Sleep quality analysis method, system, storage medium and electronic device

Abstract

The present invention provides a sleep quality analysis method, system, storage medium and electronic device, the method comprising the following steps: obtaining a multimodal signal of a test subject when sleeping; the multimodal signal comprises an electroencephalogram signal, a pulse signal and a body movement signal; preprocessing the multimodal signal to obtain the multimodal features of the test subject; calculating and obtaining multiple types of sleep analysis parameters of the test subject based on the multimodal features; calculating and obtaining the corresponding sleep score coefficient for each threshold interval to which the sleep analysis parameter belongs; and calculating and obtaining the sleep quality analysis value of the test subject based on the multiple types of sleep score coefficients. The sleep quality analysis method, system, storage medium and electronic device of the present invention are configured to achieve accurate analysis of sleep quality based on multimodal signals.

Description

Technical Field

[0001] The present invention belongs to the field of big health technology and relates to a sleep quality analysis method, system, storage medium and electronic equipment. Background Art

[0002] Sleep plays an extremely important role for humans. During sleep, the body repairs and grows at the cellular level, and the immune system is strengthened. At the same time, adequate sleep can maintain normal neurotransmitter levels in the brain, helping people better cope with stress and emotional fluctuations in life.

[0003] However, according to statistics, nearly 60% of people think that their sleep quality is "unsatisfactory" and they have various sleep problems or even sleep disorders. Insomnia, poor sleep, insufficient sleep, and daytime fatigue have become "diseases of the times" that affect people's health.

[0004] As people's health awareness improves, they pay more and more attention to sleep health, hoping to objectively understand their sleep quality and effectively improve it. Technological upgrades have brought about smart sleep monitoring products, such as smart bracelets, watches, pillows, and mattresses. However, the existing sleep quality monitoring methods have large errors and cannot accurately evaluate sleep quality. Summary of the invention

[0005] The present invention provides a sleep quality analysis method, system, storage medium and electronic device, which are used to realize accurate analysis of sleep quality based on multimodal signals.

[0006] In a first aspect, the present invention provides a method for analyzing sleep quality, the method comprising the following steps:

[0007] Acquire a multimodal signal of the test subject in a sleeping state; the multimodal signal includes an electroencephalogram signal, a pulse signal, and a body movement signal;

[0008] Preprocessing the multimodal signal to obtain multimodal features of the test object;

[0009] Calculating and obtaining multiple types of sleep analysis parameters of the test subject based on the multimodal features;

[0010] For each threshold interval to which the sleep analysis parameter belongs, the corresponding sleep score coefficient is calculated; wherein each threshold interval corresponds to a sleep score coefficient; the sleep score coefficient corresponding to the nth threshold interval is , wherein each of the threshold intervals includes m sleep analysis parameter values, m is a preset positive integer greater than 1; x i Indicates i sleep analysis parameter values,i is a positive integer greater than or equal to 1 and less than or equal to m; x low Indicates the lower limit of the sleep analysis parameter, x high Indicates the upper limit of sleep analysis parameters; y high Indicates the upper limit value x of the sleep analysis parameter high The corresponding sleep score coefficient, Indicates the preset j Influencing factors of sleep analysis parameters, y basic A base number representing a preset sleep score coefficient;

[0011] The sleep quality analysis value of the test subject is calculated based on the multiple types of sleep score coefficients.

[0012] In an implementation of the first aspect, for each threshold interval, Calculated As y basic Based on The calculated sleep score coefficients for each threshold interval are The attenuation coefficient in Make corrections.

[0013] In an implementation of the first aspect, the sleep quality analysis value of the test subject is obtained by calculating based on the multiple types of sleep score coefficients. ,in represents a continuous multiplication operation, J represents the total number of types of sleep score coefficients of the test subject, j Indicates j Sleep score coefficient, j is greater than or equal to 1 and less than or equal to J A positive integer of ; Indicates j Sleep score coefficient, β age Indicates the preset age coefficient.

[0014] In an implementation of the first aspect, it further includes presetting a mapping relationship between a threshold interval to which the sleep analysis parameter belongs and a single sleep quality rating, and acquiring a single sleep quality rating corresponding to each sleep analysis parameter based on the mapping relationship.

[0015] In an implementation of the first aspect, preprocessing the multimodal signal to obtain the multimodal features of the test object includes the following steps:

[0016] Acquire the sleep stages and micro-arousal events of the test subject based on the EEG signal;

[0017] acquiring the pulse oxygen saturation of the test subject based on the pulse signal;

[0018] Acquiring a body motion change characteristic of the test subject based on the body motion signal;

[0019] The sleep staging, the micro-arousal events, the pulse blood oxygen saturation and the body movement change characteristics are used as the multimodal features.

[0020] In an implementation of the first aspect, obtaining the sleep staging and micro-arousal events of the test subject based on the EEG signal includes: filtering and segmenting the EEG signal, and obtaining the sleep staging and micro-arousal events corresponding to the EEG signal after filtering and segmenting based on a machine learning algorithm;

[0021] Acquiring the pulse oxygen saturation of the test subject based on the pulse signal includes: acquiring the pulse oxygen saturation based on the absorbance ratio of oxygenated hemoglobin and reduced hemoglobin in the pulse signal;

[0022] Acquiring the body motion change characteristics of the test object based on the body motion signal includes: filtering the collected acceleration signal and angular acceleration signal of the test object, extracting body motion parameters based on the filtered acceleration signal and angular acceleration signal, and acquiring the body motion change characteristics corresponding to the body motion parameters based on a regression analysis model.

