WO2020133536A1 - Sleep state determining method and apparatus - Google Patents

Abstract

A sleep state determining method and apparatus. The method comprises: receiving a body movement signal and a physiological signal of a user, which are fed back by a monitoring device (101); preprocessing the body movement signal of the user, and obtaining a real-time quantized value for determining a current motion state of the user (102); processing the physiological signal to obtain heart rate characteristic information (103); and determining a sleep state of the user according to the real-time quantized value and the heart rate characteristic information. According to the technical solution provided by the present application, whether a user is in a sleep state can be determined according to heart rate characteristic information and motion characteristics of the user, so that whether the user is in the sleep state can be more accurately identified.

Description

Method and device for judging sleep state Technical field

The invention relates to the field of Internet of Things, in particular to a method and device for judging sleep state.

Background technique

One-third of human life is spent in sleep. The quality of sleep directly affects the health of the human body, especially the brain health.

However, the current sleep state analysis has the problems of high cost, complicated operation, and low accuracy, and cannot be widely used in the analysis and monitoring of sleep state of clinical users.

Summary of the invention

Embodiments of the present invention provide a sleep state judgment method and device. By using the method provided by the present invention, it is possible to determine whether the user is in a sleep state according to the user's heart rate characteristic information and exercise characteristics, thereby being able to more accurately identify whether the user is in Sleep state.

A first aspect of the present invention discloses a device for determining a sleep state. The device includes a receiving unit, a processing unit, and a determining unit;

The receiving unit is configured to receive the user's body movement signal and physiological signal fed back by the monitoring device;

The processing unit is configured to preprocess the user's body motion signal to obtain a real-time quantized value, where the real-time quantized value is used to judge the current movement of the user;

The processing unit is further configured to process the physiological signal to obtain heart rate characteristic information;

The judgment unit is configured to determine the sleep state of the user according to the real-time quantized value and the heart rate characteristic information.

A second aspect of the present invention discloses a sleep state judgment method, characterized in that the method includes:

Receive the user's body movement signals and physiological signals fed back by the monitoring equipment;

Preprocessing the user's body motion signal to obtain a real-time quantized value for judging the user's current motion situation;

Processing the physiological signal to obtain heart rate characteristic information;

The sleep state of the user is determined according to the real-time quantized value and the heart rate characteristic information.

A third aspect of the present invention discloses a device for determining a sleep state. The device for determining a sleep state includes a transceiver, a processor, and a memory; wherein the memory stores program codes, and when the program codes are executed, processing The device performs the method of any one of the first aspect.

A fourth aspect of the present invention discloses a storage medium that stores program codes. When the program codes are executed, any method described in the first aspect will be executed.

A fifth aspect of the present invention discloses a computer program product. The computer program product includes program code; when the program code is executed, the method of the first aspect is executed.

It can be seen that in the solution of the embodiment of the present invention, the user's body motion signal and physiological signal fed back by the monitoring device are received; wherein, the physiological signal includes an electrocardiographic signal, and the body motion signal includes a triaxial acceleration signal; The user's body motion signal is preprocessed to obtain a real-time quantized value, wherein the real-time quantized value is used to judge the current movement of the user; the physiological signal is processed to obtain heart rate characteristic information; according to The real-time quantized value and the heart rate characteristic information determine the sleep state of the user. Through the technical solution provided by the present invention, whether the user is in a sleep state can be determined according to the user's heart rate characteristic information and exercise characteristics, so that it is possible to more accurately identify whether the user is in a sleep state.

BRIEF DESCRIPTION

In order to more clearly explain the technical solutions in the embodiments of the present invention, the drawings required in the embodiments will be briefly described below. Obviously, the drawings in the following description are some embodiments of the present invention. Those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

1 is a schematic diagram of a method for determining a sleep state according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a change in feature value of sleep center rate feature information provided by an embodiment of the present invention;

3 is a schematic diagram of another sleep state judgment method provided by an embodiment of the present invention;

4 is a schematic diagram of another sleep state judgment method provided by an embodiment of the present invention;

FIG. 5 is a logical structure diagram of a sleep state judgment device provided by an embodiment of the present invention;

6 is a logic structure diagram of another apparatus for determining a sleep state according to an embodiment of the present invention;

7 is a logic structure diagram of another apparatus for determining a sleep state according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a physical structure of a sleep state judgment device according to an embodiment of the present invention;

9 is a system structural diagram of a monitoring device according to an embodiment of the present invention.

detailed description

In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be described clearly in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are the present invention Some embodiments, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

The terms "first", "second" and "third" appearing in the description, claims and drawings of the present invention are used to distinguish different objects, not to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally also includes Other steps or units inherent to these processes, methods, products or equipment.

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of a method for determining a sleep state according to an embodiment of the present invention. Wherein, as shown in FIG. 1, a method for determining a sleep state provided by an embodiment of the present invention includes the following:

101. Receive the user's body movement signal and physiological signal fed back by the monitoring device;

Among them, it should be pointed out that the execution subject of this embodiment is a sleep state judgment device, which can be installed in a mobile terminal or a medical instrument, and of course, it can also be an independent device.

Wherein, the physiological signal includes at least one of the following parameters, such as blood pressure, blood oxygen, electrocardiogram, heart sound, cardiac shock map, pressure, nasal airflow, pulse wave, etc. It can be understood that physiological signals can be measured by the following devices, including but not limited to ECG leads, blood pressure cuffs, blood oxygen probes, invasive pressure sensors, heart sound sensors, acceleration sensors, airflow sensors. In general, as long as the heart rate characteristic information can be obtained from the physiological signal, the type of the physiological signal is not limited. The heart rate characteristic information may be frequency domain characteristic information or time threshold characteristic information.

