A method, apparatus, device, medium and product for user health monitoring

Abstract

This invention provides a method, apparatus, device, medium, and product for user health monitoring, applied in the field of wireless sensing technology. The method includes: acquiring channel state information collected by a wireless network device on multiple subcarriers; performing multi-user separation on the channel state information to obtain channel state information components for each user; performing phase extraction on the channel state information components to obtain continuous phase signals for each user; performing spectral analysis on the continuous phase signals to obtain the respiratory frequency and heart rate of each user; and monitoring health status based on the respiratory frequency and heart rate. Through this invention, user health monitoring is achieved using wireless network devices, eliminating the need to deploy dedicated health monitoring equipment, thus reducing costs. Furthermore, by separating different users through multi-user separation, user-level health monitoring is achieved, improving the effectiveness of health monitoring.

Description

Technical Field

[0001] This invention relates to the field of wireless sensing technology, and in particular to a method, apparatus, device, medium, and product for user health monitoring. Background Technology

[0002] With the development of science and technology, the demand for user health monitoring is increasing, but existing user health monitoring methods are usually costly and ineffective.

[0003] For example, dedicated devices can be used for user health monitoring, but most dedicated devices are limited to clinic use and require trained technicians for installation, which is costly. There are also some portable devices, but these are not user-friendly and require professionals to install the sensors.

[0004] For example, wearable technology can be used for user health monitoring, but it requires the purchase of wearable devices, which is costly, and users may experience discomfort from wearing wearable devices continuously.

[0005] For example, computer vision technology can be used for user health monitoring, but it has privacy and security issues and cannot work in non-line-of-sight scenarios, resulting in poor performance. Summary of the Invention

[0006] In view of the above problems, a method, apparatus, device, medium, and product for user health monitoring are proposed to overcome or at least partially solve the above problems, including: A method for monitoring user health, the method comprising: Acquire channel state information collected by wireless network devices on multiple subcarriers; The channel state information is separated into multiple users to obtain the channel state information components for each user. Phase extraction is performed on the channel state information components to obtain the continuous phase signal for each user; The continuous phase signal is subjected to spectral analysis to obtain the respiratory rate and heart rate of each user, and the health status is monitored based on the respiratory rate and heart rate.

[0007] Optionally, the channel state information is subjected to multi-user separation to obtain channel state information components for each user, including: Based on the channel state information, construct the spatial frequency covariance matrix; The spatial frequency covariance matrix is ​​subjected to eigenvalue decomposition to obtain the angle of arrival for each user; Beamforming is performed on the channel state information based on the angle of arrival to obtain the channel state information components for each user.

[0008] Optionally, based on the channel state information, a spatial frequency covariance matrix is ​​constructed, including: Determine the channel state information of each subcarrier and the product of the conjugate transpose of the channel state information; Based on the number of subcarriers, the products of all subcarriers are summed and averaged to obtain the spatial frequency covariance matrix.

[0009] Optionally, after beamforming the channel state information based on the angle of arrival to obtain the channel state information components for each user, the method further includes: The path delay of the user is determined based on the channel state information components; Based on each user's angle of arrival, path delay, and circadian rhythm information, a joint spatial-temporal information of the user is constructed, and a Gaussian mixture model is constructed based on the joint spatial-temporal information; wherein, each Gaussian component in the Gaussian mixture model corresponds to one user; When multiple frames of channel state information exist, for the current frame, the user's spatial-temporal joint information is matched with each Gaussian component in the Gaussian mixture model to obtain the matched Gaussian component, and the tracking relationship between the user in the current frame and the user in the previous frame is established based on the matched Gaussian component.

[0010] Optionally, determining the user's path delay based on the channel state information components includes: The channel state information components are transformed to obtain the time-domain impulse response; The peak position in the time-domain impulse response is detected to determine the user's path delay.

[0011] Optionally, phase extraction is performed on the channel state information components to obtain continuous phase signals for each user, including: Phase extraction is performed on the channel state information components to obtain the original phase sequence; The original phase sequence is unwound to obtain the user's continuous phase signal.

[0012] Optionally, after unwinding the original phase sequence to obtain the user's continuous phase signal, the method further includes: Differential operation processing is performed on the continuous phase signal of the user.

[0013] Optionally, spectral analysis is performed on the continuous phase signal to obtain the respiratory rate and heart rate of each user, including: The continuous phase signal is filtered to obtain the respiratory frequency band signal and the heartbeat frequency band signal; The user's breathing frequency is obtained by performing spectral analysis on the breathing frequency band signal; The heartbeat frequency of the user is obtained by performing spectral analysis on the heartbeat frequency band signal.

[0014] Optionally, before performing spectral analysis on the continuous phase signal to obtain the respiratory rate and heart rate of each user, the method further includes: The continuous phase signal is enhanced.

[0015] Optionally, signal enhancement of the continuous phase signal includes: The continuous phase signal is transformed to obtain the signal spectrum; Construct the frequency response of a time-varying filter; The signal spectrum is filtered based on the frequency response to obtain a continuous phase signal with enhanced signal.

[0016] Optionally, the frequency response of the time-varying filter is constructed, including: Based on the signal spectrum, determine the environmental noise intensity index; Determine the high-frequency suppression coefficient based on the aforementioned environmental noise intensity index; Determine the passband range of the time-varying filter based on historical breathing intervals; The frequency response of the time-varying filter is constructed based on the high-frequency suppression coefficient and the passband range.

