Sleep breathing trend detection and auxiliary adjustment method, system and device

Abstract

According to the sleep breathing trend detection and auxiliary adjustment method, system and device, sleep breathing dynamics trend signals are recognized and extracted, and scientific quantitative evaluation of sleep breathing trend behaviors is achieved through sleep breathing dynamics trend characteristics, sleep breathing trend intensity and a sleep breathing trend intensity curve; the sleep breathing trend auxiliary regulation strategy is generated and sent to the sleep breathing regulation and control equipment by predicting and analyzing the sleep state and the sleep breathing trend behavior of the user, so that the efficiency of the sleep breathing regulation and control equipment can be dynamically optimized and improved; finally, personalized, accurate and dynamic auxiliary adjustment of the sleep breathing trend of the user is realized through detection quantification of the sleep breathing trend and generation of a dynamic strategy, and the sleep quality of the user can be improved.

Description

Technical Field

[0001] The present invention relates to the field of sleep breathing detection evaluation and auxiliary regulation, and in particular to a sleep breathing trend detection and auxiliary regulation method, system and device. Background Art

[0002] Breathing is the most basic need for humans to maintain normal physiological functions. Human breathing behavior is rhythmic, a cyclical process of inhaling oxygen and exhaling carbon dioxide. In various states such as different intensity exercises, different resting states, and different sleep periods, the depth, intensity, and breathing patterns of human breathing are different, and the baseline and trend of the depth and intensity are also different. In the awake states such as exercise and rest, the strong autonomic nervous regulation ability and the autonomous conscious behavior of the human body can regulate breathing behavior well; while in sleep, people lack autonomous consciousness, and the entire respiratory behavior regulation ability is heavily dependent on the basic functional state ability of the physiological organs, and is also affected by the sleeping position, sleeping environment, etc.; the baseline or trend of the depth and intensity of sleep breathing is an important measure of the basic and long-term functional state ability of respiratory-related physiological organs.

[0003] At present, the technical solutions for sleep breathing behavior detection and evaluation are mainly focused on respiratory event detection and statistical analysis, lacking a clear definition or quantification of the baseline of sleep breathing depth and intensity, sleep breathing trend regularity behavior, trend intensity and trend behavior development. In addition, existing sleep breathing control devices are usually separated from sleep breathing detection devices. Most sleep breathing control devices can be connected to the Internet to feedback control parameters but still use offline preset program control to complete device feedback control, and cannot complete the user's sleep breathing trend regularity, personalized and accurate dynamic auxiliary adjustment according to the user's real-time breathing status.

[0004] The prior art solution CN117338250A discloses a vital sign detection method based on millimeter wave radar and a sleep monitoring method thereof. The vital sign detection and sleep monitoring system proposed in the present invention performs information sensing based on millimeter wave radar, and can perform relevant processing on the collected radar signals through the millimeter wave radar placed at the side, obliquely above, directly above, etc. of the object to be measured, and completes the extraction and collection of characteristic information such as breathing, heartbeat, and limb movements of the object to be measured. The vital sign algorithm used in the extraction can effectively remove static clutter and dynamic clutter interference in the detection, improve the accuracy and robustness of the algorithm, and then establish an efficient sleep staging and sleep quality assessment model based on accurate vital sign data, realize the recognition of the four sleep stages of wakefulness, light sleep, deep sleep, and rapid eye movement sleep, and the analysis and judgment of sleep quality, and improve the accuracy of the assessment. Similarly, the applicant's prior application CN116392085A provides a method for quantifying and regulating sleep stability based on trend analysis, including: collecting, monitoring, processing, feature analysis and phase identification of the user's physiological state during sleep to obtain a sleep depth characteristic curve and a sleep staging curve; selecting a window scale and a fitting method according to the characteristics of the sleep depth characteristic curve and performing a detrending analysis on it, reversely extracting trend components, and extracting a sleep trend characteristic curve; dynamically calculating and extracting a sleep trend index, a phase trend correlation coefficient, and a phase trend distribution characteristic based on the sleep staging curve, the sleep depth characteristic curve, and the sleep trend characteristic curve; establishing and dynamically updating a user's personalized sleep trend database, dynamically predicting, intervening, regulating, and evaluating the effects of the user's sleep behavior, dynamically updating the database, and optimizing the regulation strategy. From the above, it can be seen that the existing technical solution CN117338250A realizes sleep quality assessment through signal collection and feature analysis of breathing, heartbeat, limb movements, etc., while the prior application technical solution CN116392085A realizes sleep stabilization characteristic assessment and intervention regulation through recognition, extraction, feature analysis and dynamic prediction of sleep depth characteristic curves; the above two technical solutions are focused on the assessment or intervention of broadly defined sleep quality, but lack a scientific and in-depth integrated technical solution for the detection and intervention of the user's sleep breathing physiological process; the above two technical solutions, both of which do not observe and analyze the sleep breathing dynamics process from the perspective of sleep breathing dynamics, extract sleep breathing dynamics signals and further deeply quantify and analyze the characteristics of the sleep breathing physiological changes in different sleeping positions, sleep phases and sleep breathing dynamics states, thereby failing to achieve targeted, accurate assessment and dynamic intervention of the sleep breathing process.

[0005] From the above, we can see that how to scientifically and comprehensively detect, analyze and quantitatively evaluate the sleep respiratory dynamics process and basic trend direction, sleep respiratory trend behavior and trend intensity, and further optimize the operation control of sleep respiratory regulation equipment to achieve personalized, precise and dynamic auxiliary adjustment of the user's sleep respiratory trend and improve the user's sleep quality are issues that need to be further addressed in current domestic and foreign product technical solutions and actual application scenarios. Summary of the invention

[0006] In view of the above defects and improvement needs of the existing methods, the purpose of the present invention is to provide a sleep breathing trend detection and auxiliary adjustment method, collect and obtain sleep respiratory dynamics signals and adjust the amplitude according to the user's sleeping position information, further decompose the signal to obtain the sleep respiratory dynamics trend signal, extract the sleep respiratory dynamics trend characteristics and trend strength; predict and analyze the user's sleep state and sleep respiratory trend behavior, generate a sleep respiratory trend auxiliary adjustment strategy and send it to the sleep respiratory control device, so as to realize dynamic auxiliary adjustment of the user's sleep breathing. The present invention also provides a sleep respiratory trend detection and auxiliary adjustment system for realizing the above method. The present invention also provides a sleep respiratory trend detection and auxiliary adjustment device for realizing the above system.

[0007] According to the purpose of the present invention, the present invention proposes a sleep breathing trend detection and auxiliary adjustment method, comprising the following steps:

[0008] Collecting and obtaining the user's sleep breathing behavior and sleep position information to obtain a first sleep breathing signal;

[0009] According to the sleeping position signal, performing signal processing and amplitude adjustment on the first sleeping breathing signal to obtain a second sleeping breathing signal;

[0010] Performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to obtain a sleep respiratory dynamics trend signal and obtaining a sleep respiratory dynamics trend feature through signal feature analysis;

[0011] Predict and analyze the user's sleeping position, the sleep respiratory dynamics trend signal, and the sleep respiratory dynamics trend characteristics, and generate a sleep respiratory trend auxiliary adjustment strategy in combination with a sleep respiratory knowledge base and push it to a sleep respiratory adjustment device;

[0012] Generate and output sleep breathing trend detection and auxiliary adjustment reports according to the preset report cycle.

[0013] More preferably, the specific step of collecting and acquiring the sleep breathing behavior signal and sleep position information of the user during sleep to obtain the first sleep breathing signal also includes:

[0014] Monitor and collect the user's sleep breathing physiological behavior to obtain sleep breathing physiological signals;

[0015] Monitor and collect the user's sleeping position information to obtain a sleeping position signal;

[0016] The sleep breathing physiological signal and the sleep body position signal are aggregated to obtain the first sleep breathing signal.