For example, the body motion signal may be a three-axis acceleration signal, a six-axis acceleration signal, a nine-axis acceleration signal, an angular acceleration signal, etc., as long as the real-time quantification for judging the user's current movement status can be obtained by preprocessing the body motion signal Value. It can be understood that the body motion signal can be obtained through a motion sensor. For example, the motion sensor may be an acceleration sensor, a gyroscope, or the like. When the motion sensor is an acceleration sensor, the real-time quantification value is the real-time acceleration value or the sum of the real-time acceleration values measured by the acceleration sensor; when the motion sensor is a gyroscope, since the gyroscope can monitor the user's motion track, therefore, at this time, The real-time quantized value can also be the user's moving distance in a period of time.

In an embodiment of the present invention, the monitoring device includes a motion sensor, such as a three-axis acceleration motion sensor, for the three-axis acceleration signal; further, the monitoring device further includes an electrocardiogram (Electrocardiograph, ECG) sensor for Collect the user's ECG signal. In addition, it should be pointed out that the electrocardiogram refers to the heart is excited by the pacing point, atrium, and ventricle in each cardiac cycle, accompanied by changes in bioelectricity, and a variety of potentials are drawn from the body surface through the electrocardiograph Changing graphics.

It can be understood that the monitoring device may be a part of the sleep state judgment device, and of course, it may also be an independent device.

102. Pre-process the user's body motion signal to obtain a real-time quantized value for judging the user's current motion situation;

Wherein, preprocessing the user's body motion signal to obtain a real-time quantifiable value includes: preprocessing the user's body motion signal to obtain the user's three-axis acceleration signal; The acceleration signal of the shaft is accumulated in absolute value to obtain the real-time quantized value.

It can be understood that the quantized value can be used to identify whether the current state is motion or still.

For example, the preprocessing process includes: after the sleep state determination device receives the user's body motion signal (triaxial acceleration signal), it will filter the body motion signal to remove noise, and then use a signal amplifier to expand the processed The amplitude of the signal, and finally A/D conversion (It can be understood that A/D conversion is analog-to-digital conversion, and the role of A/D conversion is to convert the analog value with continuous time and amplitude to continuous time and amplitude. Also discrete digital signals), convert analog signals into data signals.

103. Process the physiological signal to obtain heart rate characteristic information;

The heart rate characteristic information refers to the difference in physiological signals collected at two different times; the different times are two or more physiological signals with the same length in the sequence; the sequence can be continuous or intermittent collection; The physiological signal difference may be a physiological signal waveform or a waveform characteristic difference; the difference is a degree of difference or variability.

For example, the heart rate characteristic information may refer to a small change in the interval between two heartbeats. Heart rate feature information includes frequency domain feature information and time domain feature information.

In one embodiment, the processing of the physiological signal to obtain frequency domain characteristic information includes: processing the physiological signal to obtain ECG data; and analyzing the ECG data to extract real-time and effective R wave interval; resampling the R wave interval; calculating the heart rate characteristic information according to the R wave interval at different scales to obtain heart rate characteristic information.

Among them, for example, the process of processing physiological signals to obtain ECG data includes: after the sleep state determination device receives the user's ECG ECG signal, the ECG ECG signal is filtered to remove noise, and then the signal is used The amplifier expands the amplitude of the processed signal, and finally performs A/D conversion (It is understandable that A/D conversion is analog-to-digital conversion. The role of A/D conversion is to convert continuous time and amplitude analog values into continuous Digital signal with discrete time and discrete amplitude), convert analog signal to data signal. It can be understood that the data signal includes the electrocardiographic data. Understandably, when the physiological signal is a signal other than the ECG ECG signal, such as a pulse wave signal, the pulse wave signal can also be processed to obtain ECG data, as long as it performs physiological data data to obtain ECG The data is sufficient.

In addition, it should be noted that the electrocardiogram is composed of a series of wave groups, and each wave group represents each cardiac cycle. A wave group includes P wave, QRS wave group, T wave and U wave. Among them, QRS wave group includes three closely connected waves, the first downward wave is called Q wave, a high-pointed upright wave following Q wave is called R wave, and the downward wave after R wave is called S wave. Because they are closely connected and reflect the process of ventricular electrical excitation, they are collectively called QRS complexes. This wave group reflects the depolarization process of the left and right ventricles.

104. Determine the sleep state of the user according to the real-time quantized value and the heart rate characteristic information.

For example, if the heart rate characteristic information is frequency domain characteristic information, the judging the sleep state of the user according to the real-time quantized value and the heart rate characteristic information includes: comparing the real-time quantized value with the first A threshold, and comparing the heart rate characteristic information with a second threshold; when the real-time quantized value is lower than the first threshold and the heart rate characteristic information is less than the second threshold, it is determined that the user is in a sleep state. It can be understood that the second threshold is an adaptive threshold or a fixed value. When the heart rate feature information is time domain feature information, the time domain feature information includes the standard deviation of intervals within a preset time segment, and the user's sleep state is determined according to the real-time quantized value and the standard deviation. Specifically, the real-time quantized value and the first threshold, the standard deviation and the third threshold can be compared to determine the user's sleep state. Understandably, the third threshold may be a fixed threshold or an adaptive threshold. If it is an adaptive threshold, the determination method is similar to that of the second threshold, which is not limited herein.

Wherein, when the second threshold is an adaptive threshold, it should be pointed out that the adaptive threshold dynamically changes with the heart rate. Therefore, before comparing the heart rate characteristic information and the adaptive threshold, the method further includes: acquiring the user's current heart rate value; inputting the user's current heart rate value into a threshold determination model to determine the adaptive threshold .