[0017] A device for monitoring user health, the device comprising: The channel state information acquisition module is used to acquire channel state information collected by the wireless network device on multiple subcarriers; The channel state information component acquisition module is used to perform multi-user separation on the channel state information to obtain the channel state information component for each user. A continuous phase signal acquisition module is used to extract the phase of the channel state information components to obtain the continuous phase signal for each user; The health status monitoring module is used to perform spectral analysis on the continuous phase signal to obtain the respiratory rate and heart rate of each user, and to monitor the health status based on the respiratory rate and heart rate.

[0018] An electronic device includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method described above.

[0019] A computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the method described above.

[0020] A computer program product includes a computer program that, when executed by a processor, implements the method described above.

[0021] The embodiments of the present invention have the following advantages: In this embodiment of the invention, channel state information collected by a wireless network device on multiple subcarriers is acquired, and the channel state information is separated into multiple users to obtain channel state information components for each user. Phase extraction is performed on the channel state information components to obtain continuous phase signals for each user. Spectral analysis is performed on the continuous phase signals to obtain the respiratory frequency and heart rate of each user. Health status monitoring is then performed based on the respiratory frequency and heart rate. This enables user health monitoring using a wireless network device without the need to deploy health monitoring equipment, reducing costs. Furthermore, by separating multiple users, different users can be distinguished, achieving user-level health monitoring and improving the effectiveness of health monitoring. Attached Figure Description

[0022] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of the steps of a user health monitoring method provided in some embodiments of the present invention; Figure 2 This is a schematic diagram of a multi-user separation process provided in some embodiments of the present invention; Figure 3a This is a schematic diagram of a distance-dimensional FFT result provided by some embodiments of the present invention; Figure 3b This is a schematic diagram of a clutter suppression range dimension FFT result provided in some embodiments of the present invention; Figure 3c This is a schematic diagram of an unexpanded phase signal provided in some embodiments of the present invention; Figure 3d This is a schematic diagram of a phase-unwrapped signal provided in some embodiments of the present invention; Figure 3e This is a schematic diagram of a phase-differentiated signal provided in some embodiments of the present invention; Figure 3f This is a schematic diagram of a moving average filtered phase signal provided in some embodiments of the present invention; Figure 3g This is a schematic diagram of a phase signal FFT result provided in some embodiments of the present invention; Figure 3h This is a schematic diagram of a respiratory time-domain waveform provided in some embodiments of the present invention; Figure 3i This is a schematic diagram of a respiratory signal FFT result provided in some embodiments of the present invention; Figure 3j This is a schematic diagram of a time-domain waveform of a heartbeat signal provided in some embodiments of the present invention; Figure 3k This is a schematic diagram of a heartbeat signal FFT provided in some embodiments of the present invention; Figure 3l This is a schematic diagram of a heartbeat wave envelope curve provided in some embodiments of the present invention; Figure 3m This is a schematic diagram of a normalized heartbeat waveform provided in some embodiments of the present invention; Figure 4 This is a schematic diagram of a signal enhancement process provided in some embodiments of the present invention; Figure 5 This is a flowchart of the steps of a second method for user health monitoring provided in some embodiments of the present invention; Figure 6 This is a structural block diagram of a user health monitoring device provided in some embodiments of the present invention. Detailed Implementation

[0024] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0025] Among related technologies, wireless sensing technologies, such as WiFi sensing, can be used for health monitoring. By leveraging the invisibility of radio waves, health monitoring can be performed without the user's knowledge, thus minimizing discomfort. Moreover, radio waves can penetrate walls, enabling operation even in challenging non-line-of-sight (NLOS) scenarios. Furthermore, multipath effects, which are detrimental to data communication, may have a positive impact on wireless sensing by expanding the dimensions of spatial sensing.

[0026] However, using wireless sensing technology for health monitoring makes it difficult to distinguish the individual physiological signals of multiple people in the same room, leading to confusing or even false alarms in the health monitoring results. Furthermore, it lacks sensitivity to slower physiological signals (such as breathing during sleep) and is easily masked by environmental noise. For example, in home health monitoring, the WiFi signal can be affected by multiple members simultaneously, causing their individual physiological signals to mix together. If these signals cannot be distinguished, the health monitoring function will alias and fail.

[0027] In this embodiment of the invention, a space-time combined human body separation technology is proposed. Based on this, an adaptive low-frequency enhancement technology is further proposed for the separated single-user signal to improve the accuracy of weak respiratory rhythms, thereby enabling stable and reliable operation in complex home environments.

[0028] Specifically, this invention proposes a multi-user separation sensing technology based on spatial-temporal joint sensing. By utilizing the unique time delay and angular characteristics of wireless signals (such as WiFi signals) on different human body reflection paths, it constructs wireless physiological information for each individual. This enables automatic identification and separation of the micro-motion signals of multiple users in the same space without relying on cameras or wearable devices, using only channel state information data from ordinary routers. This achieves seamless monitoring at the user level, effectively solving the signal aliasing problem among multiple users, significantly improving the accuracy of health anomaly detection, avoiding false triggers caused by the activities of others, and solving the problem of difficulty in distinguishing the physiological signals of multiple people in the same room, which leads to confusion or even false alarms in health monitoring results.

