the loss function parameter when the loss is the smallest. Therefore, in the training phase of the convolutional neural network, various parameters of the convolutional layer, pooling layer, fully connected layer, and classification model need to be determined to ensure high accuracy of subsequent target recognition.
  • sampling frequency 250Hz, acquisition 30s is only an example, and other sampling frequencies and durations can also be selected.
  • energy and ratio are only a feature of the signal, and other features, such as power spectrum estimation of various signals, can be selected for model training to obtain a sleep classification model for sleep classification.
  • FIG. 9 corresponds to a sleep detection system according to an embodiment of the present application, and the system includes an ear wearing device 101 and a sleep detection device 102 corresponding to FIG. 5.
  • the ear-side wearing device 101 is used to collect the user's bioelectric signal from the ear side; it is used to perform feature decomposition of the user's bioelectric signal to obtain the biometric signal;
  • the biometric signal includes, electrocardiographic signal, eye electrical signal Signal, one or more of EMG signals, and EEG signals;
  • the ear wearing device 101 can be specifically divided into unilateral or bilateral measurement.
  • the ear wearing device 101 is for unilateral measurement and its structure is shown in Figure 10a.
  • the unilateral ear signal measurement unit 1011 is used to measure from the left or right ear canal.
  • the ear canal obtains the user's bioelectric signal.
  • the ear wearing device 101 is used for bilateral measurement and its structure is shown in Figure 10b.
  • the left ear ear signal measuring unit 101a is used to obtain user bioelectric signals from the left ear canal
  • the right ear ear signal measuring unit 101b is used to measure from the right The ear canal obtains the user's bioelectric signal.
  • the ear-side wearing device 101 corresponding to bilateral measurement, that is, the ear-side wearing device includes a left-ear ear-side signal measuring unit 101a and a right-ear ear-side signal measuring unit 101b.
  • the ear-side wearing device 101 determines the left-ear ear-side signal Whether the impedance between the measuring unit 101a and the right ear signal measuring unit 101b is lower than the preset threshold to determine whether the ear wearing device can measure normally, when it is judged that the ear wearing device can measure normally,
  • the potential difference signal between the bioelectric signal collected by the left ear side signal measuring unit and the bioelectric signal collected by the right ear side signal measuring unit is used to obtain the user's bioelectric signal, and when the judgment result is the ear side wearing device
  • the measurement cannot be performed normally, and it is determined whether the impedance between two of the plurality of left ear signal measuring units is lower than a preset threshold, and whether the impedance between two of the plurality of right ear signal measuring units is Whether
  • the user's bioelectric signal is acquired according to the potential difference signal of the bioelectric signal collected by the two bioelectric measuring devices in the ear canal on the side whose impedance is lower than the preset threshold.
  • the specific judgment method can be parameter steps S60101-S60103.
  • the ear side wearing device 101 for unilateral ear canal measurement, that is, the ear side wearing device 101 only includes the left ear side signal measurement unit or the right ear side signal measurement unit 1011.
  • the left ear side signal measurement The unit or the right ear side signal measurement unit needs to be multiple, that is, there are multiple single ear side signal measurement units.
  • the ear side wearing device 101 determines whether the ear side wearing device can perform measurements normally by determining whether the impedance between the two signal measurement units in the unilateral ear side signal measurement unit is lower than a preset threshold.
  • the device can perform measurement normally, and obtain the user's bioelectric signal according to the potential difference signal of the bioelectric signal collected by two of the plurality of unilateral ear signal measuring units. Refer to steps S60111-S60112 for specific judgment methods.
  • the ear-side wearing device is also used to collect sensor signals, such as heart rate signals, exercise signals (perceive user activity), sound signals (detect user sounds), one or more of them Kind.
  • the bioelectric signal can be a mixed signal of the user's biometric signal, which is used for the later extraction of the biometric signal.
  • the sensor signal can be motion sensor signal or heart rate sensor according to the deployment of sensors in the specific implementation process. One or more of signal and sound sensor signal.
  • the ear-side wearing device 101 is also used to perform feature decomposition of the user's bioelectric signal to obtain the biometric signal;
  • the biometric signal includes one or more of ECG signals, EOG signals, EMG signals, and EEG signals.
  • the sleep detection device 102 is configured to obtain a sleep stage classification result of the user according to the biometric signal.
  • the analysis of sleep classification results in the embodiment of the present invention may be implemented in a machine learning manner.
  • machine learning models such as SVM model for analysis, or deep neural network model for analysis.
  • the specific implementation can be implemented with reference to step S503.
  • the sleep detection device or the ear-worn device may also include a sleep adjustment function, which is used to prompt the user when the user's sleep condition is not good according to the sleep detection result, or to intervene to help the user improve the quality of sleep, such as playing some soothing music.
  • the specific implementation form of the sleep detection device in the implementation process can be various types of portable terminals, or can be set in a cloud server.
  • Fig. 10c is an exemplary structural diagram of an ear-side wearing device that obtains bioelectric signals from the inside of the ear canal according to an embodiment of the present invention.
  • the ear-side wearing device can have various forms, for example, it can be in the form of earphones or It is the form of earplugs.
  • the ear-side wearing device given in this example is in the form of earplugs, but it is not limited in this application.
  • the ear-side wearing device includes an earplug body 301, a flexible electrode carrier 302 and a plurality of surface flexible electrodes 303.
  • the flexible electrode carrier 302 provides a sufficiently elastic support to ensure that the multiple flexible electrodes 303 attached to the surface of the flexible electrode carrier 302 form a close fit with the inner surface of the user's ear canal, ensuring stable collection of bioelectric signals.
  • Section 310 exemplarily presents a structure of a surface flexible electrode 303, including a biosensing flexible electrode 303A, a biosensing flexible electrode 303B, and a grounded common flexible electrode 303G with an equiangular 120 degree distribution, and 304 is an earplug hole.
  • the earplug body 301 may also be connected with a reference electrode, which is not shown here.
  • the reference electrode can also be realized by electric shock of the electrode on the auricle support.
  • the wearing schematic diagram of the ear-side wearing device in the form of earplugs in Fig. 10c is shown in Fig. 5b, where 401 is the user’s ear canal, 402 is the earplug for EEG signal measurement, 403 is the flexible electrode, and 404 is the user’s auricle . It can be seen from FIG.
  • the ear-worn device may also include a communication module for receiving or sending EEG signals, and optionally an attention detection unit for analyzing the user's attention type through EEG signals.
  • the step of characterizing the bioelectric signal can also be implemented in the sleep detection device 102.
  • Figures 9a and 9b are two system structure diagrams corresponding to the embodiment of the present invention.
  • Figure 9a corresponds to the implementation scheme implemented by setting the feature decomposition function on the ear-side wearing device, and Figure 9a the middle ear-side wearing device 210 has more Data processing function.
  • the ear side signal measurement unit 211 of the ear side wearing device 210 obtains the user's bioelectric signal
  • the sensor signal measurement unit 212 obtains various sensor signals, which can be heart rate PPG, exercise IMU, microphone, etc., and respectively
  • bioelectric signals and sensor signals are preprocessed by the ear canal signal processing unit 213 and the sensor signal processing unit 214, such as noise-removing preprocessing, A/D conversion, etc., and the sleep adjustment module 216 is used according to the sleep detection unit 221
  • the feature decomposition unit 215 is used to perform feature extraction of the bioelectric signal, and decompose it into EEG, ECG, EOG, and EMG.
  • the decomposed characteristic signals and sensor signals are sent to the terminal or the cloud through the communication unit 217.
  • the terminal or the cloud receives these signals through the communication unit 222, they are transmitted to the sleep detection unit 221, and after processing by the sleep detection unit 221, The sleep state monitoring result will be obtained.
  • the sleep adjustment instruction can be generated according to the adjustment algorithm in the sleep adjustment module 216, and the playback module can be controlled to play suitable music sounds.
  • the sleep adjustment module can be a miniature vibration motor.
  • the ear canal signal processing unit 213 and the sensor signal processing unit 214 may optionally include an input buffer amplifier circuit or a preprocessing circuit, a filter circuit, and a secondary amplifier circuit; the signal measurement unit 211 and the sensor signal measurement unit
  • the signal detected by 212 may be processed by the input buffer amplifier circuit, filter circuit, secondary amplifier circuit, etc., and then transmitted to the A/D conversion circuit.
  • the feature extraction unit for example, extracts heart rate information from the ECG signal.
  • Fig. 9b corresponds to an implementation solution implemented by setting the ear-side wearing device on the sleep detection device, that is, the terminal or the cloud, and will not be repeated here.
  • Figures 9a and 9b are only exemplary cases. In the specific implementation process, the unit modules can be added, reduced and adjusted, or the functions between the units can be integrated.
  • the sleep detection device and the ear wearing device may also be integrated, as shown in FIG. 11, which corresponds to an ear wearing device with integrated sleep detection function 110 according to the embodiment of the present application.
  • the device includes:
  • the ear side signal measuring unit 111 is used to collect user bioelectric signals from the ear side.
  • the ear signal measuring unit 111 may include a left ear signal measuring unit 111a and a right ear signal measuring unit 111b.
  • the ear side signal measurement unit 111 may only include the unilateral ear side signal measurement unit 111c.
  • the feature decomposition unit 112 is configured to perform feature decomposition on the user's bioelectric signal to obtain a biometric signal; the biometric signal includes one or more of an electrocardiographic signal, an ocular signal, and an electromyographic EMG signal, And brain electrical signals.
  • the sleep detection unit 113 is configured to obtain a sleep stage classification result of the user according to the biometric signal.
  • the specific analysis method please refer to the above specific embodiment, which will not be repeated here.
  • the first judging unit 114 is configured to judge whether the impedance between the two ear side signal measuring units is lower than the preset threshold; when the impedance between the two ear side signal measuring units is lower than the preset threshold; The potential difference signal of the bioelectric signal collected by the bioelectric signal measured by the two ear side signal measuring units is used as the user's bioelectric signal.
  • the ear-side wearing device may optionally include a second judgment unit.
  • the first breaking unit 114 is used to determine whether the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold (the specific judgment method has been introduced above, and it is not here. Repeat); when the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold; the bioelectric signal collected by the left ear side signal measurement unit and The potential difference signal of the bioelectric signal collected by the right ear signal measuring unit is used as the user's bioelectric signal.
  • a preset threshold the specific judgment method has been introduced above, and it is not here. Repeat
  • the second judging unit 115 is used for when the first judging unit 114 judges that the ear-mounted device cannot be measured normally (the specific judging method has been introduced above and will not be repeated here), the second judging unit 115 respectively judges Whether the impedance between two of the plurality of left ear signal measuring units is lower than a preset threshold, and whether the impedance between two of the plurality of right ear signal measuring units is lower than a preset Threshold; and the potential difference signal of the bioelectric signal collected by two bioelectric measurement devices in the ear canal on the side whose impedance is lower than the preset threshold is used as the user's bioelectric signal.
  • the second judging unit 115 is an optional unit, and the second judging unit 115 is applied to the case where there are multiple ear-side signal measurement units for the left ear and multiple right-ear ear-side signal measurement units.
  • the ear-side wearing device includes a first judging unit 114 for judging whether the impedance between the two unilateral ear-side signal measurement units is lower than a preset threshold (specifically, the judgment method is It has been introduced in the article and will not be repeated here.)
  • a preset threshold specifically, the judgment method is It has been introduced in the article and will not be repeated here.
  • the ear wearing device 110 may optionally also include a sensor signal measuring unit 117 for collecting sensor signals; the sensor signal measuring unit 117 may include various sensor devices, such as a heart rate sensor ( Specifically, it can be a PPG sensor, or other sensor devices used to measure heart rate) for measuring and acquiring heart rate signals, motion sensors (specifically, it can be an IMU motion sensor, or other sensing devices for measuring motion) It is used to measure and perceive the user's activity.
  • the sound sensor (specifically, it can be a microphone or other sensing devices for measuring sound) is used to detect one or more of the sounds made by the user, and is used to measure motion transmission.
  • One or more of sensory signal, heart rate sensor signal, and sound sensor signal is used to measure motion transmission.
  • the embodiment of the present invention also discloses a method for measuring user-related signals, as shown in Figure 16: where steps S1601 and S1602 are the same as those in Figure 7, and S1603 is to send the biometric signal to the signal analysis device.
  • the signal analysis device is The embodiment of the present application may specifically be a sleep detection device.
  • the corresponding embodiment of the present invention also discloses an ear-side wearing device for measuring user-related signals.
  • the ear-side signal measuring unit 121 is used to collect user bioelectric signals from the ear side.
  • the ear signal measuring unit 121 may include a left ear signal measuring unit 121a and a right ear signal measuring unit 121b.
  • the ear side wearing device 120 is a unilateral measurement device, the ear side signal measurement unit 121 may only include the unilateral ear side signal measurement unit 121c.
  • the feature decomposition unit 122 is configured to perform feature decomposition on the user's bioelectric signal to obtain a biometric signal; the biometric signal includes one or more of an electrocardiographic signal, an ocular signal, and an electromyographic EMG signal, And brain electrical signals.
  • the sending unit 123 is configured to send the biometric signal to the signal analysis device; the signal analysis device may specifically be a sleep detection device in the embodiment of the present application.
  • the first judging unit 124 is configured to judge whether the impedance between the two ear side signal measuring units is lower than the preset threshold; when the impedance between the two ear side signal measuring units is lower than the preset threshold; The potential difference signal of the bioelectric signal collected by the bioelectric signal measured by the two ear side signal measuring units is used as the user's bioelectric signal.
  • the ear-side wearing device may optionally further include a second judgment unit 125.
  • the first disconnection unit 124 is used to determine whether the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold (the specific determination method has been introduced above, and it is not here. Repeat); when the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold; the bioelectric signal collected by the left ear side signal measurement unit and The potential difference signal of the bioelectric signal collected by the right ear signal measuring unit is used as the user's bioelectric signal.
  • a preset threshold the specific determination method has been introduced above, and it is not here. Repeat
  • the second judging unit 125 is used for when the first judging unit 124 judges that the ear-side wearing device cannot be measured normally (the specific judging method has been introduced above and will not be repeated here), the third judging unit judges the Whether the impedance between two of the plurality of left ear signal measuring units is lower than a preset threshold, and whether the impedance between two of the plurality of right ear signal measuring units is lower than the preset threshold And the potential difference signal of the bioelectric signal collected by the two bioelectric measuring devices of the ear canal on the side whose impedance is lower than the preset threshold is used as the user's bioelectric signal.
  • the second judging unit 125 is an optional unit, and the second judging unit 125 is applied to the case where there are multiple ear-side signal measurement units for the left ear and multiple right-ear ear-side signal measurement units.
  • the first judgment unit 124 of the ear-side wearing device is used to judge whether the impedance between the two unilateral ear-side signal measurement units is lower than a preset threshold (the specific judgment method is described above It has been introduced and will not be repeated here), when the impedance between the two unilateral ear signal measurement units is lower than a preset threshold, the two of the multiple unilateral ear signal measurement units are collected The potential difference signal of the bioelectric signal is used as the user's bioelectric signal.
  • the ear-side wearing device 120 may optionally also include a sensing signal measuring unit 127 for collecting sensing signals; the sensing signal measuring unit 127 may include various sensor devices, such as a heart rate sensor ( Specifically, it can be a PPG sensor, or other sensor devices used to measure heart rate) for measuring and acquiring heart rate signals, motion sensors (specifically, it can be an IMU motion sensor, or other sensing devices for measuring motion) It is used to measure and perceive the user's activity.
  • the sound sensor (specifically, it can be a microphone or other sensing devices for measuring sound) is used to detect one or more of the sounds made by the user, and is used to measure motion transmission.
  • One or more of sensory signal, heart rate sensor signal, and sound sensor signal is used to measure motion transmission.
  • Step S1702 is the same as S603 in Fig. 7, and S1701 is receiving a biometric signal from an ear wearing device.
  • the biometric signal includes one or more of an electrocardiographic signal, an ocular electrical signal, an electromyographic EMG signal, and an electroencephalographic signal.
  • a sensing signal can also be received from the ear-side wearing device; the sensing signal is one or more of motion sensing signals, heart rate sensing signals, and sound sensing signals.
  • the embodiment of the present invention also discloses a sleep detection device 130, as shown in FIG. 13.
  • the device includes:
  • the receiving unit 131 is configured to receive biometric signals from the ear-side wearing device
  • the biometric signal includes one or more of ECG signal, EOG signal, EMG signal, and EEG signal;
  • the sleep detection unit 132 is configured to obtain the sleep stage classification result of the user according to the biometric signal.
  • the feature decomposition unit 112 is configured to perform feature decomposition on the user's bioelectric signal to obtain a biometric signal; the biometric signal includes one or more of an electrocardiographic signal, an ocular signal, and an electromyographic EMG signal, And brain electrical signals.
  • the sleep detection unit 113 is configured to obtain a sleep stage classification result of the user according to the biometric signal.
  • the specific analysis method please refer to the above specific embodiment, which will not be repeated here.
  • the optional receiving unit 131 is also used to receive sensing signals from the ear-side wearing device; the sensing signals are one or more of motion sensing signals, heart rate sensing signals, and sound sensing signals.
  • the sleep detection unit 132 analyzes the user's sleep staging classification result according to the biometric signal, and specifically may also be: obtaining the user's sleep staging classification result according to the biometric signal and the sensor signal .
  • the sleep detection device may be a user's terminal equipment such as a mobile phone, or other wearable or portable terminals, or may be set in a server in the cloud.
  • FIG. 14 is a schematic diagram of the processor structure of the device corresponding to Embodiments 11 and 12 of the present application.
  • the ear wearing device 1400 integrated with the sleep detection function may include one or more processors 1406, one or more memories 1401, a sensor signal measurement unit 1402, and a feature decomposition unit 1403.
  • the ear wearing device may further include a sensor unit 1404 and a communication unit 1405.
  • the processor 1406 can be respectively connected to the memory 1401, the measuring electrode 1402, the feature decomposition circuit 1403, the sensor 1404 and other components through the bus. They are described as follows:
  • the processor 1406 is the control center of the ear wearing device, and various interfaces and lines are used to connect various components of the ear wearing device.
  • the processor 1406 may further include one or more processing cores.
  • the processor 1400 can determine whether the measurement electrode can be measured normally (whether the ear-worn device can be measured normally) by executing the program instructions, and analyze the user's sleep stage according to the measurement signal.
  • the processor 1406 may be a dedicated processor or a general-purpose processor, when the processor 1406 is a general-purpose processor, the processor 1406 runs or executes software programs (instructions) and/or modules stored in the memory 1401.
  • the memory 1401 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
  • the memory 1401 may further include a memory controller to provide the processor 1400 and the input unit to access the memory 1401.
  • the memory 1401 may be specifically used to store software programs (instructions) and collected user bioelectric signals.
  • the ear side signal measuring unit 1402 is used to collect user bioelectric signals from the ear side.
  • the ear side signal measurement unit 1402 may include a left ear side signal measurement unit and a right ear side signal measurement unit.
  • the ear side signal measurement unit 1402 may only include a unilateral ear side signal measurement unit.
  • the ear signal measuring unit 1402 is usually implemented by hardware.
  • the ear signal measuring unit 1402 may be an electrode, and the ear signal measuring unit 1402 may be one or more.
  • the feature decomposition unit 1403 is configured to perform feature decomposition on the user's bioelectric signal to obtain a biometric signal; the biometric signal includes one or more of an electrocardiographic signal, an eye electrical signal, and an electromyographic EMG signal, And brain electrical signals.
  • the feature decomposition unit 1403 is usually implemented by hardware, such as a feature decomposition circuit and an ICA component.
  • a sensor signal measuring unit 1404 may also be included for collecting sensor signals; the sensor signal measuring unit 1404 may include multiple sensor devices, such as heart rate
  • the sensor specifically can be a PPG sensor, or other sensing devices for measuring heart rate
  • the motion sensor specifically can be an IMU motion sensor, or other sensors for measuring motion Device
  • the sound sensor specifically, a microphone or other sensing device for measuring sound
  • the communication unit 1405 is used to communicate with the ear-worn device and other devices through wireless or wired communication technology, such as cellular mobile communication technology, WLAN, Bluetooth, etc.
  • the ear-side wearing device in the embodiments of the present application may include more or fewer components than those shown in the figure, or a combination of certain components, or different component arrangements.
  • the ear wearing device may further include a speaker, a camera, etc., which will not be repeated here.
  • the processor 1406 can read and analyze the measurement signal stored in the memory 1401 to determine whether the measurement electrode can be measured normally (whether the ear-worn device can be measured normally), and perform user sleep staging based on the measurement signal analysis.
  • the processor 1406 can read and analyze the measurement signal stored in the memory 1401 to determine whether the measurement electrode can be measured normally (whether the ear-worn device can be measured normally), and perform user sleep staging based on the measurement signal analysis.
  • the processor 1406 is configured to determine whether the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold (the specific determination method has been introduced above , Not repeat them here); when the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold; according to the left ear side signal measurement unit
  • the potential difference signal between the bioelectric signal and the bioelectric signal collected by the right ear side signal measuring unit acquires the user’s bioelectric signal; when it is determined that the ear side wearing device cannot be measured normally (the specific determination method has been described above , I will not repeat them here), respectively determine whether the impedance between two of the multiple left ear signal measurement units is lower than a preset threshold, and whether the impedance between the multiple right ear signal measurement units Whether the impedance between the two is lower than a preset threshold; and obtaining the user's bioelectricity according to the potential difference signal of the bioelectric
  • the processor 1406 is configured to determine whether the impedance between the two unilateral ear signal measurement units is lower than a preset threshold (the specific determination method has been introduced above, and will not be repeated here), When the impedance between the two unilateral ear signal measurement units is lower than the preset threshold, the obtained signal is obtained according to the potential difference signal of the two collected bioelectric signals among the multiple unilateral ear signal measurement units. Describe the user's bioelectric signal.
  • the processor 1406 is further configured to obtain a sleep stage classification result of the user according to the biometric signal.
  • a sleep stage classification result of the user please refer to the above specific embodiment, which will not be repeated here.
  • FIG. 14 is only an implementation of the ear-side wearing device of the present application, the processor 1406 and the memory 1401 in the ear-side wearing device may also be integratedly deployed in possible embodiments. .
  • FIG. 14 may also be an ear side wearing device for measuring user related signals according to an embodiment of the present invention. It may include one or more processors 1406, one or more memories 1401, an ear side signal measurement unit 1402, and a feature decomposition unit. 1403.
  • the ear wearing device may further include a sensor unit 1404 and a communication unit 1405 (including a sending unit and a receiving unit).
  • the processor 1406 can be respectively connected to the memory 1401, the measuring electrode 1402, the feature decomposition circuit 1403, the sensor 1404 and other components through the bus. They are described as follows:
  • the processor 1406 is the control center of the ear wearing device, and various interfaces and lines are used to connect various components of the ear wearing device.
  • the processor 1406 may further include one or more processing cores.
  • the processor 1400 can determine whether the measurement electrode can be measured normally (whether the ear-worn device can be measured normally) by executing program instructions.
  • the processor 1406 may be a dedicated processor or a general-purpose processor, when the processor 1406 is a general-purpose processor, the processor 1406 runs or executes software programs (instructions) and/or modules stored in the memory 1401.
  • the memory 1401 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
  • the memory 1401 may further include a memory controller to provide the processor 1400 and the input unit to access the memory 1401.
  • the memory 1401 may be specifically used to store software programs (instructions) and collected user bioelectric signals.
  • the ear side signal measuring unit 1402 is used to collect user bioelectric signals from the ear side.
  • the ear side signal measurement unit 1402 may include a left ear side signal measurement unit and a right ear side signal measurement unit.
  • the ear side signal measurement unit 1402 may only include a unilateral ear side signal measurement unit.
  • the ear signal measuring unit 1402 is usually implemented by hardware.
  • the ear signal measuring unit 1402 may be an electrode, and the ear signal measuring unit 1402 may be one or more.
  • it may further include a feature decomposition unit 1403, configured to perform feature decomposition on the user's bioelectric signal to obtain a biometric signal;
  • the biometric signal includes, an electrocardiographic signal, an eye signal , One or more of EMG signals, and brain electrical signals.
  • the feature decomposition unit 1403 is usually implemented by hardware, such as a feature decomposition circuit and an ICA component.
  • a sensor signal measuring unit 1404 may also be included for collecting sensor signals; the sensor signal measuring unit 1404 may include multiple sensor devices, such as heart rate
  • the sensor specifically can be a PPG sensor, or other sensing devices for measuring heart rate
  • the motion sensor specifically can be an IMU motion sensor, or other sensors for measuring motion Device
  • the sound sensor specifically, a microphone or other sensing device for measuring sound
  • the communication unit 1405 is used to communicate with the ear-worn device and other devices through wireless or wired communication technology, such as cellular mobile communication technology, WLAN, Bluetooth, etc., to collect and process bioelectric signals or biometrics.
  • the signal or biometric signal and sensor signal are sent to the signal analysis device; the signal analysis device may specifically be a sleep detection device in the embodiment of the present application.
  • the acquired bioelectric signals, biometric signals and sensor signals can also be applied to the analysis of other characteristics of the user, such as the recognition of the movement state, attention state, and emotional state, so the signal analysis device can also be Motion state detection device, attention detection device, emotion detection device and other devices that need to obtain information through biometric signal analysis.
  • the ear-side wearing device in the embodiments of the present application may include more or fewer components than those shown in the figure, or a combination of certain components, or different component arrangements.
  • the ear wearing device may further include a speaker, a camera, etc., which will not be repeated here.
  • the processor 1406 can read and analyze the measurement signal stored in the memory 1401 to determine whether the measurement electrode can be measured normally (whether the ear-worn device can be measured normally), and perform user sleep staging based on the measurement signal analysis.
  • the processor 1406 can read and analyze the measurement signal stored in the memory 1401 to determine whether the measurement electrode can be measured normally (whether the ear-worn device can be measured normally), and perform user sleep staging based on the measurement signal analysis.
  • the processor 1406 is configured to determine whether the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold (the specific determination method has been introduced above , Not repeat them here); when the impedance between the left ear side signal measurement unit and the right ear side signal measurement unit is lower than a preset threshold; according to the left ear side signal measurement unit
  • the potential difference signal between the bioelectric signal and the bioelectric signal collected by the right ear side signal measuring unit acquires the user’s bioelectric signal; when it is determined that the ear side wearing device cannot be measured normally (the specific determination method has been described above , I will not repeat them here), respectively determine whether the impedance between two of the multiple left ear signal measurement units is lower than a preset threshold, and whether the impedance between the multiple right ear signal measurement units Whether the impedance between the two is lower than a preset threshold; and obtaining the user's bioelectricity according to the potential difference signal of the bioelectric
  • the processor 1406 is configured to determine whether the impedance between the two unilateral ear signal measurement units is lower than a preset threshold (the specific determination method has been introduced above, and will not be repeated here), When the impedance between the two unilateral ear signal measurement units is lower than the preset threshold, the obtained signal is obtained according to the potential difference signal of the two collected bioelectric signals among the multiple unilateral ear signal measurement units. Describe the user's bioelectric signal.
  • FIG. 14 is only an implementation of the ear-side wearing device of the present application.
  • the processor 1406 and the memory 1401 in the ear-side wearing device may also be integratedly deployed in possible embodiments.
  • FIG. 15 may also be a sleep detection apparatus 1500 according to an embodiment of the present invention, which may include one or more processors 1406 and one or more memories 1401.
  • the sleep detection device 1500 may further include a communication unit 1405 (including a sending unit and a receiving unit).
  • the processor 1506 may be respectively connected to the memory 1401, the communication unit 1505 and other components through a bus. They are described as follows:
  • the processor 1406 is the control center of the sleep detection device, and various interfaces and lines are used to connect various components of the sleep detection device.
  • the processor 1406 may also include one or more processing cores.
  • the processor 1400 may determine the user's sleep staging result by executing program instructions.
  • the processor 1406 may be a dedicated processor or a general-purpose processor, when the processor 1406 is a general-purpose processor, the processor 1406 runs or executes software programs (instructions) and/or modules stored in the memory 1401.
  • the memory 1401 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
  • the memory 1401 may further include a memory controller to provide the processor 1400 and the input unit to access the memory 1401.
  • the memory 1401 may be specifically used to store software programs (instructions) and received sleep detection signals.
  • the communication unit 1505 is used to communicate with the ear wearing device and other devices through wireless or wired communication technology, such as cellular mobile communication technology, WLAN, Bluetooth, etc., for receiving sleep detection signals; sleep detection signals can be
  • the biometric signal may also be a directly collected bioelectric signal.
  • the sleep detection device 1500 may further include a feature decomposition unit for decomposing the bioelectric signal.
  • the sleep detection device in the embodiments of the present application may include more or less components than those shown in the figure, or a combination of certain components, or different component arrangements.
  • the sleep detection device may further include a speaker, a camera, etc., which will not be repeated here.
  • the processor 1506 can analyze the sleep stages of the user by reading, analyzing and judging the sleep detection signal stored in the memory 1501. It includes: being used to obtain the sleep stage classification result of the user according to the biometric signal.
  • FIG. 15 is only an implementation of the sleep detection device of the present application.
  • the processor 1506 and the memory 1501 in the sleep detection device may also be integrated deployment in possible embodiments.
  • the sleep detection device may be a user's terminal equipment such as a mobile phone, or other wearable or portable terminals, or may be set in a server in the cloud.
  • the above embodiments it may be implemented in whole or in part by software, hardware, firmware or any combination.
  • software it can be implemented in the form of a computer program product in whole or in part.
  • the computer program product includes one or more computer instructions, and when the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part.
  • the processor may be a general-purpose processor or a special-purpose processor.
  • the ear wearing device may be one or a computer network composed of multiple ear wearing devices.
  • the computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a network site, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer, and may also be a data storage device such as a server or a data center integrated with one or more available media.
  • the usable medium may be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape, etc.), an optical medium (such as a DVD, etc.), or a semiconductor medium (such as a solid state hard disk), and so on.
  • the execution subject may be ASIC, FPGA, CPU, GPU, etc., which may be implemented by hardware or software, and the memory may be volatile, such as DDR, SRAM, HDD, SSD, etc. Or non-volatile storage devices.
  • the data ear wearing device can be applied to a variety of scenarios, such as a server used in a video surveillance system, and may be in the form of a PCIe expansion card.
  • ASIC and FPGA are hardware implementations, that is, the method of this application is implemented by means of hardware description language during hardware design;
  • CPU and GPU are software implementations, that is, the method of this application is implemented by means of software program codes during software design. .