Further, it should be noted that before inputting the current heart rate of the user into a threshold determination model to determine the adaptive threshold, the method further includes:

Acquiring data of the user's arousal sleep including acceleration signals and electrocardiogram signals within a preset time period; labeling the user's arousal sleep cycle according to a time series; wherein the content of the label includes the arousal state and sleep state; extraction The heart rate value of the user and the adaptive threshold value corresponding to the heart rate value (ie, the value of ECG) during all sleep cycles; obtaining a threshold determination model according to the extracted heart rate value and the adaptive threshold value corresponding to the heart rate value .

It is understandable that the length of the preset time period is not limited, of course, the longer the better, and the newer the data, the better. It is best to have data within a period of time when the user’s physical condition is stable. For example, if the user has a cold before 1 month, then the preset time period is the most recent month’s data, because the stable data of the body state can more accurately reflect the user’s body. Performance.

For example, a machine learning algorithm may be used to train the extracted heart rate value and the second threshold corresponding to the heart rate value to obtain a threshold determination model. Among them, common machine learning algorithms include classification learning algorithms, support vector machine algorithms, Bayesian algorithms, etc., which are not listed here.

In addition, it should be further noted that, after determining that the user is in a sleep state, the method further includes:

The sleep stage of the user is determined according to the ratio and corresponding relationship between multi-scale heart rate feature information, the sleep stage includes but not limited to deep sleep, light sleep and fast phase sleep REM (or called fast wave sleep or out of phase Sleep). It should be pointed out that sleep phase is a specific physiological process in sleep state. Physiologists divide the sleep process into two major phases based on changes in human EEG, EMG, ECG and electrooculograms, blood pressure and breathing during sleep: slow wave sleep and fast wave sleep. The two major phases alternate periodically, about six times a night. Each cycle includes 20 to 30 minutes of fast wave sleep and about 60 minutes of slow wave sleep. Most of the sleep that occurs after people fall asleep belongs to non-rapid eye movement sleep (NREMS). According to the characteristics of human brain waves, the current phase is generally divided into stages 1, 2, 3, and 4, corresponding to the process of sleeping from shallow to deep. In the first phase, low-amplitude brain waves were presented, and the frequencies were mixed slowly and slowly, and the theta waves were mainly 4-7 times/sec. This period often occurs after the onset of sleep and a brief awakening at night. Phase 2 also presents lower amplitude brain waves, often with a short series of 12-14 beats/second sleep fusiform and some complex waves. Represents the process of light sleep. In phase 3, there are often brief high-amplitude brain waves with amplitudes exceeding 50 microvolts and delta waves with a frequency of 1 to 2 times per second. Phase 4 showed high amplitude brain waves. This period is dominated by delta waves. Its appearance time accounts for more than 1/2 of the total time, representing deep sleep. There is only a quantitative difference between Phase 3 and Phase 4, but no qualitative difference. It is generally believed that stage 4 slow wave sleep has the function of promoting physical and energy recovery. Because it is observed that after a long period of physical work or not sleeping, this period lasts the longest in resuming sleep. As sleep goes from shallow to deep, gradual loss of consciousness, a slight drop in blood pressure, slower heart rate and breathing, reduced pupils, decreased body temperature and basal metabolic rate, decreased urine output, increased gastric juice, reduced saliva secretion, and increased sweating, all of the above physiological changes Relatively stable. Out-of-phase sleep is an agitated state that occurs periodically during sleep. The electroencephalogram is similar to that during arousal, showing a low amplitude desynchronized fast wave. Although various sensory functions are further reduced, motor functions are further reduced, muscles are almost completely relaxed, and the motor system is strongly suppressed, but the autonomic nervous system activities are enhanced, such as increased blood pressure, increased heart rate and breathing, cerebral blood flow and oxygen consumption Increase in volume, etc. In addition, intermittent paroxysmal performance will also occur within this phase. For example, there are frequent eye movements, twitching of the extremities and facial muscles.

For example, as shown in FIG. 2, the specific sleep state of the user can be determined according to the ratio between the multi-scale heart rate feature information and the correspondence between the heart rate feature information and the heart rate. Among them, it should be noted that when it is confirmed that the current sleep state, there are deep, light sleep and REM sleep in the human sleep cycle, according to the continuous sleep cycle, the heart rate characteristic information characteristics of the three sleep states have corresponding sizes difference. Therefore, during the sleep process, you can see that the characteristics of the heart rate characteristic information fluctuate regularly with the change of the sleep cycle. When it is at the peak, the sleep state is light sleep, and when the period is at the valley, the sleep state is deep sleep.

In addition, when it is determined that the user is in a sleep state, identifying the user's sleep state according to the real-time quantized value and the heart rate characteristic information includes:

If the real-time quantized value is higher than the first threshold and the heart rate characteristic information is less than the second threshold, it is determined that the user is in a sleep apnea state.

It can be seen that in the solution of this embodiment, the user's body motion signal and physiological signal fed back by the monitoring device are received; wherein, the physiological signal includes an electrocardiographic signal, and the body motion signal includes a triaxial acceleration signal; for the The user's body motion signals are pre-processed to obtain real-time quantized values, where the real-time quantized values are used to judge the current movement of the user; the physiological signals are processed to obtain heart rate characteristic information; according to the real-time The quantized value and the heart rate characteristic information determine the sleep state of the user. Through the technical solution provided by the present invention, whether the user is in a sleep state can be determined according to the user's heart rate characteristic information and exercise characteristics, so that it is possible to more accurately identify whether the user is in a sleep state.

