A non-contact vital signs data monitoring method and system

Abstract

The present invention relates to the field of physiological information monitoring technology, and specifically to a non-contact vital sign data monitoring method and system, including the following contents: chest micro-motion data acquisition module, heartbeat data analysis module, body temperature measurement module, threshold parameter adjustment module, and health index calculation module. In the present invention, by using millimeter wave radar sensors and infrared sensors to collect and analyze the chest micro-motion and infrared radiation data of target individuals in real time, accurate monitoring of vital signs is achieved, and the abnormal detection threshold is adjusted in combination with the individual's physiological state, so that the monitoring results fit the individual's actual health status. Through the joint analysis of multiple vital signs, a comprehensive assessment of health status is achieved, combined with health trend prediction, data support is provided for preventive health management and early disease diagnosis, the practicality of the monitoring system is improved, and the application scope of non-contact monitoring technology in complex environments is expanded.

Description

Technical Field

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

[0002] The field of physiological information monitoring technology focuses on the use of a variety of sensors and equipment to collect and analyze human physiological parameters in real time, including body temperature, heart rate, pulse, respiration, blood pressure, blood oxygen level and other vital signs. It is applied to medical health monitoring, sports science, rehabilitation treatment and personal health management. By continuously monitoring the health status of individuals, health problems can be discovered in a timely manner, treatment plans can be adjusted or exercise training plans can be optimized. Combined with data processing and analysis, including signal processing, pattern recognition and machine learning, the accuracy and reliability of monitoring data can be improved, making the monitoring results more practical and instructive.

[0003] Among them, the non-contact vital sign data monitoring method aims to achieve remote collection of vital sign data without direct contact with the body of the monitored person, using infrared sensors, radars, acoustic sensors, and video cameras to capture and analyze physiological signals at a certain distance, and is applied to hospital monitoring of patients' vital signs, home health management, health monitoring of the elderly, infectious disease areas, and other complex environments for risk-free monitoring. The non-contact monitoring method reduces the risk of infection, improves patient comfort, and provides continuous and accurate health data for medical providers.

[0004] Traditional non-contact vital sign data monitoring methods have poor data accuracy and environmental adaptability. In dynamic or complex environments, they lack sufficient environmental adaptation adjustment mechanisms and cannot effectively adjust sensor sensitivity to cope with changes in ambient light, resulting in decreased data accuracy. It is difficult to fully consider individual differences, including age, gender and multiple physiological characteristics. When designing abnormal detection thresholds, there is a lack of necessary personalized configuration, which limits the applicability and sensitivity of the system, resulting in instability in monitoring results, affecting the judgment of health status, leading to blind spots in monitoring patient health status, and limiting the application of non-contact monitoring technology in a wider range of medical and family health management scenarios. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a non-contact vital sign data monitoring method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution, a non-contact vital sign data monitoring method, comprising the following steps:

[0007] S1: Based on the millimeter wave radar sensor, it collects the chest micro-motion data of the target individual in real time, separates the chest movement signals caused by heartbeat and breathing, identifies the frequency and changes of breathing, and obtains breathing pattern data;

[0008] S2: Based on the breathing pattern data, by analyzing the chest movement signal caused by the heartbeat, evaluating the change pattern of the target individual's heartbeat data, identifying the speed and frequency of the heartbeat, and generating a heartbeat pattern analysis result;

[0009] S3: Based on the heartbeat pattern analysis result, using an infrared sensor, real-time monitoring of infrared radiation data emitted by the target individual and calculating body temperature, and outputting body temperature monitoring results;

[0010] S4: Based on the body temperature monitoring result, according to the age, gender, height, weight and real-time activity status of the target individual, adjusting the abnormal detection thresholds of the heart rate and respiratory rate, and generating a monitoring parameter adjustment record;

[0011] S5: Based on the monitoring parameter adjustment record, the abnormal state of the target individual is identified by analyzing the heart rate, respiration, and body temperature data of the target individual, and an abnormal state identification record is generated;

[0012] S6: Based on the abnormal state identification record, a real-time assessment of the health state of the target individual is performed, and a health index is calculated. Combined with time series analysis, a change trend of the health state of the target individual is predicted to generate physiological state assessment information.

[0013] As a further scheme of the present invention, the breathing pattern data includes breathing frequency data, breathing cycle duration information, and amplitude change data of the breathing waveform; the heartbeat pattern analysis results include heart rate, mean and variance of heart rate, and time series characteristics of chest movement caused by heartbeat; the body temperature monitoring results include the real-time body temperature value of the target individual, time series change data of body temperature, and compensation data for the impact of ambient light on body temperature measurement; the monitoring parameter adjustment record includes an abnormal heart rate detection threshold, an abnormal breathing frequency monitoring threshold, and an abnormal body temperature alarm threshold; the abnormal state identification record includes abnormal heart rate events of the target individual, abnormal breathing pattern recognition results, and abnormal body temperature event records; the physiological state assessment information includes the health index of the target individual, health state change trend information, and physiological state assessment data.

