Non-contact physiological sign monitoring system

Through a variety of sensors and signal processing technologies, the accuracy of the contactless physiological sign monitoring system in the installation position and movement is solved, efficient and comprehensive monitoring of physiological signs is achieved, and the accuracy and completeness of the data is enhanced. .

CN119033343APending Publication Date: 2024-11-29SUZHOU PELU TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411132251.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

Due to the installation position limitations and the movement of the monitored object, the existing non-contact physiological sign monitoring system cannot ensure that the radar antenna is facing the human chest cavity at all times, affecting the accuracy of the monitoring results.

Method used

A variety of sensor modules (optical, electromagnetic, acoustic, image analysis, wireless signals) are used to collect physiological characteristic data, and combine the filtering, amplification, noise reduction, adaptive filtering and motion compensation units in the signal processing module to extract and analyze physiological characteristics. Ensure the accuracy and completeness of the data.

Benefits of technology

It improves the accuracy and comprehensiveness of physiological sign monitoring, can provide accurate physiological indicators under exercise, enhances the system's ability to compensate for movement interference, reduces noise interference, and enhances the processing ability of weak signals.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119033343A_ABST
    Figure CN119033343A_ABST
Patent Text Reader

Abstract

The invention provides a non-contact physiological sign monitoring system, which relates to the technical field of physiological sign monitoring and comprises a sensor module, a signal processing module, a feature extraction module, a data analysis module, a communication module, a power management module, a display and interaction module, a storage module and the like. The amplification processing unit is arranged in the signal processing module, weak physiological signals in collected original signals can be enhanced so that the weak physiological signals can be subsequently processed and analyzed, damaged or incomplete signals can be reconstructed through an interpolation or fitting method and the like through the signal reconstruction unit, and therefore the signal reconstruction efficiency is improved. Through the arrangement of the motion compensation unit, the system can compensate and correct the signal interference caused by the motion of the monitored object in the motion by adopting an algorithm, thereby preventing the deviation of the feature data, and facilitating the improvement of the accuracy of the feature data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of physiological sign monitoring, and in particular to a non-contact physiological sign monitoring system. Background Art

[0002] Physiological parameters of the human body, such as breathing and heart rate, are important physiological indicators for doctors to diagnose and treat abnormal cardiopulmonary diseases. Common methods for measuring breathing and heart rate usually use contact methods, such as electrocardiograms. Contact measurement methods are relatively difficult to implement for infants and young children. For those elderly apartments and hotels with remote monitoring, and human health monitoring applications at night, although there are a large number of wearable bracelets, watches and other products on the market, contact measurement methods are still inconvenient. With the development of science and technology, non-contact measurement methods can make up for the above shortcomings and have broad development prospects and application value.

[0003] Existing non-contact physiological sign monitoring systems usually use microwave radar to monitor human physiological sign parameters during use. When a person is in a relatively static state, the chest cavity produces periodic vibrations due to breathing and heartbeat. The microwave radar transmits microwave signals to the human body, and the signals reflected from the human body will contain information about the vibration of the human chest cavity, including breathing and heart rate information. From these signals, through certain signal processing methods and algorithms, information such as human breathing and heart rate can be extracted. This information can be used for daily physiological sign detection and health monitoring.

[0004] Ideally, the radar is facing the chest of the monitored person, so that the signal reflected from the person contains the best information about breathing and heart rate. However, in actual applications, due to a series of reasons such as installation location limitations and movement of the monitored object, it is impossible to always ensure that the radar antenna is facing the chest of the monitored person, which will affect the monitoring results. For this reason, we propose a non-contact physiological sign monitoring system to solve the above problems. Summary of the invention

[0005] The problem to be solved by the present invention is that due to a series of reasons such as installation position limitation and movement of the monitored object, it is impossible to ensure that the radar antenna is always facing the chest of the monitored person, which will affect the monitoring results.

