Physiological state monitoring method, apparatus, device, storage medium, computer program product

Abstract

The application discloses a physiological state monitoring method, device, equipment, storage medium and computer program product, and aims to solve the problem that the existing physiological monitoring scheme cannot realize all-weather continuous monitoring of deep physiological parameters such as heart rate, respiration and heart rate of a driver without contacting the human body. The method comprises the following steps: transmitting a frequency-modulated continuous wave signal to a to-be-monitored driver through a radar sensing front end, receiving a reflected echo signal reflected by the to-be-monitored driver, and determining a displacement signal representing chest cavity displacement of the to-be-monitored driver according to the echo signal; performing frequency band decomposition on the displacement signal to obtain a respiration signal component and a heartbeat signal component corresponding to the to-be-monitored driver; determining respiration frequency data corresponding to the to-be-monitored driver according to the respiration signal component, and determining heart rate data corresponding to the to-be-monitored driver according to the heartbeat signal component; and determining a physiological state of the to-be-monitored driver according to the respiration frequency data and the heart rate data.

Description

Technical Field

[0001] This application relates to the field of safety control technology for hydrogen-powered transportation equipment, and in particular to a physiological state monitoring method, device, equipment, storage medium, and computer program product. Background Technology

[0002] In modern rail transit systems, the physiological state of locomotive drivers is a key factor affecting driving safety. Continuous monitoring of drivers' deep physiological parameters such as heart rate, respiratory rate, and heart rate variability helps to promptly detect the risk of physiological disability caused by fatigue, microsleep, or sudden illness.

[0003] Currently, the driver monitoring technologies used in the industry mainly fall into two categories.

[0004] The first type is a visual monitoring system, which mainly uses cameras to capture images of the driver's face and computer vision algorithms to identify external behavioral features such as closed eyes and yawning, thereby inferring their alertness level. However, this type of system cannot obtain deeper physiological parameters such as heart rate and respiration, and its performance is greatly affected by changes in lighting conditions.

[0005] The second category is contact-based physiological monitoring devices. These devices are typically worn by the driver in the form of smart bracelets or ECG straps, or integrated into the control handle and require skin contact to acquire cardiovascular signals. However, this type of solution suffers from low effective utilization in practice and requires the driver's active cooperation.

[0006] Therefore, how to achieve continuous 24 / 7 monitoring of a driver's heart rate, respiration, and other deep physiological parameters without any contact with the human body or the collection of biometric images, in order to improve driving safety, has become a technical problem that urgently needs to be solved by existing technologies. Summary of the Invention

[0007] This application provides a physiological state monitoring method to solve the problem that existing physiological monitoring schemes cannot achieve continuous 24 / 7 monitoring of deep physiological parameters such as driver's heart rate and respiration without contact with the human body.

[0008] This application also provides a physiological state monitoring device to solve the problem that existing physiological monitoring solutions cannot achieve continuous 24 / 7 monitoring of deep physiological parameters such as driver's heart rate and respiration without contact with the human body.

[0009] This application also provides a physiological state monitoring device to solve the problem that existing physiological monitoring solutions cannot achieve continuous 24 / 7 monitoring of deep physiological parameters such as driver's heart rate and respiration without contact with the human body.

[0010] This application also provides a computer-readable storage medium to address the problem that existing physiological monitoring schemes cannot achieve continuous, 24 / 7 monitoring of deep physiological parameters such as driver's heart rate and respiration without contact with the human body.

[0011] A computer program product designed to address the shortcomings of existing product recommendation schemes, specifically the inability of existing physiological monitoring schemes to achieve continuous, 24 / 7 monitoring of drivers' deep physiological parameters such as heart rate and respiration without human contact.

[0012] The embodiments of this application adopt the following technical solutions: A method for monitoring physiological state includes: transmitting a frequency-modulated continuous wave signal to a driver to be monitored via a radar sensing front end, receiving an echo signal reflected by the driver to be monitored, and determining a displacement signal characterizing the displacement of the driver's chest cavity based on the echo signal; performing frequency band decomposition on the displacement signal to obtain a respiratory signal component and a heartbeat signal component corresponding to the driver to be monitored; determining respiratory frequency data corresponding to the driver to be monitored based on the respiratory signal component, and determining heart rate data corresponding to the driver to be monitored based on the heartbeat signal component; and determining the physiological state of the driver to be monitored based on the respiratory frequency data and the heart rate data.

[0013] A physiological state monitoring device includes: a radar sensing unit, configured to transmit a frequency-modulated continuous wave signal to a driver to be monitored via a radar sensing front end, receive an echo signal reflected by the driver to be monitored, and determine a displacement signal characterizing the chest cavity displacement of the driver to be monitored based on the echo signal; a signal acquisition unit, configured to perform frequency band decomposition on the displacement signal to obtain a respiratory signal component and a heartbeat signal component corresponding to the driver to be monitored; a physiological parameter determination unit, configured to determine the respiratory frequency data corresponding to the driver to be monitored based on the respiratory signal component, and determine the heart rate data corresponding to the driver to be monitored based on the heartbeat signal component; and a state determination unit, configured to determine the physiological state of the driver to be monitored based on the respiratory frequency data and the heart rate data.