[0014] As a further solution of the present invention, based on the millimeter wave radar sensor, the chest micro-motion data of the target individual is collected in real time, the chest movement signals caused by heartbeat and breathing are separated, and the frequency and changes of breathing are identified. The steps of obtaining the breathing pattern data are specifically as follows:

[0015] S101: Based on the millimeter wave radar sensor, the micro-motion data of the target individual's chest is collected in real time, the chest movement signal and timestamp information are recorded, and the chest movement data is obtained;

[0016] S102: Based on the chest movement data, separate the chest movement signals caused by heartbeat and breathing through high-pass filtering and low-pass filtering, identify the breathing signal causing the chest movement, and obtain breathing signal data;

[0017] S103: Based on the breathing signal data, identify the frequency and change pattern of the target individual's breathing by performing time series analysis on the breathing data, and generate breathing pattern data.

[0018] As a further solution of the present invention, based on the breathing pattern data, by analyzing the chest motion signal caused by the heartbeat, evaluating the change pattern of the target individual's heartbeat data, identifying the speed and frequency of the heartbeat, and generating the heartbeat pattern analysis result, the specific steps are:

[0019] S201: Based on the breathing pattern data, by analyzing the chest motion signal caused by the heartbeat, the time series data is converted into multi-dimensional space data by using time delay embedding, and phase space reconstruction is performed to obtain reconstructed space data;

[0020] S202: Based on the reconstructed spatial data, calculating statistical parameters in multiple dimensions, including variance and mean, analyzing the change pattern of the heartbeat signal, and obtaining change pattern information;

[0021] S203: Based on the change pattern information, identify the speed and frequency of the target individual's heartbeat, classify the heartbeat type according to the change pattern, and generate a heartbeat pattern analysis result.

[0022] As a further solution of the present invention, based on the heartbeat pattern analysis result, infrared sensors are used to monitor infrared radiation data emitted by the target individual in real time and calculate body temperature, and the steps of outputting the body temperature monitoring result are specifically as follows:

[0023] S301: Based on the heartbeat pattern analysis result, using an infrared sensor to monitor the ambient light intensity in real time, adjusting the sensitivity compensation parameter of the infrared sensor, optimizing the accuracy of data collection, and obtaining compensation parameter configuration;

[0024] S302: Based on the compensation parameter configuration, collecting infrared radiation data emitted by the target individual, recording the intensity of multiple wavelengths in the infrared spectrum, and generating infrared data measurement results;

[0025] S303: Based on the infrared data measurement result, the body temperature of the target individual is calculated in real time through the infrared data to generate a body temperature monitoring result.

[0026] As a further solution of the present invention, based on the body temperature monitoring results, the abnormal detection thresholds of the heart rate and respiratory rate are adjusted according to the age, gender, height, weight and real-time activity status of the target individual, and the steps of generating the monitoring parameter adjustment record are specifically as follows:

[0027] S401: Based on the body temperature monitoring result, the age, gender, height, weight and activity status data of the target individual are collected in real time to obtain individual physiological and status data;

[0028] S402: Based on the individual physiological and state data, considering activity intensity and individual differences, calculating a heart rate abnormality detection threshold for the target individual, and generating a detection parameter calculation result;

[0029] S403: Based on the detection parameter calculation results, according to the individual's physiological and real-time status data, adjust the abnormal detection thresholds of the breathing pattern and body temperature, including the sensitivity of the breathing rate to changes in activity and the normal fluctuation range of body temperature, to obtain a monitoring parameter adjustment record.

[0030] As a further solution of the present invention, based on the monitoring parameter adjustment record, the abnormal state of the target individual is identified by analyzing the heart rate, respiration and body temperature data of the target individual, and the steps of generating the abnormal state identification record are specifically as follows:

[0031] S501: Based on the monitoring parameter adjustment record, the heart rate, respiration, and body temperature data of the target individual are timestamped and aligned to generate a vital sign data set;

[0032] S502: Based on the vital sign data set, by comparing multiple physiological parameters with abnormal detection thresholds, identifying data points that exceed a normal range, and generating a physiological data comparison result;

[0033] S503: Based on the physiological data comparison result, analyze and identify the abnormal state of the target individual, including too fast heart rate, irregular breathing, abnormal body temperature, and generate an abnormal state identification record.

[0034] As a further solution of the present invention, based on the abnormal state recognition record, the health state of the target individual is evaluated in real time, and the health index is calculated. Combined with time series analysis, the change trend of the health state of the target individual is predicted, and the steps of generating physiological state evaluation information are specifically as follows:

[0035] S601: receiving the abnormal state identification record, analyzing the impact of multiple abnormal states on the health of the target individual, evaluating the health state of the target individual, and generating a health state evaluation result;

[0036] S602: Based on the health status assessment result, calculate the health index of the target individual, quantify the vital sign status of the target individual, and generate a health status score;

[0037] S603: Based on the health status score and combined with time series data analysis, predict the changing trend of the health status of the target individual and generate physiological status assessment information.

