A method, apparatus, device, product, and storage medium for monitoring respiratory status.

Abstract

This disclosure relates to a method, apparatus, device, product, and storage medium for monitoring respiratory status. The method includes: performing real-time frequency domain transformation on the time-domain respiratory signal of the monitored object to obtain a current frame spectrum; acquiring a first threshold value corresponding to the current frame spectrum; determining the current dominant frequency amplitude corresponding to the peak frequency in the current frame spectrum; determining the respiratory stage corresponding to the current frame spectrum based on the current dominant frequency amplitude and the first threshold value; setting the respiratory state corresponding to the current frame spectrum to a paused state if the respiratory stage is a paused state; and determining the respiratory state corresponding to the current frame spectrum based on the peak frequency in the current frame spectrum if the respiratory stage is an active state. This embodiment solves the problem that the frequency characteristics of respiratory signals are easily interfered with, and improves the accuracy and reliability of respiratory status monitoring.

Description

Technical Field

[0001] This disclosure relates to the field of signal processing technology, and in particular to a method, apparatus, device, product, and storage medium for monitoring respiratory status. Background Technology

[0002] Real-time monitoring of respiratory status is widely used in various scenarios such as medical monitoring, sleep health, rehabilitation training guidance, and smart home interaction. It mainly captures relevant signals of human respiration through sensing devices, and realizes real-time judgment of respiratory status through analysis and feature extraction.

[0003] Human respiration is a typical non-linear physiological movement. The chest and abdomen alternate with inhalation and exhalation, producing periodic movements. However, the speed of chest and abdominal movements during the respiratory transition period approaches zero, and the effective signal is significantly weakened. The extracted frequency features are easily affected by environmental noise, non-respiratory movement interference, clothing obstruction, and other factors, resulting in chaotic jumps and causing problems such as misjudgment of respiratory status and dense oscillations of status.

[0004] The aforementioned technical issues severely restrict the reliability of respiratory status monitoring in applications requiring high precision, high stability, and long-term continuous operation.

[0005] This disclosure provides a method, apparatus, device, product, and storage medium for monitoring respiratory status, in order to address the problem that the frequency characteristics of respiratory signals are easily interfered with, and to improve the accuracy and reliability of respiratory status monitoring.

[0006] One aspect of this disclosure provides a method for monitoring respiratory status, the method comprising: The time-domain respiratory signal of the monitored object is transformed in the frequency domain in real time to obtain the current frame spectrum, and the first threshold value corresponding to the current frame spectrum is obtained. Determine the current main frequency amplitude corresponding to the peak frequency in the current frame spectrogram, and determine the breathing stage corresponding to the current frame spectrogram based on the current main frequency amplitude and the first threshold value; If the breathing phase is a pause phase, the breathing state corresponding to the current frame spectrogram is set to a pause state; When the breathing phase is an active phase, the breathing state corresponding to the current frame spectrum is determined based on the peak frequency in the current frame spectrum.

[0007] Another aspect of this disclosure provides a respiratory status monitoring device, the device comprising: The current frame spectrum determination module is used to perform frequency domain transformation on the time-domain respiratory signal of the monitored object in real time to obtain the current frame spectrum and acquire the first threshold value corresponding to the current frame spectrum. The breathing phase determination module is used to determine the current main frequency amplitude corresponding to the peak frequency in the current frame spectrum, and to determine the breathing phase corresponding to the current frame spectrum based on the current main frequency amplitude and the first threshold value. The pause state determination module is used to set the breathing state corresponding to the current frame spectrogram to a pause state when the breathing phase is a pause phase. A breathing state determination module is used to determine the breathing state corresponding to the current frame spectrum based on the peak frequency in the current frame spectrum when the breathing phase is an active phase.

[0008] Another aspect of this disclosure provides an electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the respiratory status monitoring method according to any embodiment of this disclosure.

[0009] Another aspect of this disclosure provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the respiratory state monitoring method according to any embodiment of this disclosure.

[0010] Another aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the respiratory state monitoring method described in any embodiment of this disclosure.

[0011] The technical solution of this disclosure acquires the current frame spectrum of the time-domain breathing signal, and combines the first threshold value of the current frame spectrum with the current main frequency amplitude corresponding to the peak frequency to first determine the breathing stage corresponding to the current frame spectrum. When the breathing stage is a pause stage, its breathing state is directly set to a pause state. Only when the breathing stage is an active stage, the breathing state is further determined based on the peak frequency in the current frame spectrum. This achieves a step-by-step hierarchical discrimination based on the dual feature dimensions of frequency and amplitude, solving the problem that single frequency features are easily interfered with, making the monitoring process of breathing state more resistant to interference and stable, thereby improving the accuracy and reliability of breathing state monitoring.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a diagram illustrating the monitoring effect of respiratory status based on Doppler frequency in existing technologies. Figure 2 A flowchart illustrating a method for monitoring respiratory status provided in one embodiment of this disclosure; Figure 3 A flowchart illustrating a specific example of a method for acquiring time-domain respiratory signals provided in an embodiment of this disclosure; Figure 4 A flowchart illustrating a specific example of a respiratory status monitoring method provided in one embodiment of this disclosure; Figure 5 A flowchart illustrating another method for monitoring respiratory status provided in one embodiment of this disclosure; Figure 6 A flowchart illustrating a specific example of another method for monitoring respiratory status provided in one embodiment of this disclosure; Figure 7 This is a diagram illustrating the monitoring effect of respiratory status according to an embodiment of the present disclosure. Figure 8 This diagram illustrates an application scenario of a respiratory status monitoring method provided in one embodiment of this disclosure. Figure 9 This is a schematic diagram of the structure of a respiratory status monitoring device provided in one embodiment of the present disclosure; Figure 10 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present disclosure. Detailed Implementation

[0015] Figure 1This is a diagram illustrating the monitoring effect of respiratory status based on Doppler frequency in existing technologies. The horizontal axis represents sampling time, and the left vertical axis represents Doppler frequency. The thick black dashed line represents the sine waveform of the ideal Doppler frequency of the respiratory signal, reflecting the Doppler frequency shift caused by the periodic fluctuations of the chest and abdomen. The thin gray solid line on the sine waveform represents the waveform of the measured Doppler frequency change of the respiratory signal. In the stable phase near the peak and trough of the sine waveform, the quality of the extracted frequency features is good and basically matches the sine waveform. However, in the respiratory transition phase near the zero crossing of the sine waveform, the extracted frequency features are severely submerged by noise because the displacement velocity of the chest and abdomen approaches zero, and the measured Doppler frequency shows significant random fluctuations.

[0016] Figure 1 The right vertical axis represents the phase of the respiratory state, with "1" indicating inhalation and "-1" indicating exhalation. The red step line represents the actual monitoring results of the respiratory state. During the stable phase, the respiratory state can switch in a square wave pattern following the respiratory cycle, but during the respiratory transition phase (… Figure 1 (The area marked by the red ellipse in the image) Due to the sharp drop in signal-to-noise ratio, even minor noise disturbances can cause repeated flips in the state determination based on zero-crossing. Therefore, the actual monitoring results show dense state oscillations and phase ambiguity, which obviously does not conform to the true changes in respiratory activity.