Please refer to FIG. 3, which is a schematic flowchart of another method for determining a sleep state according to another embodiment of the present invention. Wherein, as shown in FIG. 3, the method includes:

201. Receive the user's body movement signal and physiological signal fed back by the monitoring device;

In this embodiment, the physiological signal includes an electrocardiographic signal, and the body motion signal includes a triaxial acceleration signal;

202. Pre-process the user's body motion signal to obtain a real-time quantized value, where the real-time quantized value is used to judge the current movement of the user;

Wherein, preprocessing the user's body motion signals to obtain real-time quantized values includes:

Preprocessing the user's body motion signal to obtain the user's three-axis acceleration signal;

An absolute value accumulation calculation is performed on the three-axis acceleration signal to obtain the real-time quantized value.

203. Process the physiological signal to obtain frequency domain characteristic information;

Wherein, processing the physiological signal to obtain frequency domain characteristic information includes: processing the physiological signal to obtain electrocardiographic data; analyzing the electrocardiographic data to extract real-time effective R-wave intervals; Re-sampling the inter-wave interval; calculating the heart rate characteristic information according to the R-wave interval at different scales to obtain heart rate characteristic information.

204. Obtain the current heart rate value of the user and input the current heart rate value of the user into a threshold determination model to determine the second threshold;

Wherein, before inputting the current heart rate of the user into the threshold determination model to determine the second threshold, the method further includes: acquiring the user's acceleration signal and ECG signal within a preset time period Awake sleep data; annotate the user's arousal sleep cycle according to time series; wherein, the marked content includes the awake state and the sleep state; extract the user's heart rate value and the corresponding heart rate value during all sleep cycles A second threshold; acquiring a threshold determination model according to the extracted heart rate value and a second threshold corresponding to the heart rate value.

205. Compare the real-time quantized value with a first threshold; and compare the frequency domain feature information with a second threshold;

206. When the real-time quantization value is lower than the first threshold and the frequency domain feature information is less than the second threshold, determine that the user is in a sleep state.

207. When the user is in a sleep state, and the real-time quantization value is higher than the first threshold and the frequency domain feature information is less than the second threshold, determine that the user is in a sleep apnea state.

It should be noted that, for the specific content of the embodiment described in FIG. 3, reference may be made to the explanation of the embodiment corresponding to FIG. 1.

It can be seen that in the solution of this embodiment, the second threshold corresponding to the heart rate can be obtained from the current heart rate of the user, and then based on the frequency domain feature information and the second threshold and the real-time quantized value and the first threshold Relationship to determine the user’s sleep state. By using the technical solution provided by the embodiment of the present invention, the accuracy of the user's sleep state recognition is further ensured.

As shown in FIG. 4, a schematic flowchart of another sleep state judgment method provided by another embodiment of the present invention. Wherein, as shown in FIG. 4, the method includes:

301. Acquire data of the user's arousal sleep including acceleration signals and electrocardiogram signals within a preset time period;

302. Mark the awake sleep cycle of the user according to a time series;

Among them, the marked content includes awake state and sleep state;

303. Extract the user's heart rate value and the second threshold corresponding to the heart rate value during all sleep cycles;

304. Acquire a threshold determination model according to the extracted heart rate value and a second threshold corresponding to the heart rate value;

305. Receive the user's body movement signal and physiological signal fed back by the monitoring device;

Wherein, the physiological signal includes an electrocardiographic signal, and the body motion signal includes a triaxial acceleration signal;

306. Pre-process the user's body motion signal to obtain a real-time quantized value, and process the physiological signal to obtain frequency domain feature information;

Wherein, the real-time quantitative value is used to judge the current movement of the user;

307. Obtain the current heart rate value of the user, and input the current heart rate value of the user into a threshold determination model to determine the second threshold;

308. Compare the real-time quantized value with the first threshold and compare the frequency domain feature information with the second threshold;

309. When the real-time quantization value is lower than the first threshold and the frequency domain feature information is less than the second threshold, determine that the user is in a sleep state.

It should be noted that, for the specific content of the embodiment described in FIG. 4, reference may be made to the explanation of the embodiment corresponding to FIG. 1.

It can be seen that in the solution of this embodiment, the user's historical data is trained to obtain a threshold determination model, and then the current second threshold is determined according to the user's current heart rate and the model, and then the user's Sleep state. By using the technical solution provided by the embodiment of the present invention, the accuracy of the recognition of the sleep state of each user is protected.

As shown in FIG. 5, an apparatus 400 for determining a sleep state provided by an embodiment of the present invention, wherein the apparatus 400 includes the following units:

The receiving unit 401 is configured to receive the user's body motion signal and physiological signal fed back by the monitoring device; wherein, the physiological signal includes an electrocardiographic signal, and the body motion signal includes a triaxial acceleration signal;

The processing unit 402 is configured to preprocess the user's body motion signal to obtain a real-time quantized value for judging the user's current motion situation;

In addition, optionally, the processing unit 402 is used to preprocess the user's body motion signal to obtain a real-time quantized value at least including:

Preprocessing the acceleration signal of the user to obtain a real-time acceleration value to obtain the real-time quantized value;

Preprocessing the user's acceleration signal and angular velocity signal to obtain at least the real-time acceleration value and the user's moving distance to obtain the real-time quantized value.

The processing unit 402 is further configured to process the physiological signal to obtain heart rate characteristic information;

In addition, optionally, processing the physiological signal to obtain heart rate characteristic information includes: processing the physiological signal to obtain electrocardiographic data; analyzing the electrocardiographic data to extract real-time effective R-wave intervals; Resampling the R wave interval; calculating the heart rate characteristic information according to the R wave interval at different scales to obtain heart rate characteristic information.

The judging unit 403 is configured to determine the sleep state of the user according to the real-time quantized value and the heart rate characteristic information.

In addition, optionally, the judgment unit 403 is specifically configured to compare the real-time quantized value with a first threshold, and compare the heart rate characteristic information with a second threshold; when the real-time quantized value is lower than the first threshold When the heart rate characteristic information is less than the second threshold, it is determined that the user is in a sleep state.