[0038] As a further solution of the present invention, the specific formula for calculating the health index of the target individual is: in, is the health index, which represents the health status value after comprehensive evaluation. is the actual heart rate, the current heart rate value measured, is the actual respiratory rate, the current respiratory rate value measured, is the actual body temperature, the current temperature value measured, is the standard heart rate, the standard value of heart rate under ideal health conditions, is the standard respiratory rate, the standard value of respiratory rate under ideal health conditions, is the standard body temperature, the standard value of body temperature under ideal health conditions, is the intercept term, a constant term in the model, representing the basic health index when there is no deviation. is the weight coefficient of heart rate deviation, which indicates the contribution of the degree of heart rate deviation from the standard value to the health index. is the weight coefficient of respiratory rate deviation, which indicates the contribution of the degree of respiratory rate deviation from the standard value to the health index. is the weight coefficient of body temperature deviation, which indicates the contribution of the degree of body temperature deviation from the standard value to the health index.

[0039] A non-contact vital sign data monitoring system, the non-contact vital sign data monitoring system is used to execute the above-mentioned non-contact vital sign data monitoring method, the system comprises:

[0040] The chest micro-motion data acquisition module uses a millimeter-wave radar sensor to collect the target individual's chest micro-motion data in real time, separate the chest movement signals caused by heartbeat and breathing, and identify the target individual's breathing pattern to generate breathing data analysis results;

[0041] The heartbeat data analysis module analyzes the chest motion signal caused by the heartbeat based on the respiratory data analysis result, evaluates the change pattern of the heartbeat data, including the speed and frequency of the heartbeat, and generates the heartbeat data change pattern information;

[0042] The body temperature measurement module uses an infrared sensor to monitor the infrared radiation data emitted by the target individual in real time based on the heartbeat data change pattern information, adjusts the sensitivity of the sensor according to the change of ambient light, calculates and corrects the body temperature reading, and generates a body temperature reading record;

[0043] The threshold parameter adjustment module collects the age, gender, height, weight and real-time activity status of the target individual based on the body temperature reading record, adjusts the abnormal detection thresholds of the heart rate and respiratory rate, and generates a detection threshold configuration;

[0044] The health index calculation module is based on the detection threshold configuration, analyzes the heart rate, respiration, and body temperature data of the target individual and compares them with the abnormal detection threshold, identifies abnormal conditions, conducts real-time assessment of the health status of the target individual, calculates the health index, combines time series analysis to predict the changing trend of the health status, and generates physiological status assessment information.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are:

[0046] In the present invention, by utilizing millimeter wave radar sensors and infrared sensors to collect and analyze the chest micro-movements and infrared radiation data of the target individual in real time, accurate monitoring of vital signs is achieved. In combination with the individual's physiological state, the abnormal detection threshold is adjusted to make the monitoring results fit the individual's actual health status. Through the joint analysis of multiple vital signs, a comprehensive assessment of the health status is achieved. Combined with health trend prediction, data support is provided for preventive health management and early disease diagnosis, thereby improving the practicability of the monitoring system and expanding the application scope of non-contact monitoring technology in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0048] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0049] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0050] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0051] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0052] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0053] Figure 7 This is a detailed flow chart of S6 of the present invention;

[0054] Figure 8 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0056] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0057] See also Figure 1 The present invention provides a technical solution, a non-contact vital sign data monitoring method, comprising the following steps:

[0058] S1: Based on the millimeter wave radar sensor, it collects the chest micro-motion data of the target individual in real time, separates the chest movement signals caused by heartbeat and breathing, identifies the frequency and changes of breathing, and obtains breathing pattern data;

[0059] S2: Based on the breathing pattern data, by analyzing the chest movement signal caused by the heartbeat, the change pattern of the target individual's heartbeat data is evaluated, the speed and frequency of the heartbeat are identified, and the heartbeat pattern analysis results are generated;

[0060] S3: Based on the heartbeat pattern analysis results, use infrared sensors to monitor the infrared radiation data emitted by the target individual in real time and calculate the body temperature, and output the body temperature monitoring results;

[0061] S4: Based on the body temperature monitoring results, the abnormal detection thresholds of the heart rate and respiratory rate are adjusted according to the age, gender, height, weight and real-time activity status of the target individual, and a monitoring parameter adjustment record is generated;

[0062] S5: Based on the monitoring parameter adjustment record, the abnormal state of the target individual is identified by analyzing the heart rate, respiration, and body temperature data of the target individual, and an abnormal state identification record is generated;

[0063] S6: Based on the abnormal status recognition records, the health status of the target individual is evaluated in real time, and the health index is calculated. Combined with time series analysis, the changing trend of the health status of the target individual is predicted to generate physiological status evaluation information.

[0064] The breathing pattern data includes breathing rate data, breathing cycle duration information, and amplitude change data of the breathing waveform. The heartbeat pattern analysis results include heart rate, mean and variance of heart rate, and time series characteristics of chest movement caused by heartbeat. The body temperature monitoring results include the real-time body temperature value of the target individual, time series change data of body temperature, and compensation data for the impact of ambient light on body temperature measurement. The monitoring parameter adjustment records include abnormal heart rate detection threshold, abnormal breathing rate monitoring threshold, and abnormal body temperature alarm threshold. The abnormal state identification records include abnormal heart rate events of the target individual, abnormal breathing pattern recognition results, and abnormal body temperature event records. The physiological state assessment information includes the health index of the target individual, health state change trend information, and physiological state assessment data.