[0017] More preferably, the first sleep breathing signal includes at least the sleep breathing physiological signal and the sleep position signal; wherein, the sleep breathing physiological signal includes at least any one of an oral and nasal temperature monitoring signal, a nasal pressure monitoring signal, an oral and nasal CO2 monitoring signal, a chest and abdominal respiratory movement signal, an electrocardiogram-derived respiratory signal, and a throat electromyographic signal, and the sleep position signal includes at least a sleeping direction signal and a sleeping angle signal.

[0018] More preferably, the specific step of performing signal processing and amplitude adjustment on the first sleep breathing signal according to the sleep position signal to obtain the second sleep breathing signal further includes:

[0019] Performing signal processing on the first sleep breathing signal to obtain a sleep breathing dynamics signal;

[0020] The amplitude of the sleep respiratory dynamics signal is adjusted according to the sleep position signal to obtain the second sleep respiratory signal.

[0021] More preferably, the signal processing includes at least analog-to-digital conversion, resampling, re-referencing, artifact removal, signal correction, noise reduction, power frequency notch, low-pass filtering, high-pass filtering, band-pass filtering, mean filtering, smoothing and signal time window segmentation; wherein, the signal time window segmentation is specifically to perform continuous time window segmentation on the target signal with a preset length time window and a preset translation time step.

[0022] More preferably, the sleep respiratory dynamics signal is specifically a dynamic curve that describes the continuous strength changes of sleep breathing, including at least any one of the oral and nasal temperature dynamics signal, the nasal pressure dynamics signal, the oral and nasal CO2 dynamics signal, the chest and abdominal respiratory movement dynamics signal, the ECG-derived respiratory dynamics signal, and the pharyngeal electromyography dynamics signal.

[0023] More preferably, the amplitude adjustment is specifically to adjust the amplitude of the sleep respiratory dynamics signal according to a preset adjustment strategy in combination with the user's sleeping direction and sleeping angle, so as to achieve unified observation and analysis of sleep breathing behavior in different sleeping positions; wherein the preset adjustment strategy includes at least any one of constant coefficient correction, linear coefficient correction, and nonlinear coefficient correction.

[0024] More preferably, the specific steps of performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to obtain a sleep respiratory dynamics trend signal and obtaining a sleep respiratory dynamics trend feature through signal feature analysis also include:

[0025] Performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to extract the trend component of the signal to obtain the sleep respiratory dynamics trend signal;

[0026] Signal feature analysis is performed on the second sleep breathing signal and the sleep respiratory dynamics trend signal to obtain the sleep respiratory dynamics trend feature and extract the sleep respiratory trend intensity.

[0027] More preferably, the method of time series signal decomposition includes at least time series decomposition, empirical mode decomposition, variational mode decomposition, local mean decomposition, wavelet transform, wavelet packet transform, time-frequency transform, detrending analysis, principal component analysis, independent component analysis, waveform analysis and numerical fitting, and their evolutionary variants; the method of time-frequency analysis includes at least any one of time-frequency transform, time domain filtering and frequency domain filtering.

[0028] More preferably, the signal feature analysis includes at least numerical feature analysis, envelope feature analysis, time-frequency feature analysis, and nonlinear feature analysis; wherein the numerical features include at least mean value, root mean square, maximum value, minimum value, variance, standard deviation, coefficient of variation, kurtosis, and skewness, and the nonlinear features include at least entropy features, fractal features, and complexity features.

[0029] More preferably, the sleep respiratory dynamics trend feature specifically describes the signal baseline level or change trend direction of the sleep respiratory dynamics signal or sleep respiratory physiological behavior; the sleep respiratory dynamics trend feature at least includes the signal characteristics of the second sleep respiratory signal and the sleep respiratory dynamics trend signal, the sleep respiratory frequency and curve, the sleep respiratory trend intensity, and the sleep respiratory trend intensity curve.

[0030] More preferably, the method for extracting the sleep breathing trend intensity and the sleep breathing trend intensity curve is specifically as follows:

[0031] 1) determining a signal timing attribute (additive time series or multiplicative time series) of the second sleep breathing signal;

[0032] 2) determining a specific method of time series signal decomposition and / or time-frequency analysis according to the signal time series attribute, performing signal decomposition and / or time-frequency analysis on the second sleep respiratory signal in the current signal time window, extracting the trend component of the signal, and obtaining the sleep respiratory dynamics trend signal;

[0033] 3) performing signal feature analysis on the second sleep breathing signal and the sleep pneumodynamics trend signal to obtain a second sleep breathing signal feature and a sleep pneumodynamics trend signal feature, respectively;

[0034] 4) selecting a signal feature observation and analysis index, comparing relative changes in the signal features of the second sleep breathing signal feature and the sleep pneumodynamics trend signal feature, and obtaining a set of relative change values ​​of the sleep pneumodynamics trend feature;

[0035] 5) performing numerical combination calculation on the index parameters in the relative change value set of the sleep respiratory dynamics trend characteristics to obtain the sleep respiratory trend intensity of the current signal time window;

[0036] 6) Extracting the sleep breathing trend intensity of all signal time windows according to the time sequence to obtain the sleep breathing trend intensity curve.

[0037] More preferably, the sleep breathing trend intensity curve is specifically composed of the sleep breathing trend intensities in consecutive time windows in time sequence, describing the continuous change of the user's sleep breathing behavior trend state / intensity.

[0038] Preferably, the specific steps of predicting and analyzing the user's sleeping position, the sleep respiratory dynamics trend signal and the sleep respiratory dynamics trend characteristics, combining the sleep respiratory knowledge base, generating a sleep respiratory trend auxiliary adjustment strategy and pushing it to the sleep respiratory adjustment device also include:

[0039] Performing prediction analysis on the sleep position signal and the sleep respiratory dynamics trend signal to obtain a sleep position prediction signal and a sleep respiratory dynamics trend prediction signal respectively, and generating a sleep respiratory state description prediction signal;

[0040] Performing prediction analysis on key trend features in the sleep respiratory dynamics trend features to obtain a sleep respiratory dynamics trend feature prediction signal;

[0041] Generate the sleep breathing trend auxiliary adjustment strategy according to the sleep breathing state description prediction signal and the sleep breathing dynamics trend feature prediction signal, combined with the user's sleep breathing history database and the sleep breathing knowledge base;

[0042] The sleep breathing trend auxiliary adjustment strategy is sent to the sleep breathing adjustment device through the signal interface, and the control execution of the sleep breathing adjustment device is optimized to achieve dynamic auxiliary adjustment of the user's sleep breathing trend.

[0043] More preferably, the predictive analysis includes at least any one of exponential smoothing, Holt-Winters method, AR, MA, ARMA, ARIMA, SARIMA, SARIMAX, VAR, VARMA, VARMAX, and machine learning.

[0044] More preferably, the user sleep breathing history database is specifically a user-personalized sleep breathing database, which is used to continuously record and optimize the user's individual sleep breathing behavior and characteristic changes, and at least includes the user's basic physiological health information, the detection and quantification process method, the first sleep breathing signal, the second sleep breathing signal, the sleep breathing dynamics trend signal, the sleep breathing dynamics trend characteristic, the sleep breathing state description prediction signal, the strategy generation process method, and the sleep breathing trend auxiliary adjustment strategy; the sleep breathing knowledge base mainly comes from the knowledge and experience of health management and clinical medicine related to sleep breathing, and at least includes sleep breathing patterns, common sleep breathing event characteristics, and commonly used sleep breathing adjustment methods, namely, scene intervention parameter guidance.

[0045] More preferably, the sleep breathing trend auxiliary adjustment strategy includes at least a target adjustment value for sleep breathing frequency, a target adjustment value for sleep breathing intensity, an adjustment method, an adjustment time point, a duration and device control parameters, wherein the adjustment method includes at least off-body, contact and invasive methods; the sleep breathing adjustment device includes at least any one of a ventilator, a smart mattress, an odor stimulation device, an electrical stimulation device, a tactile stimulation device and a CO2 concentration control device.