[0017] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0018] It should be noted that the terms "first," "second," "current," "previous," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0019] Figure 2This is a flowchart illustrating a respiratory status monitoring method according to an embodiment of this disclosure. This embodiment is applicable to situations requiring real-time monitoring of the respiratory status of a monitored object. The method can be executed by a respiratory status monitoring device, which can be implemented in hardware and / or software and can be configured in a terminal device. Figure 2 As shown, the method includes: S110. Perform frequency domain transformation on the time-domain respiratory signal of the monitored object in real time to obtain the current frame spectrum, and obtain the first threshold value corresponding to the current frame spectrum.

[0020] Among them, time-domain respiratory signals refer to one-dimensional continuous or discrete electrical signals with time as the independent variable and respiratory physical quantities as the dependent variable, directly reflecting the dynamic changes in the respiratory activity of the monitored object over time. For example, respiratory physical quantities can be chest and abdominal displacement, airway pressure, airflow intensity, impedance changes, etc. Correspondingly, the signal source corresponding to the time-domain respiratory signal can be chest and abdominal sensing signals, airway airflow signals, voltage signals, or other electrical signals that can characterize respiratory activity.

[0021] Specifically, signal monitoring equipment refers to the acquisition device used to collect the aforementioned signal sources. Based on the acquisition method, it can be divided into contact monitoring equipment and non-contact monitoring equipment. Contact monitoring equipment refers to monitoring equipment that requires physical contact with the surface of the monitored object to collect respiratory-related signals. Examples of contact monitoring equipment include, but are not limited to, breathing belts, chest and abdominal electrode pads, pressure-sensitive patches, or piezoelectric sensors. Non-contact monitoring equipment refers to monitoring equipment that does not require any physical contact with the surface of the monitored object and achieves signal acquisition through non-contact methods such as air conduction, electromagnetic radiation, signal reflection, or spatial sensing. Based on spatial sensing capabilities, it can be divided into directional electromagnetic wave equipment and non-directional electromagnetic wave equipment.

[0022] Among them, directional electromagnetic wave equipment refers to electromagnetic wave equipment that can acquire angular information such as azimuth, elevation, and angle of arrival of the monitored object relative to the electromagnetic wave equipment. For example, directional electromagnetic wave equipment includes, but is not limited to, frequency-modulated continuous wave millimeter-wave radar, multi-antenna array pulse Doppler radar, or phased array radar. Non-directional electromagnetic wave equipment refers to electromagnetic wave equipment that cannot acquire angular information of the monitored object relative to the electromagnetic wave equipment. For example, non-directional electromagnetic wave equipment includes, but is not limited to, WiFi wireless network cards, continuous wave microwave radar, or ultra-wideband radar.

[0023] For example, the operating frequencies of frequency-modulated continuous wave millimeter-wave radar include, but are not limited to, 77 GHz, 60 GHz, and 24 GHz bands. Due to their short wavelength and high spatial resolution, these bands are extremely sensitive to the detection of minute displacements in the chest and abdomen, and can accurately capture the micro-Doppler frequency shift caused by respiratory activity. They also have strong penetration capabilities through clothing, making them suitable for non-contact monitoring scenarios. The operating frequencies of continuous wave microwave radar include, but are not limited to, 5.8 GHz and 10.525 GHz bands. These bands have lower hardware costs, strong penetration through clothing, and flexible deployment. They also have less impact on electromagnetic radiation to the human body, making them more suitable for close-range respiratory monitoring scenarios.

[0024] In an optional embodiment, the method further includes: when the signal monitoring device is a directional electromagnetic wave device, acquiring the chest and abdomen sensing signals of the monitored object collected by the directional electromagnetic wave device; determining the instantaneous angle data of the monitored object relative to the directional electromagnetic wave device based on the chest and abdomen sensing signals; smoothing and filtering the instantaneous angle data, and performing beamforming on the chest and abdomen sensing signals based on the smoothed and filtered instantaneous angle data to obtain the time-domain respiratory signal of the monitored object.

[0025] For example, methods for acquiring instantaneous angle data include, but are not limited to, Fast Fourier Transform (FFT), traditional beamforming, digital beamforming, minimum variance distortionless response, multiple signal classification, or maximum likelihood estimation. Taking FFT as an example, the chest and abdominal sensing signals are frequency-domain transformed in both azimuth and elevation dimensions. The angle corresponding to the peak position in the frequency component is taken as the azimuth or elevation angle. The angle of arrival is further synthesized from the azimuth and elevation angles. This example only illustrates the acquisition method of instantaneous angle data and does not limit its application.

[0026] For example, smoothing filtering methods include, but are not limited to, weighted recursive filters or Kalman smoothing algorithms. Taking a weighted recursive filter as an example, the smoothed instantaneous angle data at the t-th sampling time... Satisfy the following formula: in, This represents the smoothed and filtered instantaneous angle data at the (t-1)th sampling time. Represents the smoothing factor. This represents the extracted instantaneous angle data. Specifically, a larger smoothing factor results in better smoothing, but also increases the response latency. For example, The value range can be [0.8, 0.95], to balance the smoothness of instantaneous angle and response speed.

[0027] During human respiration, the rising and falling movements of the chest and abdomen cause alternating changes in the radar cross-section, resulting in drastic jumps in the instantaneous angle. If the extracted instantaneous angle is directly used for beamforming, the beam center will frequently deviate from the actual monitoring target. This embodiment effectively suppresses angle jitter during respiratory movements by smoothing and filtering the instantaneous angle data, thereby improving the signal enhancement effect of beamforming and ensuring the accuracy and stability of subsequent respiratory status monitoring.

[0028] Specifically, a guide vector is constructed using smoothed instantaneous angle data. Based on this guide vector, beamforming is performed on the chest and abdominal sensing signals to obtain an enhanced sensing signal. Exemplary beamforming algorithms include, but are not limited to, Minimum Variance Distortionless Response (MVDR), Linearly Constrained Minimum Variance (LCMV), or Conventional Beamforming (CBF). Taking the MVDR algorithm as an example, the covariance matrix is ​​determined based on the chest and abdominal sensing signals. A weight vector is obtained by optimizing the solution based on the covariance matrix and the guide vector. Based on the weight vector, the sensing signals from each channel in the chest and abdominal sensing signals are weighted and summed to obtain the time-domain respiratory signal.

[0029] For example, weight vector Satisfy the following formula: in, Represents the covariance matrix. Indicates the guide vector. Representing the conjugate transpose, the weight vector contains the weight values ​​corresponding to each channel of the thoracic and abdominal sensory signals, representing the time-domain respiratory signal. Satisfying the formula: , This indicates a sensory signal from the chest and abdomen.