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Artificial Intelligence (AREA)
  • Psychiatry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physiology (AREA)
  • Signal Processing (AREA)
  • Fuzzy Systems (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Anesthesiology (AREA)
  • Ophthalmology & Optometry (AREA)
  • Cardiology (AREA)
  • Psychology (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

本申请提供了一种用户睡眠分期方法及***，通过耳侧佩戴装置，从用户耳侧获取用户生物电信号；并从用户生物电信号中提取生物特征信号用于对用户的睡眠情况进行综合分析；还可以根据耳侧佩戴装置的阻抗值来判断耳侧佩戴装置是否能够正常工作。通过耳侧佩戴装置来获取，使得信号的采集更加方便易行，通过考虑多种信号能够更加准确的判断是用户的睡眠状态，同时确保了装置的正确佩戴以保证测量信号的准确性。可应用于人工智能领域用于对用户的睡眠情况进行智能监测，以便后续基于监测结果对针对性的去提升用户的睡眠质量。

Description

一种用户睡眠检测方法及*** 技术领域
本申请涉及数据处理领域，尤其涉及对人体的生物电信号的分析和处理，通过生物电信号的分析处理获得用户当前的睡眠分类结果的方法及***。
背景技术
睡眠在人类生活中扮演重要的角色，现代人由于生活压力大，睡眠质量也越来越低。如何精确地检测人的睡眠状态，以及据此来提示人们去关注自身的睡眠状况或是协助人们获得更好质量的睡眠成为关注的重点。
目前检测睡眠状态主要实现方式有：通过手环检测睡眠的特征数据，所采集的数据包括手臂从静止到摆动的次数、手臂处于静止状态的次数、手臂连续活动的时间、各阶段内手臂活动的总时间；通过读取加速度传感器中寄存器中的三轴数据，得到用于识别手臂姿势的判据；通过获取心率值，来进一步判断睡眠的开始和结束。此种方式虽然算法简单，器件成熟，但无法准确区分不同阶段睡眠；或者通过睡眠枕头或者睡眠垫测量心率来进行测量，心率会在特定睡眠阶段过渡时增加或减少，当从觉醒到轻度睡眠过渡时心率减慢，在REM期间稍微增加，然后在深度睡眠期间变得最慢，然而存在缺点是睡眠分期不准，不容易通过分期来做生理反馈从而改善睡眠；此外还有医用的睡眠测量设备，广泛应用于各大医疗院所，但是，因体积较大，人体传感器连接较多，连线复杂等原因只适合在医院病床上使用，使用地点环境受限，舒适度欠佳，无法用于日常睡眠与疲劳监测。
如何更加方便且准确的测量用户生物电信号，如何更加准确的获得用户的睡眠分期结果成为睡眠检测类产品的研究重点。
发明内容
本申请实施例提供了一种睡眠检测方法及***，能够应用于用户睡眠分期的检测，通过耳侧获取生物特征信号，使得生物电信号的获取更加便捷可行，用户可以随时随地的进行睡眠检测，不再受地点的局限，以及需要佩戴复杂的检测设备，降低了测量成本，同时由于在睡眠分类的过程中考虑了多种信号，也确保了睡眠分类结果判断的准确性。
第一方面，本申请实施例提供一种用户睡眠检测方法，所述方法包括：通过耳侧佩戴装置，采集生物电信号；所述用户生物电信号包括从耳侧采集的用户生物电信号；对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果。
具体的，在本申请的可选实现方式中睡眠分类结果可以是用户的睡眠分期分类结果。
上述方法中通过耳侧获取生物电信号，更加方便快捷，耳侧佩戴装置携带方便，设置在耳侧，佩戴过程中不易脱落，使得在睡眠检测过程中测量用户生物电信号更加方便可行。同时在进行睡眠检测的过程中考虑了生物特征信号，使得睡眠检测的结果更加准确可信。
在所述第一方面的某些实现方式下，所述通过耳侧佩戴装置，从用户耳侧获取用户生物电信号具体包括：所述耳侧佩戴装置包括多个耳侧信号测量单元；判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元采集的生物电信号的电位差值信号作为 所述用户生物电信号。
在所述第一方面的某些实现方式下，所述多个耳侧信号测量单元包括左耳耳侧信号测量单元和右耳耳侧信号测量单元；判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第一方面的某些实现方式下，所述通过耳侧佩戴装置，从用户耳侧获取用户生物电信号具体包括：所述耳侧佩戴装置为单侧耳侧佩戴装置，所述多个耳侧信号测量单元为多个单侧耳侧信号测量单元；判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值；将所述多个单侧耳侧信号测量单元中的两个采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第一方面的某些实现方式下，所述左耳耳侧信号测量单元为多个；所述右耳耳侧信号测量单元为多个；当其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值；分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。
通过判断测量单元间的阻抗，能够准确判断耳侧佩戴装置是否能够进行正常测量，排除了耳侧佩戴装置没有正常佩戴而导致耳道不贴合无法进行准确测量的情况。确保用户生物电信号的准确性。
在所述第一方面的某些实现方式下，所述用户生物电信号还包括传感信号；所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种；所述根据所述生物特征信号分析所述用户的睡眠分类结果，包括：根据所述生物特征信号和所述传感信号获得所述用户的睡眠分类结果。
考虑生物特征信号的同时，还辅助考虑其他传感信号，用于睡眠分类的判断，使得睡眠分期的结果是一个综合考量因素，确保睡眠分类结果的准确度。
在所述第一方面的某些实现方式下，所述方法包括：所述根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果，包括：根据所述生物特征信号和SVM模型获得所述用户的睡眠分类结果。
在所述第一方面的某些实现方式下，所述方法包括：所述根据所述生物特征信号和所述传感信号获得所述用户的睡眠分类结果，包括：根据所述生物特征信号和所述传感信号和SVM模型获得所述用户的睡眠分类结果。
在所述第一方面的某些实现方式下，所述方法包括：所述根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果，包括：根据所述生物特征信号和深度神经网络模型获得所述用户的睡眠分类结果。
在所述第一方面的某些实现方式下，所述方法包括：所述根据所述生物特征信号和所述传感信号获得所述用户的睡眠分类结果，包括：根据所述生物特征信号和所述传感信号和深度神经网络模型获得所述用户的睡眠分类结果。
通过机器学习模型来进行睡眠分类的判断，能够更为准确的分析出用户当前的生物特征信号和/或传感信号所对应的睡眠分类。
第二方面，本发明实施例提供一种睡眠检测***，其特征在于，所述***包括：耳侧佩戴装置，用于采集生物电信号；所述用户生物电信号包括从耳侧采集的用户生物电信号；用于对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；睡眠检测装置，用于根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果。
在所述第二方面的某些实现方式下，所述耳侧佩戴装置包括多个耳侧信号测量单元；所述耳侧佩戴装置判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第二方面的某些实现方式下，所述耳侧佩戴装置包括左耳耳侧信号测量单元和右耳耳侧信号测量单元；所述耳侧佩戴装置还用于判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第二方面的某些实现方式下，其特征在于，所述耳侧佩戴装置包括多个单侧耳侧信号测量单元；所述耳侧佩戴装置还用于判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值，将所述多个单侧耳侧信号测量单元中的两个采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第二方面的某些实现方式下，所述左耳耳侧信号测量单元为多个；所述右耳耳侧信号测量单元为多个；所述耳侧佩戴装置还用于当所述第一判断单元判断其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值，分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第二方面的某些实现方式下，所述耳侧佩戴装置还用于采集传感信号；
所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种；
所述睡眠检测装置根据所述生物特征信号分析所述用户的睡眠分类结果，具体为：根据所述生物特征信号和所述传感信号获得所述用户的睡眠分类结果。
在所述第二方面的某些实现方式下，所述睡眠检测装置，具体用于根据所述生物特征信号和SVM模型获得所述用户的睡眠分类结果。
在所述第二方面的某些实现方式下，所述睡眠检测装置，具体用于根据所述生物特征信号和所述传感信号和SVM模型获得所述用户的睡眠分类结果。
在所述第二方面的某些实现方式下，所述睡眠检测装置，具体用于根据所述生物特征信号和深度神经网络模型获得所述用户的睡眠分类结果。
在所述第二方面的某些实现方式下，所述睡眠检测装置，具体用于根据所述生物特征信号和所述传感信号和深度神经网络模型获得所述用户的睡眠分类结果。
第三方面，本发明实施例提供一种耳侧佩戴装置，所述装置包括：耳侧信号测量单元，用于采集生物电信号；所述用户生物电信号包括从耳侧采集的用户生物电信号；特征分解单元，用于对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；睡眠检测单元，用于根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果。
在所述第三方面的某些实现方式下，所述耳侧佩戴装置包括多个耳侧信号测量单元；所述耳侧佩戴装置还包括第一判断单元，用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第三方面的某些实现方式下，所述多个耳侧信号测量单元包括左耳耳侧信号测量单元和右耳耳侧信号测量单元；所述第一判断单元，用于判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第三方面的某些实现方式下，耳侧佩戴装置为单侧耳道测量装置，所述多个耳侧信号测量单元包括多个单侧耳侧信号测量单元；所述第一判断单元，用于判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值，将所述多个单侧耳侧信号测量单元中的两个采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第三方面的某些实现方式下，所述左耳耳侧信号测量单元为多个；所述右耳耳侧信号测量单元为多个；所述耳侧佩戴装置还包括第二判断单元；当所述第一判断单元判断其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值，所述第二判断单元分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第三方面的某些实现方式下，所述耳侧佩戴装置还包括传感信号测量单元，用于采集传感信号；
所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种；所述睡眠检测单元根据所述生物特征信号分析所述用户的睡眠分类结果，具体为：根据所述生物特征信号和所述传感信号获得所述用户的睡眠分类结果。
第四方面，本发明实施例提供一种耳侧佩戴装置，所述装置包括：耳侧信号测量单元，用于采集生物电信号；所述用户生物电信号包括从耳侧采集的用户生物电信号；特 征分解单元，用于对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；发送单元，用于将所述生物特征信号发送给信号分析装置。
在所述第四方面的某些实现方式下，所述耳侧佩戴装置包括多个耳侧信号测量单元；所述耳侧佩戴装置还包括第一判断单元，用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第四方面的某些实现方式下，所述多个耳侧信号测量单元包括左耳耳侧信号测量单元和右耳耳侧信号测量单元；所述第一断单元，用于判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第四方面的某些实现方式下，所述耳侧佩戴装置为单侧耳道测量装置，所述多个耳侧信号测量单元包括多个单侧耳侧信号测量单元；所述第一判断单元，用于判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值，将所述多个单侧耳侧信号测量单元中的两个采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第四方面的某些实现方式下，所述左耳耳侧信号测量单元为多个；所述右耳耳侧信号测量单元为多个；所述耳侧佩戴装置还包括第二判断单元；当所述第一判断单元判断其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值，所述第二判断单元分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第四方面的某些实现方式下，所述耳侧佩戴装置还包括传感信号测量单元，用于采集传感信号；
所述传感信号为为运动传感信号、心率传感信号、声音传感信号中的一种或多种。
第五方面，本发明实施例提供一种睡眠检测装置，所述装置包括：接收单元，用于从耳侧佩戴装置接收生物特征信号；所述生物特征信号包括，心电信号，眼电信号，肌电EMG信号中的一种或多种，以及脑电信号；睡眠检测单元，用于根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果。
在所述第五方面的某些实现方式下，所述接收单元，还用于从耳侧佩戴装置接收传感信号；所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种；所述睡眠检测单元根据所述生物特征信号分析所述用户的睡眠分类结果，具体为：根据所述生物特征信号和所述传感信号获得所述用户的睡眠分类结果。
第六方面，本发明实施例提供一种耳侧佩戴装置，所述装置包括：耳侧信号测量单元，用于采集生物电信号；所述用户生物电信号包括从耳侧采集的用户生物电信号；特 征分解单元，用于对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；处理器，用于根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果。
在所述第六方面的某些实现方式下，所述耳侧佩戴装置包括多个耳侧信号测量单元；所述处理器用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第六方面的某些实现方式下，所述多个耳侧信号测量单元包括左耳耳侧信号测量单元和右耳耳侧信号测量单元；所述处理器用于判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第六方面的某些实现方式下，所述耳侧佩戴装置为单侧耳道测量装置，所述耳侧信号测量单元包括多个单侧耳侧信号测量单元；所述处理器还用于判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值，将所述多个单侧耳侧信号测量单元中的两个采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第六方面的某些实现方式下，所述左耳耳侧信号测量单元为多个；所述右耳耳侧信号测量单元为多个；所述处理器还用于，当所述第一判断单元判断其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值，分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第六方面的某些实现方式下，所述耳侧佩戴装置还包括传感信号测量单元，用于采集传感信号；
所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种；所述睡眠检测单元根据所述生物特征信号分析所述用户的睡眠分类结果，具体为：根据所述生物特征信号和所述传感信号获得所述用户的睡眠分类结果。
第七方面，本发明实施例提供一种耳侧佩戴装置，所述装置包括：耳侧信号测量单元，用于采集生物电信号；所述用户生物电信号包括从耳侧采集的用户生物电信号；特征分解单元，用于对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；发送单元，用于将所述生物特征信号发送给用户生物电信号分析装置。
在所述第七方面的某些实现方式下，所述耳侧佩戴装置包括多个耳侧信号测量单元；所述处理器用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元采集的 生物电信号的电位差值信号作为所述用户生物电信号。