[0023] In an implementation of the first aspect, calculating and obtaining multiple types of sleep analysis parameters of the test subject based on the multimodal features includes the following steps:

[0024] The total sleep time TST is calculated according to TST=REM+N1+N2+N3, where REM represents the duration of the rapid eye movement period in the sleep stage, and N1, N2 and N3 represent the duration of the N1, N2 and N3 stages of the non-rapid eye movement period in the sleep stage respectively;

[0025] Sleep efficiency SE was calculated according to SE = (TST / TRT) × 100%, where TRT represents the total time with sleep intention;

[0026] The number of awakenings nWASO was determined based on the total number of WASO events above the threshold, where WASO events represent events during sleep that transition from sleep to awakening;

[0027] according to Calculate the total wakefulness time WASO, where Indicates the sleep period Length of awakening; is a positive integer greater than or equal to 1 and less than or equal to G; G is nWASO;

[0028] The time required to fall asleep after having the intention to sleep was calculated as the sleep latency.

[0029] The Arousal Index was calculated according to Arousal Index = (nArousal / TST) × 60, where nArousal represents the number of micro-arousals;

[0030] The oxygen depletion index was calculated according to ODI = (total number of events below the threshold / TST) × 60, where the total number of events below the threshold represents the number of times the blood oxygen level drops by more than a preset ratio per hour of sleep during sleep;

[0031] The body movement index PLMI was calculated according to PLMI=(total number of body movement events above the threshold / TST)×60, where the total number of body movement events above the threshold represents the number of times the body turns above the threshold per hour of sleep during sleep;

[0032] The total sleep time, the sleep efficiency, the number of awakenings, the total awakening time, the sleep latency, the micro-arousal index, the oxygen depletion index and the body movement index are used as the sleep analysis parameters.

[0033] In a second aspect, the present invention provides a sleep quality analysis system, the system comprising an acquisition module, a preprocessing module, a first calculation module, a second calculation module and an analysis module;

[0034] The acquisition module is configured to acquire multimodal signals of the test subject when sleeping; the multimodal signals include EEG signals, pulse signals and body movement signals;

[0035] The preprocessing module is configured to preprocess the multimodal signal to obtain the multimodal features of the test object;

[0036] The first calculation module is configured to calculate and obtain multiple types of sleep analysis parameters of the test subject based on the multimodal features;

[0037] The second calculation module is configured to calculate the corresponding sleep score coefficient for each threshold interval to which the sleep analysis parameter belongs; wherein each threshold interval corresponds to a sleep score coefficient; the sleep score coefficient corresponding to the nth threshold interval is , wherein each of the threshold intervals includes m sleep analysis parameter values, m is a preset positive integer greater than 1; x i Indicates i sleep analysis parameter values, iis a positive integer greater than or equal to 1 and less than or equal to m; x low Indicates the lower limit of the sleep analysis parameter, x high Indicates the upper limit of sleep analysis parameters; y high Indicates the upper limit value x of the sleep analysis parameter high The corresponding sleep score coefficient, Indicates the preset j Influencing factors of sleep analysis parameters, y basic A base number representing a preset sleep score coefficient;

[0038] The analysis module is configured to calculate and obtain a sleep quality analysis value of the test subject based on a plurality of types of sleep score coefficients.

[0039] In a third aspect, the present invention provides a storage medium having a computer program stored thereon, which implements the above-mentioned sleep quality analysis method when executed by a processor.

[0040] In a fourth aspect, the present invention provides an electronic device, comprising: a processor and a memory;

[0041] The memory is configured to store a computer program;

[0042] The processor is configured to execute the computer program stored in the memory, so as to enable the electronic device to perform the above-mentioned sleep quality analysis method.

[0043] As described above, the sleep quality analysis method, system, storage medium and electronic device of the present invention have the following beneficial effects.

[0044] The present invention realizes accurate evaluation of sleep quality based on multimodal signals such as EEG signals, pulse signals and body movement signals, which helps test subjects understand their whole night sleep information, comprehensive sleep quality and factors causing sleep quality problems, and provides information support to help test subjects improve their sleep in a targeted manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Shown is a schematic diagram of a scene of an electronic device in an embodiment of the present invention.

[0046] Figure 2 Shown is a flow chart of a sleep quality analysis method in one embodiment of the present invention.

[0047] Figure 3 Shown is a schematic diagram of comparison of sleep quality analysis values ​​of the sleep quality analysis method of the present invention in one embodiment when sleep aid intervention is performed and when no sleep aid intervention is performed.

[0048] Figure 4FIG. 1 is a schematic diagram showing the structure of a sleep quality analysis system according to an embodiment of the present invention.

[0049] Figure 5 It is a schematic structural diagram of an electronic device of the present invention in one embodiment. DETAILED DESCRIPTION

[0050] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0051] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0052] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0053] The following embodiments of the present invention provide a sleep quality analysis method, which can be applied to Figure 1 The analysis device (or electronic device) shown. The analysis device collects multimodal signals of the test subject, such as EEG signals, pulse signals and body movement signals. The sleep quality analysis value of the test subject is obtained by analyzing the multimodal information, thereby providing information support for helping the test subject to improve sleep in a targeted manner.

[0054] The technical solutions in the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0055] like Figure 2 As shown, in one embodiment, the sleep quality analysis method of the present invention includes steps S1 to S5.

[0056] Step S1, obtaining a multimodal signal of a test subject during sleep; the multimodal signal includes an electroencephalogram signal, a pulse signal and a body movement signal.

[0057] Specifically, a multimodal signal of the test subject during sleep is collected. The multimodal signal includes an electroencephalogram signal, a pulse signal and a body movement signal. Among them, the electroencephalogram (EEG) signal is a signal that records the electrical activity of brain neurons by placing electrodes on the scalp. The amplitude of the electroencephalogram signal varies in different brain regions and different physiological or pathological states. The frequency of the electroencephalogram signal refers to the oscillation rate of the signal, usually in Hertz (Hz). The frequency of the electroencephalogram signal can be divided into different bands, such as delta waves (0.5-4 Hz), theta waves (4-8 Hz), alpha waves (8-13 Hz), beta waves (13-30 Hz) and gamma waves (above 30 Hz). The pulse signal is a periodic pulsation signal of the arterial blood vessels caused by the beating of the heart. It can be detected at the surface arteries of the human body, such as the radial artery in the wrist, the carotid artery in the neck, etc. The pulse signal contains rich physiological information of the human body and is one of the important indicators reflecting the state of the cardiovascular system. Body movement signals refer to various physical signals generated when the human body is active. It reflects the movement of the human body, including the movements of limbs, changes in posture, and the movement of the body as a whole. These signals can be detected and recorded in a variety of ways.