[0014] A physiological state monitoring device, comprising: The processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the following operations: transmitting a frequency-modulated continuous wave signal to a driver under surveillance from a radar sensing front end, receiving an echo signal reflected by the driver under surveillance, and determining a displacement signal characterizing the chest cavity displacement of the driver under surveillance based on the echo signal; performing frequency band decomposition on the displacement signal to obtain a respiratory signal component and a heartbeat signal component corresponding to the driver under surveillance; determining respiratory frequency data corresponding to the driver under surveillance based on the respiratory signal component, and determining heart rate data corresponding to the driver under surveillance based on the heartbeat signal component; and determining the physiological state of the driver under surveillance based on the respiratory frequency data and the heart rate data.

[0015] A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including multiple application programs, cause the electronic device to perform the following operations: transmitting a frequency-modulated continuous wave signal to a driver to be monitored via a radar sensing front end, receiving an echo signal reflected by the driver to be monitored, and determining a displacement signal characterizing the chest cavity displacement of the driver to be monitored based on the echo signal; performing frequency band decomposition on the displacement signal to obtain a respiratory signal component and a heartbeat signal component corresponding to the driver to be monitored; determining respiratory frequency data corresponding to the driver to be monitored based on the respiratory signal component, and determining heart rate data corresponding to the driver to be monitored based on the heartbeat signal component; and determining the physiological state of the driver to be monitored based on the respiratory frequency data and the heart rate data.

[0016] A computer program product includes a computer program that, when executed by a processor, performs the following: transmitting a frequency-modulated continuous wave signal to a driver to be monitored via a radar sensing front end, receiving an echo signal reflected by the driver to be monitored, and determining a displacement signal characterizing the chest cavity displacement of the driver to be monitored based on the echo signal; performing frequency band decomposition on the displacement signal to obtain a respiratory signal component and a heartbeat signal component corresponding to the driver to be monitored; determining respiratory frequency data corresponding to the driver to be monitored based on the respiratory signal component, and determining heart rate data corresponding to the driver to be monitored based on the heartbeat signal component; and determining the physiological state of the driver to be monitored based on the respiratory frequency data and the heart rate data.

[0017] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: Using the physiological state monitoring method provided in this application embodiment, when monitoring the physiological state of a driver, a frequency-modulated continuous wave signal can be transmitted to the driver to be monitored by a radar sensing front end, and the echo signal reflected by the driver to be monitored can be received. Based on the echo signal, a displacement signal representing the displacement of the driver's chest cavity can be determined. Then, the displacement signal can be decomposed into frequency bands to obtain the respiratory signal component and heartbeat signal component corresponding to the driver to be monitored. Then, the respiratory frequency data corresponding to the driver to be monitored can be determined based on the respiratory signal component, and the heart rate data corresponding to the driver to be monitored can be determined based on the heartbeat signal component. Finally, the physiological state of the driver to be monitored can be determined based on the respiratory frequency data and heart rate data. The physiological state monitoring method provided in this application, on the one hand, transmits frequency-modulated continuous wave signals to the driver through a radar sensing front end and receives the echo reflected from the human chest cavity, thereby extracting signals characterizing the micro-displacement of the chest cavity. This monitoring method does not require the driver to wear any electrodes, wristbands, chest straps, or other contact sensors, nor does it require installing cameras in the cockpit to collect facial images. Under normal driving posture, the driver's breathing and heartbeat-induced micro-movements of the chest cavity can be detected by radar. The entire process is completely imperceptible to the driver, completely eliminating the poor compliance of traditional contact devices and the privacy concerns of visual monitoring. On the one hand, it has the disadvantages of traditional methods; on the other hand, by performing frequency band decomposition on the chest displacement signal, and taking advantage of the natural differences between respiratory and cardiac movements in the frequency domain (lower respiratory rate and higher heart rate), independent respiratory and cardiac signal components are separated, and respiratory rate data and heart rate data are calculated accordingly. This can directly reflect the functional state of the driver's cardiopulmonary system. Compared with visual monitoring schemes that can only observe surface behaviors such as closing eyes and yawning, it can reach the key physiological indicators for judging the driver's true alertness level, and make up for the fatal defect of traditional technology in failing to monitor intrinsic disability states such as open-eye coma and microsleep. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A schematic diagram of the specific structure of a physiological state monitoring system provided in this application embodiment; Figure 2 This is a schematic flowchart illustrating a physiological state method provided in an embodiment of this application. Figure 3 A schematic diagram of the specific structure of a physiological state monitoring device provided in this application embodiment; Figure 4 This is a schematic diagram of the specific structure of a physiological state monitoring device provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] This application provides a physiological state monitoring method to solve the problem that existing physiological monitoring schemes cannot achieve continuous 24 / 7 monitoring of deep physiological parameters such as driver's heart rate and respiration without contact with the human body.

[0021] For ease of description, the following description uses a physiological state monitoring system installed in the vehicle's driver's cab as an example to illustrate the implementation of this method. It should be understood that using a physiological state monitoring system as the implementing entity is merely an illustrative example and should not be construed as a limitation of the method.