在所述第七方面的某些实现方式下，所述多个耳侧信号测量单元包括左耳耳侧信号测量单元和右耳耳侧信号测量单元；所述耳侧佩戴装置还包括处理器，用于判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第七方面的某些实现方式下，所述耳侧佩戴装置为单侧耳道测量装置，所述耳侧信号测量单元包括多个单侧耳侧信号测量单元；所述耳侧佩戴装置还包括处理器，用于判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值，将所述多个单侧耳侧信号测量单元中的两个采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第七方面的某些实现方式下，所述左耳耳侧信号测量单元为多个；所述右耳耳侧信号测量单元为多个；所述耳侧佩戴装置还包括处理器；当所述第一判断单元判断其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值，所述处理器分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第七方面的某些实现方式下，所述耳侧佩戴装置还包括传感信号测量单元，还用于采集传感信号；
所述传感信号为为运动传感信号、心率传感信号、声音传感信号中的一种或多种。
第八方面，本发明实施例提供一种睡眠检测装置，所述装置包括：接收单元，用于从耳侧佩戴装置接收生物特征信号；所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；处理器，用于根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果。
在所述第八方面的某些实现方式下，所述接收单元，还用于从耳侧佩戴装置接收传感信号；所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种；所述处理器根据所述生物特征信号分析所述用户的睡眠分类结果，具体为：根据所述生物特征信号和所述传感信号获得所述用户的睡眠分类结果。
第九方面，本发明实施例提供一种生物电信号检测方法，包括：耳侧佩戴装置包括多个耳侧信号测量单元，用于从耳侧采集的用户生物电信号；对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；将所述生物特征信号发送给信号分析装置。
所述从耳侧采集的用户生物电信号，具体包括：判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元测量的生物电信号采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第九方面的某些实现方式下，所述多个耳侧信号测量单元包括左耳耳侧信号 测量单元和右耳耳侧信号测量单元；所述判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值，当所述两个耳侧信号测量单元之间的阻抗低于预设阈值，将所述两个耳侧信号测量单元测量的生物电信号采集的生物电信号的电位差值信号作为所述用户生物电信号，具体为：判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第九方面的某些实现方式下，所述耳侧佩戴装置为单侧耳侧佩戴装置；所述多个耳侧信号测量单元包括多个单侧耳侧信号测量单元；
所述判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值，将所述两个耳侧信号测量单元测量的生物电信号采集的生物电信号的电位差值信号作为所述用户生物电信号，具体为：
判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值，将所述两个单侧耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第九方面的某些实现方式下，所述左耳耳侧信号测量单元为多个；所述右耳耳侧信号测量单元为多个；当判断其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值，分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。
在所述第九方面的某些实现方式下，所述耳侧佩戴装置还采集传感信号；所述传感信号为为运动传感信号、心率传感信号、声音传感信号中的一种或多种；将所述传感信号发送给信号分析装置。
第十方面，本发明实施例提供一种睡眠检测方法，包括：
从耳侧佩戴装置接收生物特征信号；所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果。
在所述第十方面的某些实现方式下，方法还包括，从耳侧佩戴装置接收传感信号；所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种；根据所述生物特征信号分析所述用户的睡眠分类结果，具体为：根据所述生物特征信号和所述传感信号获得所述用户的睡眠分类结果。
在所述第十方面的某些实现方式下，方法包括，根据所述生物特征信号和SVM模型获得所述用户的睡眠分类结果。
在所述第十方面的某些实现方式下，方法包括，根据所述生物特征信号和所述传感信号和SVM模型获得所述用户的睡眠分类结果。
在所述第十方面的某些实现方式下，方法包括，根据所述生物特征信号和深度神经网络模型获得所述用户的睡眠分类结果。
在所述第十方面的某些实现方式下，方法包括，根据所述生物特征信号和所述传感 信号和深度神经网络模型获得所述用户的睡眠分类结果。
在以上方面的某些实现方式下，所述用户的睡眠分类结果具体可以是用户的睡眠分期结果，或者是用户当前是否处于睡眠状态的判断结果。
在以上方面的某些实现方式下，所述多个耳侧信号测量单元中的多个为两个或者两个以上。
在以上方面的某些实现方式下，所述生物特征信号可以是包括，心电信号，眼电信号，肌电EMG信号中的一种或多种，以及脑电信号的多种生物特征信号。
在以上方面的某些实现方式下，所述判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值，可以是基于预先的设定来从多个耳侧信号测量单元中选取两个，也可以是基于优先级的设定顺序选取两个耳侧信号测量单元进行比较，在阻抗一直低于预设阈值的情况下，可以比较预设次数终止比较，或者遍历所有情况之后终止比较。
在以上方面的某些实现方式下，所述判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值，可以是左耳耳侧信号测量单元和右耳耳侧信号测量单元均为一个，直接进行比较；也可以左耳耳侧信号测量单元和右耳耳侧信号测量单元均为多个，基于预先的设定来从多个左耳耳侧信号测量单元和多个右耳耳侧信号测量单元中分别选取两个，也可以是基于优先级的设定顺序选取两个耳侧信号测量单元进行比较，在阻抗一直低于预设阈值的情况下，可以比较预设次数终止比较，或者遍历所有情况之后终止比较。
在以上方面的某些实现方式下，所述判断所述多个单侧耳侧信号测量单元之间的阻抗是否低于预设阈值，可以是单侧耳侧信号测量单元为两个，直接进行比较；也可以是基于预先的设定来从多个单侧耳侧信号测量单元中选取两个，也可以是基于优先级的设定顺序选取两个耳侧信号测量单元进行比较，在阻抗一直低于预设阈值的情况下，可以比较预设次数终止比较，或者遍历所有情况之后终止比较。
在以上方面的某些实现方式下，当判断其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值，分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，可以是左、右耳耳侧信号测量单元分别为两个，直接进行比较；也可以是基于预先的设定来分别从多个左、右耳耳侧信号测量单元中选取两个；也可以是对于左耳耳侧信号测量单元，基于优先级的设定顺序选取两个左耳耳侧信号测量单元进行比较，在阻抗一直低于预设阈值的情况下，可以比较预设次数终止比较，或者遍历所有情况之后终止比较；对于右耳耳侧信号测量单元，基于优先级的设定顺序选取两个右耳耳侧信号测量单元进行比较，在阻抗一直低于预设阈值的情况下，可以比较预设次数终止比较，或者遍历所有情况之后终止比较。
可以看到，实施本申请实施例的技术方案，能够解决当前技术产品形态复杂不便携，用户生物电信号单一，且在未能正确佩戴的情况下无法及时察觉，或者即时适配新的测量方案的情况，通过耳部采集多类生物特征信号，使得用户生物电信号的采集更加便捷可行，同时通过测量单元间阻抗值来判断耳侧佩戴装置的佩戴状态，并通过机器学习的方法，对睡眠分期阶段进行判定，可以相对准确地判断出用户当下的睡眠状态，便于更准确方便的评估用户的睡眠质量。
附图说明
为了更清楚地说明本申请实施例或背景技术中的技术方案，下面将对本申请实施例或背景技术中所需要使用的附图进行说明。
图1示出了本申请实施例中的一种应用场景示意图；
图2示出了R&K睡眠分期标准中的睡眠分期结构图；
图3示出了人在清醒、轻度睡眠、快速眼动期和慢波睡眠不同阶段下的脑电波图；
图4示出了按照R&K睡眠分期标准中普通人在睡眠过程中的睡眠周期分布情况图；
图5a示出了本发明实施例的一种典型的应用场景；
图5b示出了本发明实施例的一种佩戴方式；
图6示出了本发明实施例的一种用户睡眠检测方法流程图；
图7示出了本申请实施例提供的一种从耳侧采集生物电信号的采集方式流程图；
图8示出了本申请实施例提供的一种从耳侧采集生物电信号的采集方式流程图；
图9对应于本申请实施例的一种睡眠检测***；
图9a对应于本申请实施例的又一种睡眠检测***；
图9b对应于本申请实施例的又一种睡眠检测***；
图10a示出了本申请实施例的一种耳侧佩戴装置为单侧测量时的结构图；
图10b示出了本申请实施例的一种耳侧佩戴装置为双侧测量时的结构图；
图10c示出了本申请实施例的一种耳侧佩戴装置的结构图；
图11示出了本申请实施例的一种集成了睡眠检测功能的耳侧佩戴装置的结构图；
图12示出了本申请实施例的另一种耳侧佩戴装置的结构图；
图13示出了本申请实施例的一种睡眠检测装置的结构示意图；
图14示出了本申请实施例的另一种耳侧佩戴装置的结构图；
图15示出了本申请实施例的另一种耳侧佩戴装置的结构图；
图16示出了本申请实施例提供的一种测量用户相关信号的方法的流程图；
图17示出了本申请实施例提供的一种睡眠检测方法的流程图。
具体实施方式
下面结合本申请实施例中的附图对本申请的具体实现方式进行举例描述。然而本申请的实现方式还可以包括在不脱离本申请的精神或范围的前提下将这些实施例组合，比如采用其它实施例和做出结构性改变。因此以下实施例的详细描述不应从限制性的意义上去理解。本申请的实施例部分使用的术语仅用于对本申请的具体实施例进行解释，而非旨在限定本申请。
本申请的具体实施例中所提到的功能、模块、特征、单元等的一个或多个结构组成可以理解为由任何物理的或有形的组件(例如，由在计算机设备上运行的软件、硬件(例如，处理器或芯片实现的逻辑功能)等、和/或其它任何组合)以任何方式来实现。在某些实施例中，所示出的将附图中的将各种设备分成不同的模块或单元可以反映在实际实现中使用对应的不同的物理和有形的组件。可选的，本申请实施例附图中的单个模块也可以由多个实际物理组件来实现。同样，在附图中描绘的任何两个或更多个模块也可以反映由单个实际物理组件所执行的不同的功能。
关于本申请实施例的方法流程图，将某些操作描述为以一定顺序执行的不同的步骤。这样的流程图属于说明性的而非限制性的。可以将在本文中所描述的某些步骤分组在一起并且在单个操作中执行、可以将某些步骤分割成多个子步骤、并且可以以不同于在本文中所示出的顺序来执行某些步骤。可以由任何电路结构和/或有形机制(例如，由在计算机设备上运行的软件、硬件(例如，处理器或芯片实现的逻辑功能)等、和/或其任何组合)以任何方式来实现在流程图中所示出的各个步骤。
以下的说明可以将一个或多个特征标识为“可选的”。该类型的声明不应当被解释为对可以被认为是可选的特征的详尽的指示；即，尽管没有在文本中明确地标识，但其他特征可以被认为是可选的。此外，对单个实体的任何描述不旨在排除对多个这样的实体的使用；类似地，对多个实体的描述不旨在排除对单个实体的使用。最后，术语“示例性的”是指在潜在的许多实现中的一个实现。
本申请实施例主要用于用户睡眠分期的监测，通过分析用户生物电信号特征判断用户的睡眠分类结果，从而能够根据判断用户当前的睡眠情况，以及用户整体的睡眠质量。
生物电信号可以从人体皮肤表层进行获取，比较常见的生物电信号有脑电EEG信号，心电ECG，眼电EOG和肌电EMG信号等。除此之外，和用户当前状态相关性较高的特征信号还有运动信号，心率信号，声音信号等。现有技术中进行睡眠分类通常考虑较多的是脑电信号，以及运动信号。在本申请中会结合上述多类用户特征信号来进行用户睡眠状态的分析，以便综合多类信息，综合考量用户的睡眠状态。下面具体就脑电信号和用户睡眠的关系进行示例说明。
脑电EEG信号是大脑活动的外在体现，不同的大脑活动表现为具有不同特征的脑电信号。研究表明，对这些脑电模式进行时空频域分析，有助于逆向分析人的意图活动，这为脑电信号的应用提供了理论基础。
头皮脑电信号是一种生物电信号，大脑860亿个神经元电位变化形成的电场，经由皮层、颅骨、脑膜及头皮构成的容积导体传导后，在头皮上产生一个电位分布。利用特定的设备记录这些变化的电位分布就可以获得脑电信号。
脑电信号又可以分为自发脑电和诱发脑电(Evoked Potential，EP)两种。自发脑电是在没有特定外界刺激时大脑中的神经细胞自发产生的电位变化。而诱发脑电是大脑中的神经细胞受声、光、电等不同类型刺激所引起的脑电位变化。本发明是实力所涉及检测睡眠状态可以是通过检测人的自发脑电信号进行分析来实现。图1为自发脑电信号根据频率范围不同划分出不同种类，以及对应的产生状态。
从清醒到睡眠，并不是两个状态的瞬间变换，而需要经历一个短暂的过渡阶段。而在睡眠阶段，睡眠状态也不是平稳不变的，而是由多个不同睡眠阶段在周而复始地交替进行。基于脑电信号的睡眠分期就是将睡眠的几个不同阶段分开，确定出每个阶段所占用的时间长度，从而分析出睡眠质量的变化。
1968年,Rechtschaffen和Kales制定《人类睡眠阶段标准化术语、技术及划分***手册》，简称R&K标准，成为睡眠分期工作的标准。在该标准下，睡眠分觉醒期(Wakefulness，W)、非快速眼动睡眠(Non-rapid Eye Movement sleep,NREM)和快速眼动睡眠(Rapid Eye Movement Sleep,REM)。非快速眼动睡眠又分为四个时期：一期、二期、三期和四期(N1，N2，N3，N4期)。
在一次完整睡眠中，睡眠的不同阶段具有不同的振幅和频率特性，这成为睡眠研究 的重要依据。为了更加具体地描述不同阶段的差别，下面将详细介绍睡眠这6个不同阶段的EEG信[发明人补充点1：各类信号和睡眠分期之间的关系。本申请中所涉及的信号都需要涉及。]号的特点：
(1)清醒时期(Wakefulness)：人在大部分情况下都处在清醒时期，处于不断感知外部刺激并作出反应的状态。视觉刺激，听觉刺激，思维活动和心理活动最活跃，大脑活动最复杂。与睡眠时期的脑电信号相比，清醒状态下的脑电信号的特点是低幅高频，振幅通常小于50μV，频率范围为1.5-50Hz。从采集到的脑电信号中可以观察到强烈的眼电信号，这对脑电信号处理造成了很大的影响。所以在脑电信号处理上，清醒时期所采集的脑电信号通常需要去伪迹减少眼电干扰。
(2)NREM睡眠I期(N1)：在N1期，人的身体活动开始减少，头脑开始茫茫然，意识逐渐模糊。经历几分钟的睡眠前期，大脑状态逐渐稳定下来，整个时期的时间大约为1-10min。在这个时期醒来人容易被唤醒，醒过来的人通常否认睡眠。从生理指标生看，肌电水平明显降低，心率明显变慢，血压和体温较清醒状态也轻度下降，呼吸逐渐规则。脑电信号是一种低压混合波，主要频率为4-8Hz，振幅为50-100μV之间，也可能出现尖峰信号，但是不会出现纺锤波和K复合波。
(3)NREM睡眠II期(N2)：一般认为，真正的睡眠是从N2期开始的，持续10-20min。N1和N2期都属于浅睡时期，有可能被唤醒，也有可能自己惊醒。在N2阶段，大脑出现了纺锤波和K复合波，主要频率为4-15Hz，振幅为50-150μV，稍大于睡眠I期。纺锤波或K复合波出现的周期一般低于3分钟，否则视为还未进入睡眠II期。
(4)NREM睡眠III期(N3)：该时期的出现标志着人开始进入深度睡眠，意识消失，难以唤醒。从脑信号来看，以慢波为主，频率为2-4Hz，振幅为100-150μV，纺锤波和K复合波也可能在此时期出现。
(5)NREM睡眠IV期(N4)：N4睡眠较深，觉醒非常困难，脑信号特征和睡眠III期类似，但是低于2Hz的成分明显增多，主要为0.5-2Hz，振幅在100-200μV之间。
(6)REM睡眠期：该时期可以发现眼球的快速运动，身体不会移动，大部分梦也在这个时期发生。REM睡眠一般为90-120分钟，NREM睡眠一般为4-7小时。REM睡眠持续时间较短，但却在人的记忆功能方面有重要作用。从脑信号来看，该阶段主要是一种混合频率低压快波，频率为15-30Hz,振幅通常小于50μV。
2007年，美国睡眠医学会综合了R&K标准，并提出了修正版本，得到了欧美大部分睡眠中心的支持，我国也已经采用了该标准。在修正的R&K睡眠分期标准中，N1和N2被合并成浅度睡眠(Light Sleep，LS)，N3和N4被合并成慢波睡眠(Slow Wave Sleep，WS)，新的睡眠分期结构图如图2所示。图3为人在清醒、轻度睡眠、快速眼动期和慢波睡眠不同阶段下的脑电波，图4为按照上述睡眠分期标准，普通人在睡眠过程中的睡眠周期分布情况。
除了脑电信号外，其他用户特征信号也能用于判断用户的睡眠状态，如是否睡眠，或者进一步的判断用户的睡眠分期结果。
图5a为本发明实施例的一种典型的应用场景，耳侧佩戴装置101贴近用户耳侧，从耳侧采集生物电信号，并将用户生物电信号发送给用户睡眠监测装置102，其中耳侧佩戴装置101具体操作可选的还可以包括左耳耳侧信号测量单元101a和右耳耳侧信号测量 单元101b，也可以只包括单侧耳侧信号测量单元。耳侧佩戴装置101采集到用户生物电信号后将用户生物电信号发送给睡眠检测设备102用于对用户的睡眠分类结果进行判断。其中从耳道采集到测量信号之后，还需要对测量信号进行相应的处理，相关处理可以包括，电位差值处理，用于排除外界杂扰信号干扰，增强信号；常规的去躁处理，以及对所采集的用户生物电信号进行特征提取，从测量信号中获取多种生物电信号，如脑电信号，眼电信号，心电信号，肌电信号中的一种或多种。由于脑电信号在进行睡眠分期分析的过程中比较重要，通常其中一种优选的提取方式为眼电信号，心电信号，肌电信号中的一种或多种以及脑电信号。耳侧佩戴装置101具体的形态可以是耳机或者耳塞。用户睡眠监测装置102(具体可以为手持终端，如手机，PDA，pad等，或者也可以是耳侧佩戴装置101的一部分，集成于耳侧佩戴装置中，或者将睡眠分类功能集成在云端服务器)对用户脑电信号进行分析。