[0058] In one embodiment, the EEG signal of the test subject is collected based on the EEG signal collection device. The pulse signal of the test subject is collected based on the pulse signal collection device. The body motion signal of the test subject is collected based on the body motion signal collection device. For example, the acceleration and angular acceleration of the test subject are collected based on the acceleration sensor, and the acceleration and the angular acceleration are used as the body motion signal.

[0059] Step S2: preprocess the multimodal signal to obtain multimodal features of the test object.

[0060] Specifically, the sleep staging and micro-awakening events of the test subject are obtained based on the EEG signal. The EEG signal is first filtered, and then the filtered EEG signal is segmented (e.g., every 30 seconds is a segment), and then the segmented EEG signal is processed based on a machine learning algorithm to obtain the corresponding sleep staging and micro-awakening events in the segment. In one embodiment, the machine learning algorithm can use a support vector machine, a neural network, a decision tree, etc.

[0061] The sleep stages include the wake stage, the rapid eye movement (REM) stage, and the non-rapid eye movement (NREM) stage, of which the NREM stage is divided into the N1 stage, the N2 stage, and the N3 stage. Among them, the N1 stage: the N1 stage is also called the light sleep stage. This is the stage at the beginning of sleep, and the human body gradually relaxes and enters the sleep state. In the N1 stage, people are easy to wake up, and there will be some muscle tremors and weakened sensory reactions. The N2 stage is considered to be the intermediate sleep stage. In the N2 stage, the human body relaxes further, and the breathing and heart rate gradually slow down. This is the stage where people spend most of their sleep time. The N3 stage is also called the deep sleep stage. In the N3 stage, the human body is the most relaxed, and the body repair and recovery process is the most active. This is the stage most needed by the body and the brain, and it is crucial for physical recovery and memory consolidation. The micro-awakening event is the situation where the alpha wave lasts for 3 to 15 seconds during sleep. Therefore, by processing the filtered EEG signals, the duration of the wakefulness period, rapid eye movement period, N1 period, N2 period, N3 period and the number of micro-awakenings during sleep were counted respectively.

[0062] The pulse oxygen saturation of the test subject is obtained based on the pulse signal, wherein the pulse oxygen saturation of the test subject is calculated by the absorbance ratio of oxygenated hemoglobin and reduced hemoglobin.

[0063] The body motion change characteristics of the test subject are obtained based on the body motion signal. The body motion signals such as acceleration and angular acceleration collected by the acceleration sensor are filtered, and body motion parameters such as frequency, amplitude, and duration of body motion are extracted therefrom. Then, a regression analysis model is used to establish a relationship model between the target threshold and body motion parameters such as frequency, amplitude, and duration, so as to obtain the corresponding body motion change characteristics to analyze the body motion changes. For example, the test subject is judged to change from a static state to a jogging state based on the frequency, amplitude, and duration of body motion.

[0064] In the present invention, the sleep staging, the micro-arousal events, the pulse blood oxygen saturation and the body movement change characteristics are used as the multimodal features.

[0065] Step S3: Calculate and obtain multiple types of sleep analysis parameters of the test subject based on the multimodal features.

[0066] Specifically, in the present invention, the sleep analysis parameters include total sleep time (TST), sleep efficiency (SE), number of wake ups (nWASO), total wake up time (WASO), sleep latency (SOL), arousal index (Arousal Index), oxygen desaturation index (ODI) and one or more combinations of body movement index.

[0067] The total sleep time refers to the sum of the sleep time of each stage during sleep, and the ideal time is 7-8 hours. In the present invention, the total sleep time TST is calculated according to TST=REM+N1+N2+N3, wherein REM represents the duration of the rapid eye movement stage in the sleep stage, and N1, N2 and N3 represent the duration of the N1 stage, N2 stage and N3 stage of the non-rapid eye movement stage in the sleep stage, respectively.

[0068] Sleep efficiency refers to the percentage of total sleep time to the total time of sleep intention, and the higher the sleep efficiency, the better. Among them, the total time of intended sleep refers to the time from the test subject getting into bed to the time when he or she gets out of bed after sleep, that is, the time when the record is started and ended during sleep. In the present invention, the sleep efficiency SE is calculated according to SE=(TST / TRT)×100%, where TRT (Total Record Time) represents the total time with sleep intention, which is the total duration of the sleep record. Specifically, TRT includes the entire time period from the start (turning off the lights) to the end (turning on the lights) of sleep monitoring, which includes the actual sleep time and the awake time during sleep. In short, TRT is the total duration during sleep monitoring, which covers the entire time period when a person tries to sleep, not just the actual time asleep.

[0069] The number of awakenings is the number of times the person transitions from sleep to wakefulness during the entire sleep period. The fewer awakenings, the better. In the present invention, the number of awakenings nWASO is determined based on the total number of WASO events above the threshold. The WASO event represents an event that transitions from sleep to wakefulness during sleep. Preferably, the threshold is 5 minutes. If the threshold is too low, it may lead to misjudgment or the test subject may not have obvious feelings.

[0070] The total awakening time refers to the total awakening time from the initial sleep to the final awakening process, and the shorter the awakening time, the better. Calculate the total wakefulness time WASO, where Indicates the sleep period Length of awakening; is a positive integer greater than or equal to 1 and less than or equal to G, where G is nWASO. For example, WASO1 represents the duration of the first awakening during sleep, WASO2 represents the duration of the second awakening during sleep, and so on.

[0071] The sleep latency SOL refers to the time required to fall asleep after having the intention to sleep. The sleep latency should not be too long.