[0006] In order to solve the above technical problems, the present invention provides a non-contact physiological sign monitoring system, comprising:

[0007] A sensor module, wherein the sensor module is mainly used to collect data related to physiological characteristics;

[0008] A signal processing module, which is used to perform preprocessing operations on the original signal collected by the sensor module to improve signal quality and remove noise interference;

[0009] A feature extraction module, which is used to extract key parameters and features that can reflect physiological characteristics from the processed signal;

[0010] A data analysis module, which analyzes and calculates the extracted features through data analysis algorithms and models to obtain accurate physiological indicators;

[0011] A communication module, which is used to transmit the monitoring data to a terminal device or a remote server for further processing, storage and display;

[0012] A power management module, which is used to provide a stable power supply to the entire system and optimize the power management to ensure low power consumption operation of the system;

[0013] A display and interaction module, which is used to display the monitoring results to the user, including a display screen, indicator lights, or an interactive interface with a mobile application, so that the user can intuitively understand the physiological status;

[0014] A storage module, which is used to temporarily or long-term store monitoring data for subsequent query and analysis;

[0015] Preferably, the sensor module collects data related to physiological characteristics by one or more of optics, electromagnetics, acoustics, image analysis, and wireless signals:

[0016] Wherein: the optical method comprises:

[0017] Photoplethysmography uses a camera to capture changes in light absorption on the skin surface due to blood flow to calculate parameters such as heart rate;

[0018] Thermal imaging, using infrared thermal imagers to detect changes in temperature distribution on the human body surface to infer physiological activities;

[0019] The electromagnetic method comprises:

[0020] Millimeter wave radar, which transmits millimeter waves and receives reflected waves, and obtains information such as breathing and heartbeat by analyzing the changes in reflected waves;

[0021] Ultra-wideband radar, similar to millimeter-wave radar but with higher resolution and accuracy;

[0022] The acoustic method is to capture the sound produced by breathing through a microphone placed at a certain distance, and analyze the sound characteristics to monitor the breathing frequency and pattern;

[0023] The image analysis method is to observe subtle changes in facial expressions, such as muscle twitches, eye movements, etc., through a camera to infer emotions and fatigue levels;

[0024] The wireless signal method utilizes the reflection and change of Wi-Fi signals to monitor the activities and physiological status of the human body.

[0025] Preferably, the signal processing module specifically includes a filtering processing unit, an amplification processing unit, a noise reduction processing unit, an adaptive filtering unit, a wavelet transform unit, a signal reconstruction unit, and a motion compensation unit;

[0026] Wherein: the amplification processing unit is used to enhance weak physiological signals so that they can be subsequently processed and analyzed;

[0027] The adaptive filtering unit is used to automatically adjust the parameters of the filter according to the statistical characteristics of the input signal to better adapt to different environments and individual differences;

[0028] The wavelet transform unit is used to perform multi-resolution analysis on the signal in the time-frequency domain, and can effectively extract the local features of the signal;

[0029] The signal reconstruction unit is used to reconstruct the damaged or incomplete signal by interpolation or fitting.

[0030] The motion compensation unit is used to compensate and correct the signal interference caused by the motion of the monitoring object by using an algorithm.

[0031] Preferably, the filtering processing unit includes:

[0032] A low-pass filter processing module, which is used to remove high-frequency noise and retain low-frequency components of physiological signals, such as slowly changing signals such as breathing and heartbeat;

[0033] A high-pass filter processing module, wherein the high-pass filter processing module is used to remove baseline drift and DC components and highlight the rapidly changing parts;

[0034] The bandpass filter processing module is used to select signals within a specific frequency range, for example, only retain the frequency band where the heart rate or breathing frequency is located.

[0035] Preferably, the noise reduction processing unit further includes:

[0036] Mean filtering, which smoothes the signal and reduces random noise by calculating the average value of adjacent sampling points;

[0037] Median filtering replaces the value of a sampling point with the median of adjacent points, effectively removing impulse noise.

[0038] Preferably, the physiological features extracted in the feature extraction module include one or more of heart rate features, breathing features, body temperature features, sleep features, movement features, expression features, skin features, and sound features.

[0039] Preferably, the data analysis module performs data analysis by one or more of statistical analysis methods, machine learning algorithms, deep learning algorithms, pattern recognition methods, time series analysis methods, data fusion methods, and visualization analysis methods.