[0046] Preferably, the specific steps of generating and outputting the sleep breathing trend detection and auxiliary adjustment report according to the preset report cycle also include:

[0047] Generate the sleep breathing trend detection and auxiliary adjustment report according to a preset report cycle;

[0048] According to the user scenario requirements, the sleep breathing trend detection and auxiliary adjustment report is output.

[0049] More preferably, the sleep breathing trend detection and auxiliary adjustment report at least includes the sleep breathing trend intensity curve, the sleep breathing trend auxiliary adjustment strategy, the sleep breathing summary, and the user's sleep behavior health suggestions.

[0050] According to the purpose of the present invention, the present invention proposes a sleep breathing trend detection and auxiliary regulation system, including the following modules:

[0051] A breathing behavior detection module is used to collect and obtain the user's sleep breathing behavior and sleep position information to obtain a first sleep breathing signal;

[0052] A respiratory dynamics analysis module, configured to perform signal processing and amplitude adjustment on the first sleep respiratory signal according to the sleep position signal to obtain a second sleep respiratory signal;

[0053] A respiratory trend analysis module, used for performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to obtain a sleep respiratory dynamics trend signal and obtain a sleep respiratory dynamics trend feature through signal feature analysis;

[0054] A breathing assistance adjustment module is used to predict and analyze the user's sleeping position, the sleep breathing dynamics trend signal and the sleep breathing dynamics trend characteristics, and generate a sleep breathing trend assistance adjustment strategy in combination with a sleep breathing knowledge base and push it to the sleep breathing adjustment device;

[0055] A user report management module, used to generate and output sleep breathing trend detection and auxiliary adjustment reports according to a preset report cycle;

[0056] The data operation management module is used for visual display, storage backup and operation management of all process data of the system.

[0057] Preferably, the breathing behavior detection module further includes the following functional units:

[0058] A respiratory physiological monitoring unit is used to monitor and collect the user's sleep respiratory physiological behavior to obtain sleep respiratory physiological signals;

[0059] A sleeping position monitoring unit is used to monitor and collect the user's sleeping position information to obtain a sleeping position signal;

[0060] The sleep signal collection unit is used to collect the sleep breathing physiological signal and the sleep body position signal to obtain the first sleep breathing signal.

[0061] Preferably, the respiratory dynamics analysis module further includes the following functional units:

[0062] A signal processing and analysis unit, configured to perform signal processing on the first sleep breathing signal to obtain a sleep breathing dynamics signal;

[0063] The signal amplitude adjustment unit is used to adjust the amplitude of the sleep respiratory dynamics signal according to the sleep position signal to obtain the second sleep respiratory signal.

[0064] Preferably, the respiratory trend analysis module further includes the following functional units:

[0065] A time series signal decomposition unit, used for performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal, extracting the trend component of the signal, and obtaining the sleep respiratory dynamics trend signal;

[0066] The trend strength analysis unit is used to perform signal feature analysis on the second sleep breathing signal and the sleep respiratory dynamics trend signal to obtain the sleep respiratory dynamics trend feature and extract the sleep respiratory trend strength.

[0067] Preferably, the breathing assistance adjustment module further includes the following functional units:

[0068] A trend state prediction unit, used for predicting and analyzing the sleep position signal and the sleep respiratory dynamics trend signal, obtaining a sleep position prediction signal and a sleep respiratory dynamics trend prediction signal respectively, and generating a sleep respiratory state description prediction signal;

[0069] A trend feature prediction unit, used for predicting and analyzing the key trend features in the sleep respiratory dynamics trend features to obtain a sleep respiratory dynamics trend feature prediction signal;

[0070] An auxiliary strategy generating unit, configured to generate the sleep breathing trend auxiliary adjustment strategy according to the sleep breathing state description prediction signal and the sleep breathing dynamics trend characteristic prediction signal, in combination with a user sleep breathing history database and a sleep breathing knowledge base;

[0071] The auxiliary strategy pushing unit is used to send the sleep breathing trend auxiliary adjustment strategy to the sleep breathing adjustment device through the signal interface, optimize the control execution of the sleep breathing adjustment device, so as to realize the dynamic auxiliary adjustment of the user's sleep breathing trend.

[0072] Preferably, the user report management module further includes the following functional units:

[0073] A user report generating unit, used for generating the sleep breathing trend detection and auxiliary adjustment report according to a preset report cycle;

[0074] The user report output unit is used to output the sleep breathing trend detection and auxiliary adjustment report according to user scenario requirements.

[0075] Preferably, the data operation management module further includes the following functional units:

[0076] User information management unit, used for registration, input, editing, query, output and deletion of user basic information;

[0077] A data visualization management unit, used for visual display and management of all data in the system;

[0078] The data operation management unit is used to store, back up, migrate and export all data in the system.

[0079] According to the purpose of the present invention, the present invention proposes a sleep breathing trend detection and auxiliary regulation device, including the following modules:

[0080] A breathing behavior detection module is used to collect and obtain the user's sleep breathing behavior and sleep position information to obtain a first sleep breathing signal;

[0081] A respiratory dynamics analysis module, configured to perform signal processing and amplitude adjustment on the first sleep respiratory signal according to the sleep position signal to obtain a second sleep respiratory signal;

[0082] A respiratory trend analysis module, used for performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to obtain a sleep respiratory dynamics trend signal and obtain a sleep respiratory dynamics trend feature through signal feature analysis;

[0083] A breathing assistance adjustment module is used to predict and analyze the user's sleeping position and the sleep breathing dynamics trend signal, and generate a sleep breathing trend assistance adjustment strategy in combination with a sleep breathing knowledge base and push it to the sleep breathing adjustment device;

[0084] User report management module, used to generate and output sleep breathing trend detection and auxiliary adjustment reports according to the preset report cycle;

[0085] The data operation management module is used for visual display, storage backup and operation management of all process data and / or result data in the device.

[0086] The present invention provides a sleep breathing trend detection and auxiliary adjustment method, system and device, creatively extracts the recognition and extraction process of the sleep breathing dynamics trend signal, and realizes the scientific quantitative evaluation of the sleep breathing trend behavior through the sleep breathing dynamics trend characteristics, sleep breathing trend intensity and sleep breathing trend intensity curve; in addition, the user's sleep state and sleep breathing trend behavior are predicted and analyzed, and the sleep breathing trend auxiliary adjustment strategy is generated and sent to the sleep breathing regulation device, which can dynamically optimize and improve the efficiency and effectiveness of the sleep breathing regulation device; finally, through the pioneering sleep breathing trend detection quantification and dynamic strategy generation, the personalized, precise and dynamic auxiliary adjustment of the user's sleep breathing trend is realized, which can improve the user's sleep quality. In actual application scenarios, the sleep breathing-related detection and adjustment systems or devices can be integrated in whole or in part with the technical points or functions provided by the technical solution of the present invention to better meet the needs of different user service scenarios.

[0087] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0089] Figure 1 It is a schematic diagram of the process steps of a sleep breathing trend detection and auxiliary adjustment method provided by an embodiment of the present invention;

[0090] Figure 2 This is a schematic diagram of the module composition of a sleep breathing trend detection and auxiliary regulation system provided by an embodiment of the present invention;

[0091] Figure 3 It is a schematic diagram of the module structure of a sleep breathing trend detection and auxiliary regulation device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0092] In order to more clearly illustrate the purpose and technical solution of the present invention, the present invention will be further described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, rather than all of the embodiments. Without creative work, other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention should all belong to the protection scope of the present invention. It should be noted that, in the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other arbitrarily.