[0030] In another optional embodiment, the method further includes: when the signal monitoring device is a non-directional electromagnetic wave device, acquiring the chest and abdomen sensing signals of the monitored object collected by the non-directional electromagnetic wave device, determining the signal quality parameters corresponding to each channel sensing signal in the chest and abdomen sensing signals; and determining the time-domain respiratory signal of the monitored object based on the chest and abdomen sensing signals and each of the signal quality parameters.

[0031] For example, signal quality parameters can be variance, signal-to-noise ratio, spectral entropy, or correlation coefficient, but are not limited to the given examples.

[0032] In an optional embodiment, determining the time-domain respiratory signal of the monitored object based on the chest and abdomen sensing signals and each of the signal quality parameters includes: filtering each of the channel sensing signals according to each of the signal quality parameters to obtain the time-domain respiratory signal of the monitored object. Specifically, the time-domain respiratory signal is the channel sensing signal with the best signal quality performance among the chest and abdomen sensing signals.

[0033] In another optional embodiment, determining the time-domain respiratory signal of the monitored object based on the chest and abdominal sensing signals and each of the signal quality parameters includes: weighting and summing the sensing signals of each channel according to each signal quality parameter to obtain the time-domain respiratory signal of the monitored object. Specifically, the time-domain respiratory signal represents the fused information of the sensing signals of each channel.

[0034] In another optional embodiment, the method further includes: when the signal monitoring device is a non-directional electromagnetic wave device, acquiring the chest and abdomen sensing signals of the monitored object collected by the non-directional electromagnetic wave device, performing principal component analysis on the chest and abdomen sensing signals, and using the channel sensing signal corresponding to the first principal component as the time-domain respiratory signal of the monitored object.

[0035] Figure 3 This is a flowchart illustrating a specific example of a method for acquiring time-domain respiratory signals provided in an embodiment of this disclosure. Specifically, the method involves acquiring chest and abdominal sensing signals collected by a signal monitoring device, determining whether the signal monitoring device is a directional electromagnetic wave device, and if so, extracting instantaneous angle data of the monitored object relative to the directional electromagnetic wave device based on the chest and abdominal sensing signals, smoothing and filtering the instantaneous angle data, constructing a steering vector based on the smoothed and filtered instantaneous angle data, and using a high-precision MVDR algorithm, a constrained LCMY algorithm, or a low-complexity CBF algorithm to obtain a weight vector based on the steering vector and the chest and abdominal sensing signals. The method then performs a weighted summation of the sensing signals from each channel in the chest and abdominal sensing signals based on the weight vector, and outputs the time-domain respiratory signal of the monitored object.

[0036] When the signal monitoring equipment is a non-directional electromagnetic wave device, the channel sensing signal of the chest and abdomen sensing signal is separated. When the non-directional electromagnetic wave device is a WiFi wireless network card, the chest and abdomen sensing signal is channel state information, and multiple subcarrier signals are separated. The signal quality parameter of each channel sensing signal or subcarrier signal is determined. When the signal quality parameter is variance, the channel sensing signal or subcarrier signal with the largest variance is taken as the time-domain respiratory signal of the monitored object. When the signal quality parameter is signal-to-noise ratio, the signal-to-noise ratio is taken as the weighting coefficient of the channel sensing signal or subcarrier signal. The chest and abdomen sensing signals are weighted and summed according to each weighting coefficient to obtain the time-domain respiratory signal of the monitored object. Alternatively, principal component analysis is directly performed on the channel sensing signal or subcarrier signal in the chest and abdomen sensing signal, and the channel sensing signal or subcarrier signal corresponding to the first principal component is taken as the time-domain respiratory signal of the monitored object.

[0037] Among them, frequency domain transformation is used to convert the time-domain respiratory signal from the time-amplitude dimension to the frequency-intensity dimension, and the spectrum represents the intensity distribution characteristics of different frequency components in the time-domain respiratory signal.

[0038] For example, the frequency domain transformation method can be the Short-Time Fourier Transform (SFT). Specifically, the principle of the SFT is to use a window function to divide the time-domain breathing signal into several short-time frames of fixed length that overlap with each other. A Fast Fourier Transform is then performed on each short-time frame to obtain the spectrum corresponding to each frame period. The window length of the window function can be customized according to the sampling rate and the desired frequency resolution. For example, the window length can range from 256 to 1025 sampling points, and the signal overlap rate between adjacent frame spectra can range from [50%, 75%] to balance time resolution, frequency resolution, and computational efficiency.

[0039] Specifically, the first threshold is an amplitude judgment threshold set for a single frame spectrum, used to distinguish the amplitude of valid signals from interference signals, and is the core judgment benchmark for determining the breathing stage.

[0040] In one optional embodiment, the first threshold value is either a fixed threshold value or an adaptive dynamic threshold value. In the embodiment with a fixed threshold value, the first threshold value is the same for each frame of the spectrogram. For example, the first threshold value can be determined based on the quantiles of the noise amplitude statistically obtained from the object sample set. In the embodiment with a dynamic threshold value, the first threshold value may be the same or different for each frame of the spectrogram. For example, the first threshold value can be obtained by statistically analyzing the first threshold values ​​corresponding to the historical spectrograms of a preset number of frames of the monitored object. Such statistical values ​​include, but are not limited to, the maximum value, median value, or average value.

[0041] S120. Determine the current main frequency amplitude corresponding to the peak frequency in the current frame spectrum, and determine the breathing stage corresponding to the current frame spectrum based on the current main frequency amplitude and the first threshold value.

[0042] Specifically, the peak frequency represents the frequency component with the highest energy in the current frame's spectrum, and the main frequency amplitude represents the signal strength corresponding to the peak frequency in the current frame's spectrum.

[0043] For example, the peak frequency can be obtained by performing maximum energy statistics on the frequency components in the current frame's spectrogram, or it can be obtained by fitting the peak value to the current frame's spectrogram using parabolic interpolation, in order to achieve accurate estimation at sub-frequency resolution. This is merely an illustrative example of how to obtain the peak frequency and is not intended to limit its application.

[0044] In this embodiment, the breathing phase is either a pause phase or an active phase. The pause phase refers to a phase in which breathing is nearly still, with the respiratory airflow amplitude close to zero, no obvious airflow exchange, or a significant decrease in the respiratory signal amplitude. The active phase refers to a phase in which there is obvious respiratory airflow movement, chest wall rise and fall, or continuous change in the respiratory signal amplitude.

[0045] In an optional embodiment, determining the breathing phase corresponding to the current frame spectrogram based on the current main frequency amplitude and the first threshold value includes: setting the breathing phase corresponding to the current frame spectrogram to a pause phase when the current main frequency amplitude is less than the first threshold value; and setting the breathing phase corresponding to the current frame spectrogram to an active phase when the current main frequency amplitude is greater than or equal to the first threshold value.

[0046] S130. Determine whether the breathing phase is a pause phase. If yes, execute S140; otherwise, execute S150.

[0047] S140. Set the breathing state corresponding to the current frame spectrogram to a pause state.

[0048] Specifically, when the breathing phase is a pause phase, the breathing state corresponding to the current frame spectrogram is only a pause state. Specifically, the pause state reflects a brief cessation of breathing, apnea, or resting state.