[0022] In this embodiment of the application, the specific structure of the physiological state monitoring system is as follows: Figure 1 As shown, it mainly includes a 4D millimeter-wave radar sensing front-end, a signal processing unit, and a multimodal fusion logic module. In this embodiment, by embedding a 77GHz~81GHz frequency-modulated continuous wave (FMCW) 4D millimeter-wave radar module inside the driver's seat back, without contacting the human body or collecting biometric images, it demodulates the Doppler phase modulation signal caused by chest cavity micro-movements in real time, extracts core physiological parameters such as respiratory rate, heart rate, and heart rate variability (HRV), and logically coordinates with the behavioral characteristics output by the driver monitoring system deployed in the cockpit. This enables highly robust identification of physiological disability states such as sudden cardiovascular and cerebrovascular events, microsleep, and open-eye coma.

[0023] The 4D millimeter-wave radar sensing front-end employs a single-chip integrated radar sensor with a working center frequency of 79 GHz, a bandwidth of 4 GHz, and a transmit power density not exceeding -41.3 dBm per megahertz. In this embodiment, the 4D millimeter-wave radar sensing front-end can be encapsulated in a metal shielded housing made of 6061-T6 aluminum alloy, with an anodized surface to suppress electromagnetic leakage. The antenna array of the 4D millimeter-wave radar sensing front-end adopts a 2-transmit, 4-receive topology, with a horizontal field of view of ±60 degrees, a vertical field of view of ±15 degrees, a range resolution of 4 cm, and a velocity resolution of 0.1 m / s. In one embodiment, the 4D millimeter-wave radar sensing front-end can be fixed to the driver's seat backrest frame using M4 stainless steel screws. The installation position is 40 cm vertically above the upper surface of the seat cushion, laterally centered and aligned with the midline of the human spine, ensuring that the radar main beam coverage area is concentrated on the back surface area corresponding to the lower edge of the scapula to the 10th thoracic vertebra.

[0024] In this embodiment, the signal processing unit can be composed of an embedded processor, memory, an analog-to-digital converter (ADC), and a dedicated signal conditioning circuit. The embedded processor uses an ARM Cortex-A72 quad-core architecture with a clock frequency of 1.8 GHz. Its built-in hardware acceleration engine supports Fast Fourier Transform and complex matrix operations for efficient execution of phase demodulation and mode decomposition algorithms. The memory configuration includes 4 GB LPDDR4 SDRAM and 32 GB eMMC flash memory. The former is used to cache the raw intermediate frequency signal and intermediate processing results, while the latter is used to store system firmware, calibration parameters, and operation logs. The ADC uses a 12-bit resolution, 5 Msps successive approximation ADC. Its reference voltage is provided by a low-temperature drift reference source LM385, with a temperature drift coefficient of less than 5 ppm per degree Celsius, ensuring stable ADC accuracy over a wide temperature range. The signal conditioning circuit includes an anti-aliasing low-pass filter with a cutoff frequency of 2.4 MHz and a passband ripple of less than 0.1 dB, used to suppress high-frequency noise aliasing into the digital domain.

[0025] In this embodiment, the multimodal fusion logic module runs on an independent safety-grade microcontroller, employing a dual-core lockstep architecture and possessing memory ECC verification and fault injection testing capabilities. This module receives physiological state signals from the 4D millimeter-wave radar sensing front-end deployed in the cockpit via the CAN FD bus to determine the physiological state of the driver to be monitored.

[0026] Based on the aforementioned physiological state monitoring system, a schematic diagram illustrating the specific implementation process of the physiological state monitoring method provided in this application is shown below. Figure 2 As shown, the main steps include the following: Step 11: The radar sensing front end transmits a frequency-modulated continuous wave signal to the driver to be monitored and receives the echo signal reflected by the driver to be monitored. Based on the echo signal, the displacement signal characterizing the displacement of the driver's chest cavity is determined. In this embodiment of the application, when it is necessary to monitor the physiological state of the driver, the frequency-modulated continuous wave signal can be transmitted to the driver to be monitored through the radar sensing front end, and the echo signal reflected by the driver's chest cavity can be received. Then, based on the analysis of the received echo information, the displacement signal can be determined.

[0027] In one embodiment, the physiological state monitoring system may determine a displacement signal characterizing the chest cavity displacement of the driver to be monitored based on the echo signal according to the following sub-steps: Sub-step 1101 involves anti-aliasing filtering and analog-to-digital conversion of the received echo signal to obtain a discrete time series; Specifically, the echo signals output from the four receiving channels of the radar sensing front end can first be processed by an anti-aliasing low-pass filter. The cutoff frequency of the anti-aliasing low-pass filter can be set to 2.4 MHz, and the passband ripple is less than 0.1 dB, which is used to suppress high-frequency noise aliasing.

[0028] Subsequently, the echo signal, after anti-aliasing filtering, is sent to an analog-to-digital converter (ADC) for analog-to-digital conversion to obtain four discrete-time series. In this embodiment, the ADC can be a 12-bit resolution, 5Msps sampling rate Successive Approximation Register (SAR) ADC, with its reference voltage provided by a low-temperature drift reference source LM385, and a temperature drift coefficient of less than 5ppm / ℃.

