AI human body sensor and human body state monitoring system

Abstract

The invention discloses an AI human body sensor and a human body state monitoring system, and the system comprises a millimeter wave radar module which is used for transmitting a millimeter wave signal and receiving a reflection signal; the signal processing module is connected with the millimeter wave radar module and is used for processing the reflected signal received by the millimeter wave radar module to obtain a processed signal; the AI algorithm processing module is connected with the signal processing module and is used for carrying out human body existence detection, movement detection, fall detection and position detection based on the processing signal to obtain a detection result; the communication module is connected with the AI algorithm processing module and is used for sending the detection result to external equipment; and the power supply module is used for supplying power to the millimeter wave radar module, the signal processing module, the AI algorithm processing module and the communication module. The problems that in the prior art, a human body sensor is single in function, has the privacy disclosure risk, is low in data processing efficiency and lacks a linkage mechanism are solved.

Description

Technical Field

[0001] The present invention relates to the field of sensor technology, and in particular to an AI human body sensor and a human body state monitoring system. Background Art

[0002] Currently, with the rapid development of the Internet of Things (IoT) and intelligent monitoring technologies, human body sensors are widely used in smart homes, smart elderly care, security monitoring, and other fields. Traditional human body sensors, such as infrared sensors, can only detect human motion signals and cannot accurately determine a person's presence, location, or posture changes. They are prone to missing detections when the person is stationary, and their limited monitoring capabilities make them difficult to meet the needs of complex scenarios.

[0003] While some human monitoring solutions based on image recognition technology can capture rich information about human status, they pose a serious risk of privacy leakage, especially in intimate settings like homes and bedrooms, where user acceptance of image acquisition is low. Furthermore, existing human monitoring systems often rely on cloud-based data processing, which results in data transmission delays and malfunctions when network conditions are poor. This also poses security risks during data transmission. Furthermore, sensors with different functions are independent of each other and lack a linkage mechanism, preventing the formation of a functionally complementary ecosystem. This results in low resource utilization efficiency and makes intelligent, integrated management difficult. Summary of the Invention

[0004] The present invention aims to at least partially address one of the technical problems in the aforementioned technologies. To this end, the present invention proposes an AI human body sensor and human body status monitoring system, which aims to address existing issues such as the single function of human body sensors, the risk of privacy leakage, low data processing efficiency, and the lack of a linkage mechanism.

[0005] To achieve the above objectives, an embodiment of the present invention provides an AI human body sensor, comprising:

[0006] Millimeter-wave radar module, used to transmit millimeter-wave signals and receive reflected signals;

[0007] A signal processing module is connected to the millimeter-wave radar module and is used to process the reflected signal received by the millimeter-wave radar module to obtain a processed signal;

[0008] The AI ​​algorithm processing module is connected to the signal processing module and is used to perform human presence detection, movement detection, fall detection, and position detection based on the processed signals to obtain detection results;

[0009] The communication module is connected to the AI ​​algorithm processing module and is used to send the detection results to external devices;

[0010] The power module is used to power the millimeter-wave radar module, signal processing module, AI algorithm processing module, and communication module.

[0011] According to some embodiments of the present invention, the signal processing module includes:

[0012] A filtering module, used for filtering the reflected signal to obtain a filtered signal;

[0013] an amplification module, used for amplifying the filtered signal to obtain an amplified signal;

[0014] The analog-to-digital conversion module is used to perform analog-to-digital conversion on the amplified signal to obtain a digital signal as a processed signal.