[0065] See also Figure 2 Based on the millimeter wave radar sensor, the chest micro-motion data of the target individual is collected in real time, the chest movement signals caused by heartbeat and breathing are separated, and the frequency and changes of breathing are identified. The specific steps for obtaining the breathing pattern data are as follows:

[0066] S101: Based on the millimeter wave radar sensor, the micro-motion data of the target individual's chest is collected in real time, the chest movement signal and timestamp information are recorded, and the chest movement data is obtained;

[0067] In sub-step S101, based on the millimeter-wave radar sensor, the micro-motion data of the target individual's chest is collected in real time. Signal acquisition technology and time synchronization technology are used in the real-time monitoring process. Sensors are used to capture subtle changes in the chest caused by breathing and heartbeat. The data acquisition interval is set to milliseconds to ensure that all physiological change signals are captured. The recorded chest movement signal is subjected to preliminary noise filtering after reception to eliminate interference from environmental noise. The timestamp information is corrected using the network time protocol to ensure the time accuracy of the data recording. The chest movement data that has been preliminarily processed is stored in a structured data format to facilitate subsequent data processing and analysis, thereby improving data accuracy.

[0068] S102: Based on the chest movement data, separate the chest movement signals caused by heartbeat and breathing through high-pass filtering and low-pass filtering, identify the breathing signal causing the chest movement, and obtain breathing signal data;

[0069] In sub-step S102, based on the chest movement data, high-pass filtering and low-pass filtering are used, and digital signal processing technology is used to set the cutoff frequencies of the high-pass filter and the low-pass filter respectively to separate the chest movement signals caused by heartbeat and breathing. The high-pass filter removes the low-frequency breathing signal, and the low-pass filter is used to weaken the high-frequency heartbeat signal. The Butterworth filter is used to automatically adjust the filter parameters to adapt to the differences in individual physiological signals. The filtered data is used to distinguish and identify the key factors that cause chest movement, and the obtained respiratory signal data reflects the individual's breathing pattern.

[0070] S103: Based on the breathing signal data, by performing time series analysis on the breathing data, the frequency and change pattern of the target individual's breathing are identified to generate breathing pattern data;

[0071] In sub-step S103, based on the respiratory signal data, by performing time series analysis on the respiratory data, the autoregressive moving average model is used to analyze the changes in respiratory frequency and pattern, the trend and periodic changes in the time series data are captured, the data stationarity test is performed, the parameters of the model are estimated, and the least squares method is used to estimate the parameters to ensure the accuracy and adaptability of the model. The generated respiratory pattern data can indicate the breathing regularity and possible abnormal patterns of the target individual, help medical professionals understand the patient's respiratory condition, and provide a scientific basis for the early diagnosis and treatment of respiratory-related diseases.

[0072] See also Figure 3 Based on the breathing pattern data, by analyzing the chest movement signal caused by the heartbeat, evaluating the change pattern of the target individual's heartbeat data, identifying the speed and frequency of the heartbeat, and generating the heartbeat pattern analysis results, the specific steps are:

[0073] S201: Based on the breathing pattern data, by analyzing the chest motion signal caused by the heartbeat, the time series data is converted into multi-dimensional space data by using time delay embedding, and phase space is reconstructed to obtain reconstructed space data;

[0074] In sub-step S201, time delay embedding is performed based on the breathing pattern data, the time series data is converted into multi-dimensional space data, and phase space reconstruction is performed, including selecting the embedding dimension and delay time, and determining the optimal delay time by calculating the autocorrelation function and the mutual information function. The embedding dimension is determined by the false nearest neighbor method to ensure that the geometric structure of the reconstructed space is not distorted by the embedding process. The obtained multi-dimensional space data reflects the dynamic characteristics of the original time series data, improves the understanding and analysis depth of the time series data, and provides a data basis for subsequent analysis.

[0075] S202: Based on the reconstructed spatial data, statistical parameters in multiple dimensions are calculated, including variance and mean, and a change pattern of the heartbeat signal is analyzed to obtain change pattern information;

[0076] In sub-step S202, statistical parameter calculations are performed based on the reconstructed spatial data, including variance and mean. The statistical parameters are calculated in multiple dimensions to analyze the change pattern of the heartbeat signal. Multidimensional statistical analysis is used to reveal the main characteristics of the heartbeat signal, including the regularity and abnormal fluctuations of the heartbeat. During the calculation process, the fluctuation range and central trend of each dimension are accurately measured. The obtained change pattern information accurately reflects the stability and variability of the heartbeat signal, which is the key to identifying arrhythmia or other heart conditions, and provides a scientific basis for subsequent diagnosis.

[0077] S203: Based on the change pattern information, identify the speed and frequency of the target individual's heartbeat, and classify the heartbeat type according to the change pattern to generate a heartbeat pattern analysis result;

[0078] In the above content, the speed and frequency of the target individual's heartbeat are identified based on the change pattern information, and the heartbeat type is classified according to the formula , calculate the heart rate ;

[0079] In the formula, Represents the heart rate, Represents at time The number of heartbeats recorded in represents the length of observation time;

[0080] Detailed explanation of the formula and the process of formula calculation and derivation:

[0081] Assuming observation time The number of heartbeats recorded during the measurement period is 1 minute is 70, which is a typical heart rate for an adult at rest. :

[0082] The result 70 indicates that the number of heartbeats per minute is 70. The calculation process is used to estimate the heartbeat frequency through time series analysis based on the reconstructed spatial data and to assist in the classification of heartbeat types.