[0029] Sub-step 1102: Perform a two-dimensional frequency domain transformation on the discrete time series obtained by executing sub-step 1101 to obtain a distance-velocity heatmap; Specifically, the physiological state monitoring system can perform a two-dimensional fast fourier transform (2D FFT) on each discrete time series, where the distance dimension FFT has 1024 points and the velocity dimension FFT has 256 points, generating a four-channel distance-velocity heatmap. The four-channel heatmaps are then incoherently superimposed to improve the signal-to-noise ratio.

[0030] Sub-step 1103: Based on the range-velocity heatmap obtained by performing sub-step 1102, search for the range cell corresponding to the energy peak in the range dimension, and extract the complex baseband signal corresponding to the range cell. In this embodiment, the search range of the energy peak can be limited to the interval between 0.1 meters and 0.5 meters, with a step size corresponding to a distance resolution of 4 centimeters. After locking the target distance cell, the time series of the complex baseband signal corresponding to the cell is extracted, as shown in the following formula [1]: s(t)=I(t)+jQ(t)s(t)=I(t)+jQ(t) [1] Where I(t) and Q(t) are the in-phase component and the quadrature component, respectively.

[0031] Sub-step 1104: Determine the instantaneous phase corresponding to the complex baseband signal, perform continuous phase processing on the instantaneous phase, and obtain the continuous phase trajectory; In this embodiment of the application, the instantaneous phase corresponding to the complex baseband signal can be determined according to the following formula [2]: (t)= =arctan(I(t)Q(t)) [2] It should also be noted that, in order to eliminate the phase entanglement effect, a phase unwrapping algorithm can be used in the embodiments of this application. (t) is processed to obtain a continuous phase trajectory without jumps.

[0032] Sub-step 1105: Determine the displacement signal based on the continuous phase trajectory obtained by executing sub-step 1104; In this embodiment of the application, the continuous phase trajectory can be converted into a thoracic displacement signal x(t) after scaling transformation according to the following formula [3]: x(t) = λ / (4π)· (t) [3] Where λ is the radar wavelength, for example, at a center frequency of 79 GHz, λ is 3.8 mm.

[0033] In this embodiment of the application, the displacement signal x(t) obtained by performing the above sub-steps may include, but is not limited to, the following three main components: 1. Respiratory displacement signal: In one embodiment, the displacement amplitude caused by respiratory movements is generally 1 mm to 10 mm, and the frequency range is 0.1 Hz to 0.5 Hz. 2. Cardiac pulsation displacement signal: In one embodiment, the amplitude of the micro-vibrations on the body surface caused by the heartbeat can generally be 0.1 mm to 0.5 mm, and the frequency range is 0.8 Hz to 2.0 Hz. 3. Low-frequency motion interference signals: The main source of interference is low-frequency bodily motion, which is caused by arm manipulation or torso rotation. Its frequency is below 0.1 Hz and its amplitude can reach several millimeters.

[0034] It should be noted that, in order to further improve signal quality and reduce low-frequency body movement interference signals, an adaptive body movement inhibition module can also be integrated into the physiological state monitoring system in this embodiment.

[0035] Specifically, a triaxial micro-electro-mechanical system (MEMS) accelerometer can be installed under the driver's seat armrest. The accelerometer communicates with the signal processing unit via an I²C bus, with a sampling rate of 100 Hz. When any axial acceleration amplitude exceeds 0.3g and its duration is greater than 200 milliseconds, it can be identified as a significant body movement event. At this point, the physiological state monitoring system can activate a Normalized Least Mean Square (NLMS) adaptive filter, using the envelope of the acceleration signal as a reference input, to perform online interference cancellation on the thoracic displacement signal x(t). The order of this adaptive filter can be set to 64, and the step size factor is μ=0.01 to ensure that the integrity of the heartbeat signal is effectively preserved during body movement.

[0036] Step 12: Perform frequency band decomposition on the displacement signal obtained by executing step 11 to obtain the respiratory signal component and heartbeat signal component corresponding to the driver to be monitored. In this embodiment, the physiological state monitoring system can perform frequency band decomposition on the displacement signal to obtain the respiratory signal component and heartbeat signal component corresponding to the driver to be monitored, including: inputting the displacement signal into a variational mode decomposition model, setting the number of modes to 3, and solving the center frequency and bandwidth of each mode component through iterative search; performing frequency band decomposition on the displacement signal according to the variational mode decomposition algorithm, and solving the center frequency and bandwidth of each mode component through iterative search; after decomposition, the body motion clutter corresponding to the first mode, the respiratory signal component corresponding to the second mode, and the heartbeat signal component corresponding to the third mode are obtained.

[0037] Specifically, the physiological state monitoring system can input displacement signals into a Variational Mode Decomposition (VMD) model, and set the VMD model to have the number of modes K=3, a penalty factor α=2000, and a convergence tolerance ε=1×10⁻⁶. -7 The VMD model adaptively decomposes the signal into multiple intrinsic mode functions by iteratively searching for the center frequency and bandwidth of each modal component.

[0038] After decomposition, the following three eigenmode functions can be obtained: 1. The first mode corresponds to bulk noise, with a frequency below 0.1 Hz; 2. The second mode corresponds to the respiratory signal component, the frequency range of which is 0.1Hz~0.5Hz; 3. The third mode corresponds to the heartbeat signal component, the frequency range of which is 0.8Hz~2.0Hz.