[0015] According to some embodiments of the present invention, the filtering module includes:

[0016] A first generation module is configured to divide the reflected signal into a plurality of sub-signals, determine the spectrum amplitude of each sub-signal, calculate an average spectrum amplitude of the plurality of sub-signals, calculate the absolute value of the difference between the spectrum amplitude of each sub-signal and the average spectrum amplitude, and select sub-signals corresponding to spectrum amplitudes whose absolute values ​​of the differences are greater than a preset difference, thereby generating a first set;

[0017] The second generation module is used to analyze the reflected signal and determine all local maxima and local minima of the reflected signal; fit the maximum points using cubic spline interpolation to obtain an upper envelope; fit the minimum points using cubic spline interpolation to obtain a lower envelope; calculate the average of the upper and lower envelopes as a trend term; subtract the trend term from the reflected signal to obtain an IMF component, and generate a second set based on the sub-signals corresponding to the IMF components;

[0018] The first determination module is used to determine the target sub-signal according to the first set and the second set, analyze the type of the target sub-signal, perform filtering processing according to the type of the target sub-signal, and reconstruct the signal based on the processed target sub-signal to obtain a filtered signal.

[0019] According to some embodiments of the present invention, the first generating module divides the reflected signal into several sub-signals, including:

[0020] Determine the sliding window width based on the sampling rate of the reflection signal and the expected peak width, and set the window step size;

[0021] Set a width constraint condition, perform peak detection in the sliding window based on the width constraint condition, and obtain several peaks;

[0022] Filter out the peaks that span multiple sliding windows as the peaks to be merged, merge the peaks to be merged, and obtain several target peaks;

[0023] Determine the time point corresponding to each target wave crest, segment the reflection signal according to the time points corresponding to adjacent target wave crests to obtain a plurality of sub-signals.

[0024] According to some embodiments of the application, the AI algorithm processing module comprises:

[0025] The 3D-FFT-based processing signal is processed to obtain distance-Doppler-angle three-dimensional imaging information;

[0026] According to the distance-Doppler-angle three-dimensional imaging information and the LSTM prediction model, the respiratory signal existence is determined; according to the distance-Doppler-angle three-dimensional imaging information and the CNN classification module, the micro-motion feature is determined; and based on the respiratory signal existence and the micro-motion feature, the human existence detection is performed.

[0027] According to some embodiments of the application, the AI algorithm processing module further comprises a movement detection module configured to:

[0028] Based on the distance-Doppler-angle three-dimensional imaging information, trajectory analysis is performed; the trajectory analysis includes Kalman filter tracking and velocity mutation detection;

[0029] Based on the trajectory analysis result, when the processing signal appears continuous change in time sequence and meets the human movement feature, it is determined that the human is in a moving state, and the movement-related information is recorded.

[0030] According to some embodiments of the application, the AI algorithm processing module further comprises a fall detection module configured to:

[0031] Based on the distance-Doppler-angle three-dimensional imaging information, feature analysis is performed to determine feature information; the feature information includes vertical velocity mutation, attitude angle change and impact duration;

[0032] The feature information is input into a preset fall posture model for judgment; when the matching degree of the feature information and the fall posture model is greater than a preset threshold, it is determined that the human has a fall action.

[0033] According to some embodiments of the application, the AI algorithm processing module further comprises a position detection module configured to:

[0034] Based on the distance-Doppler-angle three-dimensional imaging information, time delay and angle information are determined;

[0035] According to the time delay and angle information, the Doppler positioning algorithm is used to determine the position information of the human in the region.

[0036] According to some embodiments of the present invention, it also includes: a guard alarm module, which selects a corresponding alarm method to issue an alarm based on the detection result and the preset alarm rules, and transmits the alarm information to the monitoring terminal via wired or wireless means.

[0037] According to some embodiments of the present invention, a human body status monitoring system includes a control module, an execution device, a server, and the AI ​​human body sensor as described above; wherein;

[0038] The control module is connected to the AI ​​human body sensor and the server respectively, and is used to:

[0039] Receive monitoring information of human body status transmitted by AI human body sensor and transmit it to the server;

[0040] Generate a corresponding control strategy based on the monitoring information, determine the corresponding execution device based on the control strategy, and transmit the execution instruction to the execution device;

[0041] The server is used to obtain monitoring information and execution information of the execution device, generate a monitoring data table, and transmit it to the mobile terminal.