本申请实施例中，分析获得的用户睡眠情况还可以用于后续的睡眠改善处理，如当判断用户睡眠质量不好时，提醒用户注意休息，增加运动量，或者通过在耳侧佩戴装置中播放助眠音乐来帮助改善用户睡眠。所述用于睡眠调节或提醒的模块可以设置于***的任意位置，如耳侧佩戴装置101中或睡眠检测装置102中。
本发明实施例中的耳侧指的是人体耳朵上以及耳朵附近可以测量得到生物电信号的区域，如耳道内侧，耳廓，耳沟，耳背，以及耳周等位置。通过将耳侧信号测量单元部署在人耳区域上，以及人耳附近来采集生物电信号。
图5b是本发明实施例的一种示例性的耳侧佩戴装置的佩戴即信号采集方式，示例性的给出了一种从耳道内侧获取生物电信号的信号采集方式。其中401为人体耳道，403为耳侧信号测量单元，402为耳侧佩戴装置的主体，404为用户的耳廓。
图6是本发明实施例的一种用户睡眠检测方法，具体包括以下步骤：
S601：通过耳侧佩戴装置从耳侧采集生物电信号；
具体包括，耳侧佩戴装置可以包括耳侧信号测量单元，用于配戴在耳侧，佩戴时贴合耳侧皮肤，以便采集生物电信号。其中耳侧佩戴装置根据采集需要可以是单侧也可以是双侧，单侧耳侧信号测量单元，用于从左耳道或者右耳道获取用户生物电信号，双侧则可以具体划分为左耳耳侧信号测量单元和右耳耳侧信号测量单元，用于分别从左右耳道获取用户生物电信号。需要从耳侧测量获取的用户生物电信号可以为用户生物电信号。通常的获取方式为通过柔性电极贴近耳侧皮肤测量获取，测量得到的通常为混合信号，需要经过后续的分解处理来获得一种或生物特征信号。可选的，耳侧佩戴装置可以通过开关控制来控制其是否开始信号采集工作，具体的操作方式可以包括摁下耳机实体按钮，或者触摸相应APP上的开始工作的虚拟按钮，或者也可以不通过开关控制电源有电的情况下始终处于工作状态。
由于耳侧佩戴装置在配戴过程中可能会出现，脱落，或者没有正确配戴的问题，因此直接获取耳侧佩戴装置采集的信号进行处理，可能会存在因为设备脱落，或者没有正确配戴而导致测量结果不准确，从而不能正确分析出用户的睡眠分类结果的问题，因此本申请的实施例会对耳侧佩戴装置的配戴情况进行判断，根据判断结果决定是否采集数据，或者是否将采集的数据用于进行用户睡眠分类的分析。
具体包括所述耳侧佩戴装置包括多个耳侧信号测量单元；判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预 设阈值；将所述两个耳侧信号测量单元测量的生物电信号的电位差值信号作为所述用户生物电信号。
对应于耳侧佩戴装置为双侧耳道测量，即耳侧佩戴装置包括左耳耳侧信号测量单元和右耳耳侧信号测量单元，从耳侧采集生物电信号的采集方式还可以进一步如图7所示，包括：
S60101：通过判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值，来判断耳侧佩戴装置是否可以正常进行测量。
判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值，以此来判断耳侧佩戴装置是否可以正常进行测量(即正常配戴)。
具体的，左耳耳侧信号测量单元和右耳耳侧信号测量单元可以为一个也可以为多个，左/右耳耳侧信号测量单元的在实现的过程中其形态可以是电极，通过电极来测量耳侧的用户生物电信号。通过判断左右耳耳侧信号测量单元之间的阻抗值来判断耳侧佩戴装置的左耳耳侧信号测量单元和所述右耳耳侧信号测量单元是否贴合耳道，即耳侧佩戴装置是否配戴正确。当左右耳耳侧信号测量单元贴合耳道时，左右耳耳侧信号测量单元之间的阻抗值较低，通常是低于耳侧表面阻抗值，当左右耳耳侧信号测量单元有一侧或者两侧均不贴合耳道时，左右耳耳侧信号测量单元之间的阻抗值较高，通常是高于耳侧表面阻抗值。因此可以设置一个预设阈值用于判断耳侧佩戴装置的配戴情况，可选的，阻抗预设的判断阈值可以是耳侧表面的阻抗值。
当左耳耳侧信号测量单元和右耳耳侧信号测量单元为一个时，直接获取两个测量单元之间的阻抗值进行判断。
当左耳耳侧信号测量单元和右耳耳侧信号测量单元为多个时，可以有多种测量策略。如任意选择一个左耳耳侧信号测量单元和一个右耳耳侧信号测量单元进行阻抗值的获取，也可以是获取预设位置的左耳耳侧信号测量单元和获取预设位置的右耳耳侧信号测量单元之间的阻抗值，只获取一次阻抗值，根据获取的阻抗值判断左右耳配戴是否正常。或者也可以是设置优先级顺序来进行逐个匹配的测量，在不满足预设阈值的情况下测量预设数量次后终止测量和判断，或者逐个进行测量直到测量到低于预设值的阻抗，则说明耳侧佩戴装置可以正常测量，否则说明无法正常工作。在此对多测量单元情况下具体的测量方法不做限定。
S60102：当判断耳侧佩戴装置可以正常进行测量，根据所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号获取所述用户生物电信号。
即当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值，根据所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号获取所述用户生物电信号。
具体为，当耳侧信号测量单元为左右各一个的情况下，当测量到左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值则判断耳侧佩戴装置可以正常进行测量；根据所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号获取所述用户生物电信号。
其中根据所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号获取所述用户生物电信号具体方式可以包括，直接 将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号获取所述用户生物电信号；耳侧佩戴装置上还可以设置参考电极，分别获取所述左耳耳侧信号测量单元采集的生物电信号和参考电极的第一电位差信号，以及所述右耳耳侧信号测量单元采集的生物电信号和参考电极的第二电位差信号，然后获取第一电位差信号和第二电位差信号的差值信号。
在耳侧信号测量单元为多个且测量次数可以为多次的情况下，当测量到左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值则判断所测量的两个测量单元对应的耳道均可以正常进行测量。将测量后判定为可以正常进行测量的所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
在耳侧信号测量单元为多个且测量次数为一次的情况下，当测量左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值则判断所测量的两个测量单元对应的耳道均可以正常进行测量。将测量后判定为可以正常进行测量的所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号，或者也可以基于测量结果认为耳侧佩戴装置为可以正常进行测量，则选择任意的左侧耳侧信号测量单元和右侧耳侧信号测量单元，或者预先指定的左侧耳侧信号测量单元和右侧耳侧信号测量单元来获取采集的生物电信号的电位差值信号作为所述用户生物电信号。
进一步当判断耳侧佩戴装置无法正常进行测量时，可以选择不再进行采集信号和睡眠分类的分析步骤。
可选的，也可以当判断耳侧佩戴装置没有正常配戴时，进一步分别判断左侧或者右侧有没有正常配戴，由此可选的，可以包括步骤S50103。
S60103：当判断结果为耳侧佩戴装置无法正常进行测量，分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值。将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。
在此步骤下，左耳耳侧信号测量单元和右耳耳侧信号测量单元需要为多个。
在耳侧信号测量单元为多个且测量次数可以为多次的情况下，当多次测量左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗均高于预设阈值则判断所测量的两个测量单元对应的耳道至少有一个无法进行正常测量。
在耳侧信号测量单元为多个且测量次数为一次的情况下，当测量左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗高于预设阈值则判断所测量的两个测量单元对应的耳道至少有一个无法正常进行测量。即当其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值，则判断所测量的两个测量单元对应的耳道至少有一个无法正常进行测量。
判断为所测量的两个测量单元对应的耳道至少有一个无法正常进行测量后，分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值。同样可以有多种测量策略。如任意选择两个左/右耳耳侧信号测量单元进行阻抗值的获取，也可以是获取预设位置的两个左/右耳耳侧信号测量单元之间的阻抗值，只获取一次阻抗值，根据获取的阻 抗值判断左右耳配戴是否正常。或者也可以是设置优先级顺序来进行两个左/右耳耳侧信号测量单元之间的测量，在不满足预设阈值的情况下测量预设数量次后终止测量和判断，或者逐对进行测量直到测量到低于预设值的阻抗，则说明耳侧佩戴装置可以正常测量，否则当遍历所有情况均无测量到低于预设值的阻抗说明无法正常测量。在此同样本申请对单侧多测量单元情况下具体的测量方法不做限定。
将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号：
可以是将测量后判定为可以正常进行测量的所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
其中将测量后判定为可以正常进行测量的所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号具体方式可以包括，直接将两个可以正常测量一侧的耳侧信号测量单元采集的生物电信号的电位差值信号获取所述用户生物电信号；耳侧佩戴装置上还可以设置参考电极，分别获取所述一个耳侧信号测量单元采集的生物电信号和参考电极的第三电位差信号，以及另一个耳侧信号测量单元采集的生物电信号和参考电极的第四电位差信号，然后获取第三电位差信号和第四电位差信号的差值信号。
其中耳侧信号测量单元的选取可以有多种发送，如直接选取进行阻抗值判断的两个测量单元来获取电位差值信号，也可以是按照预先设置来选择测量单元，或者是任意选取。
本申请中获取电位差值信号的方式具体可以是通过软件指令来实现，也可以是通过硬件电路来实现。
对应于耳侧佩戴装置为单侧测量，即耳侧佩戴装置仅包括左耳耳侧信号测量单元或右耳耳侧信号测量单元，在此实施方式下，左耳耳侧信号测量单元或右耳耳侧信号测量单元需要为多个，即单侧耳侧信号测量单元为多个。从耳侧采集生物电信号的采集方式还可以如图8所示，进一步包括：
S60111：通过判断所述单侧耳侧信号测量单元中的两个信号测量单元之间的阻抗是否低于预设阈值，来判断耳侧佩戴装置是否可以正常进行测量。
判断所述单侧耳侧信号测量单元中的两个信号测量单元之间的阻抗是否低于预设阈值，以此来判断耳侧佩戴装置是否可以正常进行测量(即正常配戴)。
具体的，可以有多种测量策略，如任意选择两个单侧耳侧信号测量单元进行阻抗值的获取，也可以是获取预设位置的两个单侧耳侧信号测量单元之间的阻抗值，只获取一次阻抗值，根据获取的阻抗值判断单侧耳道配戴是否正常。即判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值；低于阈值则判断为配戴正常。
或者也可以是设置优先级顺序来进行两个单侧耳侧信号测量单元之间的测量，在不满足预设阈值的情况下测量预设数量次后终止测量和判断，或者逐对进行测量直到测量到低于预设值的阻抗，则说明耳侧佩戴装置可以正常测量，否则当遍历所有情况均无测量到低于预设值的阻抗说明无法正常测量。在此本申请同样对单侧多测量单元情况下具体的测量方法不做限定。
S60112：当判断耳侧佩戴装置可以正常进行测量，将所述多个单侧耳侧信号测量单元中的两个采集的生物电信号的电位差值信号作为所述用户生物电信号。
在单个耳侧信号测量单元为多个且测量次数可以为多次的情况下，当测量到两个单侧耳侧信号测量单元之间的阻抗低于预设阈值则判断耳侧佩戴装置可以正常进行测量。将测量后判定为可以正常进行测量的两个单侧耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
其中将测量后判定为可以正常进行测量的两个单侧耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号具体方式可以包括，直接将两个可以正常测量耳侧信号测量单元采集的生物电信号的电位差值信号获取所述用户生物电信号；耳侧佩戴装置上还可以设置参考电极，分别获取所述一个耳侧信号测量单元采集的生物电信号和参考电极的第五电位差信号，以及另一个耳侧信号测量单元采集的生物电信号和参考电极的第六电位差信号，然后获取第五电位差信号和第六电位差信号的差值信号。
在单侧耳侧信号测量单元为多个且测量次数为一次的情况下，当测量到单侧耳侧信号测量单元之间的阻抗低于预设阈值则判断所测量的两个测量单元对应的耳道均可以正常进行测量。将测量后判定为可以正常进行测量的两个单侧耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号，或者也可以基于测量结果认为耳侧佩戴装置为可以正常进行测量，则选择任意的两个单侧耳道测量单元，或者预先指定的两个单侧耳道测量单元来获取采集的生物电信号的电位差值信号作为所述用户生物电信号。
除了耳侧信号测量单元，耳侧佩戴装置还可以包括传感器单元，例如心率传感器(具体可以是PPG传感器，也可以是其它用于测量心率的传感装置)用于测量获取心率信号，运动传感器(具体可以是IMU运动传感器，也可以是其它的用于测量运动的传感装置)用于测量感知用户活动情况，声音传感器(具体可以是麦克风，也可以是其它的用于测量声音的传感装置)用于检测用户发出的声音。
所述生物电信号可以是用户生物特征信号的混合信号，用于后期进行生物特征信号的提取，传感信号根据具体实现过程中传感器的部署，可以为运动传感信号、心率传感信号、声音传感信号中的一种或多种。
S602：对所述用户生物电信号进行特征分解，获得生物特征信号；
所述生物特征信号包括，心电ECG信号，眼电EOG信号，肌电EMG信号以及脑电EEG信号中的一种或多种。进行特征分解来提取不同类的生物特征信号的方法有多种，可以根据不同类信号存在的频谱不同而进行提取，较为常用的是利用盲信源分离算法独立成分分析(ICA)分解得到多个生物特征信号的成分：这些成分可能分别对应脑电EEG信号，心电ECG，眼电EOG和肌电EMG信号等，并提取信号特征。
S603：根据所述生物特征信号获得所述用户的睡眠分类结果。
本发明实施例中的睡眠分类结果的分析可以通过机器学习的方式来实现。机器学习的模型可以有多种，例如可以通过SVM模型来进行分析，也可以是通过深度神经网络模型来进行分析。
根据SVM模型来进行分析：根据生物特征信号采样和SVM模型来获得生物特征信号 采样对应的睡眠时段的睡眠分类概率，以此来判断对应的睡眠时段的睡眠分类。
根据深度神经网络模型来进行分析，本实施例具体为CNN卷积神经网络模型，分析方式为根据生物特征信号的采样和CNN模型来获得对应的睡眠时段的睡眠所属分期的概率，以此来判断对应的睡眠时段的睡眠分类。
根据实施方式的不同，当耳侧佩戴装置还包括传感器单元时，根据所述生物特征信号获得所述用户的睡眠分类结果，具体包括，根据所述生物特征信号和传感信号获得所述用户的睡眠情况，具体的可以是获得用户当前的睡眠分期分类结果，或者是获取用户整个睡眠阶段的睡眠分期组成，可以是全阶段的分析，或者是间隔采样不同睡眠时段来进行分析。
根据SVM模型来进行分析：根据生物特征信号和传感信号的采样和SVM模型来获得对应的睡眠时段的睡眠所属分期的概率，以此来判断对应的睡眠时段的睡眠分期。
根据深度神经网络模型来进行分析，本实施例具体为CNN卷积神经网络模型，分析方式为根据生物特征信号和传感信号的采样和CNN模型来获得信号对应的睡眠时段的睡眠所属分类的概率，以此来判断对应的睡眠时段的睡眠分类。
其中本发明实施例在采用机器学习模型来进行睡眠分类结果的分析时，也可以不进行S502步骤，即不进行生物特征信号的提取，直接用用户生物电信号进行模型的训练，然后在分析过程中，直接使用检测到的用户生物电信号的采样作为输入，来获取相应的睡眠分类概率。
本发明实施例中的睡眠分类结果，可以输出的是所分析的信号对应的睡眠分期的概率，或者是用户是否在睡眠状态的概率，或者是直接的基于概率的判断结果。
其中在本发明实施例的判断过程中提到大于预设阈值，根据具体实现时的需要也可以是大于等于预设阈值，同样小于预设阈值，根据具体实现时的需要也可以是小于等于预设阈值。
此外，本申请实施例中用于进行特征分解的生物电信号还可以是经过二次处理后的生物电信号，如进行缓冲放大、滤波、二级放大，A/D转换等常规处理后的生物电信号。或是其他的去噪、放大，数模转换处理后的信号。同样后续用于进行睡眠分类的传感信号也是如此。此外还可以是进一步提取特征信息后的信号，如可以直接基于心电信号提取心率信号用于后续的睡眠分类分析。
在此以SVM模型和CNN模型为例，来示例性的说明如何进行睡眠分类结果的获取。SVM(Support Vector Machine)支持向量机，是在分类与回归分析中分析数据的监督式学习模型与相关的学习算法。CNN(Convolutional Neural Network,卷积神经网路)是一种前馈神经网络，它的人工神经元可以响应一部分覆盖范围内的周围单元，对于大型图像处理有出色表现。