[0049] S150. Determine the breathing state corresponding to the current frame spectrum based on the peak frequency in the current frame spectrum.

[0050] Specifically, when the breathing phase is active, the breathing state of the current frame spectrogram is either exhalation or inhalation.

[0051] In an optional embodiment, before determining the breathing state corresponding to the current frame spectrogram based on the peak frequency in the current frame spectrogram, the method further includes: employing a state filter to perform smoothing tracking processing on the extracted peak frequency. Exemplary examples of state filters include, but are not limited to, Kalman filters, particle filters, or least mean square filters, etc.

[0052] Taking the Kalman filter as an example, the state vector is defined. ,in, Indicates peak frequency. This represents the rate of change of peak frequency, used to describe the dynamic characteristics of respiratory rate changes. Specifically, it is based on the target state vector corresponding to the spectrogram of frame t-1. Predict the initial state vector of the spectrogram in frame t. And the target covariance estimation based on the spectrogram of frame t-1. Predict the initial covariance estimate corresponding to the spectrogram of frame t. The prediction method satisfies the following formula: in, Represents the state transition matrix. Indicates the inter-frame time interval or frame step size. The process noise covariance matrix represents the natural fluctuations and physiological disturbances of the peak frequency over time.

[0053] For example, the target state vector corresponding to the spectrogram of frame t. and target covariance estimation Satisfy the following formula: in, The Kalman gain represents the degree to which the observed peak frequency corrects for the predicted peak frequency. The observation matrix represents a linear transformation that maps a high-dimensional state vector to a one-dimensional observation space. Its typical form is... , This represents the variance of the observed noise, reflecting the measurement error or noise level during the peak frequency extraction process. This represents the peak frequency extracted from the spectrogram of frame t. Represents the identity matrix.

[0054] Specifically, the target state vector The first state component in the equation is used as the peak frequency after smoothing and filtering.

[0055] The advantage of this setting is that it suppresses high-frequency noise and random jitter, reduces noise interference at peak frequencies, and further ensures the stability of respiratory status monitoring.

[0056] In an optional embodiment, determining the breathing state corresponding to the current frame spectrum based on the peak frequency in the current frame spectrum includes: setting the breathing state corresponding to the current frame spectrum to an exhalation state when the peak frequency is less than zero; and setting the breathing state corresponding to the current frame spectrum to an inhalation state when the peak frequency is greater than or equal to zero.

[0057] Specifically, a peak frequency less than zero indicates a negative Doppler frequency shift, reflecting an increase in the radial distance between the chest / abdomen and the signal monitoring device, and is determined to be the expiratory phase. A peak frequency greater than or equal to zero indicates a positive Doppler frequency shift, reflecting a decrease in the radial distance between the chest / abdomen and the signal monitoring device, and is determined to be the inspiratory phase.

[0058] Figure 4 This is a flowchart illustrating a specific example of a respiratory state monitoring method provided in an embodiment of this disclosure. Specifically, the time-domain respiratory signal of the monitored object is acquired, and a short-time Fourier transform is performed on the time-domain respiratory signal in real time to obtain a single-frame spectrum. Feature extraction is performed on the single-frame spectrum to obtain the peak frequency and the main frequency amplitude at the peak frequency. Based on the main frequency amplitude and a first threshold value, the respiratory stage corresponding to the single-frame spectrum is determined. If the respiratory stage is a pause stage, the phase analysis of the respiratory rhythm is blocked, and the respiratory phase position is directly set to 0, indicating that the respiratory state corresponding to the single-frame spectrum is a pause state. If the respiratory stage is an active stage, the phase analysis of the respiratory rhythm is allowed. The respiratory state corresponding to the single-frame spectrum is determined based on the peak frequency. If the respiratory state is an inhalation state, the respiratory phase position is set to 1; otherwise, the respiratory phase position is set to -1, realizing a three-state four-beat cyclic output. The "three states" include the exhalation state, the inhalation state, and the pause state. The "four beats" represent the periodic breathing pattern of inhalation (1) - pause (0) - exhalation (-1) - pause (0) alternating sequentially.

[0059] The technical solution of this embodiment obtains the current frame spectrum of the time-domain breathing signal, and combines the first threshold value of the current frame spectrum with the current main frequency amplitude corresponding to the peak frequency to first determine the breathing stage corresponding to the current frame spectrum. When the breathing stage is a pause stage, its breathing state is directly set to a pause state. Only when the breathing stage is an active stage, the breathing state is further determined based on the peak frequency in the current frame spectrum. This realizes a step-by-step hierarchical discrimination based on the dual feature dimensions of frequency and amplitude, which solves the problem that single frequency features are easily interfered with, making the monitoring process of breathing state more resistant to interference and stable, thereby improving the accuracy and reliability of breathing state monitoring.

[0060] Figure 5 This is a flowchart illustrating another method for monitoring respiratory status according to an embodiment of this disclosure. This embodiment further refines the step of "obtaining the first threshold value corresponding to the current frame spectrogram" in the above embodiment. In this embodiment, obtaining the first threshold value corresponding to the current frame spectrogram includes: determining the first threshold value corresponding to the current frame spectrogram based on the first threshold value corresponding to the previous frame spectrogram. Figure 5 As shown, the method includes: S210. Perform real-time frequency domain transformation on the time-domain respiratory signal of the monitored object to obtain the current frame spectrum.

[0061] S210 in this embodiment is the same as that in the above embodiment. Figure 2 The S110 shown is the same or similar, and will not be described again in this embodiment.

[0062] S220. Determine the first threshold value corresponding to the current frame spectrum based on the first threshold value corresponding to the previous frame spectrum.

[0063] In an embodiment with a fixed threshold value, determining the first threshold value corresponding to the current frame spectrum based on the first threshold value corresponding to the previous frame spectrum includes: using the first threshold value corresponding to the previous frame spectrum as the first threshold value corresponding to the current frame spectrum.

[0064] In one embodiment of the dynamic threshold value, optionally, determining the first threshold value corresponding to the current frame spectrum based on the first threshold value corresponding to the previous frame spectrum includes: determining the first threshold value corresponding to the current frame spectrum based on the first threshold value corresponding to the previous frame spectrum and the first main frequency amplitude value.

[0065] In another embodiment of the dynamic threshold, optionally, determining the first threshold corresponding to the current frame spectrum based on the first threshold corresponding to the previous frame spectrum includes: if the breathing phase corresponding to the previous frame spectrum is a pause phase, using the first threshold corresponding to the previous frame spectrum as the first threshold corresponding to the current frame spectrum; if the breathing phase corresponding to the previous frame spectrum is an active phase, determining the first threshold corresponding to the current frame spectrum based on the first threshold corresponding to the previous frame spectrum and the first main frequency amplitude value.