[0042] The present invention proposes an AI human body sensor and human body status monitoring system. By combining a millimeter-wave radar module with an all-in-one AI algorithm, it can achieve accurate detection of multi-dimensional information such as human presence, position, and posture, thereby making up for the defects of incomplete detection of traditional sensors; while ensuring the nursing function, it strictly protects user privacy; with the help of the linkage design between the communication module and external equipment, based on multi-dimensional detection results such as posture, area, and direction, it triggers a variety of intelligent linkage scenarios, thereby improving the intelligence level and practicality of the monitoring system.

[0043] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0044] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0046] Figure 1 is a block diagram of an AI human body sensor according to one embodiment of the present invention;

[0047] Figure 2is a block diagram of a human body status monitoring system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0049] like Figure 1 As shown, an embodiment of the present invention provides an AI human body sensor, including:

[0050] Millimeter-wave radar module, used to transmit millimeter-wave signals and receive reflected signals;

[0051] A signal processing module is connected to the millimeter-wave radar module and is used to process the reflected signal received by the millimeter-wave radar module to obtain a processed signal;

[0052] The AI ​​algorithm processing module is connected to the signal processing module and is used to perform human presence detection, movement detection, fall detection, and position detection based on the processed signals to obtain detection results;

[0053] The communication module is connected to the AI ​​algorithm processing module and is used to send the detection results to external devices;

[0054] The power module is used to power the millimeter-wave radar module, signal processing module, AI algorithm processing module, and communication module.

[0055] The working principle of the above technical solution is as follows: the millimeter-wave radar module transmits a linear frequency modulation signal through FMCW technology, and the intermediate frequency signal is obtained by mixing the received signal with the transmitted signal. The target distance and speed are calculated through FFT. Through the MIMO antenna array, the target angle is calculated using beamforming technology (such as the MUSIC algorithm). The signal processing module processes the reflected signal received by the millimeter-wave radar module, including filtering, amplification, analog-to-digital conversion, etc. The AI ​​algorithm processing module performs human presence detection, movement detection, fall detection and position detection based on the processed signal to obtain the detection results; the detection results are sent to external devices based on the communication module to facilitate the triggering of rich intelligent linkage scenarios.

[0056] The beneficial effects of the above technical solution are: through the combination of millimeter-wave radar modules and all-in-one AI algorithms, accurate detection of multi-dimensional information such as human presence, position, and posture can be achieved, making up for the defects of incomplete detection of traditional sensors; while ensuring the nursing function, user privacy is strictly protected; with the help of the linkage design between the communication module and external equipment, based on multi-dimensional detection results such as posture, area, and direction, a variety of intelligent linkage scenarios are triggered, thereby improving the intelligence level and practicality of the monitoring system.

[0057] According to some embodiments of the present invention, the signal processing module includes:

[0058] A filtering module, used for filtering the reflected signal to obtain a filtered signal;

[0059] an amplification module, used for amplifying the filtered signal to obtain an amplified signal;

[0060] The analog-to-digital conversion module is used to perform analog-to-digital conversion on the amplified signal to obtain a digital signal as a processed signal.

[0061] The above technical solution works as follows: The filtering module suppresses noise and interference, improving signal accuracy. The amplification module increases signal amplitude to ensure that the dynamic range of subsequent analog-to-digital conversion covers the valid signal. The analog-to-digital conversion module converts the analog signal into a digital signal for easier signal processing.

[0062] The beneficial effects of the above technical solution are as follows: the signal processing module converts the reflected signal of the millimeter wave radar into a high-quality digital signal through three steps: filtering, amplification, and analog-to-digital conversion.