[0040] Preferably, the specific steps of the statistical analysis method are as follows:

[0041] S1: Calculate statistics such as mean, median, standard deviation, etc. to describe the central tendency and dispersion of physiological characteristic data;

[0042] S2: Conduct correlation analysis to determine the degree of association between different physiological characteristics;

[0043] S3: Display data in the form of charts (such as line charts, bar charts, heat maps, etc.) to help intuitively understand data distribution and trends and discover potential patterns and anomalies.

[0044] Technical effects and advantages of the present invention:

[0045] 1. The present invention collects data related to physiological characteristics by adopting multiple schemes such as optical methods, electromagnetic methods, acoustic methods, image analysis methods, wireless signal methods, etc., which is beneficial to improving the accuracy of the data collected by the system, thereby improving the comprehensiveness of the system.

[0046] 2. The present invention can enhance weak physiological signals in the collected original signals through the amplification processing unit provided in the signal processing module so that they can be subsequently processed and analyzed. Through the signal reconstruction unit provided, it can reconstruct damaged or incomplete signals through interpolation or fitting methods, thereby improving the integrity of the data. Through the motion compensation unit provided, it can increase the system's monitoring of moving objects and use algorithms to compensate and correct signal interference caused by motion, which is beneficial to improving the accuracy of feature data.

[0047] 3. The present invention combines low-pass filtering, high-pass filtering and band-pass filtering in the filtering processing unit, so that the signal processing module can remove high-frequency noise, retain the low-frequency components of physiological signals, remove baseline drift and DC components, highlight rapidly changing parts, and select signals in a specific frequency range, thereby providing more accurate monitoring data for subsequent processing, which is conducive to further improving the accuracy of characteristic data. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION

[0049] The present invention provides a non-contact physiological sign monitoring system, such as Figure 1 As shown, including:

[0050] Sensor module: The sensor module is mainly used to collect data related to physiological characteristics;

[0051] The signal processing module is used to perform preprocessing operations on the original signal collected by the sensor module to improve signal quality and remove noise interference;

[0052] Feature extraction module, the feature extraction module is used to extract key parameters and features that can reflect physiological characteristics from the processed signal;

[0053] Data analysis module, which analyzes and calculates the extracted features through data analysis algorithms and models to obtain accurate physiological indicators;

[0054] A communication module, which is used to transmit the monitoring data to a terminal device or a remote server for further processing, storage and display;

[0055] Power management module: The power management module is used to provide a stable power supply to the entire system and optimize the power management to ensure low power consumption of the system;

[0056] Display and interaction module, which is used to show the monitoring results to the user, including a display screen, indicator lights or an interactive interface with a mobile application, so that the user can intuitively understand the physiological status;

[0057] Storage module: The storage module is used to temporarily or long-term store monitoring data for subsequent query and analysis;

[0058] Furthermore, the sensor module collects data related to physiological characteristics by one or more of optics, electromagnetics, acoustics, image analysis, and wireless signals:

[0059] Among them: Optical methods include:

[0060] Photoplethysmography uses a camera to capture changes in light absorption on the skin surface due to blood flow to calculate parameters such as heart rate;

[0061] Thermal imaging, using infrared thermal imagers to detect changes in temperature distribution on the human body surface to infer physiological activities;

[0062] Electromagnetic methods include:

[0063] Millimeter wave radar, which transmits millimeter waves and receives reflected waves, and obtains information such as breathing and heartbeat by analyzing the changes in reflected waves;

[0064] Ultra-wideband radar, similar to millimeter-wave radar but with higher resolution and accuracy;

[0065] The acoustic method is to capture the sound produced by breathing through a microphone placed at a certain distance and analyze the sound characteristics to monitor the breathing rate and pattern;

[0066] The image analysis method uses a camera to observe subtle changes in facial expressions, such as muscle twitches and eye movements, to infer emotions and fatigue levels;

[0067] The wireless signal method uses the reflection and changes of Wi-Fi signals to monitor human activities and physiological states.