[0083] See also Figure 4 Based on the heartbeat pattern analysis results, infrared sensors are used to monitor the infrared radiation data emitted by the target individual in real time and calculate the body temperature. The steps for outputting the body temperature monitoring results are as follows:

[0084] S301: Based on the heartbeat pattern analysis result, the infrared sensor is used to monitor the ambient light intensity in real time, and the sensitivity compensation parameter of the infrared sensor is adjusted to optimize the accuracy of data collection and obtain the compensation parameter configuration;

[0085] In sub-step S301, based on the heartbeat pattern analysis results, an infrared sensor is used to monitor the ambient light intensity, including real-time capture of changes in light intensity in the environment, and adjustment of sensitivity compensation parameters of the infrared sensor according to the light intensity data. Automatic gain control technology is used to adjust the sensor sensitivity to ensure the accuracy of data collection. The ambient light intensity is measured and the required compensation coefficient is dynamically calculated through an algorithm. The compensation parameters are optimized and adjusted according to the real-time data of light intensity to adapt to different lighting conditions. By applying the optimized compensation parameter configuration to the sensor, the sensor's adaptability to environmental changes is improved, thereby ensuring accuracy and reliability during data collection.

[0086] S302: Based on the compensation parameter configuration, collect infrared radiation data emitted by the target individual, record the intensity of multiple wavelengths in the infrared spectrum, and generate infrared data measurement results;

[0087] In sub-step S302, based on the compensation parameter configuration, the infrared radiation data emitted by the target individual is collected. An infrared sensor is used to record the intensity of multiple wavelengths in the infrared spectrum. The intensity recording of each wavelength point is achieved through a spectrophotometer to accurately measure the light intensity of different wavelengths. According to the adjusted compensation parameters, the reading of each wavelength point is automatically corrected to ensure the accuracy of the data. The generated infrared data measurement results reflect the infrared radiation characteristics of the target individual. The data provides a data basis for physiological parameter analysis, ensuring the scientificity and practicality of subsequent applications.

[0088] S303: Based on the infrared data measurement result, the body temperature of the target individual is calculated in real time through the infrared data to generate a body temperature monitoring result;

[0089] In the above content, based on the infrared data measurement results, the body temperature of the target individual is calculated in real time according to the formula , generate body temperature monitoring results;

[0090] In the formula, represents the calculated body temperature, is the reference temperature, is the measured infrared radiation energy, is the base energy, is the energy to temperature conversion coefficient;

[0091] Detailed explanation of the formula and the process of formula calculation and derivation:

[0092] Assuming base temperature , the base energy Unit, measured energy Units, assuming energy and temperature conversion factors Unit / °C, calculation :

[0093] The result of 37.25°C indicates that the target individual's body temperature is slightly higher than the normal body temperature. The formula is used to accurately monitor the real-time changes in body temperature based on the slight changes in infrared radiation energy to obtain accurate body temperature monitoring results.

[0094] See also Figure 5 Based on the temperature monitoring results, the abnormal detection thresholds of heart rate and respiratory rate are adjusted according to the target individual's age, gender, height, weight and real-time activity status. The specific steps for generating monitoring parameter adjustment records are as follows:

[0095] S401: Based on the body temperature monitoring results, the age, gender, height, weight and activity status data of the target individual are collected in real time to obtain individual physiological and status data;

[0096] In sub-step S401, based on the temperature monitoring results, real-time collection of physiological and status data of the target individual is carried out, including age, gender, height, weight and activity status. Multi-source data integration is used in combination with data input to ensure accurate entry of relevant parameters. The data is transmitted to the central database via a wireless network for processing and storage. The collection of each data item is standardized according to a preset physiological data model. The physiological and status data provide a basis for subsequent individualized health monitoring and analysis, so that the monitoring system can accurately adjust the monitoring parameters according to individual characteristics, thereby improving the effectiveness of personalized medical services.

[0097] S402: Based on the individual physiological and state data, considering the activity intensity and individual differences, calculating the heart rate abnormality detection threshold for the target individual, and generating a detection parameter calculation result;

[0098] In sub-step S402, based on individual physiological and status data, taking into account activity intensity and individual differences, the heart rate abnormality detection threshold of the target individual is calculated, and statistical analysis and machine learning algorithms are used to analyze historical health data sets, and decision trees and random forest algorithms are applied to determine the key factors affecting heart rate changes. A personalized heart rate abnormality detection threshold is set for each individual, and the threshold is dynamically adjusted according to the individual's activity intensity and physiological data to ensure the accuracy and adaptability of the threshold. The generated detection parameter calculation results provide an important auxiliary tool for preventing heart rate-related health problems and enhance the prediction and early warning functions of the heart rate monitoring system.