[0029] Furthermore, this invention proposes an adaptive low-frequency enhanced sensing technology. By dynamically suppressing high-frequency interference components at the wireless signal receiver and simultaneously amplifying weak phase fluctuations in the 0.1 to 0.5 Hz range, it is used to capture slow physiological rhythms such as breathing. An adaptive low-frequency enhanced filter is designed on the pilot subcarrier in the communication signal. By learning the environmental noise pattern in real time, the sensing bandwidth is automatically adjusted to improve the accuracy of breathing monitoring. This enables stable extraction of sleep breathing signals in ordinary home WiFi environments, effectively identifying sleep apnea events, and providing a low-cost, highly available solution for home sleep monitoring. It also solves the problem that WiFi sensing systems are not sensitive enough to slow physiological signals and are easily masked by environmental noise.

[0030] Reference Figure 1 The diagram illustrates a flowchart of a user health monitoring method according to some embodiments of the present invention, which may specifically include the following steps: Step 101: Obtain channel state information on multiple subcarriers collected by the wireless network device.

[0031] As an example, a wireless network device can be a router, a wireless access point, or other device with wireless communication capabilities, and the wireless network can be WiFi. Specifically, a wireless network device can be configured with multiple receiving antennas, such as having a number N. t ≥2 receiving antennas.

[0032] Channel State Information (CSI) refers to the physical channel characteristics that a wireless signal experiences as it propagates from the transmitter to the receiver. Specifically, when a wireless signal propagates in space, it is affected by various factors such as reflection, scattering, diffraction, and path loss, causing varying degrees of change in the signal's amplitude and phase. In some examples, CSI can be in complex form, i.e., complex CSI, where the modulus reflects the amplitude attenuation and the argument reflects the phase shift.

[0033] For example, in N sc The complex CSI on each subcarrier is:

[0034] Where n is the time frame index (i.e., there are multiple CSI frames). , For complex fields, Let be the dimension of the matrix. Let m be the actual frequency of the m-th subcarrier. For the center frequency, It is the subcarrier spacing.

[0035] In some examples, consider U stationary or slightly moving users indoors, each of whom can be modeled as a dominant scatterer. Under this assumption, the receiver's CSI can be represented as a superposition of signals from multiple users: in, For the composite path gain of the u-th user, d u [n] represents chest cavity displacement (caused by respiration or body movement). For static attenuation, j is the imaginary unit, λ is the wavelength of the wireless signal, and θ is the angle of arrival of the signal; For the round-trip path delay, Let c be the distance from the user to the router, and c be the speed of light. The guide vector for the Uniform Linear Array (ULA) is d = λ / 2; w represents additive white Gaussian noise.

[0036] Step 102: Perform multi-user separation on the channel state information to obtain the channel state information component for each user.

[0037] In scenarios such as home health monitoring, when multiple users are in the same room, the collected CSI (Constant Sensory Indication) is an overlay of reflected signals from all users and static objects in the environment, making it impossible to directly distinguish the physiological signals of each user. Therefore, CSI can be separated into multiple users to obtain the CSI components for each individual user.

[0038] For example, by utilizing the multi-antenna structure and multi-subcarrier characteristics of wireless network devices, aliased CSI can be decoupled from both spatial and frequency dimensions. Spatially, different users face different directions relative to the wireless network device, resulting in varying phase differences when signals arrive at different receiving antennas. Frequency-wise, different users are at different distances, leading to differences in phase rotation of the signal on different subcarriers. By jointly analyzing information from these two dimensions, the spatial characteristics (e.g., angle of arrival) and propagation characteristics (e.g., path delay) of each user's reflected signal can be estimated. Based on this, spatial filtering and signal extraction can be performed on the original CSI using these characteristic parameters, thus separating the aliased multi-user signals and obtaining the channel state information components corresponding to each user.

[0039] The following combination Figure 2 The process of separating multiple users is illustrated by example: In some embodiments of the present invention, the channel state information is subjected to multi-user separation to obtain channel state information components for each user, including: Sub-step 11: Construct the spatial frequency covariance matrix based on the channel state information.

[0040] The spatial frequency covariance matrix can be used to simultaneously characterize the spatial correlation between different receiving antennas and the frequency correlation between different subcarriers. For example, the spatial frequency covariance matrix contains information on the spatial correlation between different receiving antennas and information on the frequency correlation between different subcarriers. The spatial correlation information between different receiving antennas can be the phase difference between each antenna component, which is determined by the signal angle of arrival and reflects the user's direction in space. The frequency correlation information between different subcarriers can be the phase difference between the channel state information on each subcarrier within the same time frame, which is determined by the signal path delay and reflects the distance from the user to the wireless network device.

[0041] In some embodiments of the present invention, constructing a spatial frequency covariance matrix based on the channel state information includes: determining the channel state information of each subcarrier and the product of the conjugate transpose of the channel state information; summing and averaging the products of all subcarriers according to the number of subcarriers to obtain the spatial frequency covariance matrix.

[0042] In the specific implementation, for each subcarrier, the CSI on that subcarrier is multiplied by its conjugate transpose, and the product is the spatial covariance matrix corresponding to that subcarrier. Then, the products obtained for all subcarriers are summed and divided by the number of subcarriers, i.e., the average value is taken, thus obtaining the spatial frequency covariance matrix.

[0043] For example, the spatial frequency covariance matrix takes the following form:

[0044] in, The number of subcarriers, For the CSI corresponding to the nth time frame and the mth subcarrier, It is its conjugate transpose.