[0039] It should be noted that the embodiments of this application do not specifically limit the method of frequency band decomposition. In addition to the above methods, any method of empirical mode decomposition (EMD) or wavelet transform can also be used.

[0040] Step 13: Determine the respiratory rate data of the driver to be monitored based on the respiratory signal components obtained by performing Step 12; In this embodiment of the application, the physiological state monitoring system can determine respiratory rate data by means of the following method: determining the power spectrum corresponding to the respiratory signal component by using sliding window processing on the respiratory signal component; determining the main peak frequency in the power spectrum according to the power spectrum; and determining the main peak frequency as the respiratory rate when the signal-to-noise ratio of the main peak frequency is greater than a preset threshold.

[0041] Specifically, the physiological state monitoring system can determine the power spectrum corresponding to the respiratory signal component by using a sliding window processing method with a window length of 10 seconds and an overlap rate of 50%, applying a Hanning window to each window of data, and then performing Welch power spectrum estimation with a spectral resolution of 0.01 Hz.

[0042] Then, based on the power spectrum, the main peak frequency in the power spectrum is determined. When the signal-to-noise ratio of the main peak frequency is greater than a preset threshold (e.g., 6 dB), the main peak frequency is determined as the respiratory rate. If the signal-to-noise ratio of the main peak is less than 6 dB, it is determined that the respiratory signal quality is insufficient, triggering the data confidence mark and marking it as low confidence.

[0043] Step 14: Determine the heart rate data of the driver to be monitored based on the heartbeat signal components obtained by performing Step 12; In this embodiment of the application, the physiological state monitoring system can determine the heart rate data of the driver to be monitored by the following method: determining the local maximum point corresponding to the heartbeat signal component by performing waveform feature enhancement processing on the heartbeat signal component; determining the adjacent heartbeat interval sequence based on the local maximum point; and determining the heart rate data of the driver to be monitored based on the heartbeat interval sequence.

[0044] Specifically, the physiological state monitoring system can first perform a five-point differential operation on the heartbeat signal using the following formula [4] to enhance the steepness of the R wave: s diff(t) =14[x(t+2) 2x(t)+x(t twenty four] Subsequently, the dynamic threshold Th was set to 0.6·max(|s diff(t) |), detect all local maxima points that exceed the dynamic threshold Th, and remove outliers with adjacent intervals of less than 300 milliseconds or greater than 2000 milliseconds to obtain an effective sequence of local maxima points.

[0045] Based on the local maxima, the Inter-Beat Interval (IBI) sequence is determined and denoted as {IBIn}, where each IBI represents the time interval between two adjacent heartbeats.

[0046] Finally, based on the heart rate interval sequence, the heart rate data corresponding to the driver to be monitored is determined according to the following formula [5]: HR = 60 / mean(IBIn) [5] In addition, in this embodiment of the application, the heart rate variability (HRV) index can be determined based on the standard deviation of the heart rate interval sequence {IBIn}. In this embodiment of the application, the calculation window length for the HRV index can be set to 5 minutes and the update cycle to 30 seconds.

[0047] Step 15: Determine the physiological state of the driver to be monitored based on the respiratory rate data determined by performing Step 13 and the heart rate data obtained by performing Step 14.

[0048] In this embodiment of the application, the physiological state monitoring system can acquire the driver status flags output by the driver monitoring system (DMS). The DMS is an existing system in the cockpit that can output Boolean variables such as "driver is seated", "eyes open", and "head posture is normal" to indicate the driver's current state.

[0049] Furthermore, the physiological state monitoring system can logically fuse respiratory rate data, heart rate data, and heart rate variability indicators with the driver status flags uploaded by the DMS, and determine the physiological state of the driver to be monitored according to the following two preset judgment strategies, which may include: The first strategy is to determine the cause of sudden physiological disability: Specifically, when the physiological state monitoring system determines that the heart rate data or respiratory rate data is abnormal for a preset first duration, such as outputting "invalid heart rate" or "zero respiratory rate" for 10 consecutive seconds, and the driver status indicator indicates that the driver is seated, the physiological state monitoring system can determine that the driver's current physiological state is a sudden physiological disability event, such as cardiac arrest or respiratory arrest.

[0050] Then, the physiological state monitoring system can initiate the first-level intervention measures: immediately drive the buzzer in the cockpit to sound at a frequency of 2.4 kHz with a sound pressure level of 85 dB, and at the same time illuminate the red warning light (wavelength 625 nm, brightness 500 candela per square meter), and send an emergency braking request message to the Train Control and Management System (TCMS) through the Multifunction Vehicle Bus (MVB). The message identifier is 0x1A3, and the data field contains the event type code 0x01 and timestamp information.

[0051] The second rule strategy, determining cognitive disability status: Specifically, when the physiological state monitoring system determines that the driver's status indicator indicates that the driver's eyes are open, and the heart rate variability index is consistently below the first threshold (e.g., 20 milliseconds), the fluctuation range of the respiratory rate is consistently below the second threshold (e.g., 0.5 breaths / minute), and the duration reaches the second duration (e.g., 30 seconds), then the physiological state monitoring system can determine that the driver's current physiological state is a state of cognitive impairment, such as microsleep or open-eye coma.