[0099] S403: Based on the detection parameter calculation results, according to the individual's physiological and real-time status data, the abnormal detection thresholds of the breathing pattern and body temperature are adjusted, including the sensitivity of the breathing rate to changes in activity and the normal fluctuation range of body temperature, to obtain a monitoring parameter adjustment record;

[0100] In sub-step S403, based on the calculation results of the detection parameters, the abnormal detection thresholds of the breathing pattern and body temperature are adjusted, the close correlation between the breathing rate and body temperature and the individual activity intensity is taken into account, the physiological model and real-time status data analysis technology are applied, and the time series analysis method is used to adjust the sensitivity of the breathing rate and the normal fluctuation range of the body temperature in real time. The adjustment is based on a comprehensive consideration of activity data and environmental factors to ensure the individualization and real-time nature of the monitoring parameters. The generated monitoring parameter adjustment record records the basis and results of each adjustment, enhances the adaptability and accuracy of the health monitoring system, provides a scientific basis for health management, and enables the monitoring to accurately reflect the health status of the individual.

[0101] See also Figure 6 Based on the monitoring parameter adjustment record, the abnormal state of the target individual is identified by analyzing the heart rate, respiration, and body temperature data of the target individual. The specific steps of generating the abnormal state identification record are as follows:

[0102] S501: Based on the monitoring parameter adjustment records, the heart rate, respiration, and body temperature data of the target individual are timestamped and aligned to generate a vital sign data set;

[0103] In sub-step S501, records are adjusted based on monitoring parameters, and timestamps of heart rate, respiration, and body temperature data are aligned. Data synchronization technology is used to ensure accurate timestamp matching of physiological signals to improve the consistency and reliability of data sets. Through the data integration platform, data formats from different equipment sources are collected and unified. Alignment operations ensure the synchronization accuracy of each data stream. The SQL database management system is used to query and manage time series data, and query algorithms are optimized to reduce data processing time and improve efficiency. The generated vital signs data set ensures the accuracy and reliability of subsequent analysis. The integrated data provides a solid foundation for medical monitoring and health assessment.

[0104] S502: Based on the vital sign data set, by comparing multiple physiological parameters with abnormal detection thresholds, identifying data points that are beyond the normal range, and generating physiological data comparison results;

[0105] In sub-step S502, based on the vital signs data set, a comparison of multiple physiological parameters with the abnormal detection threshold is performed to identify data points that exceed the normal range. The technologies used include anomaly detection algorithms and data mining techniques. The statistical analysis methods standard deviation and interquartile range are applied to define the boundaries of abnormal data points. Machine learning algorithms random forest and support vector machine are used for data pattern recognition to enhance the detection accuracy of abnormal points. The generated physiological data comparison results list the data points that exceed the threshold, including specific physiological parameters and abnormal values, to enhance the sensitivity of data monitoring.

[0106] S503: Analyze and identify the abnormal state of the target individual based on the physiological data comparison result, including fast heart rate, irregular breathing, abnormal body temperature, and generate an abnormal state identification record;

[0107] In sub-step S503, based on the comparison results of physiological data, the abnormal conditions of the target individual are analyzed and identified, including rapid heart rate, irregular breathing, and abnormal body temperature. Time series analysis and trend analysis are used to track the changing trends of physiological conditions. Multivariate regression models are used to evaluate the correlation and impact between different parameters and the ability to predict abnormal conditions. The generated abnormal condition identification records describe the physiological background, detection time point, and health impact of each abnormal condition. The records provide decision support for medical care, help medical personnel respond to patients' needs, and ensure effective management and timely intervention of abnormal health conditions.

[0108] See also Figure 7 Based on the abnormal state recognition records, the health status of the target individual is evaluated in real time, and the health index is calculated. Combined with time series analysis, the changing trend of the health status of the target individual is predicted. The specific steps for generating physiological state evaluation information are as follows:

[0109] S601: Receive abnormal status recognition records, analyze the impact of multiple abnormal statuses on the health of the target individual, evaluate the health status of the target individual, and generate a health status evaluation result;

[0110] In sub-step S601, abnormal status identification records are received, and the impact of multiple abnormal statuses on the health of the target individual is analyzed. A comprehensive health assessment model is used, including multiple indicators such as heart rate, respiration and body temperature. The assessment model adopts a multi-parameter health scoring system. Based on statistical methods and clinical health standards, multiple abnormal statuses and health influencing factors are quantified to assess the overall health status of the target individual. The techniques used include Bayesian networks and logistic regression analysis to accurately calculate health risks. The generated health status assessment results provide a scientific basis for medical decision-making and reflect the health risks and urgent concerns of the target individual.

[0111] S602: Based on the health status assessment result, calculate the health index of the target individual, quantify the vital sign status of the target individual, and generate a health status score;

[0112] The specific formula for calculating the health index of the target individual is: in, is the health index, which represents the health status value after comprehensive evaluation. is the actual heart rate, the current heart rate value measured, is the actual respiratory rate, the current respiratory rate value measured, is the actual body temperature, the current temperature value measured, is the standard heart rate, the standard value of heart rate under ideal health conditions, is the standard respiratory rate, the standard value of respiratory rate under ideal health conditions, is the standard body temperature, the standard value of body temperature under ideal health conditions, is the intercept term, a constant term in the model, representing the basic health index when there is no deviation. is the weight coefficient of heart rate deviation, which indicates the contribution of the degree of heart rate deviation from the standard value to the health index. is the weight coefficient of respiratory rate deviation, which indicates the contribution of the degree of respiratory rate deviation from the standard value to the health index. is the weight coefficient of body temperature deviation, which indicates the contribution of the degree of body temperature deviation from the standard value to the health index.