[0045] Sub-step 12 involves performing eigenvalue decomposition on the spatial frequency covariance matrix to obtain the angle of arrival for each user.

[0046] After obtaining the spatial frequency covariance matrix, we can perform eigenvalue decomposition on the constructed spatial frequency covariance matrix to decompose it into eigenvalues ​​and eigenvectors.

[0047] In this subspace, the eigenvectors corresponding to larger eigenvalues ​​constitute the signal subspace, while the eigenvectors corresponding to smaller eigenvalues ​​constitute the noise subspace. The dimension of the signal subspace corresponds to the number of users within the same space, and the noise subspace and signal subspace are orthogonal to each other. Utilizing this orthogonality, spatial spectral functions, such as the MUSIC (Multiple Signal Classification) spectral function, are constructed.

[0048] By searching for the peak position of this spatial spectral function across the entire angular range, the angle of arrival for each user can be determined. The angle of arrival reflects the user's orientation relative to the wireless network device.

[0049] For example, performing eigenvalue decomposition on R[n] and taking the noise subspace U n Substitute into the MUSIC spectral function:

[0050] Here, a(θ) is the array manifold vector, which depends on the angle θ and the specific configuration of the antenna array.

[0051] The angle of arrival estimate is obtained by searching for U peaks of P_MUSIC(θ). .

[0052] In some examples, users at different distances can be pre-distinguished along the distance dimension. Then, by combining the discrimination results, eigenvalue decomposition can be performed on the spatial frequency covariance matrix to obtain the angle of arrival for each user, such as using the number of users in the discrimination results as the dimension of the signal subspace. For example, by performing a distance-dimensional FFT on a single linear frequency modulated pulse (Chirp), targets at different distances can be distinguished along the distance dimension.

[0053] like Figure 3a MATLAB (Matrix Laboratory) simulation results show that by performing a range-dimensional FFT on a single chirp, targets at different distances can be distinguished in the range dimension. Simulation parameters were set as follows: 200 sampling points, a frequency modulation slope of 64.985 MHz / μs, an effective bandwidth of 3.25 GHz, and a range resolution of 4.615 cm. Due to the presence of static objects reflecting light in the environment, clutter suppression is necessary. The MATLAB simulation implemented several suppression methods, including the MTI (Moving Target Indication) and MTD (Moving Target Detection) algorithms. After static clutter filtering, the target signal is more prominent. After static clutter suppression, the range-dimensional FFT results show a clearer signal peak at the target's location, and background noise is effectively suppressed. The DC component (the first 10 range cells) was set to zero in the simulation to further eliminate interference. Figure 3b In the MATLAB simulation, the distance-dimensional FFT results of multiple frames of data are displayed in a three-dimensional grid, with the horizontal axis representing distance, the vertical axis representing the number of chirps, and the vertical axis representing amplitude. The simulation is set with 1024 chirps, allowing for clear observation of the signal energy distribution at the target location.

[0054] Sub-step 13: Beamforming is performed on the channel state information based on the angle of arrival to obtain the channel state information components for each user.

[0055] After obtaining the angle of arrival, the angle of arrival is used to beamform the CSI, enhancing the signal from the direction of the target angle of arrival while suppressing signals from other directions, thus obtaining the channel state information component for each user, thereby achieving signal separation for multiple users.

[0056] For example, for each estimated angle The corresponding CSI components are extracted using beamforming, as follows: Where w_bf is the beamforming weight vector.

[0057] In some embodiments of the present invention, after beamforming the channel state information according to the angle of arrival to obtain the channel state information components for each user, the method further includes: The path delay of the user is determined based on the channel state information components; Based on each user's angle of arrival, path delay, and circadian rhythm information, a joint spatial-temporal information of the user is constructed, and a Gaussian mixture model is constructed based on the joint spatial-temporal information; wherein, each Gaussian component in the Gaussian mixture model corresponds to one user; When multiple frames of channel state information exist, for the current frame, the user's spatial-temporal joint information is matched with each Gaussian component in the Gaussian mixture model to obtain the matched Gaussian component, and the tracking relationship between the user in the current frame and the user in the previous frame is established based on the matched Gaussian component.

[0058] In the specific implementation, the path delay for each user is determined based on the separated CSI components. Path delay reflects the propagation time required for a signal to travel from the transmitter to the user and back to the receiver, and is directly related to the distance from the user to the wireless network device. Then, the angle of arrival, path delay, and circadian rhythm information of each user are combined to construct the user's joint space-time information.

[0059] Among them, the angle of arrival reflects the user's spatial orientation, the path delay reflects the user's spatial distance, and the physiological rhythm information reflects the user's breathing characteristics.

[0060] After obtaining the joint spatial-temporal information, a Gaussian mixture model is constructed based on the joint spatial-temporal information of all users. Each Gaussian component in the model corresponds to a user, and the mean vector of each Gaussian component represents the typical position of that user in the feature space.

[0061] When acquiring channel state information from multiple consecutive frames, for each user in the current frame, their joint spatial-temporal information is matched with each Gaussian component in the Gaussian mixture model. The probability of them belonging to each existing user is calculated, and the probability is assigned to the Gaussian component with the highest probability, thus obtaining the matching result. Based on this matching result, a tracking relationship is established between the user in the current frame and the user in the previous frame, ensuring that the identity of the same user remains consistent across different time frames.