Optionally, the sleep state determining apparatus further includes an obtaining unit 404 and a determining unit 405;

An obtaining unit 404, configured to obtain the current heart rate value of the user;

The determining unit 405 is configured to input the current heart rate value of the user into a threshold determination model to determine the second threshold.

Optionally, the sleep state determination device further includes a labeling unit 406 and an extraction unit 407;

The obtaining unit 404 is further configured to obtain data of the user's awake sleep including a body motion signal and an electrocardiogram signal within a preset time period;

The labeling unit 406 is configured to label the user's awakening sleep cycle according to a time series; wherein the content of the labeling includes the awakening state and the sleeping state;

An extraction unit 407, configured to extract the user's heart rate value and the second threshold corresponding to the heart rate value during all sleep cycles;

The obtaining unit 404 is further configured to obtain a threshold determination model according to the extracted heart rate value and a second threshold corresponding to the heart rate value.

Optionally, the determining unit 403 is configured to determine that the user is in a sleep apnea state if the real-time quantized value is higher than the first threshold and the heart rate characteristic information is less than the second threshold.

Understandably, in this embodiment, with reference to FIG. 5 and referring to FIG. 9, the processor includes the above-mentioned processing unit 402, judgment unit 403, acquisition unit 404, determination unit 405, annotation unit 406, extraction unit 407, and reception unit 401 The parameter measurement circuit 112 is included, and the monitoring device includes the sensor accessory 111. The receiving unit 401, the processing unit 402, and the judging unit 403 can be used to execute the methods described in steps 101-104 in Embodiment 1. For specific descriptions, see the description of the method in Embodiment 1, and details are not described herein.

As shown in FIG. 6, an apparatus 500 for determining a sleep state provided by an embodiment of the present invention, wherein the apparatus 500 includes the following units:

The receiving unit 501 is configured to receive the user's body movement signal and physiological signal fed back by the monitoring device;

Wherein, the physiological signal includes an electrocardiographic signal, and the body motion signal includes a triaxial acceleration signal;

The processing unit 502 is configured to preprocess the user's body motion signal to obtain a real-time quantized value, where the real-time quantized value is used to judge the current movement of the user;

Wherein, preprocessing the user's body motion signals to obtain real-time quantized values includes:

Preprocessing the user's body motion signal to obtain the user's three-axis acceleration signal; performing absolute value cumulative calculation on the three-axis acceleration signal to obtain the real-time quantized value.

The processing unit 502 is further configured to process the physiological signal to obtain frequency domain characteristic information;

Wherein, processing the physiological signal to obtain frequency domain characteristic information includes: processing the physiological signal to obtain ECG data; analyzing the ECG data to extract real-time and effective R-wave intervals; Re-sampling the R-wave interval; calculating the frequency-domain feature information according to the R-wave interval at different scales to obtain frequency-domain feature information.

An obtaining unit 503, configured to obtain the current heart rate value of the user and input the current heart rate value of the user into a threshold determination model to determine the second threshold;

Wherein, before inputting the current heart rate of the user into the threshold determination model to determine the second threshold, the method further includes: acquiring the user's acceleration signal and ECG signal within a preset time period Awake sleep data; annotate the user's awake sleep cycle according to time series; wherein, the marked content includes the awake state and the sleep state; extract the user's heart rate value and the corresponding heart rate value during all sleep cycles A second threshold; acquiring a threshold determination model according to the extracted heart rate value and a second threshold corresponding to the heart rate value.

The judging unit 504 is used to compare the real-time quantized value and the first threshold; and compare the heart rate characteristic information and the second threshold;

The determining unit 505 is configured to determine that the user is in a sleep state when the real-time quantized value is lower than the first threshold and the heart rate characteristic information is less than the second threshold; and When the real-time quantized value is higher than the first threshold and the heart rate characteristic information is less than the second threshold, it is determined that the user is in a sleep apnea state.

Among them, the above units 501-505 can be used to execute the method described in steps 201-207 in Embodiment 2. For a detailed description, please refer to the description of the method in Embodiment 2, which will not be repeated here.

As shown in FIG. 7, an apparatus 600 for determining a sleep state provided by an embodiment of the present invention, wherein the apparatus 600 includes the following units:

An obtaining unit 601, configured to obtain data of the user's arousal sleep including acceleration signals and electrocardiogram signals within a preset time period;

The labeling unit 602 is configured to label the user's wakeful sleep cycle according to a time series;

Among them, the marked content includes awake state and sleep state;

The extracting unit 603 extracts the user's heart rate value and the second threshold corresponding to the heart rate value during all sleep cycles;

The obtaining unit 601 is further configured to obtain a threshold determination model according to the extracted heart rate value and a second threshold corresponding to the heart rate value;

The receiving unit 604 is configured to receive the user's body motion signal and physiological signal fed back by the monitoring device;

Wherein, the physiological signal includes an electrocardiographic signal, and the body motion signal includes a triaxial acceleration signal;

The processing unit 605 is configured to preprocess the user's body motion signal to obtain a real-time quantized value, and process the physiological signal to obtain frequency domain feature information;

Wherein, the real-time quantitative value is used to judge the current movement of the user;

The obtaining unit 601 is also used to obtain the current heart rate value of the user;

The determining unit 606 is configured to input the current heart rate value of the user into a threshold determination model to determine the second threshold;

The judging unit 607 is configured to compare the real-time quantized value with the first threshold and compare the heart rate characteristic information with the second threshold; when the real-time quantized value is lower than the first threshold and the heart rate characteristic information is less than the At the second threshold, it is determined that the user is in a sleep state.