[0113] formula:

[0114] Detailed explanation of the formula and the process of formula calculation and derivation:

[0115] The formula is used to calculate the health index, which assesses the deviation of an individual's physiological parameters relative to the health standard values;

[0116] Parameter meaning and setting value:

[0117] : Basic health index, set to 100, reflects the best health score under ideal conditions;

[0118] , , is the negative impact weight on the deviation of heart rate, respiratory rate, and body temperature from the standard value, assumed to be -0.5, -1.0, and -1.5;

[0119] , , The actual measured heart rate, respiratory rate, and body temperature values ​​are assumed to be 82 bpm, 22 bpm, and 37.5°C, respectively;

[0120] , , The healthy standard values ​​of heart rate, respiratory rate and body temperature are assumed to be 70 bpm, 16 times / minute, and 37.0°C for the target individual;

[0121] Substitute the parameters into the formula for calculation:

[0122] result It indicates that an individual's vital signs deviate from health standards, reflecting that heart rate, respiratory rate and body temperature are higher than ideal values. By quantifying health status, it helps identify and pay attention to health problems and take appropriate health intervention measures.

[0123] S603: Based on the health status score and combined with time series data analysis, predict the change trend of the health status of the target individual and generate physiological status assessment information;

[0124] In sub-step S603, based on the health status score, time series data analysis is used to predict the changing trend of the target individual's health status. The autoregressive moving average model is used to process and predict the time series changes of physiological parameter data. The historical data of the individual health index is analyzed through the model to predict future health trends, including short-term and long-term health changes. The generated physiological status assessment information describes the prediction results and possible health risks, providing forward-looking information for medical management and preventive measures.

[0125] See also Figure 8 A non-contact vital sign data monitoring system is provided, and the non-contact vital sign data monitoring system is used to execute the above-mentioned non-contact vital sign data monitoring method, and the system comprises:

[0126] The chest micro-motion data acquisition module uses a millimeter-wave radar sensor to collect the target individual's chest micro-motion data in real time, separate the chest movement signals caused by heartbeat and breathing, and identify the target individual's breathing pattern to generate breathing data analysis results;

[0127] The heartbeat data analysis module analyzes the chest movement signal caused by the heartbeat based on the respiratory data analysis results, evaluates the change pattern of the heartbeat data, including the speed and frequency of the heartbeat, and generates the heartbeat data change pattern information;

[0128] The temperature measurement module uses an infrared sensor to monitor the infrared radiation data emitted by the target individual in real time based on the heartbeat data change pattern information, adjusts the sensitivity of the sensor according to the ambient light changes, calculates and corrects the temperature reading, and generates a temperature reading record;

[0129] The threshold parameter adjustment module collects the target individual’s age, gender, height, weight, and real-time activity status based on the temperature reading record, adjusts the abnormal detection thresholds of heart rate and respiratory rate, and generates the detection threshold configuration;

[0130] The health index calculation module is based on the detection threshold configuration, analyzes the heart rate, respiration, and body temperature data of the target individual and compares them with the abnormal detection threshold, identifies abnormal conditions, conducts real-time assessment of the health status of the target individual, calculates the health index, combines time series analysis to predict the changing trend of the health status, and generates physiological status assessment information.

[0131] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A non-contact vital sign data monitoring system, characterized in that: The system comprises: The chest micro-motion data acquisition module uses a millimeter-wave radar sensor to collect the target individual's chest micro-motion data in real time, separate the chest movement signals caused by heartbeat and breathing, and identify the target individual's breathing pattern to generate breathing data analysis results; The heartbeat data analysis module analyzes the chest motion signal caused by the heartbeat based on the respiratory data analysis result, evaluates the change pattern of the heartbeat data, including the speed and frequency of the heartbeat, and generates the heartbeat data change pattern information; The body temperature measurement module uses an infrared sensor to monitor the infrared radiation data emitted by the target individual in real time based on the heartbeat data change pattern information, adjusts the sensitivity of the sensor according to the change of ambient light, calculates and corrects the body temperature reading, and generates a body temperature reading record; The threshold parameter adjustment module collects the age, gender, height, weight and real-time activity status of the target individual based on the body temperature reading record, adjusts the abnormal detection thresholds of the heart rate and respiratory rate, and generates a detection threshold configuration; The health index calculation module analyzes the heart rate, respiration, and body temperature data of the target individual based on the detection threshold configuration and compares them with the abnormal detection threshold, identifies the abnormal state, generates an abnormal state identification record, performs a real-time assessment of the health state of the target individual, calculates the health index, predicts the change trend of the health state in combination with time series analysis, and generates physiological state assessment information; The specific formula for calculating the health index of the target individual is: in, is the health index, which represents the health status value after comprehensive evaluation. is the actual heart rate, the current heart rate value measured, is the actual respiratory rate, the current respiratory rate value measured, is the actual body temperature, the current temperature value measured, is the standard heart rate, the standard value of heart rate under ideal health conditions, is the standard respiratory rate, the standard value of respiratory rate under ideal health conditions, is the standard body temperature, the standard value of body temperature under ideal health conditions, is the intercept term, a constant term in the model, representing the basic health index when there is no deviation. is the weight coefficient of heart rate deviation, which indicates the contribution of the degree of heart rate deviation from the standard value to the health index. is the weight coefficient of respiratory rate deviation, which indicates the contribution of the degree of respiratory rate deviation from the standard value to the health index. is the weight coefficient of body temperature deviation, which indicates the contribution of the degree of body temperature deviation from the standard value to the health index.