[0072] The micro-awakening index refers to the number of micro-awakenings during sleep per hour, and the lower the micro-awakening index, the better. In the present invention, the micro-awakening index Arousal Index is calculated according to Arousal Index=(nArousal / TST)×60, where nArousal represents the number of micro-awakenings. The number of micro-awakenings refers to the number of short-term (such as more than 3 seconds) changes in the EEG frequency during sleep. Although this change does not cause a change in the sleep stage, frequent micro-awakenings can cause sleep to become fragmented and affect sleep quality. Micro-awakening is an important indicator in sleep monitoring, which can be used to assess the continuity and fragmentation of sleep. Under normal circumstances, the micro-awakening index (i.e., the number of micro-awakenings per hour) throughout the night should be less than 10 times. If it is within this range, it is considered that sleep is relatively continuous; if it is 10-19.9 times / hour, it is mildly fragmented sleep; 20-29.9 times / hour is moderately fragmented sleep; if ≥30 times / hour, it is severely fragmented sleep. The increase in the number of micro-awakenings may be related to a variety of factors, including sleep apnea, periodic limb movement disorder, etc. Therefore, the number of micro-awakenings is an important parameter for assessing sleep quality and diagnosing sleep disorders.

[0073] The oxygen depletion index refers to the number of times the blood oxygen level drops by more than a preset ratio per hour of sleep. The lower the oxygen depletion index, the better. In the present invention, the oxygen depletion index is calculated according to ODI=(total number of events below the threshold / TST)×60, where the total number of events below the threshold represents the number of times the blood oxygen level drops by more than a preset ratio per hour of sleep during sleep. Preferably, the preset ratio is 3% or 4%.

[0074] The body movement index refers to the number of times the body turns above the threshold per hour of sleep, and the lower the body movement index, the better. In the present invention, the body movement index PLMI is calculated according to PLMI=(total number of body movement events above the threshold / TST)×60, where the total number of body movement events above the threshold represents the number of times the body turns above the threshold per hour of sleep during sleep. Preferably, the threshold is 60°. PLMI is the abbreviation of periodic limb movement index (PLMI), which refers to the number of regular limb movements found in sleep monitoring.

[0075] Step S4: For each threshold interval to which each sleep analysis parameter belongs, a corresponding sleep score coefficient is calculated.

[0076] Specifically, the numerical range of the sleep analysis parameter is divided into a corresponding number of threshold intervals based on a number of threshold values, each threshold interval corresponds to a sleep score coefficient, and then a mapping relationship between the sleep analysis parameter and the sleep score coefficient is obtained. Among them, the types of sleep analysis parameters include sleep latency, total sleep time, sleep efficiency, number of awakenings, total awakening time, oxygen depletion index, micro-arousal index and / or body movement index. If two sleep analysis parameters of the same type belong to different threshold intervals, the two sleep analysis parameters correspond to different sleep score coefficients.

[0077] For example, according to standard sleep guidance recommendations, a clustering method is used to group sleep analysis parameters into different intervals, each interval corresponding to a sleep score coefficient, thereby obtaining a mapping relationship between sleep analysis parameters and sleep score coefficients.

[0078] When the type of the sleep analysis parameter is sleep latency, the sleep analysis parameter corresponds to a sleep latency threshold interval, and the corresponding sleep score coefficient is a sleep latency sleep score coefficient.

[0079] When the type of the sleep analysis parameter is the total sleep time, the sleep analysis parameter corresponds to the total sleep time threshold interval, and the corresponding sleep score coefficient is the sleep score coefficient of the total sleep time.

[0080] When the type of the sleep analysis parameter is sleep efficiency, the sleep analysis parameter corresponds to a sleep efficiency threshold interval, and the corresponding sleep score coefficient is a sleep score coefficient of sleep efficiency.

[0081] When the type of the sleep analysis parameter is the number of awakenings, the sleep analysis parameter corresponds to the threshold interval of the number of awakenings, and the corresponding sleep score coefficient is the sleep score coefficient of the number of awakenings.

[0082] When the type of the sleep analysis parameter is the total wakefulness time, the sleep analysis parameter corresponds to the total wakefulness time threshold interval, and the corresponding sleep score coefficient is the sleep score coefficient of the total wakefulness time.

[0083] When the type of the sleep analysis parameter is the oxygen depletion index, the sleep analysis parameter corresponds to the oxygen depletion index threshold interval, and the corresponding sleep score coefficient is the sleep score coefficient of the oxygen depletion index.

[0084] When the type of the sleep analysis parameter is the micro-arousal index, the sleep analysis parameter corresponds to the micro-arousal index threshold interval, and the corresponding sleep score coefficient is the sleep score coefficient of the micro-arousal index.

[0085] When the type of the sleep analysis parameter is the body movement index, the sleep analysis parameter corresponds to the body movement index threshold interval, and the corresponding sleep score coefficient is the sleep score coefficient of the body movement index.

[0086] Therefore, for each sleep analysis parameter, the corresponding sleep score coefficient can be obtained according to the mapping relationship between the sleep analysis parameter and the sleep score coefficient.

[0087] In the case of insufficient sample size, the sleep score coefficient corresponding to the nth threshold interval is , n represents the threshold interval sequence, n is a positive integer greater than or equal to 1 and less than or equal to N; N is the total number of the threshold intervals; represents the adjustable attenuation coefficient, x high represents the upper limit of the known sleep analysis parameter; and the sleep quality analysis value of the test subject is calculated based on the sleep score coefficient. In one embodiment, the attenuation coefficient It can be obtained based on data statistical fitting.