[0052] At this point, the physiological state monitoring system can initiate the second-level intervention: activate the eccentric wheel motor at the bottom of the seat, which converts the rotational motion into a simple harmonic motion in the vertical direction through the crank-connecting rod mechanism, with an amplitude of 2 mm, a frequency of 5 Hz, and a duration of 10 seconds; at the same time, a yellow warning icon pops up on the cockpit display screen to alert the driver to decreased alertness.

[0053] It should be noted that, in order to improve the recognition accuracy of the physiological state monitoring system, this application embodiment also provides a self-diagnosis and environmental adaptation method for the physiological state monitoring system. Specifically, during the self-test phase of each physiological state monitoring system startup, the radar sensing front end performs a Built-In Self-Test (BIST), including transmit power calibration, receive link gain verification, and phase consistency check; if the phase error is greater than 5 degrees, a fault code 0x2F is reported to the TCMS. During operation, the physiological state monitoring system continuously monitors the radar echo signal-to-noise ratio (SNR). When the SNR is below 10 dB for 5 seconds, the signal processing frame rate is automatically switched from 20 Hz to 5 Hz (low-speed sampling mode) to extend the effective monitoring time window. In addition, the radar chip temperature can be collected in real time by a temperature sensor, and the phase measurement results can be compensated in real time according to a pre-calibrated temperature drift compensation coefficient. The compensation coefficient is stored in the embedded memory, and the calibration process covers the full operating temperature range of -25℃ to +70℃.

[0054] Using the physiological state monitoring method provided in this application embodiment, when monitoring the physiological state of a driver, a frequency-modulated continuous wave signal can be transmitted to the driver to be monitored by a radar sensing front end, and the echo signal reflected by the driver to be monitored can be received. Based on the echo signal, a displacement signal representing the displacement of the driver's chest cavity can be determined. Then, the displacement signal can be decomposed into frequency bands to obtain the respiratory signal component and heartbeat signal component corresponding to the driver to be monitored. Then, the respiratory frequency data corresponding to the driver to be monitored can be determined based on the respiratory signal component, and the heart rate data corresponding to the driver to be monitored can be determined based on the heartbeat signal component. Finally, the physiological state of the driver to be monitored can be determined based on the respiratory frequency data and heart rate data. The physiological state monitoring method provided in this application, on the one hand, transmits frequency-modulated continuous wave signals to the driver through a radar sensing front end and receives the echo reflected from the human chest cavity, thereby extracting signals characterizing the micro-displacement of the chest cavity. This monitoring method does not require the driver to wear any electrodes, wristbands, chest straps, or other contact sensors, nor does it require installing cameras in the cockpit to collect facial images. Under normal driving posture, the driver's breathing and heartbeat-induced micro-movements of the chest cavity can be detected by radar. The entire process is completely imperceptible to the driver, completely eliminating the poor compliance of traditional contact devices and the privacy concerns of visual monitoring. On the one hand, it has the disadvantages of traditional methods; on the other hand, by performing frequency band decomposition on the chest displacement signal, and taking advantage of the natural differences between respiratory and cardiac movements in the frequency domain (lower respiratory rate and higher heart rate), independent respiratory and cardiac signal components are separated, and respiratory rate data and heart rate data are calculated accordingly. This can directly reflect the functional state of the driver's cardiopulmonary system. Compared with visual monitoring schemes that can only observe surface behaviors such as closing eyes and yawning, it can reach the key physiological indicators for judging the driver's true alertness level, and make up for the fatal defect of traditional technology in failing to monitor intrinsic disability states such as open-eye coma and microsleep.

[0055] In one embodiment, this application also provides a physiological state monitoring device to address the problem that existing physiological monitoring solutions cannot achieve continuous, 24 / 7 monitoring of a driver's deep physiological parameters such as heart rate and respiration without contact with the human body. A schematic diagram of the specific structure of this physiological state monitoring device is shown below. Figure 3 As shown, it includes: a radar sensing unit 31, a signal acquisition unit 32, a physiological parameter determination unit 33, and a state determination unit 34.

[0056] Among them, the radar sensing unit 31 is used to transmit a frequency-modulated continuous wave signal to the driver to be monitored according to the radar sensing front end, receive the echo signal reflected by the driver to be monitored, and determine the displacement signal characterizing the displacement of the driver's chest cavity according to the echo signal. Signal acquisition unit 32 is used to perform frequency band decomposition on the displacement signal to obtain the respiratory signal component and heartbeat signal component corresponding to the driver to be monitored. The physiological parameter determination unit 33 is used to determine the respiratory rate data corresponding to the driver to be monitored based on the respiratory signal component, and to determine the heart rate data corresponding to the driver to be monitored based on the heartbeat signal component. The status determination unit 34 is used to determine the physiological status of the driver to be monitored based on the respiratory rate data and the heart rate data.