[0068] In this embodiment, it should be specifically explained that by using multiple schemes such as optical methods, electromagnetic methods, acoustic methods, image analysis methods, wireless signal methods, etc. to collect data related to physiological characteristics, the accuracy of the data collected by the system is improved, thereby improving the comprehensiveness of the system.

[0069] Furthermore, the signal processing module specifically includes a filtering processing unit, an amplification processing unit, a noise reduction processing unit, an adaptive filtering unit, a wavelet transform unit, a signal reconstruction unit, and a motion compensation unit;

[0070] Wherein: the amplification processing unit is used to enhance weak physiological signals so that they can be subsequently processed and analyzed;

[0071] The adaptive filtering unit is used to automatically adjust the filter parameters according to the statistical characteristics of the input signal to better adapt to different environments and individual differences;

[0072] The wavelet transform unit is used to perform multi-resolution analysis on the signal in the time-frequency domain, and can effectively extract the local features of the signal;

[0073] The signal reconstruction unit is used to reconstruct damaged or incomplete signals by interpolation or fitting methods;

[0074] The motion compensation unit is used to compensate and correct the signal interference caused by the motion of the monitored object using an algorithm.

[0075] In the present embodiment, it should be specifically explained that, through the amplification processing unit provided in the signal processing module, it is possible to enhance the weak physiological signals in the collected original signals so that they can be subsequently processed and analyzed; through the signal reconstruction unit provided, it is possible to reconstruct damaged or incomplete signals through interpolation or fitting and other methods, thereby improving the integrity of the data; through the motion compensation unit provided, it is possible to increase the system's monitoring of objects in motion, adopt algorithms to compensate and correct the signal interference caused by motion, and improve the accuracy of data acquisition.

[0076] Furthermore, the filtering processing unit includes:

[0077] Low-pass filter processing module: The low-pass filter processing module is used to remove high-frequency noise and retain the low-frequency components of physiological signals, such as slowly changing signals such as breathing and heartbeat;

[0078] High-pass filter processing module: The high-pass filter processing module is used to remove baseline drift and DC components and highlight the rapidly changing parts;

[0079] The bandpass filter processing module is used to select signals in a specific frequency range, for example, only retain the frequency band where the heart rate or breathing frequency is located.

[0080] In this embodiment, it should be specifically explained that, through the combination of low-pass filtering, high-pass filtering and band-pass filtering in the filtering processing unit, the signal processing module can remove high-frequency noise, retain the low-frequency components of physiological signals, remove baseline drift and DC components, highlight rapidly changing parts, and select signals in a specific frequency range, thereby providing more accurate monitoring data for subsequent processing.

[0081] Furthermore, the noise reduction processing unit also includes:

[0082] Mean filtering, which smoothes the signal and reduces random noise by calculating the average value of adjacent sampling points;

[0083] Median filtering replaces the value of a sampling point with the median of adjacent points, effectively removing impulse noise.

[0084] In this embodiment, it should be specifically explained that, through the processing of mean filtering and median filtering in the noise reduction processing unit, the signal processing module can reduce random noise and effectively remove pulse noise, thereby providing more accurate monitoring data for subsequent processing.

[0085] Furthermore, the physiological features extracted in the feature extraction module include one or more of heart rate features, breathing features, body temperature features, sleep features, movement features, expression features, skin features, and sound features.

[0086] In this embodiment, it should be specifically explained that the feature extraction module can efficiently extract heart rate characteristics, breathing characteristics, body temperature characteristics, sleep characteristics, movement characteristics, expression characteristics, skin characteristics, sound characteristics and other features in the monitoring data, thereby improving the comprehensiveness of the system's monitoring.

[0087] Furthermore, the data analysis module performs data analysis through one or more of statistical analysis methods, machine learning algorithms, deep learning algorithms, pattern recognition methods, time series analysis methods, data fusion methods, and visualization analysis methods.

[0088] In this embodiment, it should be specifically explained that by adopting a variety of data analysis methods to analyze and calculate the monitoring data, it is possible to avoid deviations in the process of analyzing the characteristic data by the system, thereby improving the accuracy of the system.