Wherein, the above units 601-607 can be used to execute the method described in steps 301-309 in Embodiment 3. For a detailed description, please refer to the description of the method in Embodiment 3, which will not be repeated here.

In another embodiment of the present invention, a sleep state determination device is provided. The device includes;

A physiological signal collection unit to collect one or more physiological signals, and the collected one or more physiological signals include at least an electrocardiographic signal and send it to the information processing unit;

The motion sensor acquisition unit is placed on the electrode lead wire or a device adjacent to the electrode/lead wire or integrates one or more acceleration sensors with the electrode. Collect acceleration data and send it to the information processing unit;

A signal processing unit configured to process the one or more physiological signals from the electrode and the one or more acceleration signals of the accelerometer; and send the processed signal to the analysis unit.

The analysis unit is used to obtain two or more current states with the acceleration signal, and the states include at least two states of motion/rest or similar states. Then, according to the frequency domain heart rate characteristic information characteristics of the electrocardiogram signal at different scales, the current real sleep state is judged by combining the previous motion/rest state.

Sleep state display unit, displaying real-time values, trends or accumulated time and other statistical data of one or more sleep-related states

Please refer to FIG. 8. In another embodiment of the present invention, a sleep state judgment device 700 is provided. The device 700 includes hardware such as a CPU 701, a memory 702, a bus 703, and a transceiver 704. The above logic units shown in FIGS. 4-6 can be implemented by the hardware device shown in FIG. 7.

The CPU 701 executes the server program stored in the memory 702 in advance, and the execution process specifically includes the processing method in the foregoing embodiment, and details are not described herein again.

It can be seen from the above that in the technical solution provided by the embodiments of the present invention, the user's body motion signals and physiological signals fed back by the monitoring device are received; the user's body motion signals are preprocessed to obtain real-time quantized values, wherein, the The real-time quantized value is used to judge the current movement of the user; the physiological signal is processed to obtain heart rate characteristic information; and the user's sleep state is determined according to the real-time quantized value and the heart rate characteristic information. Through the technical solution provided by the present invention, whether the user is in a sleep state can be determined according to the user's heart rate characteristic information and exercise characteristics, so that it is possible to more accurately identify whether the user is in a sleep state.

As shown in FIG. 9, a system framework diagram of a multi-parameter monitoring device or module component is provided. The multi-parameter monitoring device or module assembly includes at least a parameter measurement circuit 112. The parameter measurement circuit 112 includes at least one parameter measurement circuit corresponding to physiological parameters. The parameter measurement circuit 112 includes at least an ECG signal parameter measurement circuit, a respiratory parameter measurement circuit, a body temperature parameter measurement circuit, a blood oxygen parameter measurement circuit, a non-invasive blood pressure parameter measurement circuit, There is at least one parameter measurement circuit in the invasive blood pressure parameter measurement circuit and the like, and each parameter measurement circuit 112 is respectively connected to the externally inserted sensor accessory 111 through a corresponding sensor interface. The sensor accessory 111 includes a detection accessory corresponding to the detection of physiological parameters such as electrocardiographic respiration, blood oxygen, blood pressure, and body temperature. The parameter measurement circuit 112 is mainly used to connect the sensor accessory 111 to obtain the collected physiological parameter signal, and may include at least two or more physiological parameter measurement circuits. The parameter measurement circuit 112 may be, but not limited to, a physiological parameter measurement circuit (module), Human physiological parameter measurement circuits (modules) or sensors collect human physiological parameters, etc. Specifically, the parameter measurement circuit 112 obtains an external physiological parameter sensor accessory through an extended interface to obtain physiological sampling signals about the patient, and obtains physiological data after processing for alarming and displaying. The extended interface can also be used to output the control signal about how to collect physiological parameters output by the main control circuit to the external physiological parameter monitoring accessory through the corresponding interface to realize the monitoring and control of the patient's physiological parameters.

The multi-parameter monitoring device or module component may further include a main control circuit 113, which needs to include at least one processor and at least one memory. Of course, the main control circuit 113 may also include a power management management module, a power IP module, and an interface conversion At least one of circuits and the like. The power management module is used to control the power on/off of the whole machine, the power-on sequence of each power domain inside the board, and battery charging and discharging. The power IP module refers to correlating the schematic diagram of the power circuit unit that is frequently called repeatedly with the printed circuit board (PCB) diagram, and curing into a separate power module, that is, converting an input voltage into a predetermined circuit into An output voltage, where the input voltage and the output voltage are different. For example, convert a 15V voltage to 1.8V, 3.3V, or 3.8V. It can be understood that the power IP module may be single-channel or multi-channel. When the power IP module is single, the power IP module can convert an input voltage to an output voltage. When the power IP module is multi-channel, the power IP module can convert one input voltage to multiple output voltages, and the voltage values of the multiple output voltages can be the same or different, so as to meet the needs of multiple electronic components at the same time. Voltage demand, and the module has few external interfaces, working in the system is a black box decoupled from the external hardware system, improving the reliability of the entire power system. The interface conversion circuit is used to convert the signal output by the main control minimum system module (that is, at least one processor and at least one memory in the main control circuit) into the input standard signal required by the actual external device, for example, to support external video transmission The standard (video, graphics, array, VGA) display function is to convert the RGB digital signals output from the central processing unit (CPU) to VGA analog signals, support external network functions, and reduce the media independent interface (reduced) interface, RMII) signals are converted to standard network differential signals.