[0066] In the above embodiments, the first main frequency amplitude is obtained by statistically analyzing the main frequency amplitude of the historical spectrum obtained based on the sliding time window. For example, the first main frequency amplitude can be the maximum main frequency amplitude or the average main frequency amplitude. The sliding time window is greater than one active period, and the active period represents the number of continuous frames of an active phase, which can be the number of continuous frames of the exhalation state or the number of continuous frames of the inhalation state.

[0067] Based on the above embodiments, optionally, determining the first threshold value corresponding to the current frame spectrum based on the first threshold value and the first main frequency amplitude value corresponding to the previous frame spectrum includes: determining a basic threshold value based on the first threshold value and the first weighting coefficient; determining an initial incremental threshold value based on the first main frequency amplitude value and the second weighting coefficient; determining an effective incremental threshold value based on the initial incremental threshold value and a preset sensitivity coefficient; and using the sum of the basic threshold value and the effective incremental threshold value as the first threshold value corresponding to the current frame spectrum.

[0068] In this embodiment, the first weighting coefficient and the second weighting coefficient are complements of each other, and the preset sensitivity coefficient ranges from 0 to 0.2. The preset sensitivity coefficient reflects the sensitivity of the first threshold value to the main frequency amplitude.

[0069] Taking the first main frequency amplitude as the maximum main frequency amplitude as an example, the first threshold value corresponding to the i-th frame spectrum. Satisfying the formula: in, This represents the first weighting coefficient. This represents the second weighting coefficient. This represents the set of main frequency amplitudes corresponding to multiple historical spectrograms. This represents the preset sensitivity coefficient. For example, the value range of the first weight coefficient can be [0.8, 0.95].

[0070] In this embodiment, if the breathing phase corresponding to the previous frame spectrogram is a pause phase, the first threshold value of the subsequent spectrogram is locked until the breathing phase changes from a pause phase to an active phase. The locked first threshold value is then assigned to the current frame spectrogram as the first threshold value of the current frame spectrogram. If the breathing phase corresponding to the previous frame spectrogram is an active phase, the first threshold value of the subsequent spectrogram is allowed to be recursively updated.

[0071] A low threshold value can easily misjudge a frequency amplitude without rhythmic meaning as a frequency amplitude with rhythmic meaning, leading to false detection of respiratory status and disordered respiratory rhythm. This embodiment, by setting a threshold locking mechanism, avoids the threshold value of the amplitude feature being lowered by the continuously updated frequency amplitude value that is severely interfered with by noise during the pause phase, further eliminating the false detection spikes of respiratory status, ensuring continuous and stable output of the pause phase, and improving the accuracy and robustness of respiratory status monitoring.

[0072] S230. Determine the current main frequency amplitude corresponding to the peak frequency in the current frame spectrum, and determine the breathing stage corresponding to the current frame spectrum based on the current main frequency amplitude and the first threshold value.

[0073] In another optional embodiment, determining the breathing stage corresponding to the current frame spectrogram based on the current main frequency amplitude and the first threshold value includes: statistically analyzing the largest main frequency amplitude within at least one active cycle to obtain a second main frequency amplitude, and determining a second threshold value based on a preset attenuation coefficient and the second main frequency amplitude; if the current main frequency amplitude is less than the second threshold value, determining the breathing stage corresponding to the current frame spectrogram based on the current main frequency amplitude and the first threshold value; if the current main frequency amplitude is greater than or equal to the second threshold value, taking the breathing stage corresponding to the previous frame spectrogram as the breathing stage corresponding to the current frame spectrogram.

[0074] Specifically, the second main frequency amplitude is the largest main frequency amplitude in the current active period, or it is a statistical value of the largest main frequency amplitude corresponding to the current active period and at least one historical active period. For example, the statistical value includes, but is not limited to, the maximum value, the median value, or the average value. In this embodiment, the preset attenuation coefficient has a value range of (0,1], and the second threshold value is greater than the first threshold value.

[0075] In this embodiment, the method further includes: when the current dominant frequency amplitude is greater than or equal to the second threshold value, using the breathing state corresponding to the previous frame spectrum as the breathing state corresponding to the current frame spectrum. Specifically, if the current dominant frequency amplitude is greater than or equal to the second threshold value, it indicates that the respiratory activity is in a stable state, and the breathing state corresponding to the previous frame spectrum is directly reused.

[0076] Since the transition of the breathing phase occurs in the lower main frequency amplitude range, this embodiment sets a pre-judgment mechanism with a second threshold value, so that the spectrum corresponding to the higher main frequency amplitude can directly reuse the breathing phase and breathing phase of the previous frame spectrum. Only the phase switching judgment process and state switching judgment process are performed for the lower main frequency amplitude. This not only reduces unnecessary judgment steps and improves the response efficiency of state monitoring, but also avoids false switching caused by factors such as instantaneous strong interference and abnormal amplitude changes, thus improving the stability of state monitoring.

[0077] Based on the above embodiments, optionally, determining the breathing stage corresponding to the current frame spectrogram based on the current main frequency amplitude and the first threshold value includes: determining a third threshold value based on a preset recovery coefficient and the first threshold value; setting the breathing stage corresponding to the current frame spectrogram as a pause stage when the current main frequency amplitude is less than the first threshold value; setting the breathing stage corresponding to the current frame spectrogram as an active stage when the current main frequency amplitude is greater than the third threshold value; and taking the breathing stage corresponding to the previous frame spectrogram as the breathing stage corresponding to the current frame spectrogram when the main frequency amplitude is greater than or equal to the first threshold value and less than or equal to the third threshold value.

[0078] In this embodiment, the preset recovery coefficient is greater than or equal to 1. For example, the preset recovery coefficient can be 1.2, but it is not limited to the given example.

[0079] The advantage of this setting is that it introduces a lag effect from the pause phase to the active phase, avoiding frequent switching of the breathing phase due to noise fluctuations near the threshold, and further improving the stability of state monitoring.

[0080] In one specific embodiment, the third threshold value is greater than the first threshold value and less than the second threshold value.

[0081] S240. Determine whether the breathing phase is a pause phase. If yes, execute S250; otherwise, execute S260.

[0082] S250, Set the breathing state corresponding to the current frame spectrogram to a pause state.

[0083] S240-S250 in this embodiment are the same as those in the above embodiment. Figure 2 The S130-S140 shown are the same or similar, and will not be described again in this embodiment.

[0084] S260. Determine the breathing state corresponding to the current frame spectrum based on the peak frequency in the current frame spectrum.

[0085] In another optional embodiment, determining the breathing state corresponding to the current frame spectrum based on the peak frequency in the current frame spectrum includes: setting the breathing state corresponding to the current frame spectrum to an exhalation state when the peak frequency is less than the lower limit of the frequency range; setting the breathing state corresponding to the current frame spectrum to an inhalation state when the peak frequency is greater than the upper limit of the frequency range; and using the breathing state corresponding to the previous frame spectrum as the breathing state corresponding to the current frame spectrum when the peak frequency meets the frequency range.

[0086] In this embodiment, the lower limit of the frequency range is negative, and the upper limit of the frequency range is positive. Specifically, the absolute value of the lower limit of the frequency range can be the same as or different from the upper limit of the frequency range. For example, the frequency range can be [-a, a], such as the dead zone threshold a being 0.02Hz.