本申请的睡眠检测方法涉及机器学习相关的人工智能方法，一般人工智能方法通常涉及模型训练和实时算法识别。
第一部分：模型训练
本发明涉及生物电信号和传感信号两部分，因此在模型训练阶段同样也需要获取这两类信号来进行特征提取和模型训练，目的在于利用已知目标数据样本来训练模型，得到损失最小情况下的模型参数。
SVM模型方案：
SVM模型训练由以下部分组成：信号采集、信号预处理、特征提取与选择、模式分类和结果输出。其中，特征提取与选择和模式分类是最关键的两个步骤。
以生物电信号为例，如果需要模型能够输出各个分期对应的概率来用于睡眠分期的判断。则需要对人在睡眠分期各阶段(可以是已由医生打好睡眠分期标签)所产生的多频段多脑区的生物电信号进行去噪声预处理，例如首先进行工频陷波。再利用盲信源分离算法独立成分分析(ICA)分解得到多个特征信号成分：这些成分可能分别对应脑电EEG信号，心电ECG，眼电EOG和肌电EMG信号中的一个或多个，并提取信号特征。
提取信号特征进行的方法有多种，主要分为时域分析、频域分析和时频分析三类，此处以经典的频域分析法中能量和比值分析方法为示例。
对已经分解后的特征信号(如EEG,ECG,EOG,EMG中的一个或多个)，将每类信号分段，每段数据长度为7500点(采样频率250Hz，采集30s)，选取某个睡眠阶段25分钟的数据，并对此25分钟的数据划分为多个30s进行特征提取，计算该睡眠阶段各特征的能量和的比值。
具体来说，例如对EEG信号需要通过小波分解得到alpha、beta、theta、delta波的能量比。可以利用db4小波基进行小波分解，分别计算alpha波(8-13Hz)，beta波(13-30Hz)，theta波(4-7Hz)，delta(1-4Hz)在1-30Hz上所占能量和的比值；
同理对ECG、EMG、EOG信号利用小波基进行小波分解，计算其在该频率上所占的能量和的比值。
能量比计算公式如下所示：
Figure PCTCN2020078822-appb-000001
Figure PCTCN2020078822-appb-000002
其中μ i为分解后第i层频带(例如，进行EGG信号的能量比计算，不同频带对应不同类型的EGG信号)所占总能量和的比值，D i(k)为分解后第i层频带上的第k个小波系数；n为第i层小波系数的数据个数；E s为各个频带信号的总能量和；N为总划分频带的个数。
同样以进行EGG信号的能量比计算为例，将得到当前睡眠阶段的EEG信号中alpha、beta、theta、delta波及其他特征信号的能量和的比，如果有7类信号则对应于7维信号特征，导入SVM(支持向量机)中，其中一个30s分段数据可得到睡眠分期分类概率结果，训练得到识别准确率最高的SVM模型参数，例如这里SVM可以采用径向基核函数作为激活函数，并可以根据经验选择当gamma取8.0，惩罚因子C取10.0时进行识别。
如果生物电信号和传感器融合进行睡眠分期判断，同理提取各睡眠阶段的其他生物特征信号和传感信号特征(如能量和比值)，与EEG信号的alpha能量和的比值和其他 特征信号的能量和比值一起作为信号特征导入SVM中，进行模型参数训练。
训练得到的SVM模型，在进行睡眠分类分析的时候即可以根据特征信号，或特征信号和传感信号的能量和比值来输出睡眠分类对应的概率值，用于判断当前所分析的信号所对应的睡眠分期结果。
CNN模型方案：
一个典型的卷积神经网络架构，通常来说包括输入->[[卷积层]*N->[池化层]*M->[全连接层]*K->识别运算，其中N1,M1,K为整数，可根据需要设定。
基于生物电信号的卷积神经网络的离线训练过程为，首先需要对人在睡眠和非睡眠阶段(可以是已由医生打好睡眠分期标签)所产生的多频段多脑区的生物电信号进行去噪声预处理，根据子空间分解算法ICA分解多频段多区的生物电信号并得到脑电EEG信号，心电ECG，眼电EOG和肌电EMG信号中的一个或多个。将经过预处理的分解信号形成多维信号联同其对应的标签(例如对应的睡眠分期类别)，输入卷积神经网络，具体来说，对已经分解后的生物电信号(如EEG,ECG,EOG,EMG中的一个或多个)，将每类信号分段，每段数据长度可以为7500点(采样频率250Hz，采集30s)，如果四类生物特征信号全包括则形成EEG,ECG,EOG,EMG四维信号矩阵，将该信号矩阵联合其对应的标签，输入卷积神经网络。根据随机梯度下降算法进行迭代优化求解。最终求得目标函数收敛时对应的卷积核参数以及全连接层中的各个参数。最后识别层可以采用softmax层，当仅需要区别睡眠与非睡眠时，可以输出两个分类对应的概率。当需要区分更多睡眠状态时，可以相应增加输出端口的数目。因此卷积神经网络训练阶段，需要确定卷积层、池化层、全连接层和分类模型中的各种参数，以确保后续的目标识别准确率高。其中一个30s分段数据可得到睡眠分期分类概率结果。
基于特征信号和传感信号的卷积神经网络的离线训练过程：首先需要对人在睡眠和非睡眠阶段(已由医生打好睡眠分期标签)所产生的EGG特征信号、PPG心率信号、IMU运动信号、麦克风音频信号等(根据应用阶段所需要分析的信号种类来选择训练阶段所需的信号种类，如应用阶段通过采集脑电信号，眼电信号和运动信号来进行睡眠分析，则训练阶段需要获取不同标签阶段的脑电信号，眼电信号和运动信号。)进行去噪声预处理，如果获得的是生物电信号则可能还需要根据子空间分解算法ICA分解多频段多区的生物电信号来获取需要的脑电EEG信号，心电ECG，眼电EOG和肌电EMG信号中的一种或多种。将经过预处理的分解信号和多传感信号(PPG心率信号、IMU运动信号、麦克风音频信号中的一种或多种)形成多维信号输入卷积神经网络，具体来说，对已经分解后的生物电信号(如EEG,ECG,EOG,EMG等)和多传感信号(PPG心率信号、IMU运动信号、麦克风音频信号)，将每类信号分段，每段数据长度为7500点(采样频率250Hz，采集30s)，并形成EEG,ECG,EOG,EMG,PPG心率,IMU,音频等多维信号矩阵，维数根据具体的应用需求的不同而不同，将该信号矩阵联合其对应的标签，输入卷积神经网络。根据梯度下降算法进行迭代求使得神经网络误差最小时对应的卷积核、全连接层中的各个参数，最后识别运算阶段通常采用softmax回归分类模型，softmax模型中需要提前训练得到一个损失函数，也是通过随机梯度下降的方式，将已知训练数据概率输入计算损失最小时的损失函数参数。因此卷积神经网络训练阶段，需要确定卷积层、池化层、全连接层和分类模型种的各种参数，以确保后续的目标识别准确率高。
以上数据长度选择为7500点(采样频率250Hz，采集30s)仅为一种示例，也可以 选择其他的采样频率和时长。
同样在训练过程中能量和比值也仅为信号的一种特征，还可以选择其他特征，例如各类信号的功率谱估计来进行模型训练来获得睡眠分类模型进行睡眠分类。
图9对应于本申请实施例的一种睡眠检测***，***包括对应于图5中的耳侧佩戴装置101和睡眠检测装置102。
其中耳侧佩戴装置101，用于从耳侧采集的用户生物电信号；用于对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，心电信号，眼电信号，肌电EMG信号中的一种或多种，以及脑电信号；
耳侧佩戴装置101具体可以分为单侧或双侧测量，其中耳侧佩戴装置101为单侧测量其结构如图10a所示，其中单侧耳侧信号测量单元1011用于从左耳道或者右耳道获取用户生物电信号。
耳侧佩戴装置101为双侧测量其结构如图10b所示，其中左耳耳侧信号测量单元101a用于从左耳道获取用户生物电信号，右耳耳侧信号测量单元101b用于从右耳道获取用户生物电信号。
对应于双侧测量的耳侧佩戴装置101，即耳侧佩戴装置包括左耳耳侧信号测量单元101a和右耳耳侧信号测量单元101b，耳侧佩戴装置101通过判断所述左耳耳侧信号测量单元101a和所述右耳耳侧信号测量单元101b之间的阻抗是否低于预设阈值，来判断耳侧佩戴装置是否可以正常进行测量，当判断耳侧佩戴装置可以正常进行测量，根据所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号来获取所述用户生物电信号，当判断结果为耳侧佩戴装置无法正常进行测量，分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值。根据阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号来获取所述用户生物电信号。具体的判断方式可以参数步骤S60101-S60103。
对应于耳侧佩戴装置101为单侧耳道测量，即耳侧佩戴装置101仅包括左耳耳侧信号测量单元或右耳耳侧信号测量单元1011，在此实施方式下，左耳耳侧信号测量单元或右耳耳侧信号测量单元需要为多个，即单侧耳侧信号测量单元为多个。耳侧佩戴装置101通过判断所述单侧耳侧信号测量单元中的两个信号测量单元之间的阻抗是否低于预设阈值，来判断耳侧佩戴装置是否可以正常进行测量，当判断耳侧佩戴装置可以正常进行测量，根据所述多个单侧耳侧信号测量单元中的两个采集的生物电信号的电位差值信号来获取所述用户生物电信号。具体的判断方式参考步骤S60111-S60112。
除了采集生物电信号，耳侧佩戴装置还用于采集传感信号，如用于获取心率信号，运动信号(感知用户活动情况)，声音信号(检测用户发出的声音)，其中的一种或多种。
本发明实施例中生物电信号可以是用户生物特征信号的混合信号，用于后期进行生物特征信号的提取，传感信号根据具体实现过程中传感器的部署，可以为运动传感信号、心率传感信号、声音传感信号中的一种或多种。
耳侧佩戴装置101还用于对所述用户生物电信号进行特征分解，获得生物特征信号；
所述生物特征信号包括，心电ECG信号，眼电EOG信号，肌电EMG信号以及脑电EEG 信号中的一种或多种。
睡眠检测装置102，用于根据所述生物特征信号获得所述用户的睡眠分期分类结果。
本发明实施例中的睡眠分类结果的分析可以通过机器学习的方式来实现。机器学习的模型可以有多种，例如可以通过SVM模型来进行分析，也可以是通过深度神经网络模型来进行分析。具体实现方式可以参照步骤S503来实施。
睡眠检测装置或耳侧佩戴装置中还可以包括睡眠调节功能，用于根据睡眠检测结果在用户睡眠状况不佳时进行提示，或者进行干预，帮助用户改善睡眠质量，如播放一些舒缓的音乐等。睡眠检测装置在实现过程中具体的实现形式可以是各类便携终端，也可以是设置在云端服务器。
图10c为本发明实施例的一种从耳道内侧获取生物电信号的耳侧佩戴装置的一种示例性的结构图，耳侧佩戴装置可以有多种形态，例如可以是耳机形态，也可以是耳塞的形态，本示例给出的耳侧佩戴装置是耳塞形态，但在本申请中并不作为限定，耳侧佩戴装置包括耳塞本体301，柔性电极载体302和多个表面柔性电极303。柔性电极载体302提供一个足够弹性的支撑，确保附着在柔性电极载体302表面的多个柔性电极303和用户的耳道内表面形成紧密贴合，确保稳定地采集生物电信号信号。310部分示例性地呈现了一种表面柔性电极303的构成，包括呈现等角120度分布的生物感测柔性电极303A，生物感测柔性电极303B，接地的公共柔性电极303G，304是耳塞孔。针对另一些可行的实施例，附着在柔性电极载体302表面的生物感测柔性电极303可以只有1个或2个，而将耳塞本体301还可以连接有参考电极此处没有画出。或者在其他一些可行的实施例中，参考电极也可以采取耳廓支架上的电极触电来实现等多种方式。图10c中耳塞形态的耳侧佩戴装置的佩戴示意图如图5b所示，其中401为用户的耳道，402为脑电信号测量的入耳式的耳塞，403为柔性电极，404为用户的耳廓。从图5b可以看出，佩戴时柔性电极载体表面的多个柔性电极403和用户的耳道401内表面形成紧密贴合，和用户的头部形成一个测量***。虽然图中没有示出，耳侧佩戴装置还可以，包括通信模块用于接收或者发送脑电信号，还可以可选的包括注意力检测单元用于通过脑电信号分析用户的注意力类型。
在本发明的有些实施例中，对生物电信号进行特征分解的步骤也可以设置于睡眠检测装置102中来实施。图9a、图9b即为本发明实施例对应的两种***结构图，其中图9a对应于特征分解功能设置于耳侧佩戴装置来实现的实现方案，图9a中耳侧佩戴装置210具备较多数据处理功能，耳侧佩戴装置210的耳侧信号测量单元211获取用户生物电信号，传感信号测量单元212获取多种传感信号，具体可以是心率PPG，运动IMU，麦克风等数据，并分别通过耳道信号处理单元213和传感器信号处理单元214对这些生物电信号和传感信号进行预处理，如去噪声预处理，A/D转换等，睡眠调节模块216，用来根据睡眠检测单元221的睡眠检测结果，进行睡眠的告警或者干预。特征分解单元215用于将生物电信号进行特征提取，分解为脑电EEG，心电ECG，眼电EOG，肌电EMG。然后将这些分解后的特征信号和传感信号经过通信单元217发送到终端或者云端，终端或者云端通过通信单元222接收到这些信号后，传送到睡眠检测单元221，经过睡眠检测单元221处理后，会得到睡眠状态监测结果，得到睡眠状态监测结果后可根据睡眠调节模块216中的调控算法生成睡眠调节指令，控制播放模块播放适合的音乐声音等。
所述的睡眠调节模块可以是微型振动马达。所述耳道信号处理单元213和传感器信号处理单元214可以选择性的包括输入缓冲放大电路或预处理电路、滤波电路、二级放大电路；所述而到信号测量单元211和传感信号测量单元212所检测的信号可以是通过输入缓冲放大电路、滤波电路、二级放大电路等电路处理后传输至A/D转换电路。以及特征提取单元，例如从心电信号中提取心率信息。
图9b对应于耳侧佩戴装置设置于睡眠检测装置即终端或者云上来实现的实现方案，在此不再赘述。图9a，9b仅为示例性情况，在具体实现过程中可以对其中的单元模块进行增减和调整，或者各单元之间的功能进行整合。
在本发明的有些实施例中，还可以将睡眠检测装置和耳侧佩戴装置集成在一起，如图11所示，对应于本申请实施例的一种集成了睡眠检测功能的耳侧佩戴装置110。装置包括：
耳侧信号测量单元111，用于从耳侧采集的用户生物电信号。可选的，所述耳侧信号测量单元111可以包括左耳耳侧信号测量单元111a和右耳耳侧信号测量单元111b。当耳侧佩戴装置110为单侧测量装置时，耳侧信号测量单元111可以仅包括单侧耳侧信号测量单元111c。
特征分解单元112，用于对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，心电信号，眼电信号，肌电EMG信号中的一种或多种，以及脑电信号。
睡眠检测单元113，用于根据所述生物特征信号获得所述用户的睡眠分期分类结果。具体分析方式可以参考上文具体实施例，在此不再赘述。
第一判断单元114，用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元测量的生物电信号采集的生物电信号的电位差值信号作为所述用户生物电信号。
对应于双侧测量情况，所述耳侧佩戴装置还可以可选的包括第二判断单元。
第一断单元114，用于判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值(具体判断方式上文中已经介绍，在此不再赘述)；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
第二判断单元115，用于当第一判断单元114判断所述耳侧佩戴装置无法正常测量(具体判断方式上文中已经介绍，在此不再赘述)，所述第二判断单元115分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。所述第二判断单元115为可选单元，第二判断单元115应用于所述左耳耳侧信号测量单元，右耳耳侧信号测量单元均为多个的情况。
对应于单侧测量情况，所述耳侧佩戴装置的包括第一判断单元114，用于判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值(具体判断方式上文中已经介绍，在此不再赘述)，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设 阈值，将所述多个单侧耳侧信号测量单元中的两个采集的生物电信号的电位差值信号作为所述用户生物电信号。
耳侧佩戴装置110可选的还可以包括传感信号测量单元117，用于采集传感信号；传感信号测量单元117在具体实现的过程中，可以是包括多种传感器装置，如心率传感器(具体可以是PPG传感器，也可以是其它用于测量心率的传感装置)用于测量获取心率信号，运动传感器(具体可以是IMU运动传感器，也可以是其它的用于测量运动的传感装置)用于测量感知用户活动情况，声音传感器(具体可以是麦克风，也可以是其它的用于测量声音的传感装置)用于检测用户发出的声音中的一种或多种，用于测量运动传感信号、心率传感信号、声音传感信号中的一种或多种。
本发明实施例还公开了一种测量用户相关信号的方法，如图16所示：其中步骤S1601，S1602同图7相同，S1603为将所述生物特征信号发送给信号分析装置，信号分析装置在本申请实施例中具体可以为睡眠检测装置。
对应的本发明实施例还公开一种用于测量用户相关信号的耳侧佩戴装置，如图12所示，耳侧信号测量单元121，用于从耳侧采集的用户生物电信号。可选的，所述耳侧信号测量单元121可以包括左耳耳侧信号测量单元121a和右耳耳侧信号测量单元121b。当耳侧佩戴装置120为单侧测量装置时，耳侧信号测量单元121可以仅包括单侧耳侧信号测量单元121c。
特征分解单元122，用于对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，心电信号，眼电信号，肌电EMG信号中的一种或多种，以及脑电信号。
发送单元123，用于将所述生物特征信号发送给信号分析装置；信号分析装置在本申请实施例中具体可以为睡眠检测装置。
第一判断单元124，用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元测量的生物电信号采集的生物电信号的电位差值信号作为所述用户生物电信号。
对应于双侧测量情况，所述耳侧佩戴装置还可以可选的包括第二判断单元125。