In addition, the multi-parameter monitoring device or module component may also include one or more of a local display screen 114, an alarm circuit 116, an input interface circuit 117, an external communication, and a power interface 115. The main control circuit is used to coordinate and control the various cards, circuits and devices in the multi-parameter monitoring equipment or module assembly. In this embodiment, the main control circuit is used to control the data interaction between the parameter measurement circuit 112 and the communication interface circuit, as well as the transmission of control signals, and send the physiological data to the display screen 114 for display, and can also receive from the touch screen Or user control commands input by physical input interface circuits such as keyboards and keys, of course, can also output control signals on how to collect physiological parameters. The alarm circuit 116 may be an audible and visual alarm circuit. The main control circuit completes the calculation of physiological parameters, and can send the calculation results and waveforms of the parameters to the host (such as the host with a display, PC, central station, etc.) through external communication and power interface 115, external communication and power interface 115 It can be Ethernet (ethernet), token ring (token ring), token bus (token bus), and these three networks as the backbone network fiber distributed data interface (fiber distributed data interface (FDDI) LAN interface One or a combination thereof, it can also be one or a combination of wireless interfaces such as infrared, Bluetooth, wireless-fidelity (wifi), WMTS communication, or it can also be an asynchronous transmission standard interface (RS232), universal serial One or a combination of wired data connection interfaces such as a universal bus (USB). The external communication and power interface 115 may also be one or a combination of two of a wireless data transmission interface and a wired data transmission interface. The host computer can be any computer equipment such as a monitoring equipment, an electrocardiogram machine, an ultrasound diagnostic apparatus, a computer, etc., and a software can be installed to form a monitoring equipment. The host can also be a communication device, such as a mobile phone, a multi-parameter monitoring device, or a module component, which sends data to a mobile phone that supports Bluetooth communication through a Bluetooth interface, so as to realize remote transmission of data.

The multi-parameter monitoring module component can be set outside the shell of the monitoring device. As an independent external parameter module, it can be inserted into the host of the monitoring device (including the main control board) to form a plug-in type monitoring device as part of the monitoring device, or It can be connected to the host of the monitoring device (including the main control board) through the cable, and the external parameter module is used as an external accessory of the monitoring device. Of course, the parameter processing can also be built into the housing, integrated with the main control module, or physically separated inside the housing to form an integrated monitoring device. The monitoring equipment can be an independent monitor, a central station with a monitoring function, a nurse station, a portable monitoring device, a mobile terminal with a vital sign detection function, and so on.

The present application provides a monitoring device, including: a parameter measurement circuit 112 that is electrically connected to a sensor accessory 111 provided on a patient's body to obtain physiological signals corresponding to multiple physiological parameters and user's Body motion signal; processor and memory; the memory is used to store a computer program, and when the processor is used to execute the computer program stored in the memory, the following steps may be implemented: preprocessing the user's body motion signal to obtain real-time quantized values , Wherein the real-time quantified value is used to judge the current movement of the user; the physiological signal is processed to obtain heart rate characteristic information; and the user's sleep is determined according to the real-time quantized value and the heart rate characteristic information status.

A processor for preprocessing the user's body motion signal to obtain a real-time quantized value at least includes: pre-processing the user's acceleration signal to obtain a real-time acceleration value to obtain the real-time quantized value; The user's acceleration signal and angular velocity signal are preprocessed to obtain at least a real-time acceleration value and a user's moving distance to obtain the real-time quantized value.

Wherein, the processor is used to process the physiological signal to obtain heart rate characteristic information. The processor is used to: process the physiological signal to obtain ECG data; analyze the ECG data to extract real-time effective R Inter-wave interval; resampling the R-wave interval; calculating the heart rate characteristic information according to the R-wave interval at different scales to obtain heart rate characteristic information; wherein, the heart rate characteristic information includes time domain Feature information and frequency domain feature information.

Wherein, the processor is used to determine the sleep state of the user according to the real-time quantized value and the heart rate characteristic information includes: the processor is specifically used to compare the real-time quantized value with a first threshold, and compare the Heart rate characteristic information and a second threshold; when the real-time quantization value is lower than the first threshold and the heart rate characteristic information is less than the second threshold, it is determined that the user is in a sleep state. When it is determined that the user is in a sleep state, the processor is further configured to determine that the user is in sleep breathing if the real-time quantized value is higher than the first threshold and the heart rate characteristic information is less than the second threshold Paused state. The processor is also used to analyze whether the user's sleep state is deep sleep, light sleep, or REM sleep according to the heart rate characteristic information. The specific determination method is as described above, and details are not described here.

In order to determine the second threshold, the processor is also used to obtain the current heart rate value of the user; input the current heart rate value of the user into a threshold determination model to determine the second threshold. The method for the processor to obtain the threshold determination model is as follows: the processor is also used to acquire the user's awake sleep data including body motion signals and electrocardiogram signals within a preset time period; Annotation of the sleep cycle; wherein, the content of the label includes the awakening state and the sleep state; extracting the user's heart rate value and the second threshold corresponding to the heart rate value in all sleep cycles; according to the extracted heart rate value and the The second threshold value corresponding to the heart rate value acquires a threshold value determination model.

In another embodiment of the present invention, a computer program product is disclosed. The computer program product includes program code; when the program code is executed, the method in the foregoing method embodiment is executed.

In another embodiment of the present invention, a chip is disclosed, and the chip includes program code; when the program code is executed, the method in the foregoing method embodiment will be executed.

In the several embodiments provided in this application, it should be understood that the disclosed device may be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the unit is only a logical function division. In actual implementation, there may be another division manner, for example, multiple units or components may be combined or may Integration into another system, or some features can be ignored, or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or software function unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention essentially or part of the contribution to the existing technology or all or part of the technical solution can be embodied in the form of a software product, the computer software product is stored in a storage medium , Including several instructions to enable a computer device (which may be a personal computer, server, network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage media include: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program code .