[0063] According to some embodiments of the present invention, the filtering module includes:

[0064] A first generation module is configured to divide the reflected signal into a plurality of sub-signals, determine the spectrum amplitude of each sub-signal, calculate an average spectrum amplitude of the plurality of sub-signals, calculate the absolute value of the difference between the spectrum amplitude of each sub-signal and the average spectrum amplitude, and select sub-signals corresponding to spectrum amplitudes whose absolute values ​​of the differences are greater than a preset difference, thereby generating a first set;

[0065] The second generation module is used to analyze the reflected signal and determine all local maxima and local minima of the reflected signal; fit the maximum points using cubic spline interpolation to obtain an upper envelope; fit the minimum points using cubic spline interpolation to obtain a lower envelope; calculate the average of the upper and lower envelopes as a trend term; subtract the trend term from the reflected signal to obtain an IMF component, and generate a second set based on the sub-signals corresponding to the IMF components;

[0066] The first determination module is used to determine the target sub-signal according to the first set and the second set, analyze the type of the target sub-signal, perform filtering processing according to the type of the target sub-signal, and reconstruct the signal based on the processed target sub-signal to obtain a filtered signal.

[0067] The working principle of the above technical solution is as follows: the first generation module filters out abnormal sub-signals through spectrum analysis to generate the first set. The reflected signal is divided into several sub-signals, and FFT is performed on each sub-signal to calculate the spectrum amplitude. The average spectrum amplitude of all sub-signals is calculated, and the absolute value of the difference between the spectrum amplitude of each sub-signal and the average spectrum amplitude is calculated. The sub-signals corresponding to the spectrum amplitude whose absolute value of the difference is greater than the preset difference are filtered out to generate the first set; the preset difference is determined according to the statistical characteristics of the noise, and the example is 2σ, where σ is the standard deviation of the spectrum amplitude. The second generation module decomposes the reflected signal through EMD, extracts the IMF component, and generates the second set. All local maxima and minima of the reflected signal are detected, and the maximum points are fitted with cubic spline interpolation to obtain the upper envelope, and the minimum points are fitted with cubic spline interpolation to obtain the lower envelope. Calculate the mean of the upper and lower envelopes as the trend term. Subtract the trend term from the reflected signal to obtain the IMF component. Generate a second set based on the sub-signals corresponding to the IMF components. Intersect the first and second sets to determine the corresponding sub-signal, which serves as the target sub-signal to be filtered. Analyze the target sub-signal type, including detail signals, transition signals, and trend signals. Detail signals contain noise, sudden changes, or high-frequency details (such as edges and transient features). Threshold-based denoising: Set a threshold (such as a soft threshold or hard threshold) on the wavelet packet coefficients to filter out noise components below the threshold. Transition signals contain the main structural or periodic characteristics of the signal, lying between high-frequency noise and low-frequency trends. Spectral analysis: Analyze frequency components using the short-time Fourier transform (STFT) to remove interfering frequencies. Trend signals reflect the overall trend of the signal or background noise (such as slowly varying drift). Low-pass filtering: Filter out low-frequency noise (such as baseline drift). Reconstruct the signal based on the processed target sub-signal to obtain the filtered signal.

[0068] The beneficial effects of the above technical solution are as follows: through spectrum analysis screening and EMD decomposition of reflected signals, it is convenient to accurately determine the target sub-signal, perform filtering processing according to the type of the target sub-signal, and facilitate improving the accuracy of filtering. Signal reconstruction is performed based on the processed target sub-signal to obtain an accurate filtered signal.

[0069] According to some embodiments of the present invention, the sliding window width is determined based on the sampling rate and the expected width of the peak of the reflection signal, and the window step size is set;

[0070] Set a width constraint condition, perform peak detection in the sliding window based on the width constraint condition, and obtain several peaks;

[0071] Filter out the peaks that span multiple sliding windows as the peaks to be merged, merge the peaks to be merged, and obtain several target peaks;

[0072] The time point corresponding to each target peak is determined, and the reflected signal is divided according to the time points corresponding to adjacent target peaks to obtain several sub-signals.

[0073] The working principle of the above technical solution is as follows: the sliding window width is determined based on the sampling rate of the reflected signal and the expected peak width, that is, the product of the sampling rate and the expected peak width is the sliding window width. The window step size is 1 / 3 of the sliding window width. A width constraint is set, and peak detection is performed within the sliding window based on the width constraint to obtain several peaks; the width constraint is that at least N points on both sides of the peak are less than 50% of the peak value. Peaks that span multiple sliding windows are screened out as peaks to be merged, and the peaks to be merged are merged to obtain several target peaks; the reflected signal is divided according to the time point of the target peak to generate sub-signals. The midpoint of the adjacent peak time points is used as the segmentation boundary.