2. The non-contact vital sign data monitoring system according to claim 1, characterized in that: The respiratory data analysis results include respiratory rate data, respiratory cycle duration information, and amplitude change data of the respiratory waveform; the heartbeat data change pattern information includes heart rate, mean and variance of heart rate, and time series characteristics of chest movement caused by heartbeat; the body temperature reading record includes the real-time body temperature value of the target individual, time series change data of body temperature, and compensation data for the impact of ambient light on body temperature measurement; the detection threshold configuration includes an abnormal heart rate detection threshold, an abnormal respiratory rate monitoring threshold, and an abnormal body temperature alarm threshold; the abnormal state identification record includes the target individual's abnormal heart rate events, abnormal respiratory pattern recognition results, and abnormal body temperature event records; the physiological state assessment information includes the target individual's health index, health state change trend information, and physiological state assessment data.

3. The non-contact vital sign data monitoring system according to claim 1, characterized in that: The thoracic micro-motion data acquisition module comprises: Based on the millimeter wave radar sensor, the micro-motion data of the target individual's chest is collected in real time, the chest movement signal and timestamp information are recorded, and the chest movement data is obtained; Based on the chest cavity motion data, the chest cavity motion signals caused by heartbeat and breathing are separated by high-pass filtering and low-pass filtering, and the breathing signal causing the chest cavity motion is identified to obtain breathing signal data; Based on the respiratory signal data, the frequency and change pattern of the target individual's breathing are identified by performing time series analysis on the respiratory data, and a respiratory data analysis result is generated.

4. The non-contact vital sign data monitoring system according to claim 1, characterized in that: The heartbeat data analysis module comprises: Based on the respiratory data analysis result, by analyzing the chest motion signal caused by the heartbeat, the time series data is converted into multi-dimensional space data by using time delay embedding, and phase space reconstruction is performed to obtain reconstructed space data; Based on the reconstructed spatial data, statistical parameters in multiple dimensions are calculated, including variance and mean, and the change pattern of the heartbeat signal is analyzed to obtain change pattern information; Based on the change pattern information, the speed and frequency of the target individual's heartbeat are identified, and the heartbeat type is classified according to the change pattern to generate heartbeat data change pattern information.

5. The non-contact vital sign data monitoring system according to claim 1, characterized in that: The body temperature measurement module comprises: Based on the heartbeat data change pattern information, the infrared sensor is used to monitor the ambient light intensity in real time, the sensitivity compensation parameter of the infrared sensor is adjusted, the accuracy of data collection is optimized, and the compensation parameter configuration is obtained; Based on the compensation parameter configuration, collecting infrared radiation data emitted by the target individual, recording the intensity of multiple wavelengths in the infrared spectrum, and generating infrared data measurement results; Based on the infrared data measurement results, the body temperature of the target individual is calculated in real time through the infrared data to generate a body temperature reading record.

6. The non-contact vital sign data monitoring system according to claim 1, characterized in that: The threshold parameter adjustment module includes: Based on the temperature reading records, the age, gender, height, weight and activity status data of the target individual are collected in real time to obtain individual physiological and status data; Based on the individual physiological and status data, taking into account activity intensity and individual differences, calculating a heart rate abnormality detection threshold for the target individual and generating a detection parameter calculation result; Based on the detection parameter calculation results, according to the individual's physiological and real-time status data, the abnormal detection thresholds of breathing pattern and body temperature are adjusted, including the sensitivity of breathing rate to activity changes and the normal fluctuation range of body temperature, to obtain the detection threshold configuration.

7. The non-contact vital sign data monitoring system according to claim 1, characterized in that: The health index calculation module includes: Based on the detection threshold configuration, the heart rate, respiration, and body temperature data of the target individual are timestamped to generate a vital sign data set; Based on the vital sign data set, by comparing multiple physiological parameters with abnormal detection thresholds, identifying data points that are beyond a normal range, and generating physiological data comparison results; Based on the physiological data comparison results, analyze and identify the abnormal state of the target individual, including too fast heart rate, irregular breathing, abnormal body temperature, and generate an abnormal state identification record; receiving the abnormal state identification record, analyzing the impact of multiple abnormal states on the health of the target individual, evaluating the health state of the target individual, and generating a health state evaluation result; Based on the health status assessment result, the health index of the target individual is calculated, the vital sign status of the target individual is quantified, and a health status score is generated; Based on the health status score, combined with time series data analysis, the changing trend of the health status of the target individual is predicted to generate physiological status assessment information.

Images