[0093] The applicant found that, firstly, the sleep breathing behavior of normal and healthy people has a very good, body position-related, alternating trend of depth and shallowness, which is a relatively stable physiological process. However, this trend is easily affected by the user's sleeping position. Different degrees of diastolic compression of the upper airway and chest and abdominal cavity will directly lead to changes in the amplitude and depth of sleep breathing, which in turn leads to oscillation drift of the relative trend stability of sleep breathing behavior related to the sleeping position; secondly, the respiratory movement behavior information of the mouth, nose, chest and abdomen is the most direct and accurate expression of breathing. The change curves of signals such as pressure, tidal volume, CO2 concentration, temperature, and skin electricity all have very good sleep breathing dynamics characteristics, and can accurately depict the alternating patterns, changes in strength, and trend behaviors of sleep breathing; finally, according to the trend analysis of sleep phases, sleeping positions and sleep breathing dynamics, a better sleep breathing trend behavior auxiliary adjustment strategy can be generated, which can be linked with existing sleep breathing adjustment equipment to ensure or restore the trend of the user's sleep breathing.

[0094] Therefore, the technical solution of the present invention also creatively proposes a detection and quantification implementation path for the trend characteristics of sleep respiratory dynamics and the intensity of sleep respiratory trend. By decomposing the sleep respiratory signal, identifying and extracting the characteristics and intensity of the trend component signal, a scientific and comprehensive quantitative evaluation of the sleep respiratory trend is achieved. Through predictive analysis, predictive analysis of the sleep respiratory trend signal and sleep state and real-time generation of sleep respiratory trend auxiliary adjustment strategy are completed, thereby realizing the integration of scientific detection and evaluation of the user's sleep respiratory trend and dynamic auxiliary adjustment, and efficiently assisting the user's sleep breathing.

[0095] Combination Figure 1 As shown, a sleep breathing trend detection and auxiliary adjustment method provided by an embodiment of the present invention includes the following steps:

[0096] P100: Collect and obtain the user's sleep breathing behavior and sleep position information to obtain a first sleep breathing signal.

[0097] In actual application scenarios, the first sleep breathing signal includes at least a sleep breathing physiological signal and a sleep position signal; wherein the sleep breathing physiological signal includes at least one of an oral and nasal temperature monitoring signal, a nasal pressure monitoring signal, an oral and nasal CO2 monitoring signal, a chest and abdominal respiratory movement signal, an ECG-derived respiratory signal, and a throat electromyographic signal, and the sleep position signal includes at least a sleeping direction signal and a sleeping angle signal.

[0098] The first step is to monitor and collect the user's sleep breathing physiological behavior to obtain sleep breathing physiological signals.

[0099] In this embodiment, chest and abdomen respiratory movement signals are collected to monitor the user's sleep respiratory physiological behavior, and the specific implementation process of the present invention is described. The user's chest and abdomen sleep respiratory movement is collected through an impedance sensor chest and abdomen belt, with a sampling rate of 128Hz, divided into a chest belt and an abdomen belt, to obtain sleep respiratory physiological signals.

[0100] The second step is to monitor and collect the user's sleeping position information to obtain a sleeping position signal.

[0101] In this embodiment, the user's sleeping position information is specifically obtained by monitoring, recording and posture recognition using a gyroscope acceleration sensor. The acceleration signal of the forehead center Fpz and the upper right chest is collected by a wireless three-axis gyroscope sensor patch device with a sampling rate of 64Hz, and the sleeping position acceleration signal is recorded to obtain the sleeping position signal.

[0102] The third step is to collect the sleep breathing physiological signal and the sleep position signal to obtain the first sleep breathing signal.

[0103] In this embodiment, the first sleep breathing signal includes a chest and abdomen breathing movement signal and a sleep body position acceleration signal.

[0104] P200: According to the sleeping position signal, the first sleeping breathing signal is processed and the amplitude is adjusted to obtain a second sleeping breathing signal.

[0105] The first step is to process the first sleep breathing signal to obtain a sleep breathing dynamics signal.

[0106] In actual application scenarios, signal processing includes at least analog-to-digital conversion, resampling, re-referencing, artifact removal, signal correction, noise reduction, power frequency notch, low-pass filtering, high-pass filtering, band-pass filtering, mean filtering, smoothing and signal time window segmentation; among which, signal time window segmentation is to perform continuous time window segmentation on the target signal with a preset length time window and a preset translation time step. Select the corresponding signal processing method according to the type of sleep breathing physiological signal and application needs.

[0107] In actual application scenarios, the sleep respiratory dynamics signal is specifically a dynamic curve that describes the continuous changes in the strength of sleep breathing, including at least any one of the oral and nasal temperature dynamics signal, nasal pressure dynamics signal, oral and nasal CO2 dynamics signal, chest and abdominal respiratory movement dynamics signal, ECG-derived respiratory dynamics signal, and laryngeal electromyography dynamics signal.

[0108] In this embodiment, the respiratory movement signals of the chest belt and the abdominal belt are added and fused into a thoracic and abdominal respiratory movement signal, and the thoracic and abdominal respiratory movement signal obtained after the fusion is subjected to basic signal processing such as analog-to-digital conversion, artifact removal, signal correction, wavelet denoising, DC removal high-pass filtering, and signal time window segmentation to obtain a sleep respiratory dynamics signal composed of multiple time window signals based on the thoracic and abdominal respiratory movement signals.

[0109] The second step is to adjust the amplitude of the sleep breathing dynamics signal according to the sleep position signal to obtain a second sleep breathing signal.

[0110] In this embodiment, the sleep position acceleration signal is subjected to basic signal processing such as resampling, artifact removal, signal correction, 4Hz low-pass filtering, and signal time window segmentation, and the sleep position characteristic information is further extracted, including sleeping direction / position direction, sleeping angle / position amplitude, and finally the user's sleep position information of multiple continuous time windows. In actual application scenarios, in addition to collecting and analyzing information, the user's sleep position information can also be directly obtained through a third-party interface or product service. It is worth noting that the 64Hz sleep position acceleration signal needs to be resampled to 128Hz so that the sleep position acceleration signal has the same length as the sleep chest and abdominal breathing movement signal, which is convenient for subsequent amplitude adjustment applications.

[0111] In this embodiment, the amplitude adjustment is specifically to adjust the amplitude of the sleep respiratory dynamics signal according to a preset adjustment strategy in combination with the user's sleeping direction and sleeping angle, thereby achieving unified observation and analysis of sleep respiratory behaviors in different sleeping positions.

[0112] In this embodiment, according to the basic properties of the chest and abdominal respiratory motion signal, a constant coefficient correction is selected as the amplitude adjustment strategy, and the sleep position correction coefficients of different body positions and body position amplitudes are obtained to adjust the amplitude of the sleep respiratory dynamics signal to obtain a second sleep respiratory signal. In this embodiment, an angle-related constant coefficient strategy is used, regardless of the direction, and only the coefficient of the supine 0° angle is 0.5 and the coefficient of the prone 180° angle is 1.0, and a linear constant correction is performed. By obtaining the different sleeping posture angles of the user, the correction coefficient is directly converted.

[0113] In actual application scenarios, the amplitude of the sleep respiratory dynamics signal is adjusted according to the sleep position information such as body direction, body position amplitude and the preset sleep position correction coefficient, so as to correct the fluctuation of the user's sleep breathing behavior caused by the sleep position. Generally, the larger the body position amplitude, the greater the pressure on the upper airway, chest and abdominal cavity and heart area, the greater the impact on the sleep respiratory dynamics signal, and the greater the sleep position correction coefficient. In addition, the preset adjustment strategy includes at least one of the constant coefficient correction, linear coefficient correction and nonlinear coefficient correction.

[0114] P300: performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to obtain a sleep respiratory dynamics trend signal and obtaining a sleep respiratory dynamics trend feature through signal feature analysis.

[0115] The first step is to perform time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal, extract the trend component of the signal, and obtain a sleep respiratory dynamics trend signal.

[0116] In this embodiment, the method of time series signal decomposition includes at least time series decomposition, empirical mode decomposition, variational mode decomposition, local mean decomposition, wavelet transform, wavelet packet transform, time-frequency transform, detrending analysis, principal component analysis, independent component analysis, waveform analysis and numerical fitting, and their evolutionary variants. The method of time-frequency analysis includes at least any one of time-frequency transform, time domain filtering and frequency domain filtering.