[0057] In one embodiment, the radar sensing unit 31 is specifically used for: anti-aliasing filtering and analog-to-digital conversion of the echo signal to obtain a discrete time series; performing a two-dimensional frequency domain transformation based on the discrete time series to obtain a range-velocity heatmap; searching for the range cell corresponding to the energy peak in the range dimension based on the range-velocity heatmap, and extracting the complex baseband signal corresponding to the range cell; determining the instantaneous phase corresponding to the complex baseband signal, performing continuous processing on the instantaneous phase to obtain a continuous phase trajectory; and determining the displacement signal based on the continuous phase trajectory.

[0058] In one embodiment, the signal acquisition unit 32 is specifically used for: inputting the displacement signal into the variational mode decomposition model, setting the number of modes to 3, and solving the center frequency and bandwidth of each mode component through iterative search; performing frequency band decomposition on the displacement signal according to the variational mode decomposition algorithm, and solving the center frequency and bandwidth of each mode component through iterative search; and obtaining the body motion clutter corresponding to the first mode, the respiratory signal component corresponding to the second mode, and the heartbeat signal component corresponding to the third mode after decomposition.

[0059] In one embodiment, the physiological parameter determination unit 33 is specifically used to: determine the power spectrum corresponding to the respiratory signal component by applying sliding window processing to the respiratory signal component; determine the main peak frequency in the power spectrum according to the power spectrum; and determine the main peak frequency as the respiratory frequency when the signal-to-noise ratio of the main peak frequency is greater than a preset threshold.

[0060] In one embodiment, the physiological parameter determination unit 33 is specifically used to: determine the local maximum point corresponding to the heartbeat signal component by performing waveform feature enhancement processing on the heartbeat signal component; determine the adjacent heartbeat interval sequence based on the local maximum point; and determine the heart rate data corresponding to the driver to be monitored based on the heartbeat interval sequence.

[0061] In one embodiment, the radar sensing front end is located inside the seat back of the driver to be monitored, and the antenna array of the radar sensing front end adopts a 2-transmit 4-receive topology.

[0062] Using the physiological state monitoring device provided in this application embodiment, when monitoring the physiological state of a driver, the device can transmit a frequency-modulated continuous wave signal to the driver under test via a radar sensing front end, and receive the echo signal reflected by the driver under test. Based on the echo signal, the device can determine the displacement signal characterizing the displacement of the driver's chest cavity, and then perform frequency band decomposition on the displacement signal to obtain the respiratory signal component and heartbeat signal component corresponding to the driver under test. Based on the respiratory signal component, the device can determine the respiratory frequency data corresponding to the driver under test, and based on the heartbeat signal component, the device can determine the heart rate data corresponding to the driver under test. Finally, the device can determine the physiological state of the driver under test based on the respiratory frequency data and the heart rate data. The physiological state monitoring device provided in this application, on the one hand, transmits frequency-modulated continuous wave signals to the driver through a radar sensing front end and receives the echo reflected from the human chest cavity, thereby extracting signals characterizing the micro-displacement of the chest cavity. This monitoring method does not require the driver to wear any electrodes, wristbands, chest straps, or other contact sensors, nor does it require installing a camera in the cockpit to collect facial images. Under normal driving posture, the driver's breathing and heartbeat cause minute chest movements that can be detected by radar. The entire process is completely imperceptible to the driver, completely eliminating the poor compliance of traditional contact devices and the privacy concerns of visual monitoring. On the one hand, it has the disadvantages of traditional methods; on the other hand, by performing frequency band decomposition on the chest displacement signal, and taking advantage of the natural differences between respiratory and cardiac movements in the frequency domain (lower respiratory rate and higher heart rate), independent respiratory and cardiac signal components are separated, and respiratory rate data and heart rate data are calculated accordingly. This can directly reflect the functional state of the driver's cardiopulmonary system. Compared with visual monitoring schemes that can only observe surface behaviors such as closing eyes and yawning, it can reach the key physiological indicators for judging the driver's true alertness level, and make up for the fatal defect of traditional technology in failing to monitor intrinsic disability states such as open-eye coma and microsleep.

[0063] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 4 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0064] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0065] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0066] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming a physiological state monitoring device at the logical level. The processor executes the program stored in memory and specifically performs the following operations: The radar sensing front end transmits a frequency-modulated continuous wave signal to the driver to be monitored and receives the echo signal reflected by the driver. Based on the echo signal, a displacement signal characterizing the displacement of the driver's chest cavity is determined. The displacement signal is decomposed into frequency bands to obtain the respiratory signal component and heartbeat signal component corresponding to the driver. The respiratory rate data corresponding to the driver is determined based on the respiratory signal component, and the heart rate data corresponding to the driver is determined based on the heartbeat signal component. Based on the respiratory rate data and the heart rate data, the physiological state of the driver is determined.

[0067] The above is as stated in this application. Figure 4The method for physiological state monitoring electronic devices disclosed in the illustrated embodiments can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0068] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0069] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by a portable electronic device including multiple applications, enable the portable electronic device to perform... Figure 2 The physiological state monitoring method of the illustrated embodiment is specifically used to perform the following operations: The radar sensing front end transmits a frequency-modulated continuous wave signal to the driver to be monitored and receives the echo signal reflected by the driver. Based on the echo signal, a displacement signal characterizing the displacement of the driver's chest cavity is determined. The displacement signal is decomposed into frequency bands to obtain the respiratory signal component and heartbeat signal component corresponding to the driver. The respiratory rate data corresponding to the driver is determined based on the respiratory signal component, and the heart rate data corresponding to the driver is determined based on the heartbeat signal component. Based on the respiratory rate data and the heart rate data, the physiological state of the driver is determined.