[0062] Through the above operations, even if a user moves slowly in space, causing slight changes in their angle of arrival or path delay, the system can still correctly identify the user through the matching mechanism of the Gaussian mixture model, avoiding identity jumps caused by parameter drift.

[0063] For example, by combining angle, time delay, and physiological rhythm information, a joint spatial-temporal feature vector for the u-th user is constructed, and then joint spatial-temporal information for the u-th user is constructed:

[0064] To maintain user identity across frames, a Gaussian Mixture Model (GMM) is established:

[0065] Among them, K max This represents the maximum number of users.

[0066] Update {π} using the online EM algorithm k ,μ k ,Σ k The value of}, and the new observation F u [n] is assigned to the component k* with the highest posterior probability and given its user ID. Simultaneously, μ is assigned to the component k* corresponding to each ID. k Kalman filtering is introduced to smooth the state and prevent ID jumps caused by occlusion by other users.

[0067] In some embodiments of the present invention, determining the path delay of the user based on the channel state information components includes: transforming the channel state information components to obtain a time-domain impulse response; and detecting the peak position in the time-domain impulse response to determine the path delay of the user.

[0068] In practical implementation, the CSI components can be transformed along the frequency dimension, such as by transforming them into an IFFT (Inverse Fast Fourier Transform), converting the frequency domain signal to the time domain to obtain the time-domain impulse response. Then, by detecting the peak position in the time-domain impulse response, the location of the peak corresponds to the time it takes for the signal to travel from the router to the user and back, i.e., the path delay. u [n].

[0069] Step 103: Perform phase extraction on the channel state information components to obtain the continuous phase signal for each user.

[0070] After obtaining the CSI components, phase extraction can be performed on the CSI components to obtain the continuous phase signal for each user. The variation pattern of the continuous phase signal corresponds to the rise and fall motion of the user's chest cavity.

[0071] In some embodiments of the present invention, phase extraction is performed on the channel state information components to obtain continuous phase signals for each user, including: Sub-step 21 involves extracting the phase of the channel state information components to obtain the original phase sequence.

[0072] Sub-step 22 involves unwinding the original phase sequence to obtain the user's continuous phase signal.

[0073] In the specific implementation, phase values ​​are extracted from the CSI components of each user to obtain the original phase sequence. Since the phase values ​​are limited to the range of negative π to π, when the actual phase change exceeds this range, a jump will occur. The original phase sequence can be unwrapped to restore it to a continuous phase signal.

[0074] like Figure 3c Because the phase modulo operation causes a jump when the phase change exceeds ±π, the original phase signal extracted by MATLAB simulation exhibits jumps in the range [-π, π]. To recover the continuous phase change, phase unwrapping processing is required, as follows: From H u Extracting the original phase sequence from [n, fm], such as selecting subcarrier m_c and taking the phase value of the subcarrier, yields a time-varying phase sequence φ. u [n], then perform phase unwrapping to restore continuous phase:

[0075] After processing by the phase unwrapping algorithm, the phase signal is restored to a continuously changing curve. For example... Figure 3d The simulation employs a method of detecting phase difference point by point and performing ±2π compensation when a transition is detected.

[0076] In some embodiments of the present invention, after unwinding the original phase sequence to obtain the user's continuous phase signal, the method further includes: Differential operation processing is performed on the continuous phase signal of the user.

[0077] To enhance the heartbeat signal and eliminate hardware phase drift, differential operations can be performed on the unwrapped phase. For example... Figure 3e MATLAB simulation results show that the high-frequency components in the differential phase signal are enhanced.

[0078] In some examples, a 5-point moving average window (corresponding to 0.25 seconds) can be used for impulse noise suppression. For example... Figure 3f Simulation results show that this method can effectively smooth abrupt noise in phase signals.

[0079] Step 104: Perform spectrum analysis on the continuous phase signal to obtain the respiratory rate and heart rate of each user, and monitor the health status based on the respiratory rate and heart rate.

[0080] After obtaining the continuous phase signal, which contains periodic changes caused by the user's breathing and heartbeat, these periodic changes can be converted to the frequency domain through spectral analysis. For example, FFT can be used to perform spectral analysis on the continuous phase signal to identify the frequency components corresponding to breathing and heartbeat. Figure 3g In the MATLAB simulation, the sampling rate was set to 20Hz, and the FFT results showed that the spectral resolution was approximately 0.02Hz.

[0081] After obtaining respiratory and heart rates, the system can monitor the user's health status based on these extracted frequencies, such as determining whether the rates are within the normal range or detecting abnormal events like sleep apnea. When an abnormality is detected, the system can issue an alarm or push notification, achieving continuous and seamless monitoring of the user's health.

[0082] In some embodiments of the present invention, spectral analysis is performed on the continuous phase signal to obtain the respiratory rate and heart rate of each user, including: The continuous phase signal is filtered to obtain a respiratory frequency band signal and a heartbeat frequency band signal; the respiratory frequency band signal is subjected to spectrum analysis to obtain the user's respiratory rate; the heartbeat frequency band signal is subjected to spectrum analysis to obtain the user's heartbeat frequency.