[0074] The beneficial effects of the above technical solution are: the dynamic window width adapts to different peak widths, the peak merging strategy avoids repeated detection and missed detection, and the combination of sliding window and peak merging balances real-time and robustness, achieving efficient positioning and segmentation of peaks in the reflected signal.

[0075] According to some embodiments of the present invention, the AI ​​algorithm processing module includes: a presence detection module for:

[0076] The processed signal is processed based on 3D-FFT to obtain range-Doppler-angle three-dimensional imaging information;

[0077] The existence of respiratory signals is determined based on the distance-Doppler-angle three-dimensional imaging information and the LSTM prediction model. The micro-motion features are determined based on the distance-Doppler-angle three-dimensional imaging information and the CNN classification module. The presence of human body is detected based on the existence of respiratory signals and micro-motion features.

[0078] The working principle of the above technical solution is as follows: The processed signal is processed based on 3D-FFT to obtain range-Doppler-angle 3D imaging information. This range-Doppler-angle 3D imaging information is then analyzed using an LSTM prediction model. The Doppler time series signal of the chest region (within a fixed range-angle range) is extracted based on the range-Doppler-angle 3D imaging information. The Doppler time series signal is input into the LSTM prediction model, which outputs the presence or absence of a respiratory signal. Feature extraction is performed on the range-Doppler-angle 3D imaging information to determine range-Doppler slices. These range-Doppler slices are then input into a CNN classification module to determine micro-motion features, including limb sway and chest rise and fall. Human presence detection is performed based on the presence of respiratory signals and micro-motion features.

[0079] The beneficial effects of the above technical solutions are: through the joint method of 3D-FFT and deep learning, combining distance, Doppler, and angle information, the LSTM captures the respiratory rhythm, and the CNN extracts the micro-motion features, so that the human existence detection with high robustness is realized.

[0080] According to some embodiments of the present application, the AI algorithm processing module further comprises a movement detection module for:

[0081] Trajectory analysis is performed based on distance-Doppler-angle three-dimensional imaging information; the trajectory analysis includes Kalman filter tracking and velocity mutation detection;

[0082] When the processed signal appears continuous change in time sequence and meets the human body movement characteristics based on the trajectory analysis result, it is determined that the human body is in a moving state, and the movement related information is recorded.

[0083] The working principle of the above technical solutions is: based on distance-Doppler-angle (RDA) three-dimensional imaging information, the target trajectory is tracked through Kalman filter, the velocity mutation is detected, and the movement behavior is identified. When the processed signal appears continuous change in time sequence and meets the human body movement characteristics based on the trajectory analysis result, it is determined that the human body is in a moving state, and the movement related information is recorded.

[0084] The beneficial effects of the above technical solutions are: through the joint method of Kalman filter and velocity mutation detection, the human body movement state detection with high robustness is realized.

[0085] According to some embodiments of the present application, the AI algorithm processing module further comprises a fall detection module for:

[0086] Feature analysis is performed based on distance-Doppler-angle three-dimensional imaging information to determine feature information; the feature information includes vertical velocity mutation, attitude angle change, and impact duration;

[0087] The feature information is input into a preset fall posture model for judgment; when the matching degree of the feature information and the fall posture model is greater than a preset threshold, it is determined that the human body has a fall action.

[0088] The working principle of the above technical solutions is: based on distance-Doppler-angle three-dimensional imaging information, feature analysis is performed, human target points are extracted, vertical velocity mutation, attitude angle change (pitch angle θ and roll angle φ), and impact duration are calculated. The feature information is input into a preset fall posture model for judgment; when the matching degree of the feature information and the fall posture model is greater than a preset threshold, it is determined that the human body has a fall action.