[0117] In actual application scenarios, the classic decomposition methods in time series decomposition (divided into additive model decomposition algorithm and multiplicative model decomposition algorithm), X11 decomposition method, SEATS decomposition, STL decomposition and other methods can directly decompose the target signal into seasonal component, trend component and remainder component; while basic algorithms such as empirical mode decomposition, variational mode decomposition, local mean decomposition, wavelet transform, wavelet packet transform, time-frequency transform, detrending analysis, principal component analysis, independent component analysis, waveform analysis and numerical fitting and their evolutionary variants can decompose the signal into multiple analytical signals. Each analytical signal needs to be further judged by time-frequency analysis, and finally the analytical signals that meet the threshold requirements are synthesized to obtain the periodic component, trend component and residual component respectively.

[0118] It is particularly pointed out that in actual application scenarios, the detrending analysis DFA method and its upgraded variant methods can also quickly extract trend components and non-trend components in the target signal.

[0119] In this embodiment, according to the source attribute of the second sleep breathing signal (thoracic and abdominal respiratory movement signal, which is an additive time series), the additive model decomposition algorithm in the classical decomposition method is selected to perform time series signal decomposition on the second sleep breathing signal, extract the trend component of the signal, and obtain the sleep respiratory dynamics trend signal.

[0120] In actual application scenarios, the sleep breathing frequency range of normal healthy people corresponding to the current user can be easily converted into times per second to obtain the upper and lower frequency limits in time-frequency analysis; the lower frequency limit can usually be used as the dividing line between trend components and periodic components, and the upper frequency limit can usually be used as the dividing line between residual components and periodic components. In addition, more signal decomposition methods can be used to add time-frequency analysis to achieve component extraction of the second sleep breathing signal.

[0121] The second step is to perform signal feature analysis on the second sleep breathing signal and the sleep respiratory dynamics trend signal to obtain the sleep respiratory dynamics trend feature and extract the sleep breathing trend intensity.

[0122] In this embodiment, the signal feature analysis includes at least numerical feature analysis, envelope feature analysis, time-frequency feature analysis, and nonlinear feature analysis; wherein the numerical features include at least mean value, root mean square, maximum value, minimum value, variance, standard deviation, coefficient of variation, kurtosis, and skewness, and the nonlinear features include at least entropy features, fractal features, and complexity features.

[0123] In this embodiment, the sleep respiratory dynamics trend characteristics at least include signal characteristics of the second sleep respiratory signal and the sleep respiratory dynamics trend signal, sleep respiratory frequency and curve, sleep respiratory trend intensity, and sleep respiratory trend intensity curve.

[0124] In this embodiment, the method for extracting the sleep breathing trend intensity is specifically as follows:

[0125] 1) determining a signal timing attribute (additive time series or multiplicative time series) of the second sleep breathing signal;

[0126] 2) Determine a specific method of time series signal decomposition and / or time-frequency analysis according to the signal time series attribute, perform signal decomposition and / or time-frequency analysis on the second sleep respiratory signal in the current signal time window, extract the trend component of the signal, and obtain a sleep respiratory dynamics trend signal;

[0127] 3) performing signal feature analysis on the second sleep breathing signal and the sleep respiratory dynamics trend signal to obtain the second sleep breathing signal feature and the sleep respiratory dynamics trend signal feature respectively;

[0128] 4) selecting a signal feature observation and analysis index, comparing the relative changes of the signal features in the second sleep breathing signal feature and the sleep pneumodynamics trend signal feature, and obtaining a relative change value set of the sleep pneumodynamics trend feature;

[0129] 5) Performing numerical combination calculation on the index parameters in the relative change value set of the sleep breathing dynamics trend characteristics to obtain the sleep breathing trend intensity of the current signal time window;

[0130] 6) According to the time sequence, the sleep breathing trend intensity of all signal time windows is extracted to obtain a sleep breathing trend intensity curve.

[0131] In actual application scenarios, the average value, root mean square, maximum value and other numerical characteristics of the sleep respiratory dynamics trend signal can well reflect the trend behavior characteristics of sleep respiratory dynamics, while the sleep respiratory trend intensity as a comprehensive observation and analysis indicator is more representative of statistical analysis and research tracking. According to different sources of sleep respiratory signals and different user scenario requirements, quantitative calculation of multiple sleep respiratory trend intensities can be achieved.

[0132] The first calculation formula for sleep breathing trend intensity is:

[0133]

[0134] The second calculation formula for sleep breathing trend intensity is:

[0135]

[0136] Among them, BHT t is the intensity of sleep breathing trend and 0≤BHT t ≤1, Var() is the variance operator, T t , D t They are respectively the sleep respiratory dynamics trend signal and the second sleep respiratory signal, K td is the signal source correction coefficient of the second sleep breathing signal and is 0 <K td ≤1, max() is the maximum value operator, mean() is the mean value operator, and |||| is the absolute value operator.

[0137] In this embodiment, the sleep breathing trend intensity curve specifically comprises sleep breathing trend intensities in consecutive time windows in time sequence, and describes the continuous change of the trend state / intensity of the user's sleep breathing behavior.

[0138] P400: Predictively analyze the user's sleeping position, the sleep respiratory dynamics trend signal, and the sleep respiratory dynamics trend characteristics, and generate a sleep respiratory trend auxiliary adjustment strategy in combination with a sleep respiratory knowledge base and push it to a sleep respiratory adjustment device.

[0139] The first step is to perform predictive analysis on the sleep position signal and the sleep respiratory dynamics trend signal, obtain the sleep position prediction signal and the sleep respiratory dynamics trend prediction signal respectively, and generate a sleep respiratory state description prediction signal.

[0140] In this embodiment, the ARIMA method is selected to complete the time series prediction analysis of the sleep position signal (sleeping direction signal, sleeping angle signal) and the sleep breathing dynamics trend signal to obtain the sleep breathing state description prediction signal. In the actual application scenario, the prediction analysis includes at least any one of the exponential smoothing method, Holt-Winters method, AR, MA, ARMA, ARIMA, SARIMA, SARIMAX, VAR, VARMA, VARMAX, and machine learning.

[0141] The second step is to perform predictive analysis on the key trend features in the sleep respiratory dynamics trend features to obtain a sleep respiratory dynamics trend feature prediction signal.

[0142] In this embodiment, the sleep breathing trend intensity curve and the sleep breathing dynamics trend signal average curve in the sleep breathing dynamics trend feature are selected as key trend features, and the ARIMA method is selected to complete the prediction analysis to obtain the sleep breathing dynamics trend feature prediction signal.

[0143] The third step is to generate a sleep breathing trend auxiliary adjustment strategy based on the sleep breathing state description prediction signal and the sleep breathing dynamics trend characteristic prediction signal, combined with the user's sleep breathing history database and the sleep breathing knowledge base.

[0144] In this embodiment, the user's sleep breathing history database is specifically a user-personalized sleep breathing database, which is used to continuously record and optimize the user's individual sleep breathing behavior and characteristic changes, including at least the user's basic physiological health information, detection and quantification process methods, a first sleep breathing signal, a second sleep breathing signal, a sleep breathing dynamics trend signal, a sleep breathing dynamics trend characteristic, a sleep breathing state description prediction signal, a strategy generation process method, and a sleep breathing trend auxiliary adjustment strategy; the sleep breathing knowledge base mainly comes from the knowledge and experience of health management and clinical medicine related to sleep breathing, and at least includes sleep breathing patterns, common sleep breathing event characteristics, and commonly used sleep breathing adjustment methods, namely, scene intervention parameter guidance.

[0145] In this embodiment, the sleep breathing trend auxiliary adjustment strategy includes at least a target adjustment value of sleep breathing frequency, a target adjustment value of sleep breathing intensity, an adjustment method, an adjustment time point, a duration and a device control parameter, wherein the adjustment method includes at least off-body, contact and invasive methods.