[0087] The advantage of setting a frequency dead zone mechanism is that it further avoids frequent state switching caused by interference fluctuations near zero peak frequency, thus improving the stability of state monitoring.

[0088] Figure 6 This is a flowchart illustrating a specific example of another respiratory state monitoring method provided in an embodiment of this disclosure. Specifically, the initialization parameters are obtained as follows: sliding time window Tw, first weight coefficient γ, preset sensitivity coefficient k, preset attenuation coefficient β, preset recovery coefficient η, dead zone threshold a, and initialization threshold Th(0), wherein the first weight coefficient γ and preset sensitivity coefficient k are used for updating the threshold value.

[0089] Obtain the dominant frequency amplitude Aobs(t) corresponding to the spectrum of frame t, and obtain the maximum dominant frequency amplitude Apeak within the historical period [Tw×(t-1),Tw×t]. Use the product of the maximum dominant frequency amplitude Apeak and the preset attenuation coefficient β as the second threshold value. Determine whether the dominant frequency amplitude Aobs(t) is less than the second threshold value. If not, take the respiratory phase Phase(t-1) corresponding to the spectrum of frame t-1 as the respiratory phase Phase(t) corresponding to the spectrum of frame t. If yes, continue to determine whether the dominant frequency amplitude Aobs(t) is less than the first threshold value Th(t) corresponding to the spectrum of frame t.

[0090] If yes, pause the threshold update operation, lock the first threshold Th(t) to the first threshold Th(t+1) corresponding to the spectrum of frame t+1, and set the breathing phase Phase(t) corresponding to the spectrum of frame t to 0; if no, use the product of the preset recovery coefficient η and the first threshold Th(t) as the third threshold, and continue to determine whether the main frequency amplitude Aobs(t) is greater than the third threshold.

[0091] If not, the respiratory phase Phase(t-1) corresponding to the (t-1)th frame spectrum is taken as the respiratory phase Phase(t) corresponding to the tth frame spectrum. If yes, the threshold value update operation is performed. Based on the first threshold value Th(t), the first weight coefficient γ, and the preset sensitivity coefficient k, the first threshold value Th(t+1) corresponding to the (t+1)th frame spectrum is determined, and it is determined whether the peak frequency fpeak(t) corresponding to the tth frame spectrum satisfies the frequency range [-a, a]. If the frequency range [-a, a] is satisfied, the respiratory phase Phase(t-1) corresponding to the (t-1)th frame spectrum is taken as the respiratory phase Phase(t) corresponding to the tth frame spectrum.

[0092] If the peak frequency fpeak(t) does not satisfy the frequency range [-a, a], then continue to determine whether the peak frequency fpeak(t) is greater than the dead zone threshold a. If it is, then set the breathing phase Phase(t) corresponding to the spectrum of the t-th frame to 1. If not, then set the breathing phase Phase(t) corresponding to the spectrum of the t-th frame to -1.

[0093] Figure 7 This is a diagram illustrating the monitoring effect of respiratory status according to an embodiment of this disclosure. Specifically, the horizontal axis represents the sampling time, the left vertical axis represents the main frequency amplitude, and the blue solid line and its filled area represent the amplitude envelope calculated in real time. Figure 7 As shown, the dominant frequency amplitude exhibits a periodic, smooth, "hill-like" waveform. During the active phase, the chest and abdominal movements are large, resulting in a distinct peak in the dominant frequency amplitude. During the static phase, the chest and abdominal displacement velocity approaches zero, and the dominant frequency amplitude drops to an extremely low level, forming a trough. The thick blue dashed line represents the adaptively updated threshold value Th during the active phase. Figure 7 It can be seen that the threshold value Th always remains near the trough of the amplitude, and shows a downward trend as the maximum main frequency amplitude decreases during the active phase.

[0094] Figure 7 The right vertical axis represents the phase of the respiratory state, with "1" indicating inhalation, "-1" indicating exhalation, and "0" indicating a pause. The red step line represents the actual monitoring result of the respiratory state. The width of the gray rectangle represents the duration of the pause. The horizontal axis corresponding to the left of the gray rectangle represents the start time of the pause, and the intersection of the gray rectangle with the waveform of the dominant frequency amplitude represents the dominant frequency amplitude value less than the first threshold. The horizontal axis corresponding to the right of the gray rectangle represents the end time of the pause, and the intersection of the gray rectangle with the waveform of the dominant frequency amplitude represents the dominant frequency amplitude value greater than the third threshold.

[0095] Will Figure 1 and Figure 7Comparison shows that the embodiments of this disclosure effectively eliminate the phase jitter phenomenon at the end of breathing, and the state monitoring results present a regular four-beat cycle of inhalation (+1) → pause (0) → exhalation (-1) → pause (0), which conforms to the real change law of respiratory activity.

[0096] Assuming a sliding time window Tw = 2s, a first weighting coefficient γ = 0.95, a preset sensitivity coefficient k = 0.15, a preset attenuation coefficient β = 0.8, a preset recovery coefficient η = 1.2, and an initial threshold Th(0) = 0.2, for a respiratory signal with a respiratory rate of 0.3Hz, the threshold Th stabilizes within the range of 0.1-0.2 and follows the slow change in respiratory amplitude. When breath-holding or a respiratory transition occurs, the dominant frequency amplitude drops below 0.1 within approximately 0.3s, the respiratory state is locked into a pause state, and the update of the threshold Th is frozen until the dominant frequency amplitude exceeds 0.1 × 1.2 = 0.12, at which point the determination of the rhythm phase of inhalation / exhalation is restored.

[0097] The technical solution of this embodiment determines the first threshold value corresponding to the current frame spectrum based on the first threshold value corresponding to the previous frame spectrum, which solves the problem that a fixed threshold value cannot adapt to the random changes in the intensity of the respiratory signal. It avoids the situation where the effective main frequency peak is missed due to the threshold value being too high, and also avoids the noise interference introduced by the threshold value being too low, thereby further improving the stability and accuracy of respiratory status monitoring.

[0098] Figure 8 This diagram illustrates an application scenario of a respiratory status monitoring method according to an embodiment of this disclosure. Specifically, the terminal device equipped with the respiratory status monitoring device can be connected to an external signal monitoring platform. This platform can house electromagnetic wave devices such as frequency-modulated continuous wave millimeter-wave radar, continuous wave microwave radar, ultra-wideband radar, and WiFi wireless network cards. The electromagnetic wave devices transmit detection signals to the monitored object and receive chest and abdominal sensing signals. This embodiment of the disclosure utilizes a spatially layered signal enhancement process, making it compatible with both directional and non-directional electromagnetic wave devices. Figure 8 The generality of the embodiments of this disclosure is intuitively described.