[0089] The beneficial effects of the above technical solutions are: the accuracy of fall detection is improved.

[0090] According to some embodiments of the present invention, the AI ​​algorithm processing module further includes: a position detection module for:

[0091] determining time delay and angle information based on range-Doppler-angle three-dimensional imaging information;

[0092] The Doppler positioning algorithm is used to determine the position of the human body in the area based on the time delay and angle information.

[0093] The working principle and beneficial effects of the above technical solution are as follows: Based on three-dimensional range-Doppler-angle (RDA) imaging information, the target's time delay and angle information are determined. Based on this time delay and angle information, a Doppler positioning algorithm is used to determine the human body's position within the area, thereby improving positioning accuracy.

[0094] According to some embodiments of the present invention, it also includes: a guard alarm module, which selects a corresponding alarm method to issue an alarm based on the detection result and the preset alarm rules, and transmits the alarm information to the monitoring terminal via wired or wireless means.

[0095] The working principle of the above technical solution is: receive detection results (such as fall events, abnormal locations) from the fall detection module and the position detection module, select the alarm method according to the preset alarm rules (such as priority and time threshold), and transmit the alarm information to the monitoring terminal via wired or wireless means.

[0096] The beneficial effects of the above technical solution are: efficient and reliable intelligent alarm is achieved through dynamic rule matching and multi-channel transmission, which facilitates timely detection of abnormal information and timely processing.

[0097] like Figure 2 As shown, according to some embodiments of the present invention, a human body state monitoring system includes a control module, an execution device, a server and the AI ​​human body sensor as described above; wherein;

[0098] The control module is connected to the AI ​​human body sensor and the server respectively, and is used to:

[0099] Receive monitoring information of human body status transmitted by AI human body sensor and transmit it to the server;

[0100] Generate a corresponding control strategy based on the monitoring information, determine the corresponding execution device based on the control strategy, and transmit the execution instruction to the execution device;

[0101] The server is used to obtain monitoring information and execution information of the execution device, generate a monitoring data table, and transmit it to the mobile terminal.

[0102] The working principle and beneficial effects of the above technical solution: The AI ​​human body sensor integrates millimeter wave radar, Doppler positioning, fall detection and other modules to collect human body status data (such as position, posture, and motion status) in real time. The control module receives the monitoring information of the human body status transmitted by the AI ​​human body sensor and transmits it to the server; generates a corresponding control strategy based on the monitoring information, determines the corresponding execution device based on the control strategy, and transmits the execution instruction to the execution device; the server obtains the monitoring information and the execution information of the execution device, generates a monitoring data table, and transmits it to the mobile terminal. The edge-cloud collaborative architecture realizes high-precision, low-latency, and privacy-protected human body status monitoring, which improves the accuracy of human body status monitoring.

[0103] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. An AI human body sensor, characterized in that: include: Millimeter-wave radar module, used to transmit millimeter-wave signals and receive reflected signals; A signal processing module is connected to the millimeter-wave radar module and is used to process the reflected signal received by the millimeter-wave radar module to obtain a processed signal; The AI ​​algorithm processing module is connected to the signal processing module and is used to perform human presence detection, movement detection, fall detection, and position detection based on the processed signals to obtain detection results; The communication module is connected to the AI ​​algorithm processing module and is used to send the detection results to external devices; The power module is used to power the millimeter-wave radar module, signal processing module, AI algorithm processing module, and communication module.

2. The AI ​​human body sensor according to claim 1, wherein: The signal processing module includes: A filtering module, used for filtering the reflected signal to obtain a filtered signal; an amplification module, used for amplifying the filtered signal to obtain an amplified signal; The analog-to-digital conversion module is used to perform analog-to-digital conversion on the amplified signal to obtain a digital signal as a processed signal.