[0088] In the case of a large sample size, the upper and lower limits of each sleep analysis parameter are determined based on each calculated sleep analysis parameter. The upper and lower limits correspond to different sleep score coefficients, respectively, and then a regression analysis model is used to predict the relationship between the threshold interval and the sleep score coefficient. The data values ​​of the sleep analysis parameters are grouped into different threshold intervals according to a clustering method, and the threshold intervals can be of equal width or unequal width. For each threshold interval, the average value of the sleep score coefficients corresponding to all sleep analysis parameters in the threshold interval is calculated as the sleep score coefficient corresponding to the threshold interval. Specifically, the sleep score coefficient corresponding to the nth threshold interval is:

[0089] Each of the threshold intervals includes m sleep analysis parameter values, m is a preset positive integer greater than 1; x i Indicatesi sleep analysis parameter values, i is a positive integer greater than or equal to 1 and less than or equal to m; x low Indicates the lower limit of the sleep analysis parameter, x high Indicates the upper limit of the known sleep analysis parameters; high Indicates the upper limit value x of the sleep analysis parameter high The corresponding sleep score coefficient, Indicates the preset j Influencing factors of sleep analysis parameters, y basic Indicates the preset sleep score coefficient. It can be obtained based on data statistical fitting. According to the degree of influence on sleep quality, the influencing factors of each sleep analysis parameter are ranked from large to small as follows: sleep latency> total sleep time> sleep efficiency> number of awakenings> total awakening time> oxygen depletion index> micro-arousal index> body movement index. y basic It is necessary to explain that for a certain sleep analysis parameter, it contains m sleep analysis parameter values, where i Indicates i Sleep analysis parameters include total sleep time, sleep efficiency, number of awakenings, total awakening time, sleep latency, micro-arousal index, oxygen depletion index, and body movement index. In the present invention, the total number of types of sleep analysis parameters is J .in j Indicates j sleep analysis parameters.

[0090] Preferably, for each threshold interval, Calculated As y basic In addition, when the sample size is large, according to The sleep score coefficients of each threshold interval are calculated to The attenuation coefficient in is corrected.

[0091] In one embodiment, the mapping relationship between the sleep analysis parameters and the sleep score coefficients can be expressed as the following formula:

[0092]

[0093] in, etc. represent the sleep score coefficients corresponding to the same type of sleep analysis parameters belonging to different threshold intervals. x Indicates sleep analysis parameters; Represents thresholds of different sizes within the numerical range of sleep analysis parameters. The sorting is from small to large, or from small to large; Represents a type of sleep analysis parameter N Threshold range.

[0094] For example, when the type of the sleep analysis parameter is sleep latency, the corresponding sleep score coefficient of the type of sleep latency is calculated according to the sleep latency threshold interval to which the sleep analysis parameter belongs. At this time, n represents the order of the sleep latency threshold intervals, and n is a positive integer greater than or equal to 1 and less than or equal to N; N is the total number of the sleep latency threshold intervals; represents the adjustable sleep latency attenuation coefficient, x high Indicates the known upper limit of the sleep analysis parameter.

[0095] For another example, when the type of the sleep analysis parameter is sleep latency, the sleep score coefficient corresponding to the nth threshold interval of sleep latency is:

[0096]

[0097] Wherein, each of the threshold intervals of sleep latency includes m sleep analysis parameter values, m is a preset positive integer greater than 1; x i Indicates i sleep analysis parameter values, i is a positive integer greater than or equal to 1 and less than or equal to m; x low The lower limit of the sleep analysis parameter representing the sleep latency, x high Represents the upper limit of the known sleep analysis parameters, y high Indicates the upper limit value x of the sleep analysis parameter high The corresponding sleep score coefficient, Indicates the preset j Influencing factors of sleep analysis parameters, y basic Indicates the base number of the sleep score coefficient for the preset sleep latency.

[0098] For example, when the type of the sleep analysis parameter is total sleep time, the sleep score coefficient corresponding to the type of total sleep time is calculated according to the total sleep time threshold interval to which the sleep analysis parameter belongs. At this time, n represents the order of the total sleep time threshold intervals, and n is a positive integer greater than or equal to 1 and less than or equal to N; N is the total number of the total sleep time threshold intervals; Represents the adjustable total sleep time decay coefficient, xhigh Indicates the known upper limit of the sleep analysis parameter.

[0099] For another example, when the type of the sleep analysis parameter is the total sleep time, the sleep score coefficient corresponding to the nth threshold interval of the total sleep time is:

[0100]

[0101] Each of the threshold intervals of the total sleep time includes m sleep analysis parameter values, m is a preset positive integer greater than 1; x i Indicates i sleep analysis parameter values, i is a positive integer greater than or equal to 1 and less than or equal to m; x low The lower limit of the sleep analysis parameter representing the total sleep time, x high Indicates the upper limit of the known sleep analysis parameters; high Indicates the upper limit value x of the sleep analysis parameter high The corresponding sleep score coefficient, Indicates the preset j Influencing factors of sleep analysis parameters, y basic A base number representing the sleep score coefficient of the preset total sleep time.

[0102] For example: when the type of the sleep analysis parameter is sleep efficiency (or number of awakenings, total awakening time, oxygen depletion index, micro-arousal index, body movement index), the corresponding sleep score coefficient of the type of sleep efficiency (or number of awakenings, total awakening time, oxygen depletion index, micro-arousal index, body movement index) is calculated according to the threshold range of sleep efficiency (or number of awakenings, total awakening time, oxygen depletion index, micro-arousal index, body movement index) to which the sleep analysis parameter belongs. At this time, n represents the order of the sleep efficiency threshold intervals, and n is a positive integer greater than or equal to 1 and less than or equal to N; N is the total number of the sleep efficiency (or awakening times, total awakening time, oxygen depletion index, micro-arousal index, body movement index) threshold intervals; Indicates the adjustable sleep efficiency (or number of awakenings, total awakening time, oxygen depletion index, micro-awakening index, body movement index) attenuation coefficient, x high Indicates the known upper limit of the sleep analysis parameter.