[0146] In actual application scenarios, in addition to physical physiological factors such as obesity and fatigue, different sleeping directions and angles have a greater impact on the pressure of breathing-related body muscles or space in the throat, chest and abdominal cavity. Through the sleeping posture adjustment of smart mattresses, the respiratory muscle adjustment of smart aromatherapy and other means and strategies, a sleep breathing trend auxiliary adjustment strategy with better effects can be achieved for most user groups; and for people with more serious sleep apnea, the sleep breathing trend auxiliary adjustment strategy can also achieve real-time and rapid optimization and adjustment of the ventilator. Therefore, it is necessary to select the key strategy principles such as the basic strategy, basic direction, step target and step speed of sleep breathing trend auxiliary adjustment according to different user groups, software and hardware conditions and other factors, mainly involving the target adjustment value of sleep breathing frequency and the target adjustment value of sleep breathing intensity.

[0147] The third step is to send the sleep breathing trend auxiliary adjustment strategy to the sleep breathing adjustment device through the signal interface, optimize the control execution of the sleep breathing adjustment device, so as to realize the dynamic auxiliary adjustment of the user's sleep breathing trend.

[0148] In this embodiment, the sleep breathing adjustment device includes at least any one of a ventilator, an intelligent mattress, an odor stimulation device, an electrical stimulation device, a tactile stimulation device and a CO2 concentration control device.

[0149] In actual application scenarios, for general users, off-body sleep breathing regulation devices are preferred to assist in sleep breathing regulation; for users who often have severe sleep breathing events, contact electrical stimulation devices have a faster intervention and regulation effect. In addition, the sleep breathing regulation device needs to be able to receive and analyze the device control parameters in the sleep breathing trend auxiliary regulation strategy.

[0150] P500: Generates and outputs sleep breathing trend detection and auxiliary adjustment reports according to the preset report cycle.

[0151] The first step is to generate a sleep breathing trend detection and auxiliary adjustment report according to the preset report cycle.

[0152] In this embodiment, the sleep breathing trend detection and auxiliary adjustment report at least includes a sleep breathing trend intensity curve, a sleep breathing trend auxiliary adjustment strategy, a sleep breathing summary, and a user's sleep behavior health advice. In actual application scenarios, the frequency, content, and method of report generation can be set according to different scenario requirements.

[0153] The second step is to output sleep breathing trend detection and auxiliary adjustment report based on user scenario requirements.

[0154] In actual application scenarios, sleep breathing trend detection and assisted adjustment reports can be used for user sleep health management, user sleep environment optimization management, etc. The sleep breathing trend detection and assisted adjustment reports can be output and applied in different ways and formats.

[0155] Combination Figure 2 As shown, an embodiment of the present invention provides a sleep breathing trend detection and auxiliary regulation system, which is configured to perform the above-mentioned method steps. It includes the following modules:

[0156] The breathing behavior detection module S100 is used to collect and obtain the user's sleep breathing behavior and sleep position information to obtain a first sleep breathing signal;

[0157] The respiratory dynamics analysis module S200 is used to perform signal processing and amplitude adjustment on the first sleep breathing signal according to the sleep position signal to obtain a second sleep breathing signal;

[0158] The respiratory trend analysis module S300 is used to perform time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to obtain a sleep respiratory dynamics trend signal and obtain a sleep respiratory dynamics trend feature through signal feature analysis;

[0159] The breathing assistance adjustment module S400 is used to predict and analyze the user's sleeping position, sleep breathing dynamics trend signal and sleep breathing dynamics trend characteristics, and generate a sleep breathing trend assistance adjustment strategy in combination with a sleep breathing knowledge base and push it to the sleep breathing adjustment device;

[0160] The user report management module S500 is used to generate and output a sleep breathing trend detection and auxiliary adjustment report according to a preset report cycle;

[0161] The data operation management module S600 is used for visual display, storage backup and operation management of all process data of the system.

[0162] In this embodiment, the breathing behavior detection module S100 also includes the following functional units:

[0163] A respiratory physiological monitoring unit is used to monitor and collect the user's sleep respiratory physiological behavior to obtain sleep respiratory physiological signals;

[0164] A sleeping position monitoring unit is used to monitor and collect the user's sleeping position information to obtain a sleeping position signal;

[0165] The sleep signal collection unit is used to collect the sleep breathing physiological signal and the sleep position signal to obtain a first sleep breathing signal.

[0166] In this embodiment, the respiratory dynamics analysis module S200 also includes the following functional units:

[0167] A signal processing and analysis unit, configured to perform signal processing on the first sleep breathing signal to obtain a sleep breathing dynamics signal;

[0168] The signal amplitude adjustment unit is used to adjust the amplitude of the sleep respiratory dynamics signal according to the sleep position signal to obtain a second sleep respiratory signal.

[0169] In this embodiment, the respiratory trend analysis module S300 also includes the following functional units:

[0170] A time series signal decomposition unit, used for performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal, extracting the trend component of the signal, and obtaining a sleep respiratory dynamics trend signal;

[0171] The trend strength analysis unit is used to perform signal feature analysis on the second sleep breathing signal and the sleep respiratory dynamics trend signal to obtain the sleep respiratory dynamics trend feature and extract the sleep breathing trend strength.

[0172] In this embodiment, the breathing assistance adjustment module S400 also includes the following functional units:

[0173] A trend state prediction unit is used to predict and analyze the sleep position signal and the sleep respiratory dynamics trend signal, obtain a sleep position prediction signal and a sleep respiratory dynamics trend prediction signal, and generate a sleep respiratory state description prediction signal;

[0174] A trend feature prediction unit, used to predict and analyze key trend features in the sleep respiratory dynamics trend feature to obtain a sleep respiratory dynamics trend feature prediction signal;

[0175] An auxiliary strategy generating unit, for generating a sleep breathing trend auxiliary adjustment strategy according to the sleep breathing state description prediction signal and the sleep breathing dynamics trend characteristic prediction signal, combined with the user's sleep breathing history database and the sleep breathing knowledge base;

[0176] The auxiliary strategy push unit is used to send the sleep breathing trend auxiliary adjustment strategy to the sleep breathing adjustment device through the signal interface, optimize the control execution of the sleep breathing adjustment device, and realize dynamic auxiliary adjustment of the user's sleep breathing trend.

[0177] In this embodiment, the user report management module S500 further includes the following functional units:

[0178] A user report generation unit, used to generate a sleep breathing trend detection and auxiliary adjustment report according to a preset report cycle;

[0179] The user report output unit is used to output sleep breathing trend detection and auxiliary adjustment reports according to user scenario requirements.

[0180] In this embodiment, the data operation management module S600 also includes the following functional units:

[0181] User information management unit, used for registration, input, editing, query, output and deletion of user basic information;

[0182] Data visualization management unit, used for visualization and management of all data in the system;

[0183] The data operation management unit is used to store, back up, migrate and export all data in the system.

[0184] Combination Figure 3 As shown, a sleep breathing trend detection and auxiliary regulation device provided by an embodiment of the present invention includes the following modules:

[0185] The breathing behavior detection module M100 is used to collect and obtain the user's sleep breathing behavior and sleep position information to obtain a first sleep breathing signal;

[0186] The respiratory dynamics analysis module M200 is used to perform signal processing and amplitude adjustment on the first sleep breathing signal according to the sleep position signal to obtain a second sleep breathing signal;

[0187] The respiratory trend analysis module M300 is used to perform time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to obtain a sleep respiratory dynamics trend signal and obtain a sleep respiratory dynamics trend feature through signal feature analysis;

[0188] The breathing assistance adjustment module M400 is used to predict and analyze the user's sleeping position, sleep breathing dynamics trend signal and sleep breathing dynamics trend characteristics, and generate a sleep breathing trend assistance adjustment strategy based on the sleep breathing knowledge base and push it to the sleep breathing adjustment device;

[0189] User report management module M500, used to generate and output sleep breathing trend detection and auxiliary adjustment reports according to the preset report cycle;

[0190] The data operation management module M600 is used for visual display, storage backup and operation management of all process data and / or result data in the device.