[0083] In practical implementation, a bandpass filter is used to separate the respiratory and heartbeat components from the phase signal, obtaining the respiratory frequency band signal and the heartbeat frequency band signal. For example... Figure 3h and Figure 3i The time-domain waveform of the respiratory signal after bandpass filtering in the 0.1-0.5Hz range is shown. The MATLAB simulation uses a 4th-order Butterworth bandpass filter, clearly demonstrating the periodic fluctuations of respiration. Spectral analysis of the respiratory signal shows that the energy is concentrated in the 0.1-0.5Hz frequency band. The simulation calculates the respiratory frequency by searching for the peak positions in the spectrum. Figure 3j and Figure 3k The time-domain waveform of the heartbeat signal after passing through a 0.8-2Hz bandpass filter is shown. The MATLAB simulation uses an 8th-order Butterworth bandpass filter, and the heartbeat signal exhibits weak fluctuations at higher frequencies. Spectral analysis of the heartbeat signal shows that the energy is concentrated in the 0.8-2Hz frequency band. The simulation uses an amplitude threshold to determine the presence of a heartbeat signal.

[0084] In some examples, the heartbeat signal undergoes envelope extraction and normalization to facilitate subsequent heart rate calculation. MATLAB simulations use peak detection to extract the upper and lower envelopes of the heartbeat signal and calculate the average envelope. For example... Figure 3l and Figure 3m ,like Figure 3lIt includes the absolute value of the original heartbeat data, upper envelope, average envelope, and lower envelope. The normalized heartbeat waveform is obtained by calculating the ratio of the filtered heartbeat signal to the envelope, such as... Figure 3m This waveform highlights the relative changes in heart rate, which facilitates subsequent feature extraction.

[0085] In some embodiments of the present invention, before performing spectral analysis on the continuous phase signal to obtain the respiratory rate and heart rate of each user, the method further includes: The continuous phase signal is enhanced.

[0086] In some embodiments of the present invention, signal enhancement of the continuous phase signal includes: The continuous phase signal is transformed to obtain the signal spectrum; the frequency response of the time-varying filter is constructed; the signal spectrum is filtered according to the frequency response to obtain a signal-enhanced continuous phase signal.

[0087] Although user separation has been achieved, single-channel phase signals are still affected by environmental disturbances, so continuous phase signals can be enhanced.

[0088] In the specific implementation, a Fourier transform is performed on the continuous-phase signal to convert it from the time domain to the frequency domain, obtaining the signal spectrum. Then, the frequency response of a time-varying filter is constructed, and this frequency response is used to filter the signal spectrum, that is, to weight different frequency components in the spectrum, enhancing the low-frequency components where the breathing signal is located, while suppressing high-frequency interference components. An inverse Fourier transform is then performed on the filtered spectrum to restore it to the time domain, thus obtaining the enhanced continuous-phase signal.

[0089] In some embodiments of the present invention, constructing the frequency response of a time-varying filter includes: Based on the signal spectrum, determine the environmental noise intensity index; based on the environmental noise intensity index, determine the high-frequency suppression coefficient; based on the historical breathing interval, determine the passband range of the time-varying filter; based on the high-frequency suppression coefficient and the passband range, construct the frequency response of the time-varying filter.

[0090] In the specific implementation, the current environmental noise intensity index is determined based on the signal spectrum, for example, by calculating the average power of the high-frequency band to quantify the interference level in the environment. Then, a high-frequency suppression coefficient is determined based on this noise intensity index; the higher the noise intensity, the smaller the high-frequency suppression coefficient, thus enhancing the ability to suppress high-frequency interference. The passband range of the time-varying filter is determined based on the user's historical breathing intervals, enabling the passband to adaptively track the user's real-time breathing frequency changes.

[0091] After determining the high-frequency suppression coefficient and passband range, the frequency response of a time-varying filter is constructed based on these parameters. This response maintains the signal unchanged within the passband range, while attenuating the signal to varying degrees outside the passband range according to the high-frequency suppression coefficient. The constructed time-varying filter can dynamically adjust its characteristics based on the ambient noise level and the user's breathing state, achieving adaptive enhancement of the breathing signal.

[0092] The following combination Figure 4 The process of signal enhancement is illustrated by example: Assume a single-channel phase signal φ u [n] is derived from the actual physiological displacement d u phys [n] and environmental disturbances d u env [n] Co-modulation:

[0093] in, It is mainly concentrated in 0.1–0.5 Hz (normal breathing), while It includes high-frequency components such as fans (1–3Hz) and pet movement (>2Hz).

[0094] To improve the signal-to-noise ratio, this embodiment of the invention employs an Adaptive Low-frequency Enhancement Filter (ALEF), as detailed below: First, the set of pilot subcarriers in the OFDM symbol:

[0095] right The spectrum Φ obtained by performing FFT u (f).

[0096] Calculate the average power in the high-frequency band (e.g., 1–10 Hz) as an indicator of environmental noise intensity: Based on this, the high-frequency suppression coefficient is dynamically set:

[0097] Based on historical respiratory interval T res [n] (obtained through peak detection), dynamically adjust the passband boundary:

[0098] Finally, the frequency response of the time-varying filter is constructed:

[0099] Where f_c = 0.25Hz, γ controls the steepness of the transition band.

[0100] For Φ u (f) Applying the filter and then performing an inverse transform yields the enhanced phase:

[0101] In this embodiment of the invention, channel state information collected by a wireless network device on multiple subcarriers is acquired, and the channel state information is separated into multiple users to obtain channel state information components for each user. Phase extraction is performed on the channel state information components to obtain continuous phase signals for each user. Spectral analysis is performed on the continuous phase signals to obtain the respiratory frequency and heart rate of each user. Health status monitoring is then performed based on the respiratory frequency and heart rate. This enables user health monitoring using a wireless network device without the need to deploy health monitoring equipment, reducing costs. Furthermore, by separating multiple users, different users can be distinguished, achieving user-level health monitoring and improving the effectiveness of health monitoring.