[0103] For another example, when the type of the sleep analysis parameter is sleep efficiency (or number of awakenings, total awakening time, oxygen depletion index, micro-arousal index, body movement index), the sleep score coefficient corresponding to the nth threshold interval of sleep efficiency (or number of awakenings, total awakening time, oxygen depletion index, micro-arousal index, body movement index) is:

[0104]

[0105] Among them, each threshold interval of sleep efficiency (or awakening times, total awakening time, oxygen depletion index, micro-arousal index, body movement index) includes m sleep analysis parameter values, m is a preset positive integer greater than 1; x i Indicates i sleep analysis parameter values, i is a positive integer greater than or equal to 1 and less than or equal to m; x low The lower limit of the sleep analysis parameter representing sleep efficiency (or number of awakenings, total awakening time, oxygen depletion index, micro-arousal index, body movement index), x high The upper limit of the sleep analysis parameter indicating sleep efficiency (or number of awakenings, total awakening time, oxygen depletion index, micro-arousal index, body movement index); high The upper limit x of the sleep analysis parameter representing sleep efficiency (or number of awakenings, total awakening time, oxygen depletion index, micro-arousal index, body movement index) high The corresponding sleep score coefficient, Indicates the preset j Influencing factors of sleep analysis parameters, y basic The base number of the sleep score coefficient indicating the preset sleep efficiency (or number of awakenings, total awakening time, oxygen depletion index, micro-arousal index, body movement index).

[0106] Step S5: Calculate and obtain the sleep quality analysis value of the test subject based on the multiple types of sleep score coefficients.

[0107] Specifically, the evaluation criteria for sleep analysis parameters are different for people of different age groups. In the present invention, the score coefficients of multiple types of sleep analysis parameters are multiplied and then multiplied by the age coefficient β. age , and then multiply it by 100 to obtain the sleep quality analysis value of the test subject.

[0108] In one embodiment, the sleep quality analysis value of the test subject is obtained based on the multiple types of sleep score coefficients. ,in represents a continuous multiplication operation, J represents the total number of types of sleep score coefficients of the test subject, j Indicates j Sleep score coefficient, j is greater than or equal to 1 and less than or equal to J A positive integer of ; Indicates j Sleep score coefficient,β age Indicates the preset age coefficient. The types of sleep analysis parameters include sleep latency, total sleep time, sleep efficiency, number of awakenings, total awakening time, oxygen depletion index, micro-arousal index and / or body movement index, etc. Correspondingly, the types of sleep score coefficients also include sleep latency, total sleep time, sleep efficiency, number of awakenings, total awakening time, oxygen depletion index, micro-arousal index and / or body movement index, etc. For example: the total number of types of sleep score coefficients is 8, including 8 types such as sleep latency, total sleep time, sleep efficiency, number of awakenings, total awakening time, oxygen depletion index, micro-arousal index and body movement index.

[0109] In one embodiment, the sleep analysis parameters of a test subject before and after sleep-aiding intervention can be determined according to the above algorithm, and the corresponding sleep score coefficients are shown in Table 1.

[0110] Table 1. Sleep analysis parameters and corresponding sleep score coefficients without intervention and with sleep-aid intervention

[0111]

[0112] The test subject age coefficient is β age =1, then based on the formula , the sleep quality analysis value without intervention can be calculated as S 未干预 =0.92×1×0.94×0.94×0.8×0.97×1×1×100×1=63.1, S 干预 =0.97×1×0.94×1×0.95×0.97×1×1×100×1=84.0. It can be seen that the comprehensive quality analysis value after sleep-aiding intervention is significantly higher than that without intervention. In addition, from the single value of sleep analysis parameters, it can be seen that sleep latency is the main problem affecting the sleep quality of the test subjects. Pre-sleep intervention can be used to improve the efficiency of falling asleep and thus improve sleep quality.

[0113] In another embodiment, 116 sleep records of 34 groups of patients with difficulty falling asleep were analyzed, of which 54 cases did not receive sleep-aid intervention, and 62 cases received sleep-aid intervention. Figure 3 As shown in the figure, the statistical results show that the sleep quality analysis values ​​of those with sleep-aiding intervention are generally higher than those without sleep-aiding intervention, and are more consistent with their subjective feelings. Among them, the experiment indicates that sleep-aiding intervention was carried out, and the blank indicates that no sleep-aiding intervention was carried out.

[0114] In addition, the sleep quality analysis method of the present invention can also preset the mapping relationship between the threshold intervals of sleep analysis parameters of different types (such as sleep latency, total sleep time, sleep efficiency, number of awakenings, total awakening time, oxygen depletion index, micro-arousal index, body movement index) and the single sleep quality rating, and obtain the single sleep quality rating corresponding to each sleep analysis parameter based on the mapping relationship. In other words, the single sleep quality rating evaluates the sleep quality level of a specific sleep analysis parameter. Among them, the clustering method is used to group the sleep analysis parameters into different intervals, and each interval corresponds to a single sleep quality rating, which can be expressed as the following formula:

[0115]

[0116] in, Indicates the individual sleep quality ratings corresponding to a type of sleep analysis parameter when it belongs to different threshold intervals. x Represents sleep analysis parameters, Represents a type of sleep analysis parameter N Threshold range.

[0117] For example, sleep efficiency SE can be divided into five threshold intervals according to statistical results. The first threshold interval is SE>95%, corresponding to the first sleep score coefficient, and the single sleep quality rating is excellent sleep maintenance; the second threshold interval is 80%~94.9%, corresponding to the second sleep score coefficient, and the single sleep quality rating is normal sleep; the third threshold interval is 70%~79.9%, corresponding to the third sleep score coefficient, and the single sleep quality rating is slightly reduced sleep; the fourth threshold interval is 60%~69.9%, corresponding to the fourth sleep score coefficient, and the single sleep quality rating is moderately reduced sleep; the fifth threshold interval is SE<60%, corresponding to the fifth sleep score coefficient, and the single sleep quality rating is severely reduced sleep.

[0118] The protection scope of the sleep quality analysis method described in the embodiment of the present invention is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present invention are included in the protection scope of the present invention.