[0099] The terminal device can also use real-time monitoring results of respiratory status as the core control basis to precisely drive various external execution devices to achieve adaptive and synchronized functional outputs. These external execution devices include, but are not limited to, guide lights or ambient lights, sleep aid speakers or white noise generators, medical alarms, and sleep monitoring terminals. For example, for guide lights or ambient lights, the device can adjust display parameters in real time based on characteristic parameters such as respiratory phase, respiratory frequency, and duration of the state, including brightness, color, and gradient rhythm, to achieve synchronized guidance of respiratory rhythm and regulate breathing. For sleep aid speakers or white noise generators, the device can dynamically adapt sound effect type and volume according to the real-time respiratory phase, creating a sleep-aiding acoustic environment highly consistent with the respiratory rhythm and effectively improving sleep aid effects. For medical alarms, the device can provide graded warnings of abnormal respiratory events based on characteristic parameters such as pause duration, abnormal frequency, and sudden amplitude changes, promptly preventing safety risks such as sleep apnea and suffocation. For sleep monitoring terminals, the monitoring results of respiratory status can serve as key data for sleep stage determination and sleep breathing quality analysis, providing precise support for sleep assessment and subsequent sleep intervention optimization.

[0100] The stable and reliable status monitoring output provided in this embodiment can ensure the continuous and smooth control logic of various external execution devices, providing a reliable data foundation and control basis for application scenarios such as breathing guidance, sleep aid intervention, health early warning, and sleep analysis.

[0101] The following are embodiments of the respiratory status monitoring device provided in this disclosure. This device and the respiratory status monitoring method in the above embodiments belong to the same disclosed concept. For details not described in detail in the embodiments of the respiratory status monitoring device, please refer to the content of the respiratory status monitoring method in the above embodiments.

[0102] Figure 9 This is a schematic diagram of a respiratory status monitoring device provided in one embodiment of the present disclosure. Figure 9 As shown, the device includes: a current frame spectrogram determination module 310, a breathing phase determination module 320, a pause state determination module 330, and a breathing state determination module 340.

[0103] The current frame spectrum determination module 310 is used to perform frequency domain transformation on the time-domain respiratory signal of the monitored object in real time to obtain the current frame spectrum and acquire the first threshold value corresponding to the current frame spectrum. The breathing phase determination module 320 is used to determine the current main frequency amplitude corresponding to the peak frequency in the current frame spectrum, and determine the breathing phase corresponding to the current frame spectrum based on the current main frequency amplitude and the first threshold value. The pause state determination module 330 is used to set the breathing state corresponding to the current frame spectrogram to a pause state when the breathing phase is a pause phase. The breathing state determination module 340 is used to determine the breathing state corresponding to the current frame spectrum based on the peak frequency in the current frame spectrum when the breathing stage is an active stage.

[0104] The technical solution of this embodiment obtains the current frame spectrum of the time-domain breathing signal, and combines the first threshold value of the current frame spectrum with the current main frequency amplitude corresponding to the peak frequency to first determine the breathing stage corresponding to the current frame spectrum. When the breathing stage is a pause stage, its breathing state is directly set to a pause state. Only when the breathing stage is an active stage, the breathing state is further determined based on the peak frequency in the current frame spectrum. This realizes a step-by-step hierarchical discrimination based on the dual feature dimensions of frequency and amplitude, which solves the problem that single frequency features are easily interfered with, making the monitoring process of breathing state more resistant to interference and stable, thereby improving the accuracy and reliability of breathing state monitoring.

[0105] In an optional embodiment, the current frame spectrogram determination module 310 includes: The first threshold value update unit is used to use the first threshold value corresponding to the previous frame spectrum as the first threshold value corresponding to the current frame spectrum when the breathing stage corresponding to the previous frame spectrum is a pause stage. The second threshold update unit is used to determine the first threshold value corresponding to the current frame spectrum based on the first threshold value and the first main frequency amplitude value corresponding to the previous frame spectrum when the breathing phase corresponding to the previous frame spectrum is an active phase. The first main frequency amplitude is obtained by statistically analyzing the main frequency amplitude of the historical spectrum obtained based on a sliding time window, wherein the sliding time window is longer than one active period.

[0106] In an optional embodiment, the second threshold update unit is specifically used for: Based on the first threshold value and the first weighting coefficient, a basic threshold value is determined, and based on the first main frequency amplitude and the second weighting coefficient, an initial incremental threshold value is determined. The effective incremental threshold value is determined based on the initial incremental threshold value and the preset sensitivity coefficient; The sum of the basic threshold value and the effective incremental threshold value is used as the first threshold value corresponding to the current frame spectrogram. Wherein, the first weighting coefficient and the second weighting coefficient are complements of each other, and the preset sensitivity coefficient has a value range of (0, 0.2).

[0107] In an optional embodiment, the breathing phase determination module 320 includes: The second threshold value determination unit is used to statistically analyze the maximum main frequency amplitude within at least one active cycle to obtain a second main frequency amplitude, and to determine a second threshold value based on a preset attenuation coefficient and the second main frequency amplitude; wherein the preset attenuation coefficient has a value range of (0,1]. The first breathing stage determination unit is used to determine the breathing stage corresponding to the current frame spectrogram based on the current main frequency amplitude and the first threshold value when the current main frequency amplitude is less than the second threshold value. The second breathing stage determination unit is used to determine the breathing stage corresponding to the previous frame spectrum as the breathing stage corresponding to the current frame spectrum when the current main frequency amplitude is greater than or equal to the second threshold value.

[0108] In one optional embodiment, the first breathing stage determining unit is specifically used for: A third threshold value is determined based on a preset recovery coefficient and the first threshold value; wherein the preset recovery coefficient is greater than or equal to 1. If the current main frequency amplitude is less than the first threshold value, the breathing phase corresponding to the current frame spectrogram is set as a pause phase; If the current main frequency amplitude is greater than the third threshold value, the breathing phase corresponding to the current frame spectrogram is set as the active phase; If the main frequency amplitude is greater than or equal to the first threshold value and less than or equal to the third threshold value, the breathing phase corresponding to the previous frame spectrum is taken as the breathing phase corresponding to the current frame spectrum.

[0109] In an optional embodiment, the respiratory state determination module 340 is specifically used for: If the peak frequency is less than the lower limit of the frequency range, the breathing state corresponding to the current frame spectrogram is set to the exhalation state. If the peak frequency is greater than the upper limit of the frequency range, the breathing state corresponding to the current frame spectrogram is set to the inhalation state. If the peak frequency satisfies the frequency range, the breathing state corresponding to the previous frame spectrum is taken as the breathing state corresponding to the current frame spectrum. The lower limit of the frequency range is a negative value, and the upper limit of the frequency range is a positive value.

[0110] In an optional embodiment, the device further includes: The time-domain respiratory signal determination module is used to acquire the chest and abdominal sensory signals of the monitored object collected by the directional electromagnetic wave device when the signal monitoring device is a directional electromagnetic wave device. Based on the chest and abdominal sensing signals, the instantaneous angle data of the monitored object relative to the directional electromagnetic wave device is determined; The instantaneous angle data is smoothed and filtered, and the chest and abdomen sensing signals are beamformed based on the smoothed and filtered instantaneous angle data to obtain the time-domain respiratory signal of the monitored object.