第一断单元124，用于判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值(具体判断方式上文中已经介绍，在此不再赘述)；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
第二判断单元125，用于当第一判断单元124判断所述耳侧佩戴装置无法正常测量(具体判断方式上文中已经介绍，在此不再赘述)，所述第三判断单元分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。所述第二判断单元125为可选单元，第二判断单元125应用于所述左耳耳侧信号测量单元，右耳耳侧信号测量单元均为多个的情况。
对应于单侧测量情况，所述耳侧佩戴装置的第一判断单元124，用于判断其中两个 所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值(具体判断方式上文中已经介绍，在此不再赘述)，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值，将所述多个单侧耳侧信号测量单元中的两个采集的生物电信号的电位差值信号作为所述用户生物电信号。
耳侧佩戴装置120可选的还可以包括传感信号测量单元127，用于采集传感信号；传感信号测量单元127在具体实现的过程中，可以是包括多种传感器装置，如心率传感器(具体可以是PPG传感器，也可以是其它用于测量心率的传感装置)用于测量获取心率信号，运动传感器(具体可以是IMU运动传感器，也可以是其它的用于测量运动的传感装置)用于测量感知用户活动情况，声音传感器(具体可以是麦克风，也可以是其它的用于测量声音的传感装置)用于检测用户发出的声音中的一种或多种，用于测量运动传感信号、心率传感信号、声音传感信号中的一种或多种。
本发明实施例还公开了一种分析用户相关信号的方法，如图17所示：其中步骤S1702同图7中的S603相同，S1701为从耳侧佩戴装置接收生物特征信号。所述生物特征信号包括，心电信号，眼电信号，肌电EMG信号中的一种或多种，以及脑电信号。可选的，还可以从耳侧佩戴装置接收传感信号；所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种。
对应的，本发明实施例还公开一种睡眠检测装置130，如图13所示。装置包括：
接收单元131，用于从耳侧佩戴装置接收生物特征信号；
所述生物特征信号包括，心电信号，眼电信号，肌电EMG信号中的一种或多种，以及脑电信号；
睡眠检测单元132，用于根据所述生物特征信号获得所述用户的睡眠分期分类结果。
特征分解单元112，用于对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，心电信号，眼电信号，肌电EMG信号中的一种或多种，以及脑电信号。
睡眠检测单元113，用于根据所述生物特征信号获得所述用户的睡眠分期分类结果。具体分析方式可以参考上文具体实施例，在此不再赘述。
可选的接收单元131，还用于从耳侧佩戴装置接收传感信号；所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种。
相应的，睡眠检测单元132，根据所述生物特征信号分析所述用户的睡眠分期分类结果，具体还可以为：根据所述生物特征信号和所述传感信号获得所述用户的睡眠分期分类结果。所述睡眠检测装置可以是用户的终端设备如手机，或其他可佩戴或便携终端，也可以是设置于云端的服务器中。
图14，是对应于是本申请实施例11，12的装置的处理器结构示意图。
如图14所示集成了睡眠检测功能的耳侧佩戴装置1400可以包括一个或者多个处理器1406、一个或多个存储器1401，传感信号测量单元1402，特征分解单元1403。具体实现中，耳侧佩戴装置还可以进一步包括传感器单元1404，通信单元1405。处理器1406可通过总线分别连接存储器1401、测量电极1402，特征分解电路1403，传感器1404等部件。分别描述如下：
处理器1406是耳侧佩戴装置的控制中心，利用各种接口和线路连接耳侧佩戴装置的各个部件，在可能实施例中，处理器1406还可包括一个或多个处理核心。处理器1400可通过执行程序指令来判断测量电极是否能正常测量(耳侧佩戴装置是否能正常测量)，以及根据测量信号进行用户睡眠分期的分析。当处理器1406可以为专用处理器也可以为通用处理器，当处理器1406为通用处理器时，处理器1406通过运行或执行存储在存储器1401内的软件程序(指令)和/或模块。
存储器1401可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。相应地，存储器1401还可以包括存储器控制器，以提供处理器1400和输入单元对存储器1401的访问。存储器1401可具体用于存储软件程序(指令)、以及采集的用户生物电信号。
耳侧信号测量单元1402，用于从耳侧采集的用户生物电信号。可选的，所述耳侧信号测量单元1402可以包括左耳耳侧信号测量单元和右耳耳侧信号测量单元。当耳侧佩戴装置1400为单侧测量装置时，耳侧信号测量单元1402可以仅包括单侧耳侧信号测量单元。耳侧信号测量单元1402通常通过硬件方式来实现，例如耳侧信号测量单元1402可以为电极，耳侧信号测量单元1402可以为一个或者多个。
特征分解单元1403，用于对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，心电信号，眼电信号，肌电EMG信号中的一种或多种，以及脑电信号。特征分解单元1403通常通过硬件方式来实现，例如特征分解电路，ICA组件。
可选的，在某些实施例中还可以包括传感信号测量单元1404，用于采集传感信号；传感信号测量单元1404在具体实现的过程中，可以是包括多种传感器装置，如心率传感器(具体可以是PPG传感器，也可以是其它用于测量心率的传感装置)用于测量获取心率信号，运动传感器(具体可以是IMU运动传感器，也可以是其它的用于测量运动的传感装置)用于测量感知用户活动情况，声音传感器(具体可以是麦克风，也可以是其它的用于测量声音的传感装置)用于检测用户发出的声音中的一种或多种，用于测量运动传感信号、心率传感信号、声音传感信号中的一种或多种。
通信单元1405用于通过无线或有线通信技术和耳侧佩戴装置以及其他设备之间进行通信连接，如蜂窝移动通信技术，WLAN，蓝牙等。
本领域技术人员可以理解，本申请实施例中耳侧佩戴装置可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。例如，耳侧佩戴装置还可以进一步包括扬声器、摄像头等，在此不再赘述。
具体的，处理器1406可通过读取，并分析判断存储在存储器1401中的测量信号来判断测量电极是否能正常测量(耳侧佩戴装置是否能正常测量)，以及根据测量信号进行用户睡眠分期的分析。包括：
对应于双侧测量情况，处理器1406用于判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值(具体判断方式上文中已经介绍，在此不再赘述)；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；根据所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号获取所述用户生物电信号；当判断所述耳侧佩戴装置无法正常测量(具体判断方式上文中已经介绍，在此不再赘述)，分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳 耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并根据阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号获取所述用户生物电信号，电位差值信号可以通过处理器1406执行指令来获取，也通过电位差值获取单元即硬件电路来实现。
对应于单侧测量情况，处理器1406用于判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值(具体判断方式上文中已经介绍，在此不再赘述)，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值，根据所述多个单侧耳侧信号测量单元中的两个采集的生物电信号的电位差值信号获取所述用户生物电信号。
处理器1406还用于根据所述生物特征信号获得所述用户的睡眠分期分类结果。具体分析方式可以参考上文具体实施例，在此不再赘述。
还需要说明的是，虽然图14仅仅是本申请耳侧佩戴装置的一种实现方式，所述耳侧佩戴装置中处理器1406和存储器1401，在可能的实施例中，还可以是集成部署的。
图14还可以为本发明实施例的一种用于测量用户相关信号的耳侧佩戴装置可以包括一个或者多个处理器1406、一个或多个存储器1401，耳侧信号测量单元1402，特征分解单元1403。具体实现中，耳侧佩戴装置还可以进一步包括传感器单元1404，通信单元1405(包括发送单元和接收单元)。处理器1406可通过总线分别连接存储器1401、测量电极1402，特征分解电路1403，传感器1404等部件。分别描述如下：
处理器1406是耳侧佩戴装置的控制中心，利用各种接口和线路连接耳侧佩戴装置的各个部件，在可能实施例中，处理器1406还可包括一个或多个处理核心。处理器1400可通过执行程序指令来判断测量电极是否能正常测量(耳侧佩戴装置是否能正常测量)。当处理器1406可以为专用处理器也可以为通用处理器，当处理器1406为通用处理器时，处理器1406通过运行或执行存储在存储器1401内的软件程序(指令)和/或模块。
存储器1401可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。相应地，存储器1401还可以包括存储器控制器，以提供处理器1400和输入单元对存储器1401的访问。存储器1401可具体用于存储软件程序(指令)、以及采集的用户生物电信号。
耳侧信号测量单元1402，用于从耳侧采集的用户生物电信号。可选的，所述耳侧信号测量单元1402可以包括左耳耳侧信号测量单元和右耳耳侧信号测量单元。当耳侧佩戴装置1400为单侧测量装置时，耳侧信号测量单元1402可以仅包括单侧耳侧信号测量单元。耳侧信号测量单元1402通常通过硬件方式来实现，例如耳侧信号测量单元1402可以为电极，耳侧信号测量单元1402可以为一个或者多个。
可选的，在某些实施例中还可以包括特征分解单元1403，用于对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，心电信号，眼电信号，肌电EMG信号中的一种或多种，以及脑电信号。特征分解单元1403通常通过硬件方式来实现，例如特征分解电路，ICA组件。
可选的，在某些实施例中还可以包括传感信号测量单元1404，用于采集传感信号；传感信号测量单元1404在具体实现的过程中，可以是包括多种传感器装置，如心率传感器(具体可以是PPG传感器，也可以是其它用于测量心率的传感装置)用于测量获取心率信号，运动传感器(具体可以是IMU运动传感器，也可以是其它的用于测量运动的传 感装置)用于测量感知用户活动情况，声音传感器(具体可以是麦克风，也可以是其它的用于测量声音的传感装置)用于检测用户发出的声音中的一种或多种，用于测量运动传感信号、心率传感信号、声音传感信号中的一种或多种。
通信单元1405用于通过无线或有线通信技术和耳侧佩戴装置以及其他设备之间进行通信连接，如蜂窝移动通信技术，WLAN，蓝牙等，用于将生物电信号或采集并处理后的生物特征信号或生物特征信号和传感器信号发送给信号分析装置；信号分析装置在本申请实施例中具体可以为睡眠检测装置。除了睡眠检测装置外，由于获取的生物电信号，生物特征信号和传感信号还可以应用于用户其他特征的分析，例如运动状态，注意力状态，情绪状态的识别，因此信号分析装置还可以是运动状态检测装置，注意力检测装置，情绪检测装置等其他的需要通过生物特征信号分析来获得信息的装置。
本领域技术人员可以理解，本申请实施例中耳侧佩戴装置可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。例如，耳侧佩戴装置还可以进一步包括扬声器、摄像头等，在此不再赘述。
具体的，处理器1406可通过读取，并分析判断存储在存储器1401中的测量信号来判断测量电极是否能正常测量(耳侧佩戴装置是否能正常测量)，以及根据测量信号进行用户睡眠分期的分析。包括：
对应于双侧测量情况，处理器1406用于判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值(具体判断方式上文中已经介绍，在此不再赘述)；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；根据所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号获取所述用户生物电信号；当判断所述耳侧佩戴装置无法正常测量(具体判断方式上文中已经介绍，在此不再赘述)，分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并根据阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号获取所述用户生物电信号，电位差值信号可以通过处理器1406执行指令来获取，也通过电位差值获取单元即硬件电路来实现。
对应于单侧测量情况，处理器1406用于判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值(具体判断方式上文中已经介绍，在此不再赘述)，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值，根据所述多个单侧耳侧信号测量单元中的两个采集的生物电信号的电位差值信号获取所述用户生物电信号。
同样，图14仅仅是本申请耳侧佩戴装置的一种实现方式，所述耳侧佩戴装置中处理器1406和存储器1401，在可能的实施例中，还可以是集成部署的。
图15还可以为本发明实施例的一种睡眠检测装置1500可以包括一个或者多个处理器1406、一个或多个存储器1401。具体实现中，睡眠检测装置1500还可以进一步包括通信单元1405(包括发送单元和接收单元)。处理器1506可通过总线分别连接存储器1401，通信单元1505等部件。分别描述如下：
处理器1406是睡眠检测装置的控制中心，利用各种接口和线路连接睡眠检测装置的各个部件，在可能实施例中，处理器1406还可包括一个或多个处理核心。处理器1400 可通过执行程序指令来判断用户的睡眠分期结果。当处理器1406可以为专用处理器也可以为通用处理器，当处理器1406为通用处理器时，处理器1406通过运行或执行存储在存储器1401内的软件程序(指令)和/或模块。
存储器1401可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。相应地，存储器1401还可以包括存储器控制器，以提供处理器1400和输入单元对存储器1401的访问。存储器1401可具体用于存储软件程序(指令)、以及接收的睡眠检测用信号。
通信单元1505用于通过无线或有线通信技术和耳侧佩戴装置以及其他设备之间进行通信连接，如蜂窝移动通信技术，WLAN，蓝牙等，用于接收睡眠检测用信号；睡眠检测用信号可以是生物特征信号，也可以是直接采集的生物电信号，当通信单元接收的是生物电信号，睡眠检测装置1500中还可以包括特征分解单元用于对生物电信号进行特征分解。
本领域技术人员可以理解，本申请实施例中睡眠检测装置可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。例如，睡眠检测装置还可以进一步包括扬声器、摄像头等，在此不再赘述。
具体的，处理器1506可通过读取，并分析判断存储在存储器1501中的睡眠检测用信号来进行用户睡眠分期的分析。包括：用于根据所述生物特征信号获得所述用户的睡眠分期分类结果。
同样，图15仅仅是本申请睡眠检测装置的一种实现方式，所述睡眠检测装置中处理器1506和存储器1501，在可能的实施例中，还可以是集成部署的。所述睡眠检测装置可以是用户的终端设备如手机，或其他可佩戴或便携终端，也可以是设置于云端的服务器中。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者任意组合来实现。当使用软件实现时，可以全部或者部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令，在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述处理器可以是通用处理器或者专用处理器。所述耳侧佩戴装置可以是一个，也可以是多个耳侧佩戴装置组成的计算机网络。所述计算机指令可存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网络站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线)或无线(例如红外、微波等)方式向另一个网络站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质，也可以是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如软盘、硬盘、磁带等)、光介质(例如DVD等)、或者半导体介质(例如固态硬盘)等等。
示例性的，本申请实施例的方案，执行主体可选的可以为ASIC、FPGA、CPU、GPU等，通过硬件或软件方式实现，存储器可选的可以为DDR、SRAM、HDD、SSD等易失或非易失性的存储设备。所述数据耳侧佩戴装置可以应用于多种场景，例如用于视频监控***的服务器上，示例性的可以是以PCIe扩展卡的形式。
其中ASIC、FPGA属于硬件实现，即在硬件设计时通过硬件描述语言的方式将本申请的方法落地；CPU、GPU属于软件实现，即在软件设计时通过软件程序代码的方式将本申请的方法落地。
在上述实施例中，对各个实施例的描述各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。