[0070] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0071] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0072] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0073] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0074] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0075] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0076] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0077] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0078] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for monitoring physiological states, characterized in that, include: The radar sensing front end transmits a frequency-modulated continuous wave signal to the driver to be monitored, receives the echo signal reflected by the driver to be monitored, and determines the displacement signal characterizing the displacement of the driver's chest cavity based on the echo signal. The displacement signal is decomposed into frequency bands to obtain the respiratory signal component and heartbeat signal component corresponding to the driver to be monitored. The respiratory rate data corresponding to the driver to be monitored is determined based on the respiratory signal component, and the heart rate data corresponding to the driver to be monitored is determined based on the heartbeat signal component. The physiological state of the driver to be monitored is determined based on the respiratory rate data and the heart rate data.

2. The method according to claim 1, characterized in that, The step of determining the displacement signal characterizing the chest cavity displacement of the driver to be monitored based on the echo signal specifically includes: The echo signal is subjected to anti-aliasing filtering and analog-to-digital conversion to obtain a discrete time series; A two-dimensional frequency domain transformation is performed on the discrete time series to obtain a distance-velocity heatmap; Based on the distance-velocity heatmap, search for the distance cell corresponding to the energy peak in the distance dimension, and extract the complex baseband signal corresponding to the distance cell; Determine the instantaneous phase corresponding to the complex baseband signal, and perform continuous phase processing on the instantaneous phase to obtain a continuous phase trajectory; The displacement signal is determined based on the continuous phase trajectory.

3. The method according to claim 1, characterized in that, The step of performing frequency band decomposition on the displacement signal to obtain the respiratory signal component and heartbeat signal component corresponding to the driver to be monitored specifically includes: The displacement signal is input into the variational mode decomposition model, the number of modes is set to 3, and the center frequency and bandwidth of each modal component are solved by iterative search. According to the variational mode decomposition algorithm, the displacement signal is decomposed into frequency bands, and the center frequency and bandwidth of each modal component are solved by iterative search. After decomposition, we obtain the body motion clutter corresponding to the first mode, the respiratory signal component corresponding to the second mode, and the heartbeat signal component corresponding to the third mode.

4. The method according to claim 1, characterized in that, The step of determining the respiratory rate data corresponding to the driver to be monitored based on the respiratory signal components specifically includes: The power spectrum corresponding to the respiratory signal component is determined by applying a sliding window processing method to the respiratory signal component. Based on the power spectrum, the main peak frequency in the power spectrum is determined. When the signal-to-noise ratio of the main peak frequency is greater than a preset threshold, the main peak frequency is determined as the respiratory rate.

5. The method according to claim 1, characterized in that, The step of determining the heart rate data corresponding to the driver to be monitored based on the heartbeat signal components specifically includes: By performing waveform feature enhancement processing on the heartbeat signal component, the local maximum point corresponding to the heartbeat signal component is determined; Based on the local maxima, determine the sequence of adjacent heartbeat intervals; Based on the heart rate interval sequence, the heart rate data corresponding to the driver to be monitored is determined.

6. The method according to claim 1, characterized in that, The radar sensing front end is located inside the seat back of the driver to be monitored, and the antenna array of the radar sensing front end adopts a 2-transmit 4-receive topology.

7. A physiological state monitoring device, characterized in that, include: The radar sensing unit is used to transmit a frequency-modulated continuous wave signal to the driver to be monitored based on the radar sensing front end, receive the echo signal reflected by the driver to be monitored, and determine the displacement signal characterizing the displacement of the driver's chest cavity based on the echo signal. The signal acquisition unit is used to perform frequency band decomposition on the displacement signal to obtain the respiratory signal component and heartbeat signal component corresponding to the driver to be monitored. The physiological parameter determination unit is used to determine the respiratory rate data corresponding to the driver to be monitored based on the respiratory signal component, and to determine the heart rate data corresponding to the driver to be monitored based on the heartbeat signal component. A status determination unit is used to determine the physiological status of the driver to be monitored based on the respiratory rate data and the heart rate data.

8. A physiological state monitoring device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the following operations: The radar sensing front end transmits a frequency-modulated continuous wave signal to the driver to be monitored, receives the echo signal reflected by the driver to be monitored, and determines the displacement signal characterizing the displacement of the driver's chest cavity based on the echo signal. The displacement signal is decomposed into frequency bands to obtain the respiratory signal component and heartbeat signal component corresponding to the driver to be monitored. The respiratory rate data corresponding to the driver to be monitored is determined based on the respiratory signal component, and the heart rate data corresponding to the driver to be monitored is determined based on the heartbeat signal component. The physiological state of the driver to be monitored is determined based on the respiratory rate data and the heart rate data.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the physiological state monitoring method as described in any one of claims 1-6.

10. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the physiological state monitoring method as described in any one of claims 1-6.

Images