[0191] The device is configured to execute Figure 1 The various steps in the method are not repeated here.

[0192] The present invention also provides various types of programmable processors (FPGA, ASIC or other integrated circuits), which are used to run programs, wherein the steps in the above embodiments are executed when the program is running.

[0193] The present invention also provides a corresponding computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps in the above-mentioned embodiments are implemented when the memory executes the program.

[0194] Although the embodiments disclosed in the present invention are as above, the contents described are only embodiments adopted for facilitating the understanding of the present invention and are not intended to limit the present invention. Any technician in the field to which the present invention belongs can make any modifications and changes, equivalent substitutions, etc. in the form and details of implementation without departing from the spirit and principles disclosed in the present invention, and these all belong to the protection scope of the present invention. Therefore, the patent protection scope of the present invention shall still be subject to the scope defined by the attached claims.

Claims

1. A sleep breathing trend detection and auxiliary regulation method, It is characterized in that The following steps are involved: Collecting and obtaining the user's sleep breathing behavior and sleep position information to obtain a first sleep breathing signal; According to the sleeping position signal, performing signal processing and amplitude adjustment on the first sleeping breathing signal to obtain a second sleeping breathing signal; Performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to obtain a sleep respiratory dynamics trend signal and obtaining a sleep respiratory dynamics trend feature through signal feature analysis; Predict and analyze the user's sleeping position, the sleep respiratory dynamics trend signal, and the sleep respiratory dynamics trend characteristics, and generate a sleep respiratory trend auxiliary adjustment strategy in combination with a sleep respiratory knowledge base and push it to a sleep respiratory adjustment device; Generate and output sleep breathing trend detection and auxiliary adjustment reports according to the preset report cycle.

2. The method according to claim 1, It is characterized in that The specific step of collecting and acquiring the sleep breathing behavior signal and sleep position information of the user during sleep to obtain the first sleep breathing signal also includes: Monitor and collect the user's sleep breathing physiological behavior to obtain sleep breathing physiological signals; Monitor and collect the user's sleeping position information to obtain a sleeping position signal; The sleep breathing physiological signal and the sleep body position signal are aggregated to obtain the first sleep breathing signal.

3. The method according to claim 2, Features The first sleep breathing signal at least includes the sleep breathing physiological signal and the sleep position signal; wherein the sleep breathing physiological signal at least includes an oronasal temperature monitoring signal, a nasal pressure monitoring signal, an oronasal CO 2 The sleeping position signal comprises at least a sleeping direction signal and a sleeping angle signal.

4. The method according to claim 1 or 2, Features The specific step of performing signal processing and amplitude adjustment on the first sleep breathing signal according to the sleep position signal to obtain the second sleep breathing signal also includes: Performing signal processing on the first sleep breathing signal to obtain a sleep breathing dynamics signal; The amplitude of the sleep respiratory dynamics signal is adjusted according to the sleep position signal to obtain the second sleep respiratory signal.

5. The method according to claim 4, Features , the signal processing includes at least one of analog-to-digital conversion, resampling, re-referencing, artifact removal, signal correction, noise reduction, power frequency notch, low-pass filtering, high-pass filtering, band-pass filtering, mean filtering, smoothing and signal time window segmentation; wherein, the signal time window segmentation is specifically to perform continuous time window segmentation on the target signal with a preset length time window and a preset translation time step.

6. The method according to claim 4, It is characterized in that The sleep breathing dynamics signal is specifically a dynamic curve describing the continuous strength change of sleep breathing, including at least the oral and nasal temperature dynamics signal, the nasal pressure dynamics signal, the oral and nasal CO 2 Any one of the following: dynamic signals, chest and abdominal respiratory movement dynamic signals, ECG-derived respiratory dynamic signals, and laryngeal myoelectric dynamic signals.

7. The method according to claim 4, It is characterized in that The amplitude adjustment specifically adjusts the amplitude of the sleep respiratory dynamics signal according to a preset adjustment strategy in combination with the user's sleeping direction and sleeping angle, thereby achieving unified observation and analysis of sleep respiratory behavior in different sleeping positions; wherein the preset adjustment strategy includes at least one of a constant coefficient correction, a linear coefficient correction, and a nonlinear coefficient correction.

8. The method according to claim 1, It is characterized in that The specific steps of performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to obtain a sleep respiratory dynamics trend signal and obtaining a sleep respiratory dynamics trend feature through signal feature analysis also include: Performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to extract the trend component of the signal to obtain the sleep respiratory dynamics trend signal; Signal feature analysis is performed on the second sleep breathing signal and the sleep respiratory dynamics trend signal to obtain the sleep respiratory dynamics trend feature and extract the sleep respiratory trend intensity.

9. The method according to claim 8, It is characterized in that The method of decomposing the time series signal includes at least time series decomposition, empirical mode decomposition, variational mode decomposition, local mean decomposition, wavelet transform, wavelet packet transform, time-frequency transform, detrending analysis, principal component analysis, independent component analysis, waveform analysis and numerical fitting, and any one of their evolutionary variant methods; the method of time-frequency analysis includes at least any one of time-frequency transform, time domain filtering and frequency domain filtering.

10. The method according to claim 8, It is characterized in that The signal feature analysis includes at least any one of numerical feature analysis, envelope feature analysis, time-frequency feature analysis, and nonlinear feature analysis; wherein the numerical feature includes at least any one of mean value, root mean square, maximum value, minimum value, variance, standard deviation, coefficient of variation, kurtosis, and skewness, and the nonlinear feature includes at least any one of entropy feature, fractal feature, and complexity feature.

11. The method according to claim 8, It is characterized in that The sleep pneumodynamic trend feature specifically describes the signal baseline level or change trend direction of the sleep pneumodynamic signal or sleep respiratory physiological behavior; the sleep pneumodynamic trend feature at least includes one or more of the signal characteristics of the second sleep respiratory signal and the sleep pneumodynamic trend signal, the sleep respiratory frequency and curve, the sleep respiratory trend intensity, and the sleep respiratory trend intensity curve.

12. The method according to claim 8 or 11, It is characterized in that The method for extracting the sleep breathing trend intensity and the sleep breathing trend intensity curve comprises: 1) determining a signal timing attribute of the second sleep breathing signal; 2) determining a specific method of time series signal decomposition and / or time-frequency analysis according to the signal time series attribute, performing signal decomposition and / or time-frequency analysis on the second sleep respiratory signal in the current signal time window, extracting the trend component of the signal, and obtaining the sleep respiratory dynamics trend signal; 3) performing signal feature analysis on the second sleep breathing signal and the sleep respiratory dynamics trend signal to obtain a second sleep breathing signal feature and a sleep respiratory dynamics trend signal feature respectively; 4) selecting a signal feature observation and analysis index, comparing the relative changes of the signal features in the second sleep breathing signal feature and the sleep respiratory dynamics trend signal feature, and obtaining a set of relative change values ​​of the sleep respiratory dynamics trend feature; 5) performing numerical combination calculation on the index parameters in the relative change value set of the sleep respiratory dynamics trend characteristics to obtain the sleep respiratory trend intensity of the current signal time window; 6) Extracting the sleep breathing trend intensity of all signal time windows according to the time sequence to obtain the sleep breathing trend intensity curve.

13. The method according to claim 12, It is characterized in that The sleep breathing trend intensity curve specifically comprises the sleep breathing trend intensities in consecutive time windows in time sequence, and describes the continuous change of the sleep breathing behavior trend state / intensity of the user.