[0089] Further, such as Figure 1 The specific steps of statistical analysis are as follows:

[0090] S1: Calculate statistics such as mean, median, standard deviation, etc. to describe the central tendency and dispersion of physiological characteristic data;

[0091] S2: Conduct correlation analysis to determine the degree of association between different physiological characteristics;

[0092] S3: Display data in the form of charts (such as line charts, bar charts, heat maps, etc.) to help intuitively understand data distribution and trends and discover potential patterns and anomalies.

[0093] Working principle of the present invention:

[0094] When in use, the physiological characteristic data is first collected through the sensor module, and then the collected data is transmitted to the signal processing module. At this time, the signal processing module will filter, amplify, denoise, adaptively filter, wavelet transform, signal reconstruction, motion compensation and other steps on the collected data, and the processed data will be transmitted to the feature extraction module. At this time, the feature extraction module will extract one or more feature data of heart rate features, breathing features, body temperature features, sleep features, movement features, expression features, skin features, and sound features in the data. The extracted feature data will be transmitted to the data analysis module, and the data analysis module will analyze and calculate the extracted features through data analysis algorithms and models to obtain accurate physiological indicators, and then display the monitoring results to the user through the display and interaction module, including a display screen, indicator lights or an interactive interface with a mobile application, so that the user can intuitively understand the physiological state, thereby realizing non-contact physiological sign monitoring;

[0095] By adopting optical methods, electromagnetic methods, acoustic methods, image analysis methods, wireless signal methods and other schemes to collect physiological characteristic related data, the accuracy of the data collected by the system is improved, thereby improving the comprehensiveness of the system; through the amplification processing unit provided in the signal processing module, it can enhance the weak physiological signals in the collected original signals so that they can be subsequently processed and analyzed. Through the signal reconstruction unit provided, it can reconstruct damaged or incomplete signals through interpolation or fitting methods, thereby improving the integrity of the data. Through the motion compensation unit provided, it can increase the system's monitoring of objects in motion, and use algorithms to compensate and correct signal interference caused by motion, thereby improving the accuracy of data collection; through the combination of low-pass filtering, high-pass filtering and band-pass filtering in the filtering processing unit, the signal processing module can achieve It can remove high-frequency noise, retain the low-frequency components of physiological signals, remove baseline drift and DC components, highlight the rapidly changing parts, and select the functions of signals in a specific frequency range, thereby providing more accurate monitoring data for subsequent processing; through the mean filtering and median filtering in the noise reduction processing unit, the signal processing module can reduce random noise and effectively remove pulse noise, thereby providing more accurate monitoring data for subsequent processing; through the feature extraction module, the heart rate characteristics, breathing characteristics, body temperature characteristics, sleep characteristics, movement characteristics, expression characteristics, skin characteristics, sound characteristics and other features in the monitoring data can be efficiently extracted, thereby improving the comprehensiveness of the system's monitoring; by using a variety of data analysis methods to analyze and calculate the monitoring data, it can avoid the system from having deviations in the process of analyzing the feature data, thereby improving the accuracy of the system.

[0096] It is to be understood that the present invention is described by some embodiments, and it is known to those skilled in the art that various changes or equivalent substitutions may be made to these features and embodiments without departing from the spirit and scope of the present invention. In addition, under the teachings of the present invention, these features and embodiments may be modified to adapt to specific circumstances and materials without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the scope of protection of the present invention.

Claims

1. A non-contact physiological sign monitoring system, It is characterized in that include: A sensor module, wherein the sensor module is mainly used to collect data related to physiological characteristics; A signal processing module, which is used to perform preprocessing operations on the original signal collected by the sensor module to improve signal quality and remove noise interference; A feature extraction module, which is used to extract key parameters and features that can reflect physiological characteristics from the processed signal; A data analysis module, which analyzes and calculates the extracted features through data analysis algorithms and models to obtain accurate physiological indicators; A communication module, which is used to transmit the monitoring data to a terminal device or a remote server for further processing, storage and display; A power management module, which is used to provide a stable power supply to the entire system and optimize the power management to ensure low power consumption operation of the system; A display and interaction module, which is used to display the monitoring results to the user, including a display screen, indicator lights, or an interactive interface with a mobile application, so that the user can intuitively understand the physiological status; A storage module is used to temporarily or long-term store monitoring data for subsequent query and analysis.