Claims (38)

  1. 一种用户睡眠检测方法，其特征在于，所述方法包括：
    通过耳侧佩戴装置，从用户耳侧获取用户生物电信号；
    对所述用户生物电信号进行特征分解，获得生物特征信号；
    所述生物特征信号包括脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；
    根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果；
    所述通过耳侧佩戴装置，从用户耳侧获取用户生物电信号具体包括：所述耳侧佩戴装置包括多个耳侧信号测量单元；判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元测量的生物电信号的电位差值信号作为所述用户生物电信号。
  2. 根据权利要求1所述的方法，其特征在于，
    所述多个耳侧信号测量单元包括左耳耳侧信号测量单元和右耳耳侧信号测量单元；
    所述判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元测量的生物电信号的电位差值信号作为所述用户生物电信号，具体为：
    判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；
    将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
  3. 根据权利要求1所述的方法，其特征在于，所述通过耳侧佩戴装置，从用户耳侧获取用户生物电信号具体包括：
    所述耳侧佩戴装置为单侧耳侧佩戴装置，所述多个耳侧信号测量单元包括多个单侧耳侧信号测量单元；
    所述判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元测量的生物电信号的电位差值信号作为所述用户生物电信号，具体为：
    判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个单侧耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
  4. 根据权利要求2所述的方法，其特征在于，所述方法包括：
    所述左耳耳侧信号测量单元为多个；
    所述右耳耳侧信号测量单元为多个；
    当其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值；
    分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；
    将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。
  5. 根据权利要求1-4任意一项所述的方法，其特征在于，所述方法包括：
    所述耳侧佩戴装置还采集传感信号；
    所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种；
    所述根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果，包括：
    根据所述生物特征信号和所述传感信号基于所述机器学习模型获得所述用户的睡眠分类结果。
  6. 根据权利要求1-4任意一项所述的方法，其特征在于，所述方法包括：
    所述根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果，包括：根据所述生物特征信号和SVM模型获得所述用户的睡眠分类结果。
  7. 根据权利要求5所述的方法，其特征在于，所述方法包括：
    所述根据所述生物特征信号和所述传感信号基于所述机器学习模型获得所述用户的睡眠分类结果，包括：
    根据所述生物特征信号和所述传感信号和SVM模型获得所述用户的睡眠分类结果。
  8. 根据权利要求1-4任意一项所述的方法，其特征在于，所述方法包括：
    所述根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果，包括：
    根据所述生物特征信号和深度神经网络模型获得所述用户的睡眠分类结果。
  9. 根据权利要求5所述的方法，其特征在于，所述方法包括：
    所述根据所述生物特征信号和所述传感信号基于机器学习模型获得所述用户的睡眠分类结果，包括：
    根据所述生物特征信号和所述传感信号和深度神经网络模型获得所述用户的睡眠分类结果。
  10. 一种睡眠检测***，其特征在于，所述***包括：
    耳侧佩戴装置，包括多个耳侧信号测量单元；
    所述耳侧佩戴装置用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元测量的生物电信号的电位差值信号作为所述用户生物电信号；
    用于对所述用户生物电信号进行特征分解，获得生物特征信号；所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；
    睡眠检测装置，用于根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果。
  11. 根据权利要求10所述的***，其特征在于，
    所述多个耳侧信号测量单元包括左耳耳侧信号测量单元和右耳耳侧信号测量单元；
    所述耳侧佩戴装置用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值，将所述两个耳侧信号测量单元测量的生物电信号的电位差值信号作为所述用户生物电信号，具体为：
    所述耳侧佩戴装置用于判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
  12. 根据权利要求10所述的***，其特征在于，
    所述耳侧佩戴装置为单侧耳侧佩戴装置，所述多个耳侧信号测量单元包括多个单侧耳侧信号测量单元；
    所述耳侧佩戴装置用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值，将所述两个耳侧信号测量单元测量的生物电信号的电位差值信号作为所述用户生物电信号，具体为：
    所述耳侧佩戴装置用于判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值，将所述两个单侧耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
  13. 根据权利要求11所述的***，其特征在于，
    所述左耳耳侧信号测量单元为多个；
    所述右耳耳侧信号测量单元为多个；
    所述耳侧佩戴装置还用于当判断其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值，分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。
  14. 根据权利要求10-13任意一项所述的***，其特征在于，
    所述耳侧佩戴装置还用于采集传感信号；
    所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种；
    所述睡眠检测装置根据所述生物特征信号分析所述用户的睡眠分类结果，具体为：
    根据所述生物特征信号和所述传感信号获得所述用户的睡眠分类结果。
  15. 根据权利要求10-13任意一项所述的***，其特征在于，
    所述睡眠检测装置，具体用于根据所述生物特征信号和SVM模型获得所述用户的睡眠分类结果。
  16. 根据权利要求14所述的***，其特征在于，
    所述睡眠检测装置，具体用于根据所述生物特征信号和所述传感信号和SVM模型获得所述用户的睡眠分类结果。
  17. 根据权利要求10-13任意一项所述的***，其特征在于，
    所述睡眠检测装置，具体用于根据所述生物特征信号和深度神经网络模型获得所述用户的睡眠分类结果。
  18. 根据权利要求14所述的***，其特征在于，
    所述睡眠检测装置，具体用于根据所述生物特征信号和所述传感信号和深度神经网络模型获得所述用户的睡眠分类结果。
  19. 一种耳侧佩戴装置，其特征在于，所述装置包括：
    多个耳侧信号测量单元，用于从耳侧采集的用户生物电信号；
    第一判断单元，用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元测量的生物电信号采集的生物电信号的电位差值信号作为所述用户生物电信号；
    特征分解单元，用于对所述用户生物电信号进行特征分解，获得生物特征信号；
    所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；
    睡眠检测单元，用于根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果。
  20. 根据权利要求19所述的装置，其特征在于，
    所述多个耳侧信号测量单元包括左耳耳侧信号测量单元和右耳耳侧信号测量单元；
    所述第一判断单元，用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值，将所述两个耳侧信号测量单元测量的生物电信号采集的生物电信号的电位差值信号作为所述用户生物电信号，具体为：
    所述第一判断单元判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
  21. 根据权利要求19所述的装置，其特征在于，
    所述耳侧佩戴装置为单侧耳侧佩戴装置；
    所述多个耳侧信号测量单元包括多个单侧耳侧信号测量单元；
    所述第一断单元，用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值，将所述两个耳侧信号测量单元测量的生物电信号采集的生物电信号的电位差值信号作为所述用户生物电信号，具体为：
    所述第一判断单元用于判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值，将所述两个单侧耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
  22. 根据权利要求20所述的装置，其特征在于，
    所述左耳耳侧信号测量单元为多个；
    所述右耳耳侧信号测量单元为多个；
    所述耳侧佩戴装置还包括第二判断单元；
    当所述第一判断单元判断其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值，所述第二判断单元分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。
  23. 根据权利要求19-22任意一项所述的装置，其特征在于，
    所述耳侧佩戴装置还包括传感信号测量单元，用于采集传感信号；
    所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种；
    所述睡眠检测单元根据所述生物特征信号分析所述用户的睡眠分类结果，具体为：
    根据所述生物特征信号和所述传感信号获得所述用户的睡眠分类结果。
  24. 根据权利要求19-22任意一项所述的装置，其特征在于，
    所述睡眠检测单元，具体用于根据所述生物特征信号和SVM模型获得所述用户的睡眠分类结果。
  25. 根据权利要求23所述的装置，其特征在于，
    所述睡眠检测单元，具体用于根据所述生物特征信号和所述传感信号和SVM模型获得所述用户的睡眠分类结果。
  26. 根据权利要求19-22任意一项所述的装置，其特征在于，
    所述睡眠检测单元，具体用于根据所述生物特征信号和深度神经网络模型获得所述用户的睡眠分类结果。
  27. 根据权利要求23所述的装置，其特征在于，
    所述睡眠检测单元，具体用于根据所述生物特征信号和所述传感信号和深度神经网络模型获得所述用户的睡眠分类结果。
  28. 一种耳侧佩戴装置，其特征在于，所述装置包括：
    多个耳侧信号测量单元，用于从耳侧采集生物电信号；
    第一判断单元，用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值；将所述两个耳侧信号测量单元测量的生物电信号采集的生物电信号的电位差值信号作为所述用户生物电信号；
    特征分解单元，用于对所述用户生物电信号进行特征分解，获得生物特征信号；
    所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；
    发送单元，用于将所述生物特征信号发送给信号分析装置。
  29. 根据权利要求28所述的装置，其特征在于，
    所述多个耳侧信号测量单元包括左耳耳侧信号测量单元和右耳耳侧信号测量单元；
    所述第一判断单元，用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值，将所述两个耳侧信号测量单元测量的生物电信号采集的生物电信号的电位差值信号作为所述用户生物电信号，具体为：
    所述第一判断单元判断所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述左耳耳侧信号测量单元和所述右耳耳侧信号测量单元之间的阻抗低于预设阈值；将所述左耳耳侧信号测量单元采集的生物电信号和所述右耳耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
  30. 根据权利要求28所述的装置，其特征在于，
    所述耳侧佩戴装置为单侧耳侧佩戴装置；
    所述多个耳侧信号测量单元包括多个单侧耳侧信号测量单元；
    所述第一断单元，用于判断其中两个耳侧信号测量单元之间的阻抗是否低于预设阈值；当所述两个耳侧信号测量单元之间的阻抗低于预设阈值，将所述两个耳侧信号测量单元测量的生物电信号采集的生物电信号的电位差值信号作为所述用户生物电信号，具体为：
    所述第一判断单元用于判断其中两个所述单侧耳侧信号测量单元之间的阻抗是否低于预设阈值，当所述两个所述单侧耳侧信号测量单元之间的阻抗低于预设阈值，将所述两个单侧耳侧信号测量单元采集的生物电信号的电位差值信号作为所述用户生物电信号。
  31. 根据权利要求29所述的装置，其特征在于，
    所述左耳耳侧信号测量单元为多个；
    所述右耳耳侧信号测量单元为多个；
    所述耳侧佩戴装置还包括第二判断单元；
    当所述第一判断单元判断其中一个左耳耳侧信号测量单元和其中一个右耳耳侧信号测量单元之间的阻抗高于预设阈值，所述第二判断单元分别判断所述多个左耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值，以及所述多个右耳耳侧信号测量单元中的两个之间的阻抗是否低于预设阈值；并将阻抗低于所述预设阈值的一侧耳道的两个生物电测量装置采集的生物电信号的电位差值信号作为所述用户生物电信号。
  32. 根据权利要求28-31任意一项所述的装置，其特征在于，
    所述耳侧佩戴装置还包括耳侧信号测量单元，用于采集传感信号；
    所述传感信号为为运动传感信号、心率传感信号、声音传感信号中的一种或多种；
    所述发送单元，用于将所述传感信号发送给信号分析装置。
  33. 一种睡眠检测装置，其特征在于，所述装置包括：
    接收单元，用于从耳侧佩戴装置接收生物特征信号；
    所述生物特征信号包括，脑电信号，心电信号，眼电信号，肌电EMG信号中的一种或多种；
    睡眠检测单元，用于根据所述生物特征信号基于机器学习模型获得所述用户的睡眠分类结果。
  34. 根据权利要求33所述的装置，其特征在于，
    所述接收单元，还用于从耳侧佩戴装置接收传感信号；所述传感信号为运动传感信号、心率传感信号、声音传感信号中的一种或多种；
    所述睡眠检测单元根据所述生物特征信号分析所述用户的睡眠分类结果，具体为： 根据所述生物特征信号和所述传感信号获得所述用户的睡眠分类结果。
  35. 根据权利要求33所述的装置，其特征在于，
    所述睡眠检测单元，具体用于根据所述生物特征信号和SVM模型获得所述用户的睡眠分类结果。
  36. 根据权利要求34所述的装置，其特征在于，
    所述睡眠检测单元，具体用于根据所述生物特征信号和所述传感信号和SVM模型获得所述用户的睡眠分类结果。
  37. 根据权利要求33所述的装置，其特征在于，
    所述睡眠检测单元，具体用于根据所述生物特征信号和深度神经网络模型获得所述用户的睡眠分类结果。
  38. 根据权利要求34所述的装置，其特征在于，
    所述睡眠检测单元，具体用于根据所述生物特征信号和所述传感信号和深度神经网络模型获得所述用户的睡眠分类结果。
PCT/CN2020/078822 2019-03-15 2020-03-11 一种用户睡眠检测方法及*** WO2020187109A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910201461.8A CN110051347A (zh) 2019-03-15 2019-03-15 一种用户睡眠检测方法及***
CN201910201461.8 2019-03-15