[0119] An embodiment of the present invention further provides a sleep quality analysis system, which can implement the sleep quality analysis method described in the present invention. However, the implementation device of the sleep quality analysis system described in the present invention includes but is not limited to the structure of the sleep quality analysis system listed in this embodiment. All structural deformations and replacements of the prior art made according to the principles of the present invention are included in the protection scope of the present invention.

[0120] like Figure 4As shown, in one embodiment, the sleep quality analysis system of the present invention includes an acquisition module 41 , a preprocessing module 42 , a first calculation module 43 , a second calculation module 44 and an analysis module 45 .

[0121] The acquisition module 41 is configured to acquire multimodal signals of the test subject when the test subject is sleeping; the multimodal signals include electroencephalogram signals, pulse signals and body movement signals.

[0122] The preprocessing module 42 is connected to the acquisition module 41 and is configured to preprocess the multimodal signal to acquire the multimodal features of the test object.

[0123] The first calculation module 43 is connected to the pre-processing module 42 and is configured to calculate and obtain multiple types of sleep analysis parameters of the test subject based on the multi-modal features.

[0124] The second calculation module 44 is connected to the first calculation module 43, and is configured to calculate the corresponding sleep score coefficient for each threshold interval to which each sleep analysis parameter belongs; wherein each threshold interval corresponds to a sleep score coefficient; the sleep score coefficient corresponding to the nth threshold interval is , wherein each of the threshold intervals includes m sleep analysis parameter values, m is a preset positive integer greater than 1; x i Indicates i sleep analysis parameter values, i is a positive integer greater than or equal to 1 and less than or equal to m; x low Indicates the lower limit of the sleep analysis parameter, x high Indicates the upper limit of sleep analysis parameters; y high Indicates the upper limit value x of the sleep analysis parameter high The corresponding sleep score coefficient, Indicates the preset j Influencing factors of sleep analysis parameters, y basic Indicates the preset sleep score coefficient.

[0125] The analysis module 45 is connected to the second calculation module 44 and is configured to calculate and obtain the sleep quality analysis value of the test subject based on the multiple types of sleep score coefficients.

[0126] The structures and principles of the acquisition module 41, the preprocessing module 42, the first calculation module 43, the second calculation module 44 and the analysis module 45 correspond to the steps in the above-mentioned sleep quality analysis method, so they are not repeated here.

[0127] In another embodiment of the present invention, the functions of the preprocessing module 42 , the first calculation module 43 and the second calculation module 44 are all implemented by the analysis module 45 , and the sleep quality analysis system may only include the acquisition module 41 and the analysis template 45 .

[0128] In another embodiment of the present invention, the sleep quality analysis system may further include a GUI display interface or a human-computer interaction interface.

[0129] In the several embodiments provided by the present invention, it should be understood that the disclosed system, device or method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules / units is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules or units, which can be electrical, mechanical or other forms.

[0130] The modules / units described as separate components may or may not be physically separated, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention. For example, the functional modules / units in the various embodiments of the present invention may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0131] Those of ordinary skill in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0132] The embodiment of the present invention also provides a computer-readable storage medium. A person of ordinary skill in the art can understand that all or part of the steps in the method for implementing the above embodiment can be completed by instructing the processor through a program, and the program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as a random access memory, a read-only memory, a flash memory, a hard disk, a solid-state hard disk, a magnetic tape, a floppy disk, an optical disc, and any combination thereof. The above storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a digital video disc (DVD)), or a semiconductor medium (for example, a solid-state disk (SSD)), etc.

[0133] An embodiment of the present invention further provides an electronic device, which includes a processor and a memory.

[0134] The memory is configured to store a computer program.

[0135] The memory includes: ROM, RAM, disk, USB flash drive, memory card or CD and other media that can store program codes.

[0136] The processor is connected to the memory and is configured to execute the computer program stored in the memory so that the electronic device executes the above-mentioned EEG signal acquisition method.

[0137] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0138] like Figure 5As shown, the electronic device of the present invention is in the form of a general computing device. The components of the electronic device may include but are not limited to: one or more processors or processing units 51, a memory 52, and a bus 53 connecting different system components (including the memory 52 and the processing unit 51).

[0139] Bus 53 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0140] Electronic devices typically include a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, removable and non-removable media.

[0141] The memory 52 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 521 and / or cache memory 522. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 523 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 53 via one or more data medium interfaces. The memory 52 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0142] A program / utility 524 having a set (at least one) of program modules 5241 may be stored, for example, in the memory 52, such program modules 5241 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include an implementation of a network environment. The program modules 5241 generally perform the functions and / or methods of the embodiments described herein.

[0143] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, displays, etc.), one or more devices that enable a test subject to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via input / output (I / O) interface 54. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapter 55. Figure 5 As shown, the network adapter 55 communicates with other modules of the electronic device via the bus 53. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0144] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A sleep quality analysis method, characterized in that: The method comprises the following steps: Acquire a multimodal signal of the test subject in a sleeping state; the multimodal signal includes an electroencephalogram signal, a pulse signal, and a body movement signal; Preprocessing the multimodal signal to obtain multimodal features of the test object; Calculating and obtaining multiple types of sleep analysis parameters of the test subject based on the multimodal features; For each threshold interval to which the sleep analysis parameter belongs, the corresponding sleep score coefficient is calculated; wherein each threshold interval corresponds to a sleep score coefficient; the sleep score coefficient corresponding to the nth threshold interval is Each of the threshold intervals includes m sleep analysis parameter values, where m is a preset positive integer greater than 1; i represents the i-th sleep analysis parameter value, i is a positive integer greater than or equal to 1 and less than or equal to m; x low Indicates the lower limit of the sleep analysis parameter, x high Indicates the upper limit of sleep analysis parameters; y high Indicates the upper limit value x of the sleep analysis parameter high The corresponding sleep score coefficient, α j represents the influencing factor of the preset j-th sleep analysis parameter, y basic A base number representing a preset sleep score coefficient; Calculate and obtain the sleep quality analysis value of the test subject based on the multiple types of sleep score coefficients; The sleep quality analysis value of the test subject is obtained by calculating the sleep score coefficients of the multiple types. in represents a continuous multiplication operation, J represents the total number of types of the sleep score coefficients of the test subject, j represents the jth sleep score coefficient, and j is a positive integer greater than or equal to 1 and less than or equal to J; y j represents the jth sleep score coefficient, β age Indicates the preset age coefficient.