2. A non-contact physiological sign monitoring system according to claim 1, Features: The sensor module collects data related to physiological characteristics by one or more of optical, electromagnetic, acoustic, image analysis, and wireless signals: Wherein: the optical method comprises: Photoplethysmography uses a camera to capture changes in light absorption on the skin surface due to blood flow to calculate parameters such as heart rate; Thermal imaging, using infrared thermal imagers to detect changes in temperature distribution on the human body surface to infer physiological activities; The electromagnetic method comprises: Millimeter wave radar, which transmits millimeter waves and receives reflected waves, and obtains information such as breathing and heartbeat by analyzing the changes in reflected waves; Ultra-wideband radar, similar to millimeter-wave radar but with higher resolution and accuracy; The acoustic method is to capture the sound produced by breathing through a microphone placed at a certain distance, and analyze the sound characteristics to monitor the breathing frequency and pattern; The image analysis method is to observe subtle changes in facial expressions, such as muscle twitches, eye movements, etc., through a camera to infer emotions and fatigue levels; The wireless signal method utilizes the reflection and change of Wi-Fi signals to monitor the activities and physiological status of the human body.

3. A non-contact physiological sign monitoring system according to claim 1, Features: The signal processing module specifically includes a filtering processing unit, an amplification processing unit, a noise reduction processing unit, an adaptive filtering unit, a wavelet transform unit, a signal reconstruction unit, and a motion compensation unit; Wherein: the amplification processing unit is used to enhance weak physiological signals so that they can be subsequently processed and analyzed; The adaptive filtering unit is used to automatically adjust the parameters of the filter according to the statistical characteristics of the input signal to better adapt to different environments and individual differences; The wavelet transform unit is used to perform multi-resolution analysis on the signal in the time-frequency domain, and can effectively extract the local features of the signal; The signal reconstruction unit is used to reconstruct the damaged or incomplete signal by interpolation or fitting. The motion compensation unit is used to compensate and correct the signal interference caused by the motion of the monitoring object by using an algorithm.

4. A non-contact physiological sign monitoring system according to claim 3, Features: The filtering processing unit comprises: A low-pass filter processing module, which is used to remove high-frequency noise and retain low-frequency components of physiological signals, such as slowly changing signals such as breathing and heartbeat; A high-pass filter processing module, wherein the high-pass filter processing module is used to remove baseline drift and DC components and highlight the rapidly changing parts; The bandpass filter processing module is used to select signals within a specific frequency range, for example, only retain the frequency band where the heart rate or breathing frequency is located.

5. A non-contact physiological sign monitoring system according to claim 3, Features: The noise reduction processing unit also includes: Mean filtering, which smoothes the signal and reduces random noise by calculating the average value of adjacent sampling points; Median filtering replaces the value of a sampling point with the median of adjacent points, effectively removing impulse noise.

6. A non-contact physiological sign monitoring system according to claim 1, Features: The physiological features extracted in the feature extraction module include one or more of heart rate features, breathing features, body temperature features, sleep features, movement features, expression features, skin features, and sound features.

7. A non-contact physiological sign monitoring system according to claim 1, Features: The data analysis module performs data analysis through one or more of statistical analysis methods, machine learning algorithms, deep learning algorithms, pattern recognition methods, time series analysis methods, data fusion methods, and visualization analysis methods.

8. A non-contact physiological sign monitoring system according to claim 7, Features: The specific steps of the statistical analysis method are as follows: S1: Calculate statistics such as mean, median, and standard deviation to describe the central tendency and dispersion of physiological characteristic data; S2: Conduct correlation analysis to determine the degree of association between different physiological characteristics; S3: Display data in the form of charts (such as line charts, bar charts, heat maps, etc.) to help intuitively understand data distribution and trends and discover potential patterns and anomalies.