Publications (1)

Publication Number Publication Date
WO2020187109A1 true WO2020187109A1 (zh) 2020-09-24

Family

ID=67316163

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/078822 WO2020187109A1 (zh) 2019-03-15 2020-03-11 一种用户睡眠检测方法及***

Country Status (2)

Country Link
CN (1) CN110051347A (zh)
WO (1) WO2020187109A1 (zh)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110051347A (zh) * 2019-03-15 2019-07-26 华为技术有限公司 一种用户睡眠检测方法及***
CN110432870A (zh) * 2019-08-13 2019-11-12 重庆邮电大学 一种基于1d cnn-lstm的睡眠信号自动分期方法
CN111248922B (zh) * 2020-02-11 2022-05-17 中国科学院半导体研究所 基于加速度计和陀螺仪的人体呼吸情况采集贴及制备方法
TWI748485B (zh) * 2020-05-28 2021-12-01 長庚醫療財團法人林口長庚紀念醫院 一種資訊處理系統及其方法
CN115052221A (zh) * 2020-08-19 2022-09-13 芯海科技（深圳）股份有限公司 耳机控制方法及耳机
CN111887830B (zh) * 2020-09-10 2023-03-10 贵州省人民医院 睡眠监测方法、装置、设备及可读存储介质
TWI802134B (zh) * 2021-12-07 2023-05-11 矽譜科技股份有限公司 癲癇發作及歷程偵測系統及其資訊平台
CN114177474A (zh) * 2021-12-15 2022-03-15 中国人民解放军海军特色医学中心 一种可调节深海环境下睡眠质量的睡枕***

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102638742A (zh) * 2011-02-14 2012-08-15 索尼公司 声音信号输出设备及声音信号输出方法
WO2016176668A1 (en) * 2015-04-30 2016-11-03 Somtek, Inc. Breathing disorder detection and treatment device and methods
CN206197938U (zh) * 2016-08-04 2017-05-31 戴琨 一种心电图的处理装置
CN107865638A (zh) * 2017-09-21 2018-04-03 广东思派康电子科技有限公司 计算机可读存储介质、入耳式耳塞检测装置
CN108451505A (zh) * 2018-04-19 2018-08-28 广西欣歌拉科技有限公司 轻量入耳式睡眠分期***
CN108742526A (zh) * 2018-05-14 2018-11-06 广东思派康电子科技有限公司 一种具有入睡检测功能的智能穿戴设备及入睡检测方法
CN110051347A (zh) * 2019-03-15 2019-07-26 华为技术有限公司 一种用户睡眠检测方法及***

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN200987666Y (zh) * 2006-09-29 2007-12-12 北京新兴阳升科技有限公司 一种便携式睡眠监测装置
WO2013026481A1 (en) * 2011-08-24 2013-02-28 Widex A/S Eeg monitor with capacitive electrodes and method of monitoring brain waves
CN103040466B (zh) * 2013-01-08 2014-07-30 中国人民解放军第四军医大学 一种电阻抗检测用电极连接异常的检测方法
CN105997072B (zh) * 2016-06-20 2019-07-05 中国人民解放军第四军医大学 一种基于测量精度的电阻抗检测用电极接触状态检测方法
CN107007278A (zh) * 2017-04-25 2017-08-04 中国科学院苏州生物医学工程技术研究所 基于多参数特征融合的自动睡眠分期方法
CN108388912B (zh) * 2018-02-08 2021-12-10 南京理工大学 基于多传感器特征优化算法的睡眠分期方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102638742A (zh) * 2011-02-14 2012-08-15 索尼公司 声音信号输出设备及声音信号输出方法
WO2016176668A1 (en) * 2015-04-30 2016-11-03 Somtek, Inc. Breathing disorder detection and treatment device and methods
CN206197938U (zh) * 2016-08-04 2017-05-31 戴琨 一种心电图的处理装置
CN107865638A (zh) * 2017-09-21 2018-04-03 广东思派康电子科技有限公司 计算机可读存储介质、入耳式耳塞检测装置
CN108451505A (zh) * 2018-04-19 2018-08-28 广西欣歌拉科技有限公司 轻量入耳式睡眠分期***
CN108742526A (zh) * 2018-05-14 2018-11-06 广东思派康电子科技有限公司 一种具有入睡检测功能的智能穿戴设备及入睡检测方法
CN110051347A (zh) * 2019-03-15 2019-07-26 华为技术有限公司 一种用户睡眠检测方法及***

Also Published As

Publication number Publication date
CN110051347A (zh) 2019-07-26

Similar Documents

Publication Publication Date Title
WO2020187109A1 (zh) 一种用户睡眠检测方法及***
CN111867475B (zh) 次声生物传感器***和方法
US20220287630A1 (en) Systems and methods for determining sleep patterns and circadian rhythms
Nakamura et al. Automatic sleep monitoring using ear-EEG
US10291977B2 (en) Method and system for collecting and processing bioelectrical and audio signals
Nguyen et al. A lightweight and inexpensive in-ear sensing system for automatic whole-night sleep stage monitoring
US10178952B2 (en) Bi-hemispheric brain wave system and method of performing bi-hemispherical brain wave measurements
JP2019528104A (ja) 生体信号のモニタリングのための耳内感知システムおよび方法
US20190053756A1 (en) In-ear electrical potential sensor
AU2021250913B2 (en) Localized collection of biological signals, cursor control in speech-assistance interface based on biological electrical signals and arousal detection based on biological electrical signals
WO2020186915A1 (zh) 一种注意力检测方法及***
US20180353128A1 (en) Active unipolar dry electrode open ear wireless headset and brain computer interface
US20180078164A1 (en) Brain activity detection system, devices and methods utilizing the same
CN113633260B (zh) 多导睡眠监测方法、监测仪、计算机设备及可读存储介质
Angrisani et al. Instrumentation and measurements for non-invasive EEG-based brain-computer interface
CN203763087U (zh) 一种睡眠监测装置
US20220218941A1 (en) A Wearable System for Behind-The-Ear Sensing and Stimulation
Monori et al. Processing EEG signals acquired from a consumer grade BCI device
Nguyen et al. LIBS: a low-cost in-ear bioelectrical sensing solution for healthcare applications
Hazarika et al. Smartphone-Based Natural Environment Electroencephalogram Experimentation-Opportunities and Challenges
CN113208621A (zh) 一种基于eeg信号的梦境交互方法、***
Islam et al. Hearing disorder detection using auditory evoked potential (AEP) signals
Madhavan Design and Evaluation of a Brain Signal-based Monitoring System for Differently-Abled People
US20240236547A1 (en) Method and system for collecting and processing bioelectrical and audio signals
karigar Shivappa Brain Computer Interface Based on Auditory Steady State Response (ASSR) Paradigm for Home Automation Applications

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20774155

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20774155

Country of ref document: EP

Kind code of ref document: A1