[0102] Reference Figure 5 The diagram illustrates a flowchart of another user health monitoring method provided by some embodiments of the present invention, which may specifically include the following steps: Step 501: Obtain channel state information on multiple subcarriers collected by the wireless network device.

[0103] Step 502: Perform multi-user separation on the channel state information to obtain the channel state information component for each user.

[0104] Step 503: Perform phase extraction on the channel state information components to obtain the continuous phase signal for each user.

[0105] Step 504: Transform the continuous phase signal to obtain the signal spectrum.

[0106] Step 505: Construct the frequency response of the time-varying filter.

[0107] Step 506: Filter the signal spectrum according to the frequency response to obtain a continuous phase signal with signal enhancement.

[0108] Step 507: Perform spectrum analysis on the enhanced continuous phase signal to obtain the respiratory rate and heart rate of each user, and monitor their health status based on the respiratory rate and heart rate.

[0109] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0110] Reference Figure 6 The diagram shows a structural schematic of a user health monitoring device provided in some embodiments of the present invention, which may specifically include the following modules: The channel state information acquisition module 601 is used to acquire channel state information collected by the wireless network device on multiple subcarriers; The channel state information component acquisition module 602 is used to perform multi-user separation on the channel state information to obtain the channel state information component for each user. The continuous phase signal acquisition module 603 is used to extract the phase of the channel state information components to obtain the continuous phase signal for each user; The health status monitoring module 604 is used to perform spectrum analysis on the continuous phase signal to obtain the respiratory rate and heart rate of each user, and to monitor the health status based on the respiratory rate and heart rate.

[0111] In some embodiments of the present invention, the channel state information is subjected to multi-user separation to obtain channel state information components for each user, including: Based on the channel state information, construct the spatial frequency covariance matrix; The spatial frequency covariance matrix is ​​subjected to eigenvalue decomposition to obtain the angle of arrival for each user; Beamforming is performed on the channel state information based on the angle of arrival to obtain the channel state information components for each user.

[0112] In some embodiments of the present invention, constructing a spatial frequency covariance matrix based on the channel state information includes: Determine the channel state information of each subcarrier and the product of the conjugate transpose of the channel state information; Based on the number of subcarriers, the products of all subcarriers are summed and averaged to obtain the spatial frequency covariance matrix.

[0113] In some embodiments of the present invention, after beamforming the channel state information according to the angle of arrival to obtain the channel state information components for each user, the method further includes: The path delay of the user is determined based on the channel state information components; Based on each user's angle of arrival, path delay, and circadian rhythm information, a joint spatial-temporal information of the user is constructed, and a Gaussian mixture model is constructed based on the joint spatial-temporal information; wherein, each Gaussian component in the Gaussian mixture model corresponds to one user; When multiple frames of channel state information exist, for the current frame, the user's spatial-temporal joint information is matched with each Gaussian component in the Gaussian mixture model to obtain the matched Gaussian component, and the tracking relationship between the user in the current frame and the user in the previous frame is established based on the matched Gaussian component.

[0114] In some embodiments of the present invention, determining the user's path delay based on the channel state information components includes: The channel state information components are transformed to obtain the time-domain impulse response; The peak position in the time-domain impulse response is detected to determine the user's path delay.

[0115] In some embodiments of the present invention, phase extraction is performed on the channel state information components to obtain continuous phase signals for each user, including: Phase extraction is performed on the channel state information components to obtain the original phase sequence; The original phase sequence is unwound to obtain the user's continuous phase signal.

[0116] In some embodiments of the present invention, after unwinding the original phase sequence to obtain the user's continuous phase signal, the method further includes: Differential operation processing is performed on the continuous phase signal of the user.

[0117] In some embodiments of the present invention, spectral analysis is performed on the continuous phase signal to obtain the respiratory rate and heart rate of each user, including: The continuous phase signal is filtered to obtain the respiratory frequency band signal and the heartbeat frequency band signal; The user's breathing frequency is obtained by performing spectral analysis on the breathing frequency band signal; The heartbeat frequency of the user is obtained by performing spectral analysis on the heartbeat frequency band signal.

[0118] In some embodiments of the present invention, before performing spectral analysis on the continuous phase signal to obtain the respiratory rate and heart rate of each user, the method further includes: The continuous phase signal is enhanced.

[0119] In some embodiments of the present invention, signal enhancement of the continuous phase signal includes: The continuous phase signal is transformed to obtain the signal spectrum; Construct the frequency response of a time-varying filter; The signal spectrum is filtered based on the frequency response to obtain a continuous phase signal with enhanced signal.

[0120] In some embodiments of the present invention, constructing the frequency response of a time-varying filter includes: Based on the signal spectrum, determine the environmental noise intensity index; Determine the high-frequency suppression coefficient based on the aforementioned environmental noise intensity index; Determine the passband range of the time-varying filter based on historical breathing intervals; The frequency response of the time-varying filter is constructed based on the high-frequency suppression coefficient and the passband range.