2. The sleep quality analysis method according to claim 1, characterized in that: For each threshold interval, the n =x high +n(n-1)ω / 2Calculated y n As y basic Based on The calculated sleep score coefficients for each threshold interval are n =x high +n(n-1)ω / 2 is corrected by the attenuation coefficient ω.

3. The sleep quality analysis method according to claim 1, characterized in that: It also includes presetting a mapping relationship between the threshold interval to which the sleep analysis parameter belongs and the single sleep quality rating, and obtaining the single sleep quality rating corresponding to each sleep analysis parameter based on the mapping relationship.

4. The sleep quality analysis method according to claim 1, characterized in that: Preprocessing the multimodal signal to obtain the multimodal features of the test object includes the following steps: Acquire the sleep stages and micro-arousal events of the test subject based on the EEG signal; acquiring the pulse oxygen saturation of the test subject based on the pulse signal; Acquiring a body motion change characteristic of the test subject based on the body motion signal; The sleep staging, the micro-arousal events, the pulse blood oxygen saturation and the body movement change characteristics are used as the multimodal features.

5. The sleep quality analysis method according to claim 4, characterized in that: Acquiring the sleep staging and micro-arousal events of the test subject based on the EEG signal includes: filtering and segmenting the EEG signal, and acquiring the sleep staging and micro-arousal events corresponding to the EEG signal after filtering and segmenting based on a machine learning algorithm; Acquiring the pulse oxygen saturation of the test subject based on the pulse signal includes: acquiring the pulse oxygen saturation based on the absorbance ratio of oxygenated hemoglobin and reduced hemoglobin in the pulse signal; Acquiring the body motion change characteristics of the test object based on the body motion signal includes: filtering the collected acceleration signal and angular acceleration signal of the test object, extracting body motion parameters based on the filtered acceleration signal and angular acceleration signal, and acquiring the body motion change characteristics corresponding to the body motion parameters based on a regression analysis model.

6. The sleep quality analysis method according to claim 4, characterized in that: Calculating and obtaining multiple types of sleep analysis parameters of the test subject based on the multimodal features comprises the following steps: The total sleep time TST is calculated according to TST=REM+N1+N2+N3, where REM represents the duration of the rapid eye movement period in the sleep stage, and N1, N2 and N3 represent the duration of the N1 stage, N2 stage and N3 stage of the non-rapid eye movement period in the sleep stage respectively; Sleep efficiency SE was calculated according to SE = (TST / TRT) × 100%, where TRT represents the total time with sleep intention; The number of awakenings nWASO was determined based on the total number of WASO events above the threshold, where WASO events represent events during sleep that transition from sleep to awakening; according to The total wakefulness time WASO is calculated, where WASOg represents the duration of the g-th wakefulness during sleep; g is a positive integer greater than or equal to 1 and less than or equal to G; G is nWASO; The time required to fall asleep after having the intention to sleep was calculated as the sleep latency. The Arousal Index is calculated according to Arousal Index = (nArousal / TST) × 60, where nArousal represents the number of micro-arousals; The oxygen depletion index is calculated according to ODI = (total number of events below the threshold / TST) × 60, where the total number of events below the threshold represents the number of times the blood oxygen level drops by more than a preset ratio per hour of sleep during sleep; The body movement index PLMI is calculated according to PLMI = (total number of body movement events above the threshold / TST) × 60, where the total number of body movement events above the threshold represents the number of times the body turns above the threshold per hour of sleep during sleep; The total sleep time, the sleep efficiency, the number of awakenings, the total awakening time, the sleep latency, the micro-arousal index, the oxygen depletion index and the body movement index are used as the sleep analysis parameters.

7. A sleep quality analysis system, characterized in that: The system comprises an acquisition module, a preprocessing module, a first calculation module, a second calculation module and an analysis module; The acquisition module is configured to acquire multimodal signals of the test subject when sleeping; the multimodal signals include EEG signals, pulse signals and body movement signals; The preprocessing module is configured to preprocess the multimodal signal to obtain the multimodal features of the test object; The first calculation module is configured to calculate and obtain multiple types of sleep analysis parameters of the test subject based on the multimodal features; The second calculation module is configured to calculate the corresponding sleep score coefficient for each threshold interval to which the sleep analysis parameter belongs; wherein each threshold interval corresponds to a sleep score coefficient; the sleep score coefficient corresponding to the nth threshold interval is Each of the threshold intervals includes m sleep analysis parameter values, where m is a preset positive integer greater than 1; i represents the i-th sleep analysis parameter value, i is a positive integer greater than or equal to 1 and less than or equal to m; x low Indicates the lower limit of the sleep analysis parameter, x high Indicates the upper limit of sleep analysis parameters; y high Indicates the upper limit value x of the sleep analysis parameter high The corresponding sleep score coefficient, α j represents the influencing factor of the preset j-th sleep analysis parameter, y basic A base number representing a preset sleep score coefficient; The analysis module is configured to calculate and obtain a sleep quality analysis value of the test subject based on a plurality of types of sleep score coefficients; The sleep quality analysis value of the test subject is obtained by calculating the sleep score coefficients of the multiple types. in represents a continuous multiplication operation, J represents the total number of types of the sleep score coefficients of the test subject, j represents the jth sleep score coefficient, and j is a positive integer greater than or equal to 1 and less than or equal to J; y j represents the jth sleep score coefficient, β age Indicates the preset age coefficient.

8. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the sleep quality analysis method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: include: Processor and memory; The memory is configured to store a computer program; The processor is configured to execute the computer program stored in the memory, so as to enable the electronic device to perform the sleep quality analysis method according to any one of claims 1 to 6.

Images