3. The AI ​​human body sensor according to claim 2, wherein: Filter module, including: A first generation module is configured to divide the reflected signal into a plurality of sub-signals, determine the spectrum amplitude of each sub-signal, calculate an average spectrum amplitude of the plurality of sub-signals, calculate the absolute value of the difference between the spectrum amplitude of each sub-signal and the average spectrum amplitude, and select sub-signals corresponding to spectrum amplitudes whose absolute values ​​of the differences are greater than a preset difference, thereby generating a first set; The second generation module is used to analyze the reflected signal and determine all local maxima and local minima of the reflected signal; fit the maximum points using cubic spline interpolation to obtain an upper envelope; fit the minimum points using cubic spline interpolation to obtain a lower envelope; calculate the average of the upper and lower envelopes as a trend term; subtract the trend term from the reflected signal to obtain an IMF component, and generate a second set based on the sub-signals corresponding to the IMF components; The first determination module is used to determine the target sub-signal according to the first set and the second set, analyze the type of the target sub-signal, perform filtering processing according to the type of the target sub-signal, and reconstruct the signal based on the processed target sub-signal to obtain a filtered signal.

4. The AI ​​human body sensor according to claim 3, wherein: The first generation module divides the reflected signal into several sub-signals, including: Determine the sliding window width based on the sampling rate of the reflection signal and the expected peak width, and set the window step size; Set a width constraint condition, perform peak detection in the sliding window based on the width constraint condition, and obtain several peaks; Filter out the peaks that span multiple sliding windows as the peaks to be merged, merge the peaks to be merged, and obtain several target peaks; The time point corresponding to each target peak is determined, and the reflected signal is divided according to the time points corresponding to adjacent target peaks to obtain several sub-signals.

5. The AI ​​human body sensor according to claim 1, wherein: AI algorithm processing module, including presence detection module, for: The processed signal is processed based on 3D-FFT to obtain range-Doppler-angle three-dimensional imaging information; The existence of respiratory signals is determined based on the distance-Doppler-angle three-dimensional imaging information and the LSTM prediction model. The micro-motion features are determined based on the distance-Doppler-angle three-dimensional imaging information and the CNN classification module. The presence of human body is detected based on the existence of respiratory signals and micro-motion features.

6. The AI ​​human body sensor according to claim 5, wherein: The AI ​​algorithm processing module also includes a motion detection module for: Performing trajectory analysis based on range-Doppler-angle three-dimensional imaging information; the trajectory analysis includes Kalman filter tracking and velocity mutation detection; When the processed signal shows continuous changes in the time series and meets the characteristics of human movement based on the trajectory analysis results, it is determined that the human body is in a moving state and the movement-related information is recorded.

7. The AI ​​human body sensor according to claim 5, wherein: The AI ​​algorithm processing module also includes a fall detection module for: Performing feature analysis based on range-Doppler-angle three-dimensional imaging information to determine feature information; the feature information includes vertical velocity mutation, attitude angle change, and impact duration; The feature information is input into a preset falling posture model for judgment; when the matching degree between the feature information and the falling posture model is greater than a preset threshold, it is determined that the human body has fallen.

8. The AI ​​human body sensor according to claim 5, wherein: The AI ​​algorithm processing module also includes a position detection module for: determining time delay and angle information based on range-Doppler-angle three-dimensional imaging information; The Doppler positioning algorithm is used to determine the position of the human body in the area based on the time delay and angle information.

9. The AI ​​human body sensor according to claim 1, wherein: Also includes: The guard alarm module is used to select the corresponding alarm method based on the preset alarm rules according to the detection results, and transmit the alarm information to the monitoring terminal via wired or wireless means.

10. A human body status monitoring system, characterized in that: It includes a control module, an execution device, a server, and the AI ​​human body sensor according to any one of claims 1 to 9; wherein; The control module is connected to the AI ​​human body sensor and the server respectively, and is used to: Receive monitoring information of human body status transmitted by AI human body sensor and transmit it to the server; Generate a corresponding control strategy based on the monitoring information, determine the corresponding execution device based on the control strategy, and transmit the execution instruction to the execution device; The server is used to obtain monitoring information and execution information of the execution device, generate a monitoring data table, and transmit it to the mobile terminal.

Images