[0121] In this embodiment of the invention, channel state information collected by a wireless network device on multiple subcarriers is acquired, and the channel state information is separated into multiple users to obtain channel state information components for each user. Phase extraction is performed on the channel state information components to obtain continuous phase signals for each user. Spectral analysis is performed on the continuous phase signals to obtain the respiratory frequency and heart rate of each user. Health status monitoring is then performed based on the respiratory frequency and heart rate. This enables user health monitoring using a wireless network device without the need to deploy health monitoring equipment, reducing costs. Furthermore, by separating multiple users, different users can be distinguished, achieving user-level health monitoring and improving the effectiveness of health monitoring.

[0122] Some embodiments of the present invention also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method described above.

[0123] Some embodiments of the present invention also provide a computer-readable storage medium on which a computer program is stored, and which, when executed by a processor, implements the method described above.

[0124] Some embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the method described above.

[0125] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0126] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0127] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0128] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented 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.

[0129] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (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 terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, 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.

[0130] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal 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.

[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0132] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0133] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device 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 terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes the aforementioned element.

[0134] The above provides a detailed description of the method, apparatus, equipment, medium, and product for user health monitoring. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for monitoring user health, characterized in that, The method includes: Acquire channel state information collected by wireless network devices on multiple subcarriers; The channel state information is separated into multiple users to obtain the channel state information components for each user. Phase extraction is performed on the channel state information components to obtain the continuous phase signal for each user; The continuous phase signal is subjected to spectral analysis to obtain the respiratory rate and heart rate of each user, and the health status is monitored based on the respiratory rate and heart rate.

2. The method according to claim 1, characterized in that, The channel state information is separated into multiple users to obtain channel state information components for each user, including: Based on the channel state information, construct the spatial frequency covariance matrix; The spatial frequency covariance matrix is ​​subjected to eigenvalue decomposition to obtain the angle of arrival for each user; Beamforming is performed on the channel state information based on the angle of arrival to obtain the channel state information components for each user.

3. The method according to claim 2, characterized in that, Based on the channel state information, a spatial frequency covariance matrix is ​​constructed, including: Determine the channel state information of each subcarrier and the product of the conjugate transpose of the channel state information; Based on the number of subcarriers, the products of all subcarriers are summed and averaged to obtain the spatial frequency covariance matrix.

4. The method according to claim 2, characterized in that, After beamforming the channel state information based on the angle of arrival to obtain the channel state information components for each user, the method further includes: The path delay of the user is determined based on the channel state information components; Based on each user's angle of arrival, path delay, and circadian rhythm information, a joint spatial-temporal information of the user is constructed, and a Gaussian mixture model is constructed based on the joint spatial-temporal information; wherein, each Gaussian component in the Gaussian mixture model corresponds to one user; When multiple frames of channel state information exist, for the current frame, the user's spatial-temporal joint information is matched with each Gaussian component in the Gaussian mixture model to obtain the matched Gaussian component, and the tracking relationship between the user in the current frame and the user in the previous frame is established based on the matched Gaussian component.

5. The method according to claim 4, characterized in that, Determining the user's path delay based on the channel state information components includes: The channel state information components are transformed to obtain the time-domain impulse response; The peak position in the time-domain impulse response is detected to determine the user's path delay.

6. The method according to claim 1, characterized in that, Phase extraction is performed on the channel state information components to obtain continuous phase signals for each user, including: Phase extraction is performed on the channel state information components to obtain the original phase sequence; The original phase sequence is unwound to obtain the user's continuous phase signal.

7. The method according to claim 6, characterized in that, After unwinding the original phase sequence to obtain the user's continuous phase signal, the process further includes: Differential operation processing is performed on the continuous phase signal of the user.

8. The method according to claim 1, characterized in that, Spectral analysis of the continuous phase signal yields the respiratory rate and heart rate of each user, including: The continuous phase signal is filtered to obtain the respiratory frequency band signal and the heartbeat frequency band signal; The user's breathing frequency is obtained by performing spectral analysis on the breathing frequency band signal; The heartbeat frequency of the user is obtained by performing spectral analysis on the heartbeat frequency band signal.

9. The method according to any one of claims 1-8, characterized in that, Before performing spectral analysis on the continuous phase signal to obtain the respiratory rate and heart rate of each user, the method further includes: The continuous phase signal is enhanced.

10. The method according to claim 9, characterized in that, Signal enhancement of the continuous phase signal includes: The continuous phase signal is transformed to obtain the signal spectrum; Construct the frequency response of a time-varying filter; The signal spectrum is filtered based on the frequency response to obtain a continuous phase signal with enhanced signal.

11. The method according to claim 10, characterized in that, Constructing the frequency response of a time-varying filter includes: Based on the signal spectrum, determine the environmental noise intensity index; Determine the high-frequency suppression coefficient based on the aforementioned environmental noise intensity index; Determine the passband range of the time-varying filter based on historical breathing intervals; The frequency response of the time-varying filter is constructed based on the high-frequency suppression coefficient and the passband range.

12. A device for monitoring user health, characterized in that, The device includes: The channel state information acquisition module is used to acquire channel state information collected by the wireless network device on multiple subcarriers; The channel state information component acquisition module is used to perform multi-user separation on the channel state information to obtain the channel state information component for each user. A continuous phase signal acquisition module is used to extract the phase of the channel state information components to obtain the continuous phase signal for each user; The health status monitoring module is used to perform spectral analysis on the continuous phase signal to obtain the respiratory rate and heart rate of each user, and to monitor the health status based on the respiratory rate and heart rate.

13. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method as described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the method as described in any one of claims 1 to 11.

15. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 11.

Images