[0111] The respiratory status monitoring device provided in this disclosure can execute the respiratory status monitoring method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects for executing the method.

[0112] Figure 10 This is a schematic diagram of an electronic device provided according to one embodiment of the present disclosure. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0113] like Figure 10 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor 11. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0114] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information or data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0115] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the respiratory status monitoring method provided in the above embodiments.

[0116] In some embodiments, the respiratory status monitoring method provided in the above embodiments can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the respiratory status monitoring method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the respiratory status monitoring method by any other suitable means (e.g., by means of firmware).

[0117] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of embodiments of this disclosure.

[0118] Various embodiments of the systems and techniques described above herein can be implemented in the following systems or combinations thereof: digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), system-on-chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0119] Computer programs used to implement the respiratory status monitoring method of this disclosure can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0120] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable storage medium. Examples of machine-readable storage media include, based on an electrical connection of at least one wire, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0121] To provide interaction with a user, the systems and techniques described herein can be implemented on a terminal device having: a display device for displaying information to the user (e.g., a cathode-ray tube (CRT) or liquid crystal display (LCD) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the terminal device. Other types of devices can also provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0122] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0123] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0124] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0125] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for monitoring respiratory status, characterized in that, include: The time-domain respiratory signal of the monitored object is transformed in the frequency domain in real time to obtain the current frame spectrum, and the first threshold value corresponding to the current frame spectrum is obtained. Determine the current main frequency amplitude corresponding to the peak frequency in the current frame spectrogram, and determine the breathing stage corresponding to the current frame spectrogram based on the current main frequency amplitude and the first threshold value; If the breathing phase is a pause phase, the breathing state corresponding to the current frame spectrogram is set to a pause state; When the breathing phase is an active phase, the breathing state corresponding to the current frame spectrum is determined based on the peak frequency in the current frame spectrum.

2. The method according to claim 1, characterized in that, The step of obtaining the first threshold value corresponding to the current frame spectrogram includes: If the breathing phase corresponding to the previous frame spectrum is a pause phase, the first threshold value corresponding to the previous frame spectrum will be used as the first threshold value corresponding to the current frame spectrum. If the breathing phase corresponding to the previous frame spectrum is an active phase, the first threshold value corresponding to the current frame spectrum is determined based on the first threshold value and the first main frequency amplitude value corresponding to the previous frame spectrum. The first main frequency amplitude is obtained by statistically analyzing the main frequency amplitude of the historical spectrum obtained based on a sliding time window, wherein the sliding time window is longer than one active period.

3. The method according to claim 2, characterized in that, The step of determining the first threshold value corresponding to the current frame spectrum based on the first threshold value and the first main frequency amplitude value corresponding to the previous frame spectrum includes: Based on the first threshold value and the first weighting coefficient, a basic threshold value is determined, and based on the first main frequency amplitude and the second weighting coefficient, an initial incremental threshold value is determined. The effective incremental threshold value is determined based on the initial incremental threshold value and the preset sensitivity coefficient; The sum of the basic threshold value and the effective incremental threshold value is used as the first threshold value corresponding to the current frame spectrogram. Wherein, the first weighting coefficient and the second weighting coefficient are complements of each other, and the preset sensitivity coefficient has a value range of (0, 0.2).

4. The method according to claim 1, characterized in that, The step of determining the breathing phase corresponding to the current frame spectrogram based on the current main frequency amplitude and the first threshold value includes: The maximum main frequency amplitude within at least one active cycle is statistically analyzed to obtain a second main frequency amplitude, and a second threshold value is determined based on a preset attenuation coefficient and the second main frequency amplitude; wherein the preset attenuation coefficient ranges from (0,1]. If the current main frequency amplitude is less than the second threshold value, the breathing phase corresponding to the current frame spectrogram is determined based on the current main frequency amplitude and the first threshold value. If the current main frequency amplitude is greater than or equal to the second threshold value, the breathing phase corresponding to the previous frame spectrum is taken as the breathing phase corresponding to the current frame spectrum.

5. The method according to claim 4, characterized in that, The step of determining the breathing phase corresponding to the current frame spectrogram based on the current main frequency amplitude and the first threshold value includes: A third threshold value is determined based on a preset recovery coefficient and the first threshold value; wherein the preset recovery coefficient is greater than or equal to 1. If the current main frequency amplitude is less than the first threshold value, the breathing phase corresponding to the current frame spectrogram is set as a pause phase; If the current main frequency amplitude is greater than the third threshold value, the breathing phase corresponding to the current frame spectrogram is set as the active phase; If the main frequency amplitude is greater than or equal to the first threshold value and less than or equal to the third threshold value, the breathing phase corresponding to the previous frame spectrogram is taken as the breathing phase corresponding to the current frame spectrogram.

6. The method according to any one of claims 1-5, characterized in that, Determining the breathing state corresponding to the current frame spectrum based on the peak frequency in the current frame spectrum includes: If the peak frequency is less than the lower limit of the frequency range, the breathing state corresponding to the current frame spectrogram is set to the exhalation state. If the peak frequency is greater than the upper limit of the frequency range, the breathing state corresponding to the current frame spectrogram is set to the inhalation state. If the peak frequency satisfies the frequency range, the breathing state corresponding to the previous frame spectrum is taken as the breathing state corresponding to the current frame spectrum. The lower limit of the frequency range is a negative value, and the upper limit of the frequency range is a positive value.

7. The method according to claim 1, characterized in that, The method further includes: When the signal monitoring device is a directional electromagnetic wave device, the chest and abdominal sensory signals of the monitored object collected by the directional electromagnetic wave device are acquired. Based on the chest and abdominal sensing signals, the instantaneous angle data of the monitored object relative to the directional electromagnetic wave device is determined; The instantaneous angle data is smoothed and filtered, and the chest and abdomen sensing signals are beamformed based on the smoothed and filtered instantaneous angle data to obtain the time-domain respiratory signal of the monitored object.

8. A device for monitoring respiratory status, characterized in that, include: The current frame spectrum determination module is used to perform frequency domain transformation on the time-domain respiratory signal of the monitored object in real time to obtain the current frame spectrum and acquire the first threshold value corresponding to the current frame spectrum. The breathing phase determination module is used to determine the current main frequency amplitude corresponding to the peak frequency in the current frame spectrum, and to determine the breathing phase corresponding to the current frame spectrum based on the current main frequency amplitude and the first threshold value. The pause state determination module is used to set the breathing state corresponding to the current frame spectrogram to a pause state when the breathing phase is a pause phase. A breathing state determination module is used to determine the breathing state corresponding to the current frame spectrum based on the peak frequency in the current frame spectrum when the breathing phase is an active phase.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the respiratory state monitoring method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for monitoring respiratory status according to any one of claims 1-7.

11. A computer program product comprising a computer program that, when executed by a processor, implements the method for monitoring respiratory status according to any one of claims 1-7.

Images