14. The method according to claim 1 or 2, It is characterized in that The specific steps of predicting and analyzing the user's sleeping position, the sleep respiratory dynamics trend signal and the sleep respiratory dynamics trend characteristics, combining the sleep respiratory knowledge base, generating a sleep respiratory trend auxiliary adjustment strategy and pushing it to the sleep respiratory adjustment device also include: Performing prediction analysis on the sleep position signal and the sleep respiratory dynamics trend signal to obtain a sleep position prediction signal and a sleep respiratory dynamics trend prediction signal respectively, and generating a sleep respiratory state description prediction signal; Performing prediction analysis on key trend features in the sleep respiratory dynamics trend features to obtain a sleep respiratory dynamics trend feature prediction signal; Generate the sleep breathing trend auxiliary adjustment strategy according to the sleep breathing state description prediction signal and the sleep breathing dynamics trend feature prediction signal, combined with the user's sleep breathing history database and the sleep breathing knowledge base; The sleep breathing trend auxiliary adjustment strategy is sent to the sleep breathing adjustment device through the signal interface, and the control execution of the sleep breathing adjustment device is optimized to achieve dynamic auxiliary adjustment of the user's sleep breathing trend.

15. The method of claim 14, It is characterized in that The predictive analysis includes at least any one of exponential smoothing method, Holt-Winters method, AR, MA, ARMA, ARIMA, SARIMA, SARIMAX, VAR, VARMA, VARMAX, and machine learning.

16. The method of claim 14, It is characterized in that The user sleep breathing history database is specifically a user-personalized sleep breathing database, which is used to continuously record and optimize the user's individual sleep breathing behavior and characteristic changes, and at least includes the user's basic physiological health information, the detection and quantification process method, the first sleep breathing signal, the second sleep breathing signal, the sleep breathing dynamics trend signal, the sleep breathing dynamics trend feature, the sleep breathing state description prediction signal, the strategy generation process method, and the sleep breathing trend auxiliary adjustment strategy; The sleep breathing knowledge base mainly comes from the knowledge and experience of health management and clinical medicine related to sleep breathing, and at least includes sleep breathing patterns, common sleep breathing event characteristics, and commonly used sleep breathing adjustment methods, namely, scene intervention parameter guidance.

17. The method of claim 16, It is characterized in that The sleep breathing trend auxiliary adjustment strategy includes at least one of a target adjustment value of sleep breathing frequency, a target adjustment value of sleep breathing intensity, an adjustment method, an adjustment time point, a duration and a device control parameter, wherein the adjustment method includes at least an off-body type, a contact type and an invasive type; the sleep breathing adjustment device includes at least a ventilator, an intelligent mattress, an odor stimulation device, an electrical stimulation device, a tactile stimulation device and a CO 2 Any type of concentration control equipment.

18. The method of claim 1, It is characterized in that The specific steps of generating and outputting the sleep breathing trend detection and auxiliary adjustment report according to the preset report cycle also include: Generate the sleep breathing trend detection and auxiliary adjustment report according to a preset report cycle; According to the user scenario requirements, the sleep breathing trend detection and auxiliary adjustment report is output.

19. The method of claim 18, It is characterized in that The sleep breathing trend detection and auxiliary adjustment report at least includes the sleep breathing trend intensity curve, the sleep breathing trend auxiliary adjustment strategy, the sleep breathing summary, and the user's sleep behavior health suggestions.

20. A sleep breathing trend detection and auxiliary regulation system, It is characterized in that Includes the following modules: A breathing behavior detection module is used to collect and obtain the user's sleep breathing behavior and sleep position information to obtain a first sleep breathing signal; A respiratory dynamics analysis module, configured to perform signal processing and amplitude adjustment on the first sleep respiratory signal according to the sleep position signal to obtain a second sleep respiratory signal; A respiratory trend analysis module, used for performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to obtain a sleep respiratory dynamics trend signal and obtain a sleep respiratory dynamics trend feature through signal feature analysis; A breathing assistance adjustment module is used to predict and analyze the user's sleeping position, the sleep breathing dynamics trend signal and the sleep breathing dynamics trend characteristics, and generate a sleep breathing trend assistance adjustment strategy in combination with a sleep breathing knowledge base and push it to the sleep breathing adjustment device; A user report management module, used to generate and output sleep breathing trend detection and auxiliary adjustment reports according to a preset report cycle; The data operation management module is used for visual display, storage backup and operation management of all process data of the system.

21. The system of claim 20, It is characterized in that The breathing behavior detection module also includes the following functional units: A respiratory physiological monitoring unit is used to monitor and collect the user's sleep respiratory physiological behavior to obtain sleep respiratory physiological signals; A sleeping position monitoring unit is used to monitor and collect the user's sleeping position information to obtain a sleeping position signal; The sleep signal collection unit is used to collect the sleep breathing physiological signal and the sleep body position signal to obtain the first sleep breathing signal.

22. The system of claim 20, It is characterized in that The respiratory dynamics analysis module also includes the following functional units: A signal processing and analysis unit, configured to perform signal processing on the first sleep breathing signal to obtain a sleep breathing dynamics signal; The signal amplitude adjustment unit is used to adjust the amplitude of the sleep respiratory dynamics signal according to the sleep position signal to obtain the second sleep respiratory signal.

23. The system according to any one of claims 20 to 22, It is characterized in that The respiratory trend analysis module also includes the following functional units: A time series signal decomposition unit, used for performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal, extracting the trend component of the signal, and obtaining the sleep respiratory dynamics trend signal; The trend strength analysis unit is used to perform signal feature analysis on the second sleep breathing signal and the sleep respiratory dynamics trend signal to obtain a sleep respiratory dynamics trend feature and extract the sleep respiratory trend strength.

24. The system of claim 23, It is characterized in that The breathing assistance adjustment module also includes the following functional units: A trend state prediction unit, used for predicting and analyzing the sleep position signal and the sleep respiratory dynamics trend signal, respectively obtaining a sleep position prediction signal and a sleep respiratory dynamics trend prediction signal, and generating a sleep respiratory state description prediction signal; A trend feature prediction unit, used for predicting and analyzing the key trend features in the sleep respiratory dynamics trend features to obtain a sleep respiratory dynamics trend feature prediction signal; An auxiliary strategy generating unit, configured to generate the sleep breathing trend auxiliary adjustment strategy according to the sleep breathing state description prediction signal and the sleep breathing dynamics trend characteristic prediction signal, in combination with a user sleep breathing history database and a sleep breathing knowledge base; The auxiliary strategy pushing unit is used to send the sleep breathing trend auxiliary adjustment strategy to the sleep breathing adjustment device through the signal interface, optimize the control execution of the sleep breathing adjustment device, so as to realize the dynamic auxiliary adjustment of the user's sleep breathing trend.

25. The system according to any one of claims 20 to 22, It is characterized in that The user report management module also includes the following functional units: A user report generating unit, used for generating the sleep breathing trend detection and auxiliary adjustment report according to a preset report cycle; The user report output unit is used to output the sleep breathing trend detection and auxiliary adjustment report according to user scenario requirements.

26. The system of claim 25, It is characterized in that The data operation management module also includes the following functional units: User information management unit, used for registration, input, editing, query, output and deletion of user basic information; A data visualization management unit, used for visual display and management of all data in the system; The data operation management unit is used to store, back up, migrate and export all data in the system.

27. A sleep breathing trend detection and auxiliary regulation device, It is characterized in that Includes the following modules: A breathing behavior detection module is used to collect and obtain the user's sleep breathing behavior and sleep position information to obtain a first sleep breathing signal; A respiratory dynamics analysis module, configured to perform signal processing and amplitude adjustment on the first sleep respiratory signal according to the sleep position signal to obtain a second sleep respiratory signal; A respiratory trend analysis module, used for performing time series signal decomposition and / or time-frequency analysis on the second sleep respiratory signal to obtain a sleep respiratory dynamics trend signal and obtain a sleep respiratory dynamics trend feature through signal feature analysis; A breathing assistance adjustment module is used to predict and analyze the user's sleeping position and the sleep breathing dynamics trend signal, and generate a sleep breathing trend assistance adjustment strategy in combination with a sleep breathing knowledge base and push it to the sleep breathing adjustment device; User report management module, used to generate and output sleep breathing trend detection and auxiliary adjustment reports according to the preset report cycle; The data operation management module is used for visual display, storage backup and operation management of all process data and / or result data in the device.

Images