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still The technical solutions described in the embodiments are modified, or some of the technical features are equivalently replaced; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

Claims (16)

1. A monitoring device, characterized in that the monitoring device includes:

   A parameter measurement circuit for obtaining physiological signals corresponding to multiple physiological parameters and a user's body motion signal; wherein, the parameter measurement circuit is electrically connected to a sensor accessory provided on the patient's body;

   Processor and memory;

   The memory is used to store the computer program, and when the processor is used to execute the computer program stored in the memory, the following steps may be implemented:

   Preprocessing the user's body motion signal to obtain a real-time quantized value, where the real-time quantized value is used to judge the current movement of the user;

   Processing the physiological signal to obtain heart rate characteristic information;

   The sleep state of the user is determined according to the real-time quantized value and the heart rate characteristic information.
2. The device according to claim 1, wherein the processor is configured to preprocess the user's body motion signal to obtain a real-time quantized value at least including:

   Preprocessing the acceleration signal of the user to obtain a real-time acceleration value to obtain the real-time quantized value;

   Preprocessing the user's acceleration signal and angular velocity signal to obtain at least the real-time acceleration value and the user's moving distance to obtain the real-time quantized value.
3. The device according to claim 1, wherein the processor is used to process the physiological signal to obtain heart rate characteristic information; the processor is used to process the physiological signal to obtain electrocardiographic data; Analyze the ECG data to extract real-time and effective R-wave intervals; resample the R-wave intervals; calculate the heart rate characteristic information according to the R-wave intervals at different scales to obtain the heart rate Feature information; wherein, the heart rate feature information includes time domain feature information and frequency domain feature information.
4. The device according to claim 1, wherein the processor is used to determine the sleep state of the user according to the real-time quantization value and the heart rate characteristic information; the processor is specifically used to compare the real-time quantization A value and a first threshold, and comparing the heart rate characteristic information with a second threshold; when the real-time quantized value is lower than the first threshold and the heart rate characteristic information is less than the second threshold, the user is determined Is sleeping.
5. The apparatus according to claim 4, wherein the processor is further configured to obtain the current heart rate value of the user; input the current heart rate value of the user into a threshold determination model to determine the second threshold .
6. The device according to claim 5, wherein the processor is further configured to acquire data of the user's awake sleep including a body motion signal and an electrocardiogram signal within a preset time period;

   Labeling the user's awakening sleep cycle according to a time series; wherein the content of the labeling includes the awakening state and the sleeping state;

   Extracting the user's heart rate value and the second threshold corresponding to the heart rate value during all sleep cycles;

   Obtaining a threshold determination model according to the extracted heart rate value and a second threshold corresponding to the heart rate value.
7. The apparatus according to claim 4, wherein the processor is further configured to determine if the real-time quantized value is higher than the first threshold and the heart rate characteristic information is less than the second threshold The user is in a sleep apnea state.
8. A method for judging sleep state, characterized in that the method includes:

   Receive the user's body movement signals and physiological signals fed back by the monitoring equipment;

   Preprocessing the user's body motion signal to obtain a real-time quantized value for judging the user's current motion situation;

   Processing the physiological signal to obtain heart rate characteristic information;

   The sleep state of the user is determined according to the real-time quantized value and the heart rate characteristic information.
9. The method according to claim 8, wherein the user's body motion signal is pre-processed to obtain a real-time quantized value, including:

   Preprocessing the acceleration signal of the user to obtain a real-time acceleration value to obtain the real-time quantized value;

   Preprocessing the user's acceleration signal and angular velocity signal to obtain at least the real-time acceleration value and the user's moving distance to obtain the real-time quantized value.
10. The method according to claim 8, wherein the physiological signal is processed to obtain heart rate characteristic information, including:

    Processing physiological signals to obtain ECG data;

    Analyze the ECG data to extract real-time and effective R wave intervals;

    Resampling the R wave interval;

    The heart rate characteristic information is calculated according to the R wave intervals at different scales to obtain heart rate characteristic information; wherein, the heart rate characteristic information includes time domain characteristic information and frequency domain characteristic information.
11. The method according to claim 8, wherein determining the user's sleep state according to the real-time quantized value and the heart rate characteristic information includes:

    Comparing the real-time quantized value with a first threshold, and comparing the heart rate characteristic information with a second threshold;

    When the real-time quantized value is lower than the first threshold and the heart rate characteristic information is less than the second threshold, it is determined that the user is in a sleep state.
12. The method according to claim 11, wherein before the comparing the real-time quantized value with a first threshold, the method further comprises:

    Obtaining the current heart rate value of the user;

    The current heart rate value of the user is input into a threshold determination model to determine the second threshold.
13. The method according to claim 12, wherein before the input of the current heart rate of the user into a threshold determination model to determine the second threshold, the method further comprises:

    Acquiring data of the awake sleep of the user including a body motion signal and an electrocardiogram signal within a preset time period;

    Labeling the user's awakening sleep cycle according to a time series; wherein the content of the labeling includes the awakening state and the sleeping state;

    Extracting the user's heart rate value and the second threshold corresponding to the heart rate value during all sleep cycles;

    A threshold determination model is obtained according to the extracted heart rate value and a second threshold corresponding to the heart rate value.
14. The method according to claim 11, wherein determining the sleep state of the user according to the real-time quantized value and the heart rate characteristic information includes:

    If the real-time quantized value is higher than the first threshold and the heart rate characteristic information is less than the second threshold, it is determined that the user is in a sleep apnea state.
15. An apparatus for determining a sleep state, characterized in that the apparatus for determining a sleep state includes a transceiver, a processor, and a memory; wherein the memory stores program code, and when the program code is executed, the processor executes The method according to any one of claims 8 to 14.
16. A storage medium, characterized in that program code is stored in the storage medium, and when the program code is executed, the method according to any one of claims 8 to 